question
stringlengths 12
1.77k
| context
stringlengths 79
71.7k
| answer
stringlengths 1
1.63k
|
|---|---|---|
What is a theme that could be taken from this text?
A. enough money can make anything happen
B. it's important to see all sides of the story
C. good always triumphs over evil
D. if you stand for what you believe, you will win
|
Is <A NAME= Gambling's would-be federal regulators--the National Gambling Impact Study Commission--went to Las Vegas this week to hold hearings. In today's dispatch, we learn how gambling's foes seek to demonize wagering as a pernicious tobaccolike vice. In yesterday's dispatch, gambling's foes learn the folly of having brought their anti-sin crusade to an adult Disneyland. Tuesday's overpowering show of force by the Nevada gambling aristocracy has had at least one audible effect on the National Gambling Impact Study Commission. Wednesday, even commission Chair Kay Coles James, a gambling skeptic, succumbs to the hideous Vegas euphemism: She begins referring to the "gaming industry." After Tuesday's casino triumphalism, Wednesday is a comedown, eight hours of policy panels on teen gambling, compulsive gambling, gambling regulation, gambling marketing, and gambling credit practices. It is tough slogging, but for the first time I sense that this commission--though divided, underfunded, timid, and without any power beyond exhortation--isn't entirely useless. It may finally settle this question: Is gambling Hollywood or tobacco? Entertainment or vice? The sleek Vegas types, whose Strip palaces scramble casinos, theaters, restaurants, arcades, discos, cabarets, theme parks, concert halls, sports arenas, and museums into one giant orgy of amusement, have been selling the idea that gambling is just entertainment--Disney in the desert. This effort has largely succeeded, because Vegas is still the dominant image of American gambling, if not the dominant reality. The antis, meanwhile, cry that gambling is like cigarettes: unsafe for kids, viciously addictive, deceptively marketed, unhealthy, expensive, and unacceptable unless mightily regulated. Judging by today's hearings and by conversations with most of the commissioners, the tobacco model is winning. Today's panelists tell the commission that kids are starting to gamble too young and are getting addicted too easily, that compulsive gambling appears to be increasing as gambling spreads, that gambling marketing may be designed to addict customers, and that the industry exploits problem gamblers by allowing them to draw repeated credit card advances from ATMs on casino floors. The testimony clearly impresses the commissioners and seems especially to impress the three nonaligned commissioners who will be the swing votes on the June 1999 report. It is starting to become clear what that report will say. The commission won't (and can't) take any grand stand against gambling. Instead it will opt for small, targeted policies, concentrating on compulsive gambling. It will probably propose that casinos and state lotteries fund gambling-addiction research and that casinos take much stronger measures to bar problem gamblers from wagering. The commission may recommend that gaming taxes be used to underwrite treatment of pathological gamblers and that insurance companies be encouraged to cover gambling addiction. Similarly, the commission will try to reduce gamblers' access to cash by limiting the size of ATM advances and prodding casinos to remove the machines from their floors. The commission will also push the industry to do more to prevent kids from gambling. It will call for heavier regulation of Indian gambling and will probably try to ban or severely regulate Internet gambling, perhaps by forbidding gambling companies from running online casinos. It will rebuke state lotteries for their deceptive marketing and will try to force them to post odds and stop targeting the poor. In short, it will treat gambling as a tobaccolike vice. If the comments of the pro-industry commissioners can be believed, the industry will happily endorse such a report. Gamblers don't quite accept the cigarette analogy--though commission member Bill Bible, a former chief of the Nevada Gaming Commission, did concede that gambling was like alcohol--but they're happy to sign on to the specific measures. The casino industry is even trying to get ahead of the commission. It has already established a (mostly) independent center to fund research into pathological gambling. I suspect that the industry will not only agree to the commission's recommendations but will become their strongest advocate. Casino owners will avidly lobby Congress and state legislatures to enact the recommendations into law. Why should the pro-gamblers cooperate with a critical study? Because it provides superb cover for them. It medicalizes the problem of compulsive gambling, blaming it on psychological abnormality rather than industry machination. Likewise, cracking down on compulsives is also politically cost-effective. In exchange for losing a few compulsive gamblers, the casinos will (falsely) appear more concerned with the health of their customers than with profits. The cigarette agenda will also distract the commission and the public from the true reasons for worry. A few years ago, gambling was confined to Las Vegas and Atlantic City. It is now thriving in 48 states, and there is no sign that anyone can stop it. In this election, gambling interests dropped $100 million on a single California ballot initiative, toppled governors in two states, and bought senators and representatives by the crate. What the commission ought to be investigating is whether the gambling industry has become so powerful that it's politically untouchable. But it can't, because the gambling industry has become so powerful that it's politically untouchable. The antis can call gambling "tobacco." They can call it "vice." They can call it "a big red balloon" for all that the industry cares. As long as the commission just nibbles around the edges, the casino operators and state lotteries will be happy to indulge it. The pro-gambling folks will win credit for cooperating, without having to do anything that really hurts. The last national gambling commission was in the mid-1970s. If the gamblers play along with this commission's timid recommendations, they'll be safe for another 20 years. An Apology I owe an apology to Nevada Sen. Richard Bryan, whom I criticized yesterday for using the term "Indian country" during a speech critical of Indian casinos. As several readers pointed out to me, "Indian country" is a common phrase in the West and has no derogatory connotations. I'm sorry, Senator. Talk about quick defeats: The first sign I see outside the MGM Grand ballroom all but declares that the National Gambling Impact Study Commission has already lost. The sign reads: "National Gaming Impact Study Commission." "Gaming"? In Las Vegas, the euphemizers reign. Once upon a time, the casino owners decided that "gambling" was too crude, too avaricious, to describe their fair business. So "gambling" disappeared in Las Vegas, and "gaming" has risen in its place. He who controls language controls ideas, and at today's commission hearing, it is perfectly clear who controls the language. Video slot machines crammed into convenience stores--perhaps the most pernicious form of legal gambling there is--are called "retail gaming." People who own casinos are not "casino owners," they are "gaming visionaries." Pathological gamblers are "problem gamers"--as if they're having trouble mastering the rules of Monopoly. And the National Gambling Impact Study Commission is reborn as the National Gaming Impact Study Commission. The gambling industry did everything in its power to stop the establishment of this commission two years ago, but Congress and a fervent grassroots anti-gambling group eventually foisted it on the industry. The nine member blue-ribbon panel was charged with assessing the social and economic impact of gambling, and it will issue a final report to Congress and the president in June 1999. Even though the panel was carefully balanced between pro- and anti-gambling leaders, it was supposed to be Vegas' nemesis. The industry and Las Vegas' pro-gambling media quaked in anticipation of the onerous regulations and taxes the commission might recommend. But they quake no more. Whatever national momentum the anti-gamblers had dissolved in last week's elections. The industry routed opponents in state after state. Missouri voters passed a ballot initiative to allow boat casinos. Californians voted to expand Indian casinos. In South Carolina and Alabama, voters expelled anti-lottery, anti-gambling Republican governors and replaced them with pro-lottery Democrats. The gambling industry spent more than $100 million on political contributions and issue ads. It has never been fatter, happier, or more secure. "My goodness, no politician can withstand their resources," Focus on the Family's James Dobson, the commission's leading gambling opponent, tells me. The industry's political clout has emasculated the commission, Dobson continues: "Our report won't be acted on by the president or Congress. They are too heavily influenced by gambling money. Almost all the leaders of Congress are on the dole." It has also become obvious that the commission has too many pro-gambling members to produce a report that recommends taxes or other real penalties on the industry. So the commission's two day visit to Gomorrah has been transformed from a charged political event to a kind of victory lap for gaming. Nevada Gov. Bob Miller and the "gaming visionaries" have been planning for these hearings for months, hoping to use them to demonstrate the might and sanctity and goodness of the Nevada gambling industry. The MGM Grand, which is run by commission member Terrence Lanni, is itself the first exhibit of the Vegas triumphalists. It is gaudy testimony that consumers, at least, have no problem with this business. The MGM Grand, a k a "The City of Entertainment," has 5,000 rooms--the corridor outside my room is 200 yards long, so long I can't see its end--to feed the endless supply of slot machines, craps tables, and roulette wheels. David Cassidy performs here every night--twice! A few steps outside on the Strip is still more overwhelming evidence that Las Vegas has won the popular vote. New York, New York is just across the street, the $1.6 billion Bellagio is one door down, and a half-scale Eiffel Tower is going up next door. The setting has, as the pro-gambling folks no doubt hoped, stunned some of the gambling opponents. I asked one anti-gambling activist who had never before been to Vegas what she thinks of it. She could only blurt out "Wow." The hearings, too, reinforce the Glorious Las Vegas theme. Frank Fahrenkopf, the industry's top lobbyist (who is paid so much he can afford monogrammed shirt cuffs --I saw them), holds forth cheerfully outside the ballroom, celebrating the electoral triumph of freedom over religious moralist tyranny. Inside, the room is packed with more than 600 people in neon lime green T-shirts that read "Unions and Gaming: Together for a Better Life." They are members of the major casino union, here to cheer on their employers and their union. (Most of them, it must be said, are getting paid to do this.) Chairwoman Kay Coles James, a Christian conservative and skeptic of gambling, opens the hearing by assuring the crowd that the committee is toothless: "We're not here to take anyone's job. ... We have no power to do anything except make recommendations." This sets the mood for most of the day: Vegas is great, so you'd better leave it alone! The local government, by all appearances a wholly owned subsidiary of the casinos, puts on a bravura performance. Gov. Miller opens the show with a 15 minute hymn to Las Vegas. It is the first of many statistical barrages about Nevada's one-ders: No. 1 in job growth, No. 1 in population growth, and No. 1 on planet Earth in per capita Girl Scout troops--and Boy Scout troops! Later in the day, Nevada's senators and both its congressmen appear to chew out the commission for even thinking that Nevada might have a dark side. They pay tribute to Nevada's sophisticated gambling industry, especially its regulation (much stricter than other gambling states) and its use of gambling taxes to fund state services. It is one of the ironies of Nevada politics that its Republican congressmen (Jim Gibbons and John Ensign) end up crediting their state's success to government regulation and corporate taxation. There are also a fair share of gleeful gambling regulators, bookmakers, and casino employees among the panels of expert witnesses the commission hears from. Critics who gripe about the perils of sports gambling and the evils of convenience store slot machines leaven the pro-gambling folks. Everyone, including the gambling industry shills, agrees that Internet gambling is evil and should be destroyed. Everyone agrees to this because no one in Las Vegas is making any money off Internet gambling. If they were, you can be sure they would explain why it's as American as nickel slots and scratch-off games. Pro-Vegas forces are also perfectly happy to take shots at Indian gambling, the chief economic threat to Nevada's prosperity. The expansion of Indian casinos resulting from last week's California voter initiative will slam Las Vegas, cutting its gambling revenues by $400 million a year. So the Vegans repeatedly swing at casinos in "Indian country" (that's Nevada Sen. Richard Bryan's term--I'm not joking) for being insufficiently regulated and taxed. One tribal chief I spoke to calls this "red baiting." (Pause for an aesthetic observation: I am sitting right behind the witnesses, and after a while I begin to separate them into the Wides and the Narrows. The Wides are men in suits with enormous backs and enormous bellies, men who eat and eat and used to play football. They all testify to their love of gambling. The Narrows are thin and generally disapprove of it. I begin to wonder whether fondness for gambling correlates with general indulgence, and dislike correlates with asceticism, and decide that they probably do.) During the last hour of the day, the public comment period, the union sends a parade of casino employees to the microphone to hallelujah the gaming industry. Housekeepers, cooks, and slot change girls, almost all black or Latina, tell the same story: I was working a dead-end job in another state, "then I heard about Las Vegas, where there's opportunity!" I moved here, landed a job at a union casino with high pay, free medical insurance, a pension, and "now I am buying a house." The stories are intensely moving, by far the most persuasive tribute to the Strip that I've ever heard. Still, for all the Vegan triumphalism in the air, it's impossible not to be charmed by the chief gambling opponent, the Rev. Tom Grey. Grey is utterly irrepressible. A Vietnam rifleman turned Methodist minister, Grey has spent the last eight years evangelizing against gambling. He founded the National Coalition Against Legalized Gambling, the primary force behind the commission's creation. (Grey, in a rare acknowledgement of defeat, has just renamed it the National Coalition Against Gambling Expansion, tacitly recognizing that gambling is here to stay.) He is a genial motormouth and shameless promoter of the cause. He wears a gigantic "CasiNO" button in the casino. He posed for People in a shepherd's robe. He says "I would do anything short of lighting myself on fire in the Capitol rotunda to stop gambling." He is so excitable that I have to yank him out of the way of an oncoming car when he gets too wrapped up in one of his soliloquies. He and his Las Vegas allies, a former Las Vegas city councilman named Steve Miller and an inner city venture capitalist named Otis Harris, invite me on a tour of Las Vegas. "Behind the Mirage," they call it. For two hours, we cruise the streets behind the casinos. They show me all the evidence of gambling blight you'd never want to see, from a youth-center-turned-crack-house to pawn shops to sex shops to down at heels casinos to quickie motels. All the while, they keep up a patter about how terrible a neighbor the casino industry is and how superficial Las Vegas' prosperity is. It's very grim and mostly persuasive. Still, when we turn back on to the Strip, and pass the jaw-dropping Stratosphere and Circus Circus and Bellagio and the MGM Grand--a 30 story tower bathed in fabulous emerald light, I realize why Grey's task is hopeless here. He is committing the cardinal sin of Vegas. All he wants to do is talk about losers. In Las Vegas, under the thrilling lights of the Strip, no one wants to hear about losers. In the land of gaming, not gambling, everyone is sure he's a winner.
|
A. enough money can make anything happen
|
What subset of GLUE tasks is used?
|
### Introduction
Over the past year, models based on the Transformer architecture BIBREF0 have become the de-facto standard for state-of-the-art performance on many natural language processing (NLP) tasks BIBREF1, BIBREF2. Their key feature is the self-attention mechanism that provides an alternative to conventionally used recurrent neural networks (RNN). One of the most popular Transformer-based models is BERT, which learns text representations using a bi-directional Transformer encoder pre-trained on the language modeling task BIBREF2. BERT-based architectures have produced new state-of-the-art performance on a range of NLP tasks of different nature, domain, and complexity, including question answering, sequence tagging, sentiment analysis, and inference. State-of-the-art performance is usually obtained by fine-tuning the pre-trained model on the specific task. In particular, BERT-based models are currently dominating the leaderboards for SQuAD BIBREF3 and GLUE benchmarks BIBREF4. However, the exact mechanisms that contribute to the BERT's outstanding performance still remain unclear. We address this problem through selecting a set of linguistic features of interest and conducting a series of experiments that aim to provide insights about how well these features are captured by BERT. This paper makes the following contributions: We propose the methodology and offer the first detailed analysis of BERT's capacity to capture different kinds of linguistic information by encoding it in its self-attention weights. We present the evidence of BERT's overparametrization and suggest a counter-intuitive yet frustratingly simple way of improving its performance, showing absolute gains of up to 3.2%. ### Related work
There have been several recent attempts to assess BERT's ability to capture structural properties of language. BIBREF5 demonstrated that BERT consistently assigns higher scores to the correct verb forms as opposed to the incorrect one in a masked language modeling task, suggesting some ability to model subject-verb agreement. BIBREF6 extended this work to using multiple layers and tasks, supporting the claim that BERT's intermediate layers capture rich linguistic information. On the other hand, BIBREF7 concluded that LSTMs generalize to longer sequences better, and are more robust with respect to agreement distractors, compared to Transformers. BIBREF8 investigated the transferability of contextualized word representations to a number of probing tasks requiring linguistic knowledge. Their findings suggest that (a) the middle layers of Transformer-based architectures are the most transferable to other tasks, and (b) higher layers of Transformers are not as task specific as the ones of RNNs. BIBREF9 argued that models using self-attention outperform CNN- and RNN-based models on a word sense disambiguation task due to their ability to extract semantic features from text. Our work contributes to the above discussion, but rather than examining representations extracted from different layers, we focus on the understanding of the self-attention mechanism itself, since it is the key feature of Transformer-based models. Another research direction that is relevant to our work is neural network pruning. BIBREF10 showed that widely used complex architectures suffer from overparameterization, and can be significantly reduced in size without a loss in performance. BIBREF5 observed that the smaller version of BERT achieves better scores on a number of syntax-testing experiments than the larger one. BIBREF11 questioned the necessity of computation-heavy neural networks, proving that a simple yet carefully tuned BiLSTM without attention achieves the best or at least competitive results compared to more complex architectures on the document classification task. BIBREF12 presented more evidence of unnecessary complexity of the self-attention mechanism, and proposed a more lightweight and scalable dynamic convolution-based architecture that outperforms the self-attention baseline. These studies suggest a potential direction for future research, and are in good accordance with our observations. ### Methodology
We pose the following research questions: What are the common attention patterns, how do they change during fine-tuning, and how does that impact the performance on a given task? (Sec. SECREF17, SECREF30) What linguistic knowledge is encoded in self-attention weights of the fine-tuned models and what portion of it comes from the pre-trained BERT? (Sec. SECREF25, SECREF34, SECREF36) How different are the self-attention patterns of different heads, and how important are they for a given task? (Sec. SECREF39) The answers to these questions come from a series of experiments with the basic pre-trained or the fine-tuned BERT models, as will be discussed below. All the experiments with the pre-trained BERT were conducted using the model provided with the PyTorch implementation of BERT (bert-base-uncased, 12-layer, 768-hidden, 12-heads, 110M parameters). We chose this smaller version of BERT because it shows competitive, if not better, performance while having fewer layers and heads, which makes it more interpretable. We use the following subset of GLUE tasks BIBREF4 for fine-tuning: MRPC: the Microsoft Research Paraphrase Corpus BIBREF13 STS-B: the Semantic Textual Similarity Benchmark BIBREF14 SST-2: the Stanford Sentiment Treebank, two-way classification BIBREF15 QQP: the Quora Question Pairs dataset RTE: the Recognizing Textual Entailment datasets QNLI: Question-answering NLI based on the Stanford Question Answering Dataset BIBREF3 MNLI: the Multi-Genre Natural Language Inference Corpus, matched section BIBREF16 Please refer to the original GLUE paper for details on the QQP and RTE datasets BIBREF4. We excluded two tasks: CoLa and the Winograd Schema Challenge. The latter is excluded due to the small size of the dataset. As for CoLa (the task of predicting linguistic acceptability judgments), GLUE authors report that the human performance is only 66.4, which is explained by the problems with the underlying methodology BIBREF17. Note also that CoLa is not included in the upcoming version of GLUE BIBREF18. All fine-tuning experiments follow the parameters reported in the original study (a batch size of 32 and 3 epochs, see devlin2018bert). In all these experiments, for a given input, we extract self-attention weights for each head in every layer. This results in a 2D float array of shape $L\times L$, where $L$ is the length of an input sequence. We will refer to such arrays as self-attention maps. Analysis of individual self-attention maps allows us to determine which target tokens are attended to the most as the input is processed token by token. We use these experiments to analyze how BERT processes different kinds of linguistic information, including the processing of different parts of speech (nouns, pronouns, and verbs), syntactic roles (objects, subjects), semantic relations, and negation tokens. ### Experiments
In this section, we present the experiments conducted to address the above research questions. ### Experiments ::: BERT's self-attention patterns
Manual inspection of self-attention maps for both basic pre-trained and fine-tuned BERT models suggested that there is a limited set of self-attention maps types that are repeatedly encoded across different heads. Consistently with previous observations, we identified five frequently occurring patterns, examples of which are shown in fig:atttypes: Vertical: mainly corresponds to attention to special BERT tokens [CLS] and [SEP]; Diagonal: formed by the attention to the previous/following tokens; Vertical+Diagonal: a mix of the previous two types, Block: intra-sentence attention for the tasks with two distinct sentences (such as, for example, RTE or MRPC), Heterogeneous: highly variable depending on the specific input and cannot be characterized by a distinct structure. Whereas the attention to the special tokens is important for cross-sentence reasoning, and the attention to the previous/following token comes from language model pre-training, we hypothesize that the last of the listed types is more likely to capture interpretable linguistic features, necessary for language understanding. To get a rough estimate of the percentage of attention heads that may capture linguistically interpretable information, we manually annotated around 400 sample self-attention maps as belonging to one of the five classes. The self-attention maps were obtained by feeding random input examples from selected tasks into the corresponding fine-tuned BERT model. This produced a somewhat unbalanced dataset, in which the “Vertical” class accounted for 30% of all samples. We then trained a convolutional neural network with 8 convolutional layers and ReLU activation functions to classify input maps into one of these classes. This model achieved the F1 score of 0.86 on the annotated dataset. We used this classifier to estimate the proportion of different self-attention patterns for the target GLUE tasks using up to 1000 examples (where available) from each validation set. ### Experiments ::: BERT's self-attention patterns ::: Results
fig:attentionbydataset shows that the self-attention map types described above are consistently repeated across different heads and tasks. While a large portion of encoded information corresponds to attention to the previous/following token, to the special tokens, or a mixture of the two (the first three classes), the estimated upper bound on all heads in the “Heterogeneous” category (i.e. the ones that could be informative) varies from 32% (MRPC) to 61% (QQP) depending on the task. We would like to emphasize that this only gives the upper bound on the percentage of attention heads that could potentially capture meaningful structural information beyond adjacency and separator tokens. ### Experiments ::: Relation-specific heads in BERT
In this experiment, our goal was to understand whether different syntactic and semantic relations are captured by self-attention patterns. While a large number of such relations could be investigated, we chose to examine semantic role relations defined in frame semantics, since they can be viewed as being at the intersection of syntax and semantics. Specifically, we focused on whether BERT captures FrameNet's relations between frame-evoking lexical units (predicates) and core frame elements BIBREF19, and whether the links between them produce higher attention weights in certain specific heads. We used pre-trained BERT in these experiments. The data for this experiment comes from FrameNet BIBREF19, a database that contains frame annotations for example sentences for different lexical units. Frame elements correspond to semantic roles for a given frame, for example, “buyer", “seller", and “goods” for the “Commercial_transaction" frame evoked by the words “sell” and “spend” or “topic” and “text” for the “Scrutiny” semantic frame evoked by the verb “address”. fig:framenet shows an example of such annotation. We extracted sample sentences for every lexical unit in the database and identified the corresponding core frame elements. Annotated elements in FrameNet may be rather long, so we considered only the sentences with frame elements of 3 tokens or less. Since each sentences is annotated only for one frame, semantic links from other frames can exist between unmarked elements. We therefore filter out all the sentences longer than 12 tokens, since shorter sentences are less likely to evoke multiple frames. To establish whether BERT attention captures semantic relations that do not simply correspond to the previous/following token, we exclude sentences where the linked objects are less than two tokens apart. This leaves us with 473 annotated sentences. For each of these sentences, we obtain pre-trained BERT's attention weights for each of the 144 heads. For every head, we return the maximum absolute attention weight among those token pairs that correspond to the annotated semantic link contained within a given sentence. We then average the derived scores over all the collected examples. This strategy allows us to identify the heads that prioritize the features correlated with frame-semantic relations within a sentence. ### Experiments ::: Relation-specific heads in BERT ::: Results
The heatmap of averaged attention scores over all collected examples (fig:framenetresults) suggests that 2 out of 144 heads tend to attend to the parts of the sentence that FrameNet annotators identified as core elements of the same frame. fig:framenetresults shows an example of this attention pattern for these two heads. Both show high attention weight for “he” while processing “agitated” in the sentence “He was becoming agitated" (the frame “Emotion_directed”). ### Experiments ::: Change in self-attention patterns after fine-tuning
Fine-tuning has a huge effect on performance, and this section attempts to find out why. To study how attention per head changes on average for each of the target GLUE tasks, we calculate cosine similarity between pre-trained and fine-tuned BERT's flattened arrays of attention weights. We average the derived similarities over all the development set examples. To evaluate contribution of pre-trained BERT to overall performance on the tasks, we consider two configurations of weights initialization, namely, pre-trained BERT weights and weights randomly sampled from normal distribution. ### Experiments ::: Change in self-attention patterns after fine-tuning ::: Results
fig:cosine shows that for all the tasks except QQP, it is the last two layers that undergo the largest changes compared to the pre-trained BERT model. At the same time, tab:glue-results shows that fine-tuned BERT outperforms pre-trained BERT by a significant margin on all the tasks (with an average of 35.9 points of absolute difference). This leads us to conclude that the last two layers encode task-specific features that are attributed to the gain of scores, while earlier layers capture more fundamental and low-level information used in fine-tuned models. Randomly initialized BERT consistently produces lower scores than the ones achieved with pre-trained BERT. In fact, for some tasks (STS-B and QNLI), initialization with random weights gives worse performance that that of pre-trained BERT alone without fine-tuning. This suggests that pre-trained BERT does indeed contain linguistic knowledge that is helpful for solving these GLUE tasks. These results are consistent with similar studies, e.g., BIBREF20's results on fine-tuning a convolutional neural network pre-trained on ImageNet or BIBREF21's results on transfer learning for medical natural language inference. ### Experiments ::: Attention to linguistic features
In this experiment, we investigate whether fine-tuning BERT for a given task creates self-attention patterns which emphasize specific linguistic features. In this case, certain kinds of tokens may get high attention weights from all the other tokens in the sentence, producing vertical stripes on the corresponding attention maps (fig:atttypes). We tested this hypothesis by checking whether there are vertical stripe patterns corresponding to certain linguistically interpretable features, and to what extent such features are relevant for solving a given task. In particular, we investigated attention to nouns, verbs, pronouns, subjects, objects, and negation words, and special BERT tokens across the tasks. For every head, we compute the sum of self-attention weights assigned to the token of interest from each input token. Since the weights depend on the number of tokens in the input sequence, this sum is normalized by sequence length. This allows us to aggregate the weights for this feature across different examples. If there are multiple tokens of the same type (e.g. several nouns or negations), we take the maximum value. We disregard input sentences that do not contain a given feature. For each investigated feature, we calculate this aggregated attention score for each head in every layer and build a map in order to detect the heads potentially responsible for this feature. We then compare the obtained maps to the ones derived using the pre-trained BERT model. This comparison enables us to determine if a particular feature is important for a specific task and whether it contributes to some tasks more than to others. ### Experiments ::: Attention to linguistic features ::: Results
Contrary to our initial hypothesis that the vertical attention pattern may be motivated by linguistically meaningful features, we found that it is associated predominantly, if not exclusively, with attention to [CLS] and [SEP] tokens (see Figure FIGREF32. Note that the absolute [SEP] weights for the SST-2 sentiment analysis task are greater than for other tasks, which is explained by the fact that there is only one sentence in the model inputs, i.e. only one [SEP] token instead of two. There is also a clear tendency for earlier layers to pay attention to [CLS] and for later layers to [SEP], and this trend is consistent across all the tasks. We did detect heads that paid increased (compared to the pre-trained BERT) attention to nouns and direct objects of the main predicates (on the MRPC, RTE and QQP tasks), and negation tokens (on the QNLI task), but the attention weights of such tokens were negligible compared to [CLS] and [SEP]. Therefore, we believe that the striped attention maps generally come from BERT pre-training tasks rather than from task-specific linguistic reasoning. ### Experiments ::: Token-to-token attention
To complement the experiments in Sec. SECREF34 and SECREF25, in this section, we investigate the attention patterns between tokens in the same sentence, i.e. whether any of the tokens are particularly important while a given token is being processed. We were interested specifically in the verb-subject relation and the noun-pronoun relation. Also, since BERT uses the representation of the [CLS] token in the last layer to make the prediction, we used the features from the experiment in Sec. SECREF34 in order to check if they get higher attention weights while the model is processing the [CLS] token. ### Experiments ::: Token-to-token attention ::: Results
Our token-to-token attention experiments for detecting heads that prioritize noun-pronoun and verb-subject links resulted in a set of potential head candidates that coincided with diagonally structured attention maps. We believe that this happened due to the inherent property of English syntax where the dependent elements frequently appear close to each other, so it is difficult to distinguish such relations from the previous/following token attention coming from language model pre-training. Our investigation of attention distribution for the [CLS] token in the output layer suggests that for most tasks, with the exception of STS-B, RTE and QNLI, the [SEP] gets attended the most, as shown in fig:cls. Based on manual inspection, for the mentioned remaining tasks, the greatest attention weights correspond to the punctuation tokens, which are in a sense similar to [SEP]. ### Experiments ::: Disabling self-attention heads
Since there does seem to be a certain degree of specialization for different heads, we investigated the effects of disabling different heads in BERT and the resulting effects on task performance. Since BERT relies heavily on the learned attention weights, we define disabling a head as modifying the attention values of a head to be constant $a = \frac{1}{L}$ for every token in the input sentence, where $L$ is the length of the sentence. Thus, every token receives the same attention, effectively disabling the learned attention patterns while maintaining the information flow of the original model. Note that by using this framework, we can disable an arbitrary number of heads, ranging from a single head per model to the whole layer or multiple layers. ### Experiments ::: Disabling self-attention heads ::: Results
Our experiments suggest that certain heads have a detrimental effect on the overall performance of BERT, and this trend holds for all the chosen tasks. Unexpectedly, disabling some heads leads not to a drop in accuracy, as one would expect, but to an increase in performance. This is effect is different across tasks and datasets. While disabling some heads improves the results, disabling the others hurts the results. However, it is important to note that across all tasks and datasets, disabling some heads leads to an increase in performance. The gain from disabling a single head is different for different tasks, ranging from the minimum absolute gain of 0.1% for STS-B, to the maximum of 1.2% for MRPC (see fig:disableheadsall). In fact, for some tasks, such as MRPC and RTE, disabling a random head gives, on average, an increase in performance. Furthermore, disabling a whole layer, that is, all 12 heads in a given layer, also improves the results. fig:disablelayers shows the resulting model performance on the target GLUE tasks when different layers are disabled. Notably, disabling the first layer in the RTE task gives a significant boost, resulting in an absolute performance gain of 3.2%. However, effects of this operation vary across tasks, and for QNLI and MNLI, it produces a performance drop of up to -0.2%. ### Discussion
In general, our results suggest that even the smaller base BERT model is significantly overparametrized. This is supported by the discovery of repeated self-attention patterns in different heads, as well as the fact that disabling both single and multiple heads is not detrimental to model performance and in some cases even improves it. We found no evidence that attention patterns that are mappable onto core frame-semantic relations actually improve BERT's performance. 2 out of 144 heads that seem to be “responsible" for these relations (see Section SECREF25) do not appear to be important in any of the GLUE tasks: disabling of either one does not lead to a drop of accuracy. This implies that fine-tuned BERT does not rely on this piece of semantic information and prioritizes other features instead. For instance, we noticed that both STS-B and RTE fine-tuned models rely on attention in the same pair of heads (head 1 in the fourth layer, and head 12 in the second layer), as shown in Figure FIGREF37. We manually checked the attention maps in those heads for a set of random inputs, and established that both of them have high weights for words that appear in both sentences of the input examples. This most likely means that word-by-word comparison of the two sentences provides a solid strategy of making a classification prediction for STS-B and RTE. Unfortunately, we were not able to provide a conceptually similar interpretation of heads important for other tasks. ### Conclusion
In this work, we proposed a set of methods for analyzing self-attention mechanisms of BERT, comparing attention patterns for the pre-trained and fine-tuned versions of BERT. Our most surprising finding is that, although attention is the key BERT's underlying mechanism, the model can benefit from attention "disabling". Moreover, we demonstrated that there is redundancy in the information encoded by different heads and the same patterns get consistently repeated regardless of the target task. We believe that these two findings together suggest a further direction for research on BERT interpretation, namely, model pruning and finding an optimal sub-architecture reducing data repetition. Another direction for future work is to study self-attention patterns in a different language. We think that it would allow to disentangle attention maps potentially encoding linguistic information and heads that use simple heuristics like attending to the following/previous tokens. Figure 1: Typical self-attention classes used for training a neural network. Both axes on every image represent BERT tokens of an input example, and colors denote absolute attention weights (darker colors stand for greater weights). The first three types are most likely associated with language model pre-training, while the last two potentially encode semantic and syntactic information. Figure 2: Estimated percentages of the identified selfattention classes for each of the selected GLUE tasks. Table 1: GLUE task performance of BERT models with different initialization. We report the scores on the validation, rather than test data, so these results differ from the original BERT paper. Figure 3: Detection of pre-trained BERT’s heads that encode information correlated to semantic links in the input text. Two heads (middle) demonstrate their ability to capture semantic relations. For a random annotated FrameNet example (bottom) full attention maps with a zoom in the target token attention distribution are shown (leftmost and rightmost). Figure 4: FrameNet annotation example for the “address” lexical unit with two core frame elements of different types annotated. Figure 5: Per-head cosine similarity between pre-trained BERT’s and fine-tuned BERT’s self-attention maps for each of the selected GLUE tasks, averaged over validation dataset examples. Darker colors correspond to greater differences. Figure 6: Per-task attention weights to the [SEP] (top row) and the [CLS] (bottom row) tokens averaged over input sequences’ lengths and over dataset examples. Darker colors correspond to greater absolute weights. Figure 7: Per-task attention weights corresponding to the [CLS] token averaged over input sequences’ lengths and over dataset examples, and extracted from the final layer. Darker colors correspond to greater absolute weights. Figure 8: Performance of the model while disabling one head at a time. The orange line indicates the baseline performance with no disabled heads. Darker colors correspond to greater performance scores. Figure 9: Performance of the model while disabling one layer (that is, all 12 heads in this layer) at a time. The orange line indicates the baseline performance with no disabled layers. Darker colors correspond to greater performance scores.
|
MRPC, STS-B, SST-2, QQP, RTE, QNLI, MNLI
|
What can be inferred about the destination decision at the end of the passsage?
A. They will be turning back around to where they came from and calling off the trip
B. Retief will ensure the ship travels to Jorgensen's World, as initially planned
C. It's still unclear at the end of the passage
D. They will be traveling to Alabaster in stead, per the Captain's orders
|
THE FROZEN PLANET By Keith Laumer [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, September 1961. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] "It is rather unusual," Magnan said, "to assign an officer of your rank to courier duty, but this is an unusual mission." Retief sat relaxed and said nothing. Just before the silence grew awkward, Magnan went on. "There are four planets in the group," he said. "Two double planets, all rather close to an unimportant star listed as DRI-G 33987. They're called Jorgensen's Worlds, and in themselves are of no importance whatever. However, they lie deep in the sector into which the Soetti have been penetrating. "Now—" Magnan leaned forward and lowered his voice—"we have learned that the Soetti plan a bold step forward. Since they've met no opposition so far in their infiltration of Terrestrial space, they intend to seize Jorgensen's Worlds by force." Magnan leaned back, waiting for Retief's reaction. Retief drew carefully on his cigar and looked at Magnan. Magnan frowned. "This is open aggression, Retief," he said, "in case I haven't made myself clear. Aggression on Terrestrial-occupied territory by an alien species. Obviously, we can't allow it." Magnan drew a large folder from his desk. "A show of resistance at this point is necessary. Unfortunately, Jorgensen's Worlds are technologically undeveloped areas. They're farmers or traders. Their industry is limited to a minor role in their economy—enough to support the merchant fleet, no more. The war potential, by conventional standards, is nil." Magnan tapped the folder before him. "I have here," he said solemnly, "information which will change that picture completely." He leaned back and blinked at Retief. "All right, Mr. Councillor," Retief said. "I'll play along; what's in the folder?" Magnan spread his fingers, folded one down. "First," he said. "The Soetti War Plan—in detail. We were fortunate enough to make contact with a defector from a party of renegade Terrestrials who've been advising the Soetti." He folded another finger. "Next, a battle plan for the Jorgensen's people, worked out by the Theory group." He wrestled a third finger down. "Lastly; an Utter Top Secret schematic for conversion of a standard anti-acceleration field into a potent weapon—a development our systems people have been holding in reserve for just such a situation." "Is that all?" Retief said. "You've still got two fingers sticking up." Magnan looked at the fingers and put them away. "This is no occasion for flippancy, Retief. In the wrong hands, this information could be catastrophic. You'll memorize it before you leave this building." "I'll carry it, sealed," Retief said. "That way nobody can sweat it out of me." Magnan started to shake his head. "Well," he said. "If it's trapped for destruction, I suppose—" "I've heard of these Jorgensen's Worlds," Retief said. "I remember an agent, a big blond fellow, very quick on the uptake. A wizard with cards and dice. Never played for money, though." "Umm," Magnan said. "Don't make the error of personalizing this situation, Retief. Overall policy calls for a defense of these backwater worlds. Otherwise the Corps would allow history to follow its natural course, as always." "When does this attack happen?" "Less than four weeks." "That doesn't leave me much time." "I have your itinerary here. Your accommodations are clear as far as Aldo Cerise. You'll have to rely on your ingenuity to get you the rest of the way." "That's a pretty rough trip, Mr. Councillor. Suppose I don't make it?" Magnan looked sour. "Someone at a policy-making level has chosen to put all our eggs in one basket, Retief. I hope their confidence in you is not misplaced." "This antiac conversion; how long does it take?" "A skilled electronics crew can do the job in a matter of minutes. The Jorgensens can handle it very nicely; every other man is a mechanic of some sort." Retief opened the envelope Magnan handed him and looked at the tickets inside. "Less than four hours to departure time," he said. "I'd better not start any long books." "You'd better waste no time getting over to Indoctrination," Magnan said. Retief stood up. "If I hurry, maybe I can catch the cartoon." "The allusion escapes me," Magnan said coldly. "And one last word. The Soetti are patrolling the trade lanes into Jorgensen's Worlds; don't get yourself interned." "I'll tell you what," Retief said soberly. "In a pinch, I'll mention your name." "You'll be traveling with Class X credentials," Magnan snapped. "There must be nothing to connect you with the Corps." "They'll never guess," Retief said. "I'll pose as a gentleman." "You'd better be getting started," Magnan said, shuffling papers. "You're right," Retief said. "If I work at it, I might manage a snootful by takeoff." He went to the door. "No objection to my checking out a needler, is there?" Magnan looked up. "I suppose not. What do you want with it?" "Just a feeling I've got." "Please yourself." "Some day," Retief said, "I may take you up on that." II Retief put down the heavy travel-battered suitcase and leaned on the counter, studying the schedules chalked on the board under the legend "ALDO CERISE—INTERPLANETARY." A thin clerk in a faded sequined blouse and a plastic snakeskin cummerbund groomed his fingernails, watching Retief from the corner of his eye. Retief glanced at him. The clerk nipped off a ragged corner with rabbitlike front teeth and spat it on the floor. "Was there something?" he said. "Two twenty-eight, due out today for the Jorgensen group," Retief said. "Is it on schedule?" The clerk sampled the inside of his right cheek, eyed Retief. "Filled up. Try again in a couple of weeks." "What time does it leave?" "I don't think—" "Let's stick to facts," Retief said. "Don't try to think. What time is it due out?" The clerk smiled pityingly. "It's my lunch hour," he said. "I'll be open in an hour." He held up a thumb nail, frowned at it. "If I have to come around this counter," Retief said, "I'll feed that thumb to you the hard way." The clerk looked up and opened his mouth. Then he caught Retief's eye, closed his mouth and swallowed. "Like it says there," he said, jerking a thumb at the board. "Lifts in an hour. But you won't be on it," he added. Retief looked at him. "Some ... ah ... VIP's required accommodation," he said. He hooked a finger inside the sequined collar. "All tourist reservations were canceled. You'll have to try to get space on the Four-Planet Line ship next—" "Which gate?" Retief said. "For ... ah...?" "For the two twenty-eight for Jorgensen's Worlds," Retief said. "Well," the clerk said. "Gate 19," he added quickly. "But—" Retief picked up his suitcase and walked away toward the glare sign reading To Gates 16-30 . "Another smart alec," the clerk said behind him. Retief followed the signs, threaded his way through crowds, found a covered ramp with the number 228 posted over it. A heavy-shouldered man with a scarred jawline and small eyes was slouching there in a rumpled gray uniform. He put out a hand as Retief started past him. "Lessee your boarding pass," he muttered. Retief pulled a paper from an inside pocket, handed it over. The guard blinked at it. "Whassat?" "A gram confirming my space," Retief said. "Your boy on the counter says he's out to lunch." The guard crumpled the gram, dropped it on the floor and lounged back against the handrail. "On your way, bub," he said. Retief put his suitcase carefully on the floor, took a step and drove a right into the guard's midriff. He stepped aside as the man doubled and went to his knees. "You were wide open, ugly. I couldn't resist. Tell your boss I sneaked past while you were resting your eyes." He picked up his bag, stepped over the man and went up the gangway into the ship. A cabin boy in stained whites came along the corridor. "Which way to cabin fifty-seven, son?" Retief asked. "Up there." The boy jerked his head and hurried on. Retief made his way along the narrow hall, found signs, followed them to cabin fifty-seven. The door was open. Inside, baggage was piled in the center of the floor. It was expensive looking baggage. Retief put his bag down. He turned at a sound behind him. A tall, florid man with an expensive coat belted over a massive paunch stood in the open door, looking at Retief. Retief looked back. The florid man clamped his jaws together, turned to speak over his shoulder. "Somebody in the cabin. Get 'em out." He rolled a cold eye at Retief as he backed out of the room. A short, thick-necked man appeared. "What are you doing in Mr. Tony's room?" he barked. "Never mind! Clear out of here, fellow! You're keeping Mr. Tony waiting." "Too bad," Retief said. "Finders keepers." "You nuts?" The thick-necked man stared at Retief. "I said it's Mr. Tony's room." "I don't know Mr. Tony. He'll have to bull his way into other quarters." "We'll see about you, mister." The man turned and went out. Retief sat on the bunk and lit a cigar. There was a sound of voices in the corridor. Two burly baggage-smashers appeared, straining at an oversized trunk. They maneuvered it through the door, lowered it, glanced at Retief and went out. The thick-necked man returned. "All right, you. Out," he growled. "Or have I got to have you thrown out?" Retief rose and clamped the cigar between his teeth. He gripped a handle of the brass-bound trunk in each hand, bent his knees and heaved the trunk up to chest level, then raised it overhead. He turned to the door. "Catch," he said between clenched teeth. The trunk slammed against the far wall of the corridor and burst. Retief turned to the baggage on the floor, tossed it into the hall. The face of the thick-necked man appeared cautiously around the door jamb. "Mister, you must be—" "If you'll excuse me," Retief said, "I want to catch a nap." He flipped the door shut, pulled off his shoes and stretched out on the bed. Five minutes passed before the door rattled and burst open. Retief looked up. A gaunt leathery-skinned man wearing white ducks, a blue turtleneck sweater and a peaked cap tilted raffishly over one eye stared at Retief. "Is this the joker?" he grated. The thick-necked man edged past him, looked at Retief and snorted, "That's him, sure." "I'm captain of this vessel," the first man said. "You've got two minutes to haul your freight out of here, buster." "When you can spare the time from your other duties," Retief said, "take a look at Section Three, Paragraph One, of the Uniform Code. That spells out the law on confirmed space on vessels engaged in interplanetary commerce." "A space lawyer." The captain turned. "Throw him out, boys." Two big men edged into the cabin, looking at Retief. "Go on, pitch him out," the captain snapped. Retief put his cigar in an ashtray, and swung his feet off the bunk. "Don't try it," he said softly. One of the two wiped his nose on a sleeve, spat on his right palm, and stepped forward, then hesitated. "Hey," he said. "This the guy tossed the trunk off the wall?" "That's him," the thick-necked man called. "Spilled Mr. Tony's possessions right on the deck." "Deal me out," the bouncer said. "He can stay put as long as he wants to. I signed on to move cargo. Let's go, Moe." "You'd better be getting back to the bridge, Captain," Retief said. "We're due to lift in twenty minutes." The thick-necked man and the Captain both shouted at once. The Captain's voice prevailed. "—twenty minutes ... uniform Code ... gonna do?" "Close the door as you leave," Retief said. The thick-necked man paused at the door. "We'll see you when you come out." III Four waiters passed Retief's table without stopping. A fifth leaned against the wall nearby, a menu under his arm. At a table across the room, the Captain, now wearing a dress uniform and with his thin red hair neatly parted, sat with a table of male passengers. He talked loudly and laughed frequently, casting occasional glances Retief's way. A panel opened in the wall behind Retief's chair. Bright blue eyes peered out from under a white chef's cap. "Givin' you the cold shoulder, heh, Mister?" "Looks like it, old-timer," Retief said. "Maybe I'd better go join the skipper. His party seems to be having all the fun." "Feller has to be mighty careless who he eats with to set over there." "I see your point." "You set right where you're at, Mister. I'll rustle you up a plate." Five minutes later, Retief cut into a thirty-two ounce Delmonico backed up with mushrooms and garlic butter. "I'm Chip," the chef said. "I don't like the Cap'n. You can tell him I said so. Don't like his friends, either. Don't like them dern Sweaties, look at a man like he was a worm." "You've got the right idea on frying a steak, Chip. And you've got the right idea on the Soetti, too," Retief said. He poured red wine into a glass. "Here's to you." "Dern right," Chip said. "Dunno who ever thought up broiling 'em. Steaks, that is. I got a Baked Alaska coming up in here for dessert. You like brandy in yer coffee?" "Chip, you're a genius." "Like to see a feller eat," Chip said. "I gotta go now. If you need anything, holler." Retief ate slowly. Time always dragged on shipboard. Four days to Jorgensen's Worlds. Then, if Magnan's information was correct, there would be four days to prepare for the Soetti attack. It was a temptation to scan the tapes built into the handle of his suitcase. It would be good to know what Jorgensen's Worlds would be up against. Retief finished the steak, and the chef passed out the baked Alaska and coffee. Most of the other passengers had left the dining room. Mr. Tony and his retainers still sat at the Captain's table. As Retief watched, four men arose from the table and sauntered across the room. The first in line, a stony-faced thug with a broken ear, took a cigar from his mouth as he reached the table. He dipped the lighted end in Retief's coffee, looked at it, and dropped it on the tablecloth. The others came up, Mr. Tony trailing. "You must want to get to Jorgensen's pretty bad," the thug said in a grating voice. "What's your game, hick?" Retief looked at the coffee cup, picked it up. "I don't think I want my coffee," he said. He looked at the thug. "You drink it." The thug squinted at Retief. "A wise hick," he began. With a flick of the wrist, Retief tossed the coffee into the thug's face, then stood and slammed a straight right to the chin. The thug went down. Retief looked at Mr. Tony, still standing open-mouthed. "You can take your playmates away now, Tony," he said. "And don't bother to come around yourself. You're not funny enough." Mr. Tony found his voice. "Take him, Marbles!" he growled. The thick-necked man slipped a hand inside his tunic and brought out a long-bladed knife. He licked his lips and moved in. Retief heard the panel open beside him. "Here you go, Mister," Chip said. Retief darted a glance; a well-honed french knife lay on the sill. "Thanks, Chip," Retief said. "I won't need it for these punks." Thick-neck lunged and Retief hit him square in the face, knocking him under the table. The other man stepped back, fumbling a power pistol from his shoulder holster. "Aim that at me, and I'll kill you," Retief said. "Go on, burn him!" Mr. Tony shouted. Behind him, the captain appeared, white-faced. "Put that away, you!" he yelled. "What kind of—" "Shut up," Mr. Tony said. "Put it away, Hoany. We'll fix this bum later." "Not on this vessel, you won't," the captain said shakily. "I got my charter to consider." "Ram your charter," Hoany said harshly. "You won't be needing it long." "Button your floppy mouth, damn you!" Mr. Tony snapped. He looked at the man on the floor. "Get Marbles out of here. I ought to dump the slob." He turned and walked away. The captain signaled and two waiters came up. Retief watched as they carted the casualty from the dining room. The panel opened. "I usta be about your size, when I was your age," Chip said. "You handled them pansies right. I wouldn't give 'em the time o' day." "How about a fresh cup of coffee, Chip?" Retief said. "Sure, Mister. Anything else?" "I'll think of something," Retief said. "This is shaping up into one of those long days." "They don't like me bringing yer meals to you in yer cabin," Chip said. "But the cap'n knows I'm the best cook in the Merchant Service. They won't mess with me." "What has Mr. Tony got on the captain, Chip?" Retief asked. "They're in some kind o' crooked business together. You want some more smoked turkey?" "Sure. What have they got against my going to Jorgensen's Worlds?" "Dunno. Hasn't been no tourists got in there fer six or eight months. I sure like a feller that can put it away. I was a big eater when I was yer age." "I'll bet you can still handle it, Old Timer. What are Jorgensen's Worlds like?" "One of 'em's cold as hell and three of 'em's colder. Most o' the Jorgies live on Svea; that's the least froze up. Man don't enjoy eatin' his own cookin' like he does somebody else's." "That's where I'm lucky, Chip. What kind of cargo's the captain got aboard for Jorgensen's?" "Derned if I know. In and out o' there like a grasshopper, ever few weeks. Don't never pick up no cargo. No tourists any more, like I says. Don't know what we even run in there for." "Where are the passengers we have aboard headed?" "To Alabaster. That's nine days' run in-sector from Jorgensen's. You ain't got another one of them cigars, have you?" "Have one, Chip. I guess I was lucky to get space on this ship." "Plenty o' space, Mister. We got a dozen empty cabins." Chip puffed the cigar alight, then cleared away the dishes, poured out coffee and brandy. "Them Sweaties is what I don't like," he said. Retief looked at him questioningly. "You never seen a Sweaty? Ugly lookin' devils. Skinny legs, like a lobster; big chest, shaped like the top of a turnip; rubbery lookin' head. You can see the pulse beatin' when they get riled." "I've never had the pleasure," Retief said. "You prob'ly have it perty soon. Them devils board us nigh ever trip out. Act like they was the Customs Patrol or somethin'." There was a distant clang, and a faint tremor ran through the floor. "I ain't superstitious ner nothin'," Chip said. "But I'll be triple-damned if that ain't them boarding us now." Ten minutes passed before bootsteps sounded outside the door, accompanied by a clicking patter. The doorknob rattled, then a heavy knock shook the door. "They got to look you over," Chip whispered. "Nosy damn Sweaties." "Unlock it, Chip." The chef opened the door. "Come in, damn you," he said. A tall and grotesque creature minced into the room, tiny hoof-like feet tapping on the floor. A flaring metal helmet shaded the deep-set compound eyes, and a loose mantle flapped around the knobbed knees. Behind the alien, the captain hovered nervously. "Yo' papiss," the alien rasped. "Who's your friend, Captain?" Retief said. "Never mind; just do like he tells you." "Yo' papiss," the alien said again. "Okay," Retief said. "I've seen it. You can take it away now." "Don't horse around," the captain said. "This fellow can get mean." The alien brought two tiny arms out from the concealment of the mantle, clicked toothed pincers under Retief's nose. "Quick, soft one." "Captain, tell your friend to keep its distance. It looks brittle, and I'm tempted to test it." "Don't start anything with Skaw; he can clip through steel with those snappers." "Last chance," Retief said. Skaw stood poised, open pincers an inch from Retief's eyes. "Show him your papers, you damned fool," the captain said hoarsely. "I got no control over Skaw." The alien clicked both pincers with a sharp report, and in the same instant Retief half-turned to the left, leaned away from the alien and drove his right foot against the slender leg above the bulbous knee-joint. Skaw screeched and floundered, greenish fluid spattering from the burst joint. "I told you he was brittle," Retief said. "Next time you invite pirates aboard, don't bother to call." "Jesus, what did you do! They'll kill us!" the captain gasped, staring at the figure flopping on the floor. "Cart poor old Skaw back to his boat," Retief said. "Tell him to pass the word. No more illegal entry and search of Terrestrial vessels in Terrestrial space." "Hey," Chip said. "He's quit kicking." The captain bent over Skaw, gingerly rolled him over. He leaned close and sniffed. "He's dead." The captain stared at Retief. "We're all dead men," he said. "These Soetti got no mercy." "They won't need it. Tell 'em to sheer off; their fun is over." "They got no more emotions than a blue crab—" "You bluff easily, Captain. Show a few guns as you hand the body back. We know their secret now." "What secret? I—" "Don't be no dumber than you got to, Cap'n," Chip said. "Sweaties die easy; that's the secret." "Maybe you got a point," the captain said, looking at Retief. "All they got's a three-man scout. It could work." He went out, came back with two crewmen. They hauled the dead alien gingerly into the hall. "Maybe I can run a bluff on the Soetti," the captain said, looking back from the door. "But I'll be back to see you later." "You don't scare us, Cap'n," Chip said. "Him and Mr. Tony and all his goons. You hit 'em where they live, that time. They're pals o' these Sweaties. Runnin' some kind o' crooked racket." "You'd better take the captain's advice, Chip. There's no point in your getting involved in my problems." "They'd of killed you before now, Mister, if they had any guts. That's where we got it over these monkeys. They got no guts." "They act scared, Chip. Scared men are killers." "They don't scare me none." Chip picked up the tray. "I'll scout around a little and see what's goin' on. If the Sweaties figure to do anything about that Skaw feller they'll have to move fast; they won't try nothin' close to port." "Don't worry, Chip. I have reason to be pretty sure they won't do anything to attract a lot of attention in this sector just now." Chip looked at Retief. "You ain't no tourist, Mister. I know that much. You didn't come out here for fun, did you?" "That," Retief said, "would be a hard one to answer." IV Retief awoke at a tap on his door. "It's me, Mister. Chip." "Come on in." The chef entered the room, locking the door. "You shoulda had that door locked." He stood by the door, listening, then turned to Retief. "You want to get to Jorgensen's perty bad, don't you, Mister?" "That's right, Chip." "Mr. Tony give the captain a real hard time about old Skaw. The Sweaties didn't say nothin'. Didn't even act surprised, just took the remains and pushed off. But Mr. Tony and that other crook they call Marbles, they was fit to be tied. Took the cap'n in his cabin and talked loud at him fer half a hour. Then the cap'n come out and give some orders to the Mate." Retief sat up and reached for a cigar. "Mr. Tony and Skaw were pals, eh?" "He hated Skaw's guts. But with him it was business. Mister, you got a gun?" "A 2mm needler. Why?" "The orders cap'n give was to change course fer Alabaster. We're by-passin' Jorgensen's Worlds. We'll feel the course change any minute." Retief lit the cigar, reached under the mattress and took out a short-barreled pistol. He dropped it in his pocket, looked at Chip. "Maybe it was a good thought, at that. Which way to the Captain's cabin?" "This is it," Chip said softly. "You want me to keep an eye on who comes down the passage?" Retief nodded, opened the door and stepped into the cabin. The captain looked up from his desk, then jumped up. "What do you think you're doing, busting in here?" "I hear you're planning a course change, Captain." "You've got damn big ears." "I think we'd better call in at Jorgensen's." "You do, huh?" the captain sat down. "I'm in command of this vessel," he said. "I'm changing course for Alabaster." "I wouldn't find it convenient to go to Alabaster," Retief said. "So just hold your course for Jorgensen's." "Not bloody likely." "Your use of the word 'bloody' is interesting, Captain. Don't try to change course." The captain reached for the mike on his desk, pressed the key. "Power Section, this is the captain," he said. Retief reached across the desk, gripped the captain's wrist. "Tell the mate to hold his present course," he said softly. "Let go my hand, buster," the captain snarled. Eyes on Retief's, he eased a drawer open with his left hand, reached in. Retief kneed the drawer. The captain yelped and dropped the mike. "You busted it, you—" "And one to go," Retief said. "Tell him." "I'm an officer of the Merchant Service!" "You're a cheapjack who's sold his bridge to a pack of back-alley hoods." "You can't put it over, hick." "Tell him." The captain groaned and picked up the mike. "Captain to Power Section," he said. "Hold your present course until you hear from me." He dropped the mike and looked up at Retief. "It's eighteen hours yet before we pick up Jorgensen Control. You going to sit here and bend my arm the whole time?" Retief released the captain's wrist and turned to the door. "Chip, I'm locking the door. You circulate around, let me know what's going on. Bring me a pot of coffee every so often. I'm sitting up with a sick friend." "Right, Mister. Keep an eye on that jasper; he's slippery." "What are you going to do?" the captain demanded. Retief settled himself in a chair. "Instead of strangling you, as you deserve," he said, "I'm going to stay here and help you hold your course for Jorgensen's Worlds." The captain looked at Retief. He laughed, a short bark. "Then I'll just stretch out and have a little nap, farmer. If you feel like dozing off sometime during the next eighteen hours, don't mind me." Retief took out the needler and put it on the desk before him. "If anything happens that I don't like," he said, "I'll wake you up. With this."
|
B. Retief will ensure the ship travels to Jorgensen's World, as initially planned
|
Which is the best description of Colonel Klett?
A. He is ornery and a bit tempermental
B. He is sly and willing to accept authoritative responsibility
C. He is a liar and tricks Lane into helping him
D. He is paranoid and does not want to take risks
|
MUTINEER By ROBERT J. SHEA For every weapon there was a defense, but not against the deadliest weapon—man himself! Raging , Trooper Lane hovered three thousand feet above Tammany Square. The cool cybrain surgically implanted in him was working on the problem. But Lane had no more patience. They'd sweat, he thought, hating the chill air-currents that threw his hovering body this way and that. He glared down at the three towers bordering on the Square. He spat, and watched the little white speck fall, fall. Lock me up in barracks. All I wanted was a little time off. Did I fight in Chi for them? Damn right I did. Just a little time off, so I shouldn't blow my top. Now the lid's gone. He was going over all their heads. He'd bowled those city cops over like paper dolls, back at the Armory. The black dog was on Lane's back. Old Mayor himself was going to hear about it. Why not? Ain't old Mayor the CinC of the Newyork Troopers? The humming paragrav-paks embedded beneath his shoulder blades held him motionless above Newyork's three administrative towers. Tammany Hall. Mayor's Palace. Court House. Lane cursed his stupidity. He hadn't found out which one was which ahead of time. They keep Troopers in the Armory and teach them how to fight. They don't teach them about their own city, that they'll be fighting for. There's no time. From seven years old up, Troopers have too much to learn about fighting. The Mayor was behind one of those thousands of windows. Old cybrain, a gift from the Trooper surgeons, compliments of the city, would have to figure out which one. Blood churned in his veins, nerves shrieked with impatience. Lane waited for the electronic brain to come up with the answer. Then his head jerked up, to a distant buzz. There were cops coming. Two black paragrav-boats whirred along the translucent underside of Newyork's anti-missile force-shield, the Shell. Old cybrain better be fast. Damn fast! The cybrain jolted an impulse through his spine. Lane somersaulted. Cybrain had taken charge of his motor nerves. Lane's own mind was just along for the ride. His body snapped into a stiff dive position. He began to plummet down, picking up speed. His mailed hands glittered like arrowheads out in front. They pointed to a particular window in one of the towers. A predatory excitement rippled through him as he sailed down through the air. It was like going into battle again. A little red-white-and-green flag fluttered on a staff below the window. Whose flag? The city flag was orange and blue. He shrugged away the problem. Cybrain knew what it was doing. The little finger of his right hand vibrated in its metal sheath. A pale vibray leaped from the lensed fingertip. Breakthrough! The glasstic pane dissolved. Lane streamed through the window. The paragrav-paks cut off. Lane dropped lightly to the floor, inside the room, in battle-crouch. A 3V set was yammering. A girl screamed. Lane's hand shot out automatically. A finger vibrated. Out of the corner of his eye, Lane saw the girl fold to the floor. There was no one else in the room. Lane, still in a crouch, chewed his lip. The Mayor? His head swung around and he peered at the 3V set. He saw his own face. "Lashing police with his vibray," said the announcer, "Lane broke through the cordon surrounding Manhattan Armory. Two policemen were killed, four others seriously injured. Tammany Hall has warned that this man is extremely dangerous. Citizens are cautioned to keep clear of him. Lane is an insane killer. He is armed with the latest military weapons. A built-in electronic brain controls his reflexes—" "At ease with that jazz," said Lane, and a sheathed finger snapped out. There was a loud bang. The 3V screen dissolved into a puddle of glasstic. The Mayor. Lane strode to the window. The two police boats were hovering above the towers. Lane's mailed hand snapped open a pouch at his belt. He flipped a fist-sized cube to the floor. The force-bomb "exploded"—swelled or inflated, really, but with the speed of a blast. Lane glanced out the window. A section of the energy globe bellied out from above. It shaded the view from his window and re-entered the tower wall just below. Now the girl. He turned back to the room. "Wake up, outa-towner." He gave the blonde girl a light dose of the vibray to slap her awake. "Who are you?" she said, shakily. Lane grinned. "Trooper Lane, of the Newyork Special Troops, is all." He threw her a mock salute. "You from outa-town, girlie. I ain't seen a Newyork girl with yellow hair in years. Orange or green is the action. Whatcha doing in the Mayor's room?" The girl pushed herself to her feet. Built, Lane saw. She was pretty and clean-looking, very out-of-town. She held herself straight and her blue-violet eyes snapped at him. "What the devil do you think you're doing, soldier? I am a diplomat of the Grassroots Republic of Mars. This is an embassy, if you know what that means." "I don't," said Lane, unconcerned. "Well, you should have had brains enough to honor the flag outside this window. That's the Martian flag, soldier. If you've never heard of diplomatic immunity, you'll suffer for your ignorance." Her large, dark eyes narrowed. "Who sent you?" "My cybrain sent me." She went openmouthed. "You're Lane ." "I'm the guy they told you about on the 3V. Where's the Mayor? Ain't this his place?" "No. No, you're in the wrong room. The wrong building. That's the Mayor's suite over there." She pointed. "See where the balcony is? This is the Embassy suite. If you want the Mayor you'll have to go over there." "Whaddaya know," said Lane. "Cybrain didn't know, no more than me." The girl noticed the dark swell of the force-globe. "What's that out there?" "Force-screen. Nothing gets past, except maybe a full-size blaster-beam. Keeps cops out. Keeps you in. You anybody important?" "I told you, I'm an ambassador. From Mars. I'm on a diplomatic mission." "Yeah? Mars a big city?" She stared at him, violet eyes wide. "The planet Mars." "Planet? Oh, that Mars. Sure, I've heard of it—you gotta go by spaceship. What's your name?" "Gerri Kin. Look, Lane, holding me is no good. It'll just get you in worse trouble. What are you trying to do?" "I wanna see the Mayor. Me and my buddies, we just come back from fighting in Chi, Gerri. We won. They got a new Mayor out there in Chi. He takes orders from Newyork." Gerri Kin said, "That's what the force-domes did. The perfect defense. But also the road to the return to city-states. Anarchy." Lane said, "Yeah? Well, we done what they wanted us to do. We did the fighting for them. So we come back home to Newyork and they lock us up in the Armory. Won't pay us. Won't let us go nowhere. They had cops guarding us. City cops." Lane sneered. "I busted out. I wanna see the Mayor and find out why we can't have time off. I don't play games, Gerri. I go right to the top." Lane broke off. There was a hum outside the window. He whirled and stared out. The rounded black hulls of the two police paragrav-boats were nosing toward the force-screen. Lane could read the white numbers painted on their bows. A loudspeaker shouted into the room: "Come out of there, Lane, or we'll blast you out." "You can't," Lane called. "This girl from Mars is here." "I repeat, Lane—come out or we'll blast you out." Lane turned to the girl. "I thought you were important." She stood there with her hands together, calmly looking at him. "I am. But you are too, to them. Mars is millions of miles away, and you're right across the Square from the Mayor's suite." "Yeah, but—" Lane shook his head and turned back to the window. "All right, look! Move them boats away and I'll let this girl out!" "No deal, Lane. We're coming in." The police boats backed away slowly, then shot straight up, out of the line of vision. Lane looked down at the Square. Far below, the long, gleaming barrel of a blaster cannon caught the dim light filtering down through Newyork's Shell. The cannon trundled into the Square on its olive-drab, box-shaped caterpillar mounting and took up a position equidistant from the bases of the three towers. Now a rumble of many voices rose from below. Lane stared down to see a large crowd gathering in Tammany Square. Sound trucks were rolling to a stop around the edges of the crowd. The people were all looking up. Lane looked across the Square. The windows of the tower opposite, the ones he could see clearly, were crowded with faces. There were white dot faces on the balcony that Gerri Kin had pointed out as the Mayor's suite. The voice of a 3V newscaster rolled up from the Square, reechoing against the tower walls. "Lane is holding the Martian Ambassador, Gerri Kin, hostage. You can see the Martian tricolor behind his force-globe. Police are bringing up blaster cannon. Lane's defense is a globe of energy similar to the one which protects Newyork from aerial attack." Lane grinned back at Gerri Kin. "Whole town's down there." Then his grin faded. Nice-looking, nice-talking girl like this probably cared a lot more about dying than he did. Why the hell didn't they give him a chance to let her out? Maybe he could do it now. Cybrain said no. It said the second he dropped his force-screen, they'd blast this room to hell. Poor girl from Mars, she didn't have a chance. Gerri Kin put her hand to her forehead. "Why did you have to pick my room? Why did they send me to this crazy city? Private soldiers. Twenty million people living under a Shell like worms in a corpse. Earth is sick and it's going to kill me. What's going to happen?" Lane looked sadly at her. Only two kinds of girls ever went near a Trooper—the crazy ones and the ones the city paid. Why did he have to be so near getting killed when he met one he liked? Now that she was showing a little less fear and anger, she was talking straight to him. She was good, but she wasn't acting as if she was too good for him. "They'll start shooting pretty quick," said Lane. "I'm sorry about you." "I wish I could write a letter to my parents," she said. "What?" "Didn't you understand what I said?" "What's a letter?" "You don't know where Mars is. You don't know what a letter is. You probably can't even read and write!" Lane shrugged. He carried on the conversation disinterestedly, professionally relaxed before battle. "What's these things I can't do? They important?" "Yes. The more I see of this city and its people, the more important I realize they are. You know how to fight, don't you? I'll bet you're perfect with those weapons." "Listen. They been training me to fight since I was a little kid. Why shouldn't I be a great little fighter?" "Specialization," said the girl from Mars. "What?" "Specialization. Everyone I've met in this city is a specialist. SocioSpecs run the government. TechnoSpecs run the machinery. Troopers fight the wars. And ninety per cent of the people don't work at all because they're not trained to do anything." "The Fans," said Lane. "They got it soft. That's them down there, come to watch the fight." "You know why you were kept in the Armory, Lane? I heard them talking about it, at the dinner I went to last night." "Why?" "Because they're afraid of the Troopers. You men did too good a job out in Chi. You are the deadliest weapon that has ever been made. You. Single airborne infantrymen!" Lane said, "They told us in Trooper Academy that it's the men that win the wars." "Yes, but people had forgotten it until the SocioSpecs of Newyork came up with the Troopers. Before the Troopers, governments concentrated on the big weapons, the missiles, the bombs. And the cities, with the Shells, were safe from bombs. They learned to be self-sufficient under the Shells. They were so safe, so isolated, that national governments collapsed. But you Troopers wiped out that feeling of security, when you infiltrated Chi and conquered it." "We scared them, huh?" Gerri said, "You scared them so much that they were afraid to let you have a furlough in the city when you came back. Afraid you Troopers would realize that you could easily take over the city if you wanted to. You scared them so much that they'll let me be killed. They'll actually risk trouble with Mars just to kill you." "I'm sorry about you. I mean it, I like—" At that moment a titanic, ear-splitting explosion hurled him to the carpet, deafened and blinded him. He recovered and saw Gerri a few feet away, dazed, groping on hands and knees. Lane jumped to the window, looked quickly, sprang back. Cybrain pumped orders to his nervous system. "Blaster cannon," he said. "But just one. Gotcha, cybrain. I can beat that." He picked up the black box that generated his protective screen. Snapping it open with thumb-pressure, he turned a small dial. Then he waited. Again an enormous, brain-shattering concussion. Again Lane and Gerri were thrown to the floor. But this time there was a second explosion and a blinding flash from below. Lane laughed boyishly and ran to the window. "Look!" he called to Gerri. There was a huge gap in the crowd below. The pavement was blackened and shattered to rubble. In and around the open space sprawled dozens of tiny black figures, not moving. "Backfire," said Lane. "I set the screen to throw their blaster beam right back at them." "And they knew you might—and yet they let a crowd congregate!" Gerri reeled away from the window, sick. Lane said, "I can do that a couple times more, but it burns out the force-globe. Then I'm dead." He heard the 3V newscaster's amplified voice: "—approximately fifty killed. But Lane is through now. He has been able to outthink police with the help of his cybrain. Now police are feeding the problem to their giant analogue computer in the sub-basement of the Court House. The police analogue computer will be able to outthink Lane's cybrain, will predict Lane's moves in advance. Four more blaster cannon are coming down Broadway—" "Why don't they clear those people out of the Square?" Gerri cried. "What? Oh, the Fans—nobody clears them out." He paused. "I got one more chance to try." He raised a mailed glove to his mouth and pressed a small stud in the wrist. He said, "Trooper HQ, this is Lane." A voice spoke in his helmet. "Lane, this is Trooper HQ. We figured you'd call." "Get me Colonel Klett." Thirty seconds passed. Lane could hear the clank of caterpillar treads as the mobile blaster cannon rolled into Tammany Square. The voice of the commanding officer of the Troopers rasped into Lane's ear: "Meat-head! You broke out against my orders! Now look at you!" "I knew you didn't mean them orders, sir." "If you get out of there alive, I'll hang you for disobeying them!" "Yes, sir. Sir, there's a girl here—somebody important—from Mars. You know, the planet. Sir, she told me we could take over the city if we got loose. That right, sir?" There was a pause. "Your girl from Mars is right, Lane. But it's too late now. If we had moved first, captured the city government, we might have done it. But they're ready for us. They'd chop us down with blaster cannon." "Sir, I'm asking for help. I know you're on my side." "I am, Lane." The voice of Colonel Klett was lower. "I'd never admit it if you had a chance of getting out of there alive. You've had it, son. I'd only lose more men trying to rescue you. When they feed the data into that analogue computer, you're finished." "Yes, sir." "I'm sorry, Lane." "Yes, sir. Over and out." Lane pressed the stud on his gauntlet again. He turned to Gerri. "You're okay. I wish I could let you out. Old cybrain says I can't. Says if I drop the force-globe for a second, they'll fire into the room, and then we'll both be dead." Gerri stood with folded arms and looked at him. "Do what you have to do. As far as I can see, you're the only person in this city that has even a little bit of right on his side." Lane laughed. "Any of them purple-haired broads I know would be crazy scared. You're different." "When my grandparents landed on Mars, they found out that selfishness was a luxury. Martians can't afford it." Lane frowned with the effort of thinking. "You said I had a little right on my side. That's a good feeling. Nobody ever told me to feel that way about myself before. It'll be better to die knowing that." "I know," she said. The amplified voice from below said, "The police analogue computer is now hooked directly to the controls of the blaster cannon battery. It will outguess Lane's cybrain and check his moves ahead of time." Lane looked at Gerri. "How about giving me a kiss before they get us? Be nice if I kissed a girl like you just once in my life." She smiled and walked forward. "You deserve it, Lane." He kissed her and it filled him with longings for things he couldn't name. Then he stepped back and shook his head. "It ain't right you should get killed. If I take a dive out that window, they shoot at me, not in here." "And kill you all the sooner." "Better than getting burned up in this lousy little room. You also got right on your side. There's too many damn Troopers and not enough good persons like you. Old cybrain says stay here, but I don't guess I will. I'm gonna pay you back for that kiss." "But you're safe in here!" "Worry about yourself, not about me." Lane picked up the force-bomb and handed it to her. "When I say now, press this. Then take your hand off, real fast. It'll shut off the screen for a second." He stepped up on to the window ledge. Automatically, the cybrain cut in his paragrav-paks. "So long, outa-towner. Now! " He jumped. He was hurtling across the Square when the blaster cannons opened up. They weren't aimed at the window where the little red-white-and-green tricolor was flying. But they weren't aimed at Lane, either. They were shooting wild. Which way now? Looks like I got a chance. Old cybrain says fly right for the cannons. He saw the Mayor's balcony ahead. Go to hell, old cybrain. I'm doing all right by myself. I come to see the Mayor, and I'm gonna see him. Lane plunged forward. He heard the shouts of frightened men. He swooped over the balcony railing. A man was pointing a blaster pistol at him. There were five men on the balcony—emergency! Years of training and cybrain took over. Lane's hand shot out, fingers vibrating. As he dropped to the balcony floor in battle-crouch, the men slumped around him. He had seen the man with the blaster pistol before. It was the Mayor of Newyork. Lane stood for a moment in the midst of the sprawled men, the shrieks of the crowd floating up to him. Then he raised his glove to his lips. He made contact with Manhattan Armory. "Colonel Klett, sir. You said if we captured the city government we might have a chance. Well, I captured the city government. What do we do with it now?" Lane was uncomfortable in his dress uniform. First there had been a ceremony in Tammany Square inaugurating Newyork's new Military Protectorate, and honoring Trooper Lane. Now there was a formal dinner. Colonel Klett and Gerri Kin sat on either side of Lane. Klett said, "Call me an opportunist if you like, Miss Kin, my government will be stable, and Mars can negotiate with it." He was a lean, sharp-featured man with deep grooves in his face, and gray hair. Gerri shook her head. "Recognition for a new government takes time. I'm going back to Mars, and I think they'll send another ambassador next time. Nothing personal—I just don't like it here." Lane said, "I'm going to Mars, too." "Did she ask you to?" demanded Klett. Lane shook his head. "She's got too much class for me. But I like what she told me about Mars. It's healthy, like." Klett frowned. "If I thought there was a gram of talent involved in your capture of the Mayor, Lane, I'd never release you from duty. But I know better. You beat that analogue computer by sheer stupidity—by disregarding your cybrain." Lane said, "It wasn't so stupid if it worked." "That's what bothers me. It calls for a revision in our tactics. We've got a way of beating those big computers now, should anyone use them against us." "I just didn't want her to be hurt." "Exactly. The computer could outguess a machine, like your cybrain. But you introduced a totally unpredictable factor—human emotion. Which proves what I, as a military man, have always maintained—that the deadliest weapon in man's arsenal is still, and will always be, the individual soldier." "What you just said there, sir," said Lane. "That's why I'm leaving Newyork." "What do you mean?" asked Colonel Klett. "I'm tired of being a weapon, sir. I want to be a human being." END Work is the elimination of the traces of work. —Michelangelo Transcriber's Note: This etext was produced from If July 1959. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed. Minor spelling and typographical errors have been corrected without note.
|
B. He is sly and willing to accept authoritative responsibility
|
What was identified in Mr. Chapman's blood cultures during his stay from 04/03/2017 to 05/01/2017?
Choose the correct answer from the following options:
A. E. coli
B. Pseudomonas aeruginosa
C. Staphylococcus capitis
D. Streptococcus pneumoniae
E. Klebsiella pneumoniae
|
### Patient Report 0
**Dear colleague, **
We are reporting on our shared patient, Mr. John Chapman, born on
11/16/1994, who received emergency treatment at our clinic on
04/03/2017.
**Diagnoses**:
- Severe open traumatic brain injury with fractures of the cranial
vault, mastoid, and skull base
- Dissection of the distal internal carotid artery on both sides
- Subarachnoid hemorrhage involving both hemispheres and extending
into the basal cisterns
- Aspiration pneumonia
**Other Diagnoses: **
- Status post rib fracture 2005
- Status post appendectomy 2006
- Status post distal radius fracture 2008
- Status post elbow fracture 20010
**Procedure**: External ventricular drain (EVD) placement.
**Medical History:** Admission through the emergency department as a
polytrauma alert. The patient was involved in a motocross accident,
where he jumped, fell, and landed face-first. He was intubated at the
scene, and either during or before intubation, aspiration occurred. No
issues with airway, breathing, or circulation (A, B, or C problems) were
noted. A CT scan performed in the emergency department revealed an open
traumatic brain injury with fractures of the cranial vault, mastoid, and
skull base, as well as dissection of both carotid arteries. Upon
admission, we encountered an intubated and sedated patient with a
Richmond Agitation-Sedation Scale (RASS) score of -4. He was
hemodynamically stable at all times.
**Current Recommendations:**
- Regular checks of vigilance, laboratory values and microbiological
findings.
- Careful balancing
### Patient Report 1
**Dear colleague, **
We report on Mr. John Chapman, born on 11/16/1994, who was admitted to
our Intensive Care Unit from 04/03/2017 to 05/01/2017.
**Diagnoses:**
- Open severe traumatic brain injury with fractures of the skull
vault, mastoid, and skull base
- Dissection of the distal ACI on both sides
- Subarachnoid hemorrhage involving both hemispheres and extending
into basal cisterns
- Infarct areas in the border zone between MCA-ACA on the right
frontal and left parietal sides
- Malresorptive hydrocephalus
<!-- -->
- Rhabdomyolysis
- Aspiration pneumonia
**Other Diagnoses: **
- Status post rib fracture in 2005
- Status post appendectomy in 2006
- Status post distal radius fracture in 2008
- Status post elbow fracture in 20010
**Surgical Procedures:**
- 04/03/2017: Placement of external ventricular drain
- 04/08/2017: Placement of an intracranial pressure monitoring
catheter
- 04/13/2017: Surgical tracheostomy
- 05/01/2017: Left ventriculoperitoneal shunt placement
**Medical History:** The patient was admitted through the emergency
department as a polytrauma alert. The patient had fallen while riding a
motocross bike, landing face-first after jumping. He was intubated at
the scene. Aspiration occurred either during or before intubation. No
problems with breathing or circulation were noted. The CT performed in
the emergency department showed an open traumatic brain injury with
fractures of the skull vault, mastoid, and skull base, as well as
dissection of the carotid arteries on both sides and bilateral
subarachnoid hemorrhage.
Upon admission, the patient was sedated and intubated, with a Richmond
Agitation-Sedation Scale (RASS) score of -4, and was hemodynamically
stable under controlled ventilation.
**Therapy and Progression:**
[Neurology]{.underline}: Following the patient\'s admission, an external
ventricular drain was placed. Reduction of sedation had to be
discontinued due to increased intracranial pressure. A right pupil size
greater than the left showed no intracranial correlate. With
persistently elevated intracranial pressure, intensive intracranial
pressure therapy was initiated using deeper sedation, administration of
hyperosmolar sodium, and cerebrospinal fluid drainage, which normalized
intracranial pressure. Intermittently, there were recurrent intracranial
pressure peaks, which could be treated conservatively. Transcranial
Doppler examinations showed normal flow velocities. Microbiological
samples from cerebrospinal fluid were obtained when the patient had
elevated temperatures, but no bacterial growth was observed. Due to the
inability to adequately monitor intracranial pressure via the external
ventricular drain, an intracranial pressure monitoring catheter was
placed to facilitate adequate intracranial pressure monitoring. In the
perfusion computed tomography, progressive edema with increasingly
obstructed external ventricular spaces and previously known infarcts in
the border zone area were observed. To ensure appropriate intracranial
pressure monitoring, a Tuohy drain was inserted due to cerebrospinal
fluid buildup on 04/21/2017. After the initiation of antibiotic therapy
for suspected ventriculitis, the intracranial pressure monitoring
catheter was removed on 04/20/2017. Subsequently, a liquorrhea
developed, leading to the placement of a Tuohy drain. After successful
antibiotic treatment of ventriculitis, a ventriculoperitoneal shunt was
placed on 05/01/2017 without complications, and the Tuohy drain was
removed. Radiological control confirmed the correct positioning. The
patient gradually became more alert. Both pupils were isochoric and
reacted to light. All extremities showed movement, although the patient
only intermittently responded to commands. On 05/01/2017, a VP shunt was
placed on the left side without complications. Currently, the patient is
sedated with continuous clonidine at 60µg/h.
**Hemodynamics**: To maintain cerebral perfusion pressure in the
presence of increased intracranial pressure, circulatory support with
vasopressors was necessary. Echocardiography revealed preserved cardiac
function without wall motion abnormalities or right heart strain,
despite the increasing need for noradrenaline support. As the patient
had bilateral carotid dissection, a therapy with Aspirin 100mg was
initiated. On 04/16/2017, clinical examination revealed right\>left leg
circumference difference and redness of the right leg. Utrasound
revealed a long-segment deep vein thrombosis in the right leg, extending
from the pelvis (proximal end of the thrombus not clearly delineated) to
the lower leg. Therefore, Heparin was increased to a therapeutic dose.
Heparin therapy was paused on postoperative day 1, and prophylactic
anticoagulation started, followed by therapeutic anticoagulation on
postoperative day 2. The patient was switched to subcutaneous Lovenox.
**Pulmonary**: Due to the history of aspiration in the prehospital
setting, a bronchoscopy was performed, revealing a moderately obstructed
bronchial system with several clots. As prolonged sedation was
necessary, a surgical tracheostomy was performed without complications
on 04/13/2017. Subsequently, we initiated weaning from mechanical
ventilation. The current weaning strategy includes 12 hours of
synchronized intermittent mandatory ventilation (SIMV) during the night,
with nighttime pressure support ventilation (DuoPAP: Ti high 1.3s,
respiratory rate 11/min, Phigh 11 mbar, PEEP 5 mbar, Psupport 5 mbar,
trigger 4l, ramp 50 ms, expiratory trigger sensitivity 25%).
**Abdomen**: FAST examinations did not reveal any signs of
intra-abdominal trauma. Enteral feeding was initiated via a gastric
tube, along with supportive parenteral nutrition. With forced bowel
movement measures, the patient had regular bowel movements. On
04/17/2017, a complication-free PEG (percutaneous endoscopic
gastrostomy) placement was performed due to the potential long-term need
for enteral nutrition. The PEG tube is currently being fed with tube
feed nutrition, with no bowel movement for the past four days.
Additionally, supportive parenteral nutrition is being provided.
**Kidney**: Initially, the patient had polyuria without confirming
diabetes insipidus, and subsequently, adequate diuresis developed.
Retention parameters were within the normal range. As crush parameters
increased, a therapy involving forced diuresis was initiated, resulting
in a significant reduction of crush parameters.
**Infection Course:** Upon admission, with elevated infection parameters
and intermittently febrile temperatures, empirical antibiotic therapy
was initiated for suspected pneumonia using Piperacillin/Tazobactam.
Staphylococcus capitis was identified in blood cultures, and
Staphylococcus aureus was found in bronchial lavage. Both microbes were
sensitive to the current antibiotic therapy, so treatment with
Piperacillin/Tazobactam continued. Additionally, Enterobacter cloacae
was identified in tracheobronchial secretions during the course, also
sensitive to the ongoing antibiotic therapy. On 05/17, the patient
experienced another fever episode with elevated infection parameters and
right lower lobe infiltrates in the chest X-ray. After obtaining
microbiological samples, antibiotic therapy was switched to Meropenem
for suspected pneumonia. Microbiological findings from cerebrospinal
fluid indicated gram-negative rods. Therefore, antibiotic therapy was
adjusted to Ciprofloxacin in accordance with susceptibility testing due
to suspected ventriculitis, and the Meropenem dose was increased. This
led to a reduction in infection parameters. Finally, microbiological
examination of cerebrospinal fluid, blood cultures, and urine revealed
no pathological findings. Infection parameters decreased. We recommend
continuing antibiotic therapy until 05/02/2017.
**Anti-Infective Course: **
- Piperacillin/Tazobactam 04/03/2017-04/16/2017: Staph. Capitis in
Blood Culture Staph. Aureus in Bronchial Lavage
- Meropenem 04/16/2017-present (increased dose since 04/18) CSF:
gram-negative rods in Blood Culture: Pseudomonas aeruginosa
Acinetobacter radioresistens
- Ciprofloxacin 04/18/2017-present CSF: gram-negative rods in Blood
Culture: Pseudomonas aeruginosa, Acinetobacter radioresistens
**Weaning Settings:** Weaning Stage 6: 12-hour synchronized intermittent
mandatory ventilation (SIMV) with DuoPAP during the night (Thigh 1.3s,
respiratory rate 11/min, Phigh 11 mbar, PEEP 5 mbar, Psupport 5 mbar,
trigger 4l, ramp 50 ms, expiratory trigger sensitivity 25%).
**Status at transfer:** Currently, Mr. Chapman is monosedated with
Clonidine. He spontaneously opens both eyes and spontaneously moves all
four extremities. Pupils are bilaterally moderately dilated, round and
sensitive to light. There is bulbar divergence. Circulation is stable
without catecholamine therapy. He is in the process of weaning,
currently spontaneous breathing with intermittent CPAP. Renal function
is sufficient, enteral nutrition via PEG with supportive parenteral
nutrition is successful.
**Current Medication:**
**Medication** **Dosage** **Frequency**
------------------------------------ ---------------- ---------------
Bisoprolol (Zebeta) 2.5 mg 1-0-0
Ciprofloxacin (Cipro) 400 mg 1-1-1
Meropenem (Merrem) 4 g Every 4 hours
Morphine Hydrochloride (MS Contin) 10 mg 1-1-1-1-1-1
Polyethylene Glycol 3350 (MiraLAX) 13.1 g 1-1-1
Acetaminophen (Tylenol) 1000 mg 1-1-1-1
Aspirin 100 mg 1-0-0
Enoxaparin (Lovenox) 30 mg (0.3 mL) 0-0-1
Enoxaparin (Lovenox) 70 mg (0.7 mL) 1-0-1
**Lab results:**
**Parameter** **Results** **Reference Range**
-------------------- ------------- ---------------------
Creatinine (Jaffé) 0.42 mg/dL 0.70-1.20 mg/dL
Urea 31 mg/dL 17-48 mg/dL
Total Bilirubin 0.35 mg/dL \< 1.20 mg/dL
Hemoglobin 7.6 g/dL 13.5-17.0 g/dL
Hematocrit 28% 39.5-50.5%
Red Blood Cells 3.5 M/uL 4.3-5.8 M/uL
White Blood Cells 10.35 K/uL 3.90-10.50 K/uL
Platelets 379 K/uL 150-370 K/uL
MCV 77.2 fL 80.0-99.0 fL
MCH 24.1 pg 27.0-33.5 pg
MCHC 32.5 g/dL 31.5-36.0 g/dL
MPV 11.3 fL 7.0-12.0 fL
RDW-CV 17.7% 11.5-15.0%
Quick 54% 78-123%
INR 1.36 0.90-1.25
aPTT 32.8 sec 25.0-38.0 sec
**Addition: Radiological Findings**
[Clinical Information and Justification:]{.underline} Suspected deep
vein thrombosis (DVT) on the right leg.
[Special Notes:]{.underline} Examination at the bedside in the intensive
care unit, no digital image archiving available.
[Findings]{.underline}: Confirmation of a long-segment deep venous
thrombosis in the right leg, starting in the pelvis (proximal end not
clearly delineated) and extending to the lower leg.
Visible Inferior Vena Cava without evidence of thrombosis.
The findings were communicated to the treating physician.
**Full-Body Trauma CT on 04/03/2017:**
[Clinical Information and Justification:]{.underline} Motocross
accident. Polytrauma alert. Consequences of trauma? Informed consent:
Emergency indication. Recommended monitoring of kidney and thyroid
laboratory parameters.
**Findings**: CCT: Dissection of the distal internal carotid artery on
both sides (left 2-fold).
Signs of generalized elevated intracranial pressure.
Open skull-brain trauma with intracranial air inclusions and skull base
fracture at the level of the roof of the ethmoidal/sphenoidal sinuses
and clivus (in a close relationship to the bilateral internal carotid
arteries) and the temporal
**CT Head on 04/16/2017:**
[Clinical Information and Justification:]{.underline} History of skull
fracture, removal of EVD (External Ventricular Drain). Inquiry about the
course.
[Findings]{.underline}: Regression of ventricular system width (distance
of SVVH currently 41 mm, previously 46 mm) with residual liquor caps,
indicative of regressed hydrocephalus. Interhemispheric fissure in the
midline. No herniation.
Complete regression of subdural hematoma on the left, tentorial region.
Known defect areas on the right frontal lobe where previous catheters
were inserted.
Progression of a newly hypodense demarcated cortical infarct on the
left, postcentral.
Known bilateral skull base fractures involving the petrous bone, with
secretion retention in the mastoid air cells bilaterally. Minimal
secretion also in the sphenoid sinuses.
Postoperative bone fragments dislocated intracranially after right
frontal trepanation.
**Chest X-ray on 04/24/2017.**
[Clinical Information and Justification:]{.underline} Mechanically
ventilated patient. Suspected pneumonia. Question about infiltrates.
[Findings]{.underline}: Several previous images for comparison, last one
from 08/20/2021.
Persistence of infiltrates in the right lower lobe. No evidence of new
infiltrates. Removal of the tracheal tube and central venous catheter
with a newly inserted tracheal cannula. No evidence of pleural effusion
or pneumothorax.
**CT Head on 04/25/2017:**
[Clinical Information and Justification:]{.underline} Severe traumatic
brain injury with brain edema, one External Ventricular Drain removed,
one parenchymal catheter removed; Follow-up.
[Findings]{.underline}: Previous images available, CT last performed on
04/09/17, and MRI on 04/16/17.
Massive cerebrospinal fluid (CSF) stasis supra- and infratentorially
with CSF pressure caps at the ventricular and cisternal levels with
completely depleted external CSF spaces, differential diagnosis:
malresorptive hydrocephalus. The EVD and parenchymal catheter have been
completely removed.
No evidence of fresh intracranial hemorrhage. Residual subdural hematoma
on the left, tentorial. Slight regression of the cerebellar tonsils.
Increasing hypodensity of the known defect zone on the right frontal
region, differential diagnosis: CSF diapedesis. Otherwise, the status is
the same as for the other defects.
Secretion in the sphenoid sinus and mastoid cells bilaterally, known
bilateral skull base fractures.
**Bedside Chest X-ray on 04/262017:**
[Clinical Information and Justification]{.underline}: Respiratory
insufficiency. Inquiry about cardiorespiratory status.
[Findings]{.underline}: Previous image from 08/17/2021.
Left Central Venous Catheter and gastric tube in unchanged position.
Persistent consolidation in the right para-hilar region, differential
diagnosis: contusion or partial atelectasis. No evidence of new
pulmonary infiltrates. No pleural effusion. No pneumothorax. No
pulmonary congestion.
**Brain MRI on 04/26/2017:**
[Clinical Information and Justification:]{.underline} Severe skull-brain
trauma with skull calvarium, mastoid, and skull base fractures.
Assessment of infarct areas/edema for rehabilitation planning.
[Findings:]{.underline} Several previous examinations available.
Persistent small sulcal hemorrhages in both hemispheres (left \> right)
and parenchymal hemorrhage on the left frontal with minimal perifocal
edema.
Narrow subdural hematoma on the left occipital extending tentorially (up
to 2 mm).
No current signs of hypoxic brain damage. No evidence of fresh ischemia.
Slightly regressed ventricular size. No herniation. Unchanged placement
of catheters on the right frontal side. Mastoid air cells blocked
bilaterally due to known bilateral skull base fractures, mucosal
swelling in the sphenoid and ethmoid sinuses. Polypous mucosal swelling
in the left maxillary sinus. Other involved paranasal sinuses and
mastoids are clear.
**Bedside Chest X-ray on 04/27/2017:**
[Clinical Information and Justification:]{.underline} Tracheal cannula
placement. Inquiry about the position.
[Findings]{.underline}: Images from 04/03/2017 for comparison.
Tracheal cannula with tip projecting onto the trachea. No pneumothorax.
Regressing infiltrate in the right lower lung field. No leaking pleural
effusions.
Left ubclavian central venous catheter with tip projecting onto the
superior vena cava. Gastric tube in situ.
**CT Head on 04/28/2017:**
[Clinical Information and Justification:]{.underline} Open head injury,
bilateral subarachnoid hemorrhage (SAH), EVD placement. Inquiry about
herniation.
[Findings]{.underline}: Comparison with the last prior examination from
the previous day.
Generalized signs of cerebral edema remain constant, slightly
progressing with a somewhat increasing blurred cortical border,
particularly high frontal.
Essentially constant transtentorial herniation of the midbrain and low
position of the cerebellar tonsils. Marked reduction of inner CSF spaces
and depleted external CSF spaces, unchanged position of the ventricular
drainage catheter with the tip in the left lateral ventricle.
Constant small parenchymal hemorrhage on the left frontal and constant
SDH at the tentorial edge on both sides. No evidence of new intracranial
space-occupying hemorrhage.
Slightly less distinct demarcation of the demarcated infarcts/defect
zones, e.g., on the right frontal region, differential diagnosis:
fogging.
**CT Head Angiography with Perfusion on 04/28/2017:**
[Clinical Information and Justification]{.underline}: Post-traumatic
head injury, rising intracranial pressure, bilateral internal carotid
artery dissection. Inquiry about intracranial bleeding, edema course,
herniation, brain perfusion.
[Emergency indication:]{.underline} Vital indication. Recommended
monitoring of kidney and thyroid laboratory parameters. Consultation
with the attending physician from and the neuroradiology service was
conducted.
[Technique]{.underline}: Native moderately of the neurocranium. CT
angiography of brain-supplying cervical intracranial vessels during
arterial contrast agent phase and perfusion imaging of the neurocranium
after intravenous injection of a total of 140 ml of Xenetix-350. DLP
Head 502.4 mGy*cm. DLP Body 597.4 mGy*cm.
[Findings]{.underline}: Previous images from 08/11/2021 and the last CTA
of the head/neck from 04/03/2017 for comparison.
[Brain]{.underline}: Constant bihemispheric and cerebellar brain edema
with a slit-like appearance of the internal and completely compressed
external ventricular spaces. Constant compression of the midbrain with
transtentorial herniation and a constant tonsillar descent.
Increasing demarcation of infarct areas in the border zone of MCA-ACA on
the right frontal, possibly also on the left frontal. Predominantly
preserved cortex-gray matter contrast, sometimes discontinuous on both
frontal sides, differential diagnosis: artifact-related, differential
diagnosis: disseminated infarct demarcations/contusions.
Unchanged placement of the ventricular drainage from the right frontal
with the catheter tip in the left lateral ventricle anterior horn.
Constant subdural hematoma tentorial and posterior falx. Increasingly
vague delineation of the small frontal parenchymal hemorrhage. No new
space-occupying intracranial bleeding.
No evidence of secondary dislocation of the skull base fracture with
constant fluid collections in the paranasal sinuses and mastoid air
cells. Hematoma possible, cerebrospinal fluid leakage possible.
[CT Angiography Head/Neck]{.underline}: Constant presentation of
bilateral internal carotid artery dissection.
No evidence of higher-grade vessel stenosis or occlusion of the
brain-supplying intracranial arteries.
Moderately dilated venous collateral circuits in the cranial soft
tissues on both sides, right \> left. Moderately dilated ophthalmic
veins on both sides, right \> left.
No evidence of sinus or cerebral venous thrombosis. Slight perfusion
deficits in the area of the described infarct areas and contusions.
No evidence of perfusion mismatches in the perfusion imaging.
Unchanged presentation of the other documented skeletal segments.
Additional Note: Discussion of findings with the responsible medical
colleagues on-site and by telephone, as well as with the neuroradiology
service by telephone, was conducted.
**CT Head on 04/30/2017:**
[Clinical Information and Justification]{.underline}: Open head injury
following a motorcycle accident.. Inquiry about rebleeding, edema, EVD
displacement.
[Findings and Assessment:]{.underline} CT last performed on 04/05/2017
for comparison.
Constant narrow subdural hematoma on both sides, tentorial and posterior
parasagittal. Constant small parenchymal hemorrhage on the left frontal.
No new intracranial bleeding.
Progressively demarcated infarcts on the right frontal and left
parietal.
Slightly progressive compression of the narrow ventricles as an
indication of progressive edema. Completely depleted external CSF spaces
with the ventricular drain catheter in the left lateral ventricle.
Increasing compression of the midbrain due to transtentorial herniation,
progressive tonsillar descent of 6 mm.
Fracture of the skull base and the petrous part of the temporal bone on
both sides without significant displacement. Hematoma in the mastoid and
sphenoid sinuses and the maxillary sinus.
**CT Head on 05/01/2017:**
[Clinical Information and Justification:]{.underline} Open skull-brain
trauma. Inquiry about CSF stasis, bleeding, edema.
[Findings]{.underline}: CT last performed on 04/05/17 for comparison.
Completely regressed subarachnoid hemorrhages on both sides. Minimal SDH
components on the tentorial edges bilaterally (left more than right,
with a 3 mm margin width). No new intracranial bleeding. Continuously
narrow inner ventricular system and narrow basal cisterns. The fourth
ventricle is unfolded. Narrow external CSF spaces and consistently
swollen gyration with global cerebral edema.
Better demarcated circumscribed hypodensity in the centrum semiovale on
the right (Series 3, Image 176) and left (Series 3, Image 203);
Differential diagnosis: fresh infarcts due to distal ACI dissections.
Consider repeat vascular imaging. No midline shift. No herniation.
Regressing intracranial air inclusions. Fracture of the skull base and
the petrous part of the temporal bone on both sides without significant
displacement. Hematoma in the maxillary, sphenoidal, and ethmoidal
sinuses.
**Consultation Reports:**
**1) Consultation with Ophthalmology on 04/03/2017**
[Patient Information:]{.underline}
- Motorbike accident, heavily contaminated eyes.
- Request for assessment.
**Diagnosis:** Motorbike accident
**Findings:** Patient intubated, unresponsive. In cranial CT, the
eyeball appears intact, no retrobulbar hematoma. Intraocular pressure:
Right/left within the normal range. Eyelid margins of both eyes crusty
with sand, inferiorly in the lower lid sac, and on the upper lid with
sand. Lower lid somewhat chemotic. Slight temporal hyperemia in the left
eyelid angle. Both eyes have erosions, small, multiple, superficial.
Lower conjunctival sac clean. Round pupils, anisocoria right larger than
left. Left iris hyperemia, no iris defects in the direct light. Lens
unremarkable. Reduced view of the optic nerve head due to miosis,
somewhat pale, rather sharp-edged, central neuroretinal rim present,
central vessels normal. Left eye, due to narrow pupil, limited view,
optic nerve head not visible, central vessels normal, no retinal
hemorrhages.
**Assessment:** Eyelid and conjunctival foreign bodies removed. Mild
erosions in the lower conjunctival sac. Right optic nerve head somewhat
pale, rather sharp-edged.
**Current Recommendations:**
- Antibiotic eye drops three times a day for both eyes.
- Ensure complete eyelid closure.
**2) Consultation with Craniomaxillofacial (CMF) Surgery on 04/05/2017**
**Patient Information:**
- Motorbike accident with severe open traumatic brain injury with
fractures of the cranial vault, mastoid, and skull base
<!-- -->
- Request for assessment.
- Patient with maxillary fracture.
**Findings:** According to the responsible attending physician,
\"minimal handling in case of decompensating intracranial pressure\" is
indicated. Therefore, currently, a cautious approach is suggested
regarding surgical intervention for the radiologically hardly displaced
maxillary fracture. Re-consultation is possible if there are changes in
the clinical outcome.
**Assessment:** Awaiting developments.
**3) Consultation with Neurology on 04/06/2017**
**Patient Information:**
- Brain edema following a severe open traumatic brain injury with
fractures of the cranial vault, mastoid, and skull base
<!-- -->
- Request for assessment.
- Traumatic subarachnoid hemorrhage, intracranial artery dissection,
and various other injuries.
**Findings:** Patient comatose, intubated, sedated. Isocoric pupils. No
light reaction in either eye. No reaction to pain stimuli for
vestibulo-ocular reflex and oculomotor responses. Babinski reflex
negative.
**Assessment:** Long-term ventilation due to a history of intracerebral
bleeding and skull base fracture. No response to pain stimuli or light
reactions in the eyes.
**Procedure/Therapy Suggestion:** Monitoring of patient condition.
**4) Consultation with ENT on 04/16/2017**
**Patient Information:** Tracheostomy tube change.
**Findings:** Tracheostomy tube change performed. Stoma unremarkable.
Trachea clear up to the bifurcation. Sutures in place.
**Assessment:** Re-consultation on 08/27/2021 for suture removal.
**5) Consultation with Neurology on 04/22/2017**
**Patient Information:** Adduction deficit., Request for assessment.
**Findings:** Long-term ventilation due to a history of intracerebral
bleeding and skull base fracture. Adduction deficit in the right eye and
horizontal nystagmus.
**Assessment:** Suspected mesencephalic lesion due to horizontal
nystagmus, but no diagnostic or therapeutic action required.
**6) Consultation with ENT on 04/23/2017**
**Patient Information:** Suture removal. Request for assessment.
**Findings:** Tracheostomy site unremarkable. Sutures trimmed, and skin
sutures removed.
**Assessment:** Procedure completed successfully.
Please note that some information is clinical and may not include
specific dates or recommendations for further treatment.
**Antibiogram:**
**Antibiotic** **Organism 1 (Pseudomonas aeruginosa)** **Organism 2 (Acinetobacter radioresistens)**
------------------------- ----------------------------------------- -----------------------------------------------
Aztreonam I (4.0) \-
Cefepime I (2.0) \-
Cefotaxime \- \-
Amikacin S (\<=2.0) S (4.0)
Ampicillin \- \-
Piperacillin I (\<=4.0) \-
Piperacillin/Tazobactam I (8.0) \-
Imipenem I (2.0) S (\<=0.25)
Meropenem S (\<=0.25) S (\<=0.25)
Ceftriaxone \- \-
Ceftazidime I (4.0) \-
Gentamicin . (\<=1.0) S (\<=1.0)
Tobramycin S (\<=1.0) S (\<=1.0)
Cotrimoxazole \- S (\<=20.0)
Ciprofloxacin I (\<=0.25) I (0.5)
Moxifloxacin \- \-
Fosfomycin \- \-
Tigecyclin \- \-
\"S\" means Susceptible
\"I\" means Intermediate
\".\" indicates not specified
\"-\" means Resistant
### Patient Report 2
**Dear colleague, **
We are reporting on our mutual patient, Mr. John Chapman, born on
11/16/1994, who presented himself to our Outpatient Clinic from
08/08/2018.
**Diagnoses**:
- Right abducens Nerve Palsy and Facial Nerve Palsy
- Lagophthalmos with corneal opacities due to eyelid closure deficit
- Left Abducens Nerve Palsy with slight compensatory head leftward
rotation and preferred leftward gaze
- Bilateral disc swelling
- Suspected left cavernous internal carotid artery aneurysm following
traumatic ICA dissection
- History of shunt explantation due to dysfunction and right-sided
re-implantation (Codman, current pressure setting 12 cm H2O)
- History of left VP shunt placement (programmable
ventriculoperitoneal shunt, initial pressure setting 5/25 cm H2O,
adjusted to 3 cm H2O before discharge)
- Malresorptive hydrocephalus
- History of severe open head injury in a motocross accident with
multiple skull fractures and distal dissection
**Procedure**: We conducted the following preoperative assessment:
- Visual acuity: Distant vision: Right eye: 0.5, Left eye: 0.8p
- Eye position: Fusion/Normal with significant esotropia in the right
eye; no fusion reflex observed
- Ocular deviation: After CT, at distance, esodeviation simulating
alternating 100 prism diopters (overcorrection); at near,
esodeviation simulating alternating 90 prism diopters
- Head posture: Fusion/Normal with leftward head turn of 5-10 degrees
- Correspondence: Bagolini test shows suppression at both distance and
near fixation
- Motility: Right eye abduction limited to 25 degrees from the
midline, abduction in up and down gaze limited to 30 degrees from
midline; left eye abduction limited to 30 degrees
- Binocular functions: Bagolini test shows suppression in the right
eye at both distance and near fixation; Lang I negative
**Current Presentation:** Mr. Chapman presented himself today in our
neurovascular clinic, providing an MRI of the head.
**Medical History:** The patient is known to have a pseudoaneurysm of
the cavernous left internal carotid artery following traumatic carotid
dissection in 04/2017, along with ipsilateral abducens nerve palsy.
**Physical Examination:** Patient in good general condition. Oriented in
all aspects. No cyanosis. No edema. Warm and dry skin. Normal nasal and
pharyngeal findings. Pupils round, equal, and react promptly to light
bilaterally. Moist tongue. Pharynx and buccal mucosa unremarkable. No
jugular vein distension. No carotid bruits heard. Palpation of lymph
nodes unremarkable. Palpation of the thyroid gland unremarkable, freely
movable. Lungs: Normal chest shape, moderately mobile, vesicular breath
sounds. Heart: Regular heart action, normal rate; heart sounds clear, no
pathological sounds. Abdomen: Peristalsis and bowel sounds normal in all
quadrants; soft abdomen, no tenderness, no palpable masses, liver and
spleen not palpable due to limited access, non-tender kidneys. Normal
peripheral pulses; joints freely movable. Strength, motor function, and
sensation are unremarkable.
**Therapy and Progression:** The pseudoaneurysm has shown slight
enlargement in the recent follow-up imaging and remains partially
thrombosed. The findings were discussed on during a neurovascular board
meeting, where a recommendation for endovascular treatment was made,
which the patient has not yet pursued. Since Mr. Chapman has not been
able to decide on treatment thus far, it is advisable to further
evaluate this still asymptomatic condition through a diagnostic
angiography. This examination would also help in better planning any
potential intervention. Mr. Chapman agreed to this course of action, and
we will provide him with a timely appointment for the angiography.
**Lab results upon Discharge:**
**Parameter** **Results** **Reference Range**
-------------------- ------------- ---------------------
Creatinine (Jaffé) 0.44 mg/dL 0.70-1.20 mg/dL
Urea 31 mg/dL 17-48 mg/dL
Total Bilirubin 0.35 mg/dL \< 1.20 mg/dL
Hemoglobin 7.8 g/dL 13.5-17.0 g/dL
Hematocrit 28% 39.5-50.5%
Red Blood Cells 3.5 M/uL 4.3-5.8 M/uL
White Blood Cells 10.35 K/uL 3.90-10.50 K/uL
Platelets 379 K/uL 150-370 K/uL
MCV 77.2 fL 80.0-99.0 fL
MCH 24.1 pg 27.0-33.5 pg
MCHC 32.5 g/dL 31.5-36.0 g/dL
MPV 11.3 fL 7.0-12.0 fL
RDW-CV 17.7% 11.5-15.0%
Quick 54% 78-123%
INR 1.36 0.90-1.25
aPTT 32.8 sec 25.0-38.0 sec
### Patient Report 3
**Dear colleague, **
We are reporting on our patient, Mr. John Chapman, born on 11/16/1994,
who was under our inpatient care from 05/25/2019 to 05/26/2019.
**Diagnoses: **
- Pseudoaneurysm of the cavernous left internal carotid artery
following traumatic carotid dissection
- Abducens nerve palsy.
- History of severe open head trauma with fractures of the cranial
vault, mastoid, and skull base. Distal ICA dissection bilaterally.
Bilateral hemispheric subarachnoid hemorrhage extending into the
basal cisterns.mInfarct areas in the MCA-ACA border zones, right
frontal, and left parietal. Malresorptive hydrocephalus.
<!-- -->
- Rhabdomyolysis.
- History of aspiration pneumonia.
- Suspected Propofol infusion syndrome.
**Current Presentation:** For cerebral digital subtraction angiography
of the intracranial vessels. The patient presented with stable
cardiopulmonary conditions.
**Medical History**: The patient was admitted for the evaluation of a
pseudoaneurysm of the supra-aortic vessels. Further medical history can
be assumed to be known.
**Physical Examination:** Patient in good general condition. Oriented in
all aspects. No cyanosis. No edema. Warm and dry skin. Normal nasal and
pharyngeal findings. Pupils round, equal, and react promptly to light
bilaterally. Moist tongue. Pharynx and buccal mucosa unremarkable. No
jugular vein distension. No carotid bruits heard. Palpation of lymph
nodes unremarkable. Palpation of the thyroid gland unremarkable, freely
movable. Lungs: Normal chest shape, moderately mobile, vesicular breath
sounds. Heart: Regular heart action, normal rate; heart sounds clear, no
pathological sounds. Abdomen: Peristalsis and bowel sounds normal in all
quadrants; soft abdomen, no tenderness, no palpable masses, liver and
spleen not palpable due to limited access, non-tender kidneys. Normal
peripheral pulses; joints freely movable. Strength, motor function, and
sensation are unremarkable.
**Supra-aortic angiography on 05/25/2019:**
[Clinical context, question, justifying indication:]{.underline}
Pseudoaneurysm of the left ICA. Written consent was obtained for the
procedure. Anesthesia, Medications: Procedure performed under local
anesthesia. Medications: 500 IU Heparin in 500 mL NaCl for flushing.
[Methodology]{.underline}: Puncture of the right common femoral artery
under local anesthesia. 4F sheath, 4F vertebral catheter. Serial
angiographies after selective catheterization of the internal carotid
arteries. Uncomplicated manual intra-arterial contrast medium injection
with a total of 50 mL of Iomeron 300. Post-interventional closure of the
puncture site by manual compression. Subsequent application of a
circular pressure bandage.
[Technique]{.underline}: Biplanar imaging technique, area dose product
1330 cGy x cm², fluoroscopy time 3:43 minutes.
[Findings]{.underline}: The perfused portion of the partially thrombosed
cavernous aneurysm of the left internal carotid artery measures 4 x 2
mm. No evidence of other vascular pathologies in the anterior
circulation.
[Recommendation]{.underline}: In case of post-procedural bleeding,
immediate manual compression of the puncture site and notification of
the on-call neuroradiologist are advised.
- Pressure bandage to be kept until 2:30 PM. Bed rest until 6:30 PM.
- Follow-up in our Neurovascular Clinic
**Addition: Doppler ultrasound of the right groin on 05/26/2019:**
[Clinical context, question, justifying indication:]{.underline} Free
fluid? Hematoma?
[Findings]{.underline}: A CT scan from 04/05/2017 is available for
comparison. No evidence of a significant hematoma or an aneurysm in the
right groin puncture site. No evidence of an arteriovenous fistula.
Normal flow profiles of the femoral artery and vein. No evidence of
thrombosis.
**Treatment and Progression:** Pre-admission occurred on 05/24/2019 due
to a medically justified increase in risk for DSA of intracranial
vessels. After appropriate preparation, the angiography was performed on
05/25/2019. The puncture site was managed with a pressure bandage. In
the color Doppler sonographic control the following day, neither a
puncture aneurysm nor an arteriovenous fistula was detected. On
05/25/2019, we discharged the patient in good subjective condition for
your outpatient follow-up care.
**Current Recommendations:** Outpatient follow-up
**Lab results:**
**Parameter** **Reference Range** **Result**
----------------------- --------------------- -------------
Sodium 136-145 mEq/L 141 mEq/L
Potassium 3.5-4.5 mEq/L 4.9 mEq/L
Chloride 98-107 mEq/L 100 mEq/L
Osmolality 280-300 mOsm/kg 290 mOsm/kg
Glucose in Fluoride 60-110 mg/dL 76 mg/dL
Creatinine (Jaffé) 0.70-1.20 mg/dL 0.98 mg/dL
CRP \< 5.0 mg/L 4.5 mg/L
Triglycerides \< 150 mg/dL 119 mg/dL
Creatine Kinase \< 190 U/L 142 U/L
Free Triiodothyronine 2.00-4.40 ng/L 3.25 ng/L
Free Thyroxine 9.30-17.00 ng/L 14.12 ng/L
TSH Basal 0.27-4.20 mU/L 1.65 mU/L
Hemoglobin 13.5-17.0 g/dL 14.3 g/dL
Hematocrit 39.5-50.5% 43.4%
Erythrocytes 4.3-5.8 M/uL 5.6 M/uL
Leukocytes 3.90-10.50 K/uL 10.25 K/uL
Platelets 150-370 K/uL 198 K/uL
MCV 80.0-99.0 fL 83.2 fL
MCH 27.0-33.5 pg 28.1 pg
MCHC 31.5-36.0 g/dL 33.4 g/dL
MPV 7.0-12.0 fL 11.6 fL
RDW-CV 11.5-15.0% 13.5%
Quick \> 78% 90%
INR \< 1.25 1.07
aPTT 25.0-38.0 sec 36.1 sec
|
Staphylococcus capitis
|
Retrieval at what level performs better, sentence level or paragraph level?
|
### Introduction
Extracting external textual knowledge for machine comprehensive systems has long been an important yet challenging problem. Success requires not only precise retrieval of the relevant information sparsely restored in a large knowledge source but also a deep understanding of both the selected knowledge and the input query to give the corresponding output. Initiated by chen2017drqa, the task was termed as Machine Reading at Scale (MRS), seeking to provide a challenging situation where machines are required to do both semantic retrieval and comprehension at different levels of granularity for the final downstream task. Progress on MRS has been made by improving individual IR or comprehension sub-modules with recent advancements on representative learning BIBREF0, BIBREF1, BIBREF2. However, partially due to the lack of annotated data for intermediate retrieval in an MRS setting, the evaluations were done mainly on the final downstream task and with much less consideration on the intermediate retrieval performance. This led to the convention that upstream retrieval modules mostly focus on getting better coverage of the downstream information such that the upper-bound of the downstream score can be improved, rather than finding more exact information. This convention is misaligned with the nature of MRS where equal effort should be put in emphasizing the models' joint performance and optimizing the relationship between the semantic retrieval and the downstream comprehension sub-tasks. Hence, to shed light on the importance of semantic retrieval for downstream comprehension tasks, we start by establishing a simple yet effective hierarchical pipeline system for MRS using Wikipedia as the external knowledge source. The system is composed of a term-based retrieval module, two neural modules for both paragraph-level retrieval and sentence-level retrieval, and a neural downstream task module. We evaluated the system on two recent large-scale open domain benchmarks for fact verification and multi-hop QA, namely FEVER BIBREF3 and HotpotQA BIBREF4, in which retrieval performance can also be evaluated accurately since intermediate annotations on evidences are provided. Our system achieves the start-of-the-art results with 45.32% for answer EM and 25.14% joint EM on HotpotQA (8% absolute improvement on answer EM and doubling the joint EM over the previous best results) and with 67.26% on FEVER score (3% absolute improvement over previously published systems). We then provide empirical studies to validate design decisions. Specifically, we prove the necessity of both paragraph-level retrieval and sentence-level retrieval for maintaining good performance, and further illustrate that a better semantic retrieval module not only is beneficial to achieving high recall and keeping high upper bound for downstream task, but also plays an important role in shaping the downstream data distribution and providing more relevant and high-quality data for downstream sub-module training and inference. These mechanisms are vital for a good MRS system on both QA and fact verification. ### Related Work
Machine Reading at Scale First proposed and formalized in chen2017drqa, MRS has gained popularity with increasing amount of work on both dataset collection BIBREF5, BIBREF6 and MRS model developments BIBREF7, BIBREF8, BIBREF9. In some previous work BIBREF10, paragraph-level retrieval modules were mainly for improving the recall of required information, while in some other works BIBREF4, sentence-level retrieval modules were merely for solving the auxiliary sentence selection task. In our work, we focus on revealing the relationship between semantic retrieval at different granularity levels and the downstream comprehension task. To the best of our knowledge, we are the first to apply and optimize neural semantic retrieval at both paragraph and sentence levels for MRS. Automatic Fact Checking: Recent work BIBREF11 formalized the task of automatic fact checking from the viewpoint of machine learning and NLP. The release of FEVER BIBREF3 stimulates many recent developments BIBREF12, BIBREF13, BIBREF14 on data-driven neural networks for automatic fact checking. We consider the task also as MRS because they share almost the same setup except that the downstream task is verification or natural language inference (NLI) rather than QA. Information Retrieval Success in deep neural networks inspires their application to information retrieval (IR) tasks BIBREF15, BIBREF16, BIBREF17, BIBREF18. In typical IR settings, systems are required to retrieve and rank BIBREF19 elements from a collection of documents based on their relevance to the query. This setting might be very different from the retrieval in MRS where systems are asked to select facts needed to answer a question or verify a statement. We refer the retrieval in MRS as Semantic Retrieval since it emphasizes on semantic understanding. ### Method
In previous works, an MRS system can be complicated with different sub-components processing different retrieval and comprehension sub-tasks at different levels of granularity, and with some sub-components intertwined. For interpretability considerations, we used a unified pipeline setup. The overview of the system is in Fig. FIGREF2. To be specific, we formulate the MRS system as a function that maps an input tuple $(q, \mathbf {K})$ to an output tuple $(\hat{y}, \mathbf {S})$ where $q$ indicates the input query, $\mathbf {K}$ is the textual KB, $\hat{y}$ is the output prediction, and $\mathbf {S}$ is selected supporting sentences from Wikipedia. Let $\mathbf {E}$ denotes a set of necessary evidences or facts selected from $\mathbf {K}$ for the prediction. For a QA task, $q$ is the input question and $\hat{y}$ is the predicted answer. For a verification task, $q$ is the input claim and $\hat{y}$ is the predicted truthfulness of the input claim. For all tasks, $\mathbf {K}$ is Wikipedia. The system procedure is listed below: (1) Term-Based Retrieval: To begin with, we used a combination of the TF-IDF method and a rule-based keyword matching method to narrow the scope from whole Wikipedia down to a set of related paragraphs; this is a standard procedure in MRS BIBREF20, BIBREF10, BIBREF12. The focus of this step is to efficiently select a candidate set $\mathbf {P_I}$ that can cover the information as much as possible ($\mathbf {P_I} \subset \mathbf {K}$) while keeping the size of the set acceptable enough for downstream processing. (2) Paragraph-Level Neural Retrieval: After obtaining the initial set, we compare each paragraph in $\mathbf {P_I}$ with the input query $q$ using a neural model (which will be explained later in Sec SECREF4). The outputs of the neural model are treated as the relatedness score between the input query and the paragraphs. The scores will be used to sort all the upstream paragraphs. Then, $\mathbf {P_I}$ will be narrowed to a new set $\mathbf {P_N}$ ($\mathbf {P_N} \subset \mathbf {P_I}$) by selecting top $k_p$ paragraphs having relatedness score higher than some threshold value $h_p$ (going out from the P-Level grey box in Fig. FIGREF2). $k_p$ and $h_p$ would be chosen by keeping a good balance between the recall and precision of the paragraph retrieval. (3) Sentence-Level Neural Retrieval: Next, we select the evidence at the sentence-level by decomposing all the paragraphs in $\mathbf {P_N}$ into sentences. Similarly, each sentence is compared with the query using a neural model (see details in Sec SECREF4) and obtain a set of sentences $\mathbf {S} \subset \mathbf {P_N}$ for the downstream task by choosing top $k_s$ sentences with output scores higher than some threshold $h_s$ (S-Level grey box in Fig. FIGREF2). During evaluation, $\mathbf {S}$ is often evaluated against some ground truth sentence set denoted as $\mathbf {E}$. (4) Downstream Modeling: At the final step, we simply applied task-specific neural models (e.g., QA and NLI) on the concatenation of all the sentences in $\mathbf {S}$ and the query, obtaining the final output $\hat{y}$. In some experiments, we modified the setup for certain analysis or ablation purposes which will be explained individually in Sec SECREF6. ### Method ::: Modeling and Training
Throughout all our experiments, we used BERT-Base BIBREF2 to provide the state-of-the-art contextualized modeling of the input text. Semantic Retrieval: We treated the neural semantic retrieval at both the paragraph and sentence level as binary classification problems with models' parameters updated by minimizing binary cross entropy loss. To be specific, we fed the query and context into BERT as: We applied an affine layer and sigmoid activation on the last layer output of the [$\mathit {CLS}$] token which is a scalar value. The parameters were updated with the objective function: where $\hat{p}_i$ is the output of the model, $\mathbf {T}^{p/s}_{pos}$ is the positive set and $\mathbf {T}^{p/s}_{neg}$ is the negative set. As shown in Fig. FIGREF2, at sentence level, ground-truth sentences were served as positive examples while other sentences from upstream retrieved set were served as negative examples. Similarly at the paragraph-level, paragraphs having any ground-truth sentence were used as positive examples and other paragraphs from the upstream term-based retrieval processes were used as negative examples. QA: We followed devlin2018bert for QA span prediction modeling. To correctly handle yes-or-no questions in HotpotQA, we fed the two additional “$\mathit {yes}$" and “$\mathit {no}$" tokens between [$\mathit {CLS}$] and the $Query$ as: where the supervision was given to the second or the third token when the answer is “yes" or “no", such that they can compete with all other predicted spans. The parameters of the neural QA model were trained to maximize the log probabilities of the true start and end indexes as: where $\hat{y}^s_i$ and $\hat{y}^e_i$ are the predicted probability on the ground-truth start and end position for the $i$th example, respectively. It is worth noting that we used ground truth supporting sentences plus some other sentences sampled from upstream retrieved set as the context for training the QA module such that it will adapt to the upstream data distribution during inference. Fact Verification: Following Thorne18Fever, we formulate downstream fact verification as the 3-way natural language inference (NLI) classification problem BIBREF21, BIBREF22 and train the model with 3-way cross entropy loss. The input format is the same as that of semantic retrieval and the objective is $\mathcal {J}_{ver} = -\sum _{i} \mathbf {y}_i \cdot \log (\hat{\mathbf {y}}_i)$, where $\hat{\mathbf {y}}_i \in \mathbf {R^3}$ denotes the model's output for the three verification labels, and $\mathbf {y}_i$ is a one-hot embedding for the ground-truth label. For verifiable queries, we used ground truth evidential sentences plus some other sentences sampled from upstream retrieved set as new evidential context for NLI. For non-verifiable queries, we only used sentences sampled from upstream retrieved set as context because those queries are not associated with ground truth evidential sentences. This detail is important for the model to identify non-verifiable queries and will be explained more in Sec SECREF6. Additional training details and hyper-parameter selections are in the Appendix (Sec. SECREF8; Table TABREF27). It is worth noting that each sub-module in the system relies on its preceding sub-module to provide data both for training and inference. This means that there will be upstream data distribution misalignment if we trained the sub-module in isolation without considering the properties of its precedent upstream module. The problem is similar to the concept of internal covariate shift BIBREF23, where the distribution of each layer's inputs changes inside a neural network. Therefore, it makes sense to study this issue in a joint MRS setting rather than a typical supervised learning setting where training and test data tend to be fixed and modules being isolated. We release our code and the organized data both for reproducibility and providing an off-the-shelf testbed to facilitate future research on MRS. ### Experimental Setup
MRS requires a system not only to retrieve relevant content from textual KBs but also to poccess enough understanding ability to solve the downstream task. To understand the impact or importance of semantic retrieval on the downstream comprehension, we established a unified experimental setup that involves two different downstream tasks, i.e., multi-hop QA and fact verification. ### Experimental Setup ::: Tasks and Datasets
HotpotQA: This dataset is a recent large-scale QA dataset that brings in new features: (1) the questions require finding and reasoning over multiple documents; (2) the questions are diverse and not limited to pre-existing KBs; (3) it offers a new comparison question type BIBREF4. We experimented our system on HotpotQA in the fullwiki setting, where a system must find the answer to a question in the scope of the entire Wikipedia, an ideal MRS setup. The sizes of the train, dev and test split are 90,564, 7,405, and 7,405. More importantly, HotpotQA also provides human-annotated sentence-level supporting facts that are needed to answer each question. Those intermediate annotations enable evaluation on models' joint ability on both fact retrieval and answer span prediction, facilitating our direct analysis on the explainable predictions and its relations with the upstream retrieval. FEVER: The Fact Extraction and VERification dataset BIBREF3 is a recent dataset collected to facilitate the automatic fact checking. The work also proposes a benchmark task in which given an arbitrary input claim, candidate systems are asked to select evidential sentences from Wikipedia and label the claim as either Support, Refute, or Not Enough Info, if the claim can be verified to be true, false, or non-verifiable, respectively, based on the evidence. The sizes of the train, dev and test split are 145,449, 19,998, and 9,998. Similar to HotpotQA, the dataset provides annotated sentence-level facts needed for the verification. These intermediate annotations could provide an accurate evaluation on the results of semantic retrieval and thus suits well for the analysis on the effects of retrieval module on downstream verification. As in chen2017drqa, we use Wikipedia as our unique knowledge base because it is a comprehensive and self-evolving information source often used to facilitate intelligent systems. Moreover, as Wikipedia is the source for both HotpotQA and FEVER, it helps standardize any further analysis of the effects of semantic retrieval on the two different downstream tasks. ### Experimental Setup ::: Metrics
Following Thorne18Fever, yang2018hotpotqa, we used annotated sentence-level facts to calculate the F1, Precision and Recall scores for evaluating sentence-level retrieval. Similarly, we labeled all the paragraphs that contain any ground truth fact as ground truth paragraphs and used the same three metrics for paragraph-level retrieval evaluation. For HotpotQA, following yang2018hotpotqa, we used exact match (EM) and F1 metrics for QA span prediction evaluation, and used the joint EM and F1 to evaluate models' joint performance on both retrieval and QA. The joint EM and F1 are calculated as: $P_j = P_a \cdot P_s; R_j = R_a \cdot R_s; F_j = \frac{2P_j \cdot R_j}{P_j + R_j}; \text{EM}_j = \text{EM}_a \cdot \text{EM}_s$, where $P$, $R$, and $\text{EM}$ denote precision, recall and EM; the subscript $a$ and $s$ indicate that the scores are for answer span and supporting facts. For the FEVER task, following Thorne18Fever, we used the Label Accuracy for evaluating downstream verification and the Fever Score for joint performance. Fever score will award one point for each example with the correct predicted label only if all ground truth facts were contained in the predicted facts set with at most 5 elements. We also used Oracle Score for the two retrieval modules. The scores were proposed in nie2019combining and indicate the upperbound of final FEVER Score at one intermediate layer assuming all downstream modules are perfect. All scores are averaged over examples in the whole evaluation set. ### Results on Benchmarks
We chose the best system based on the dev set, and used that for submitting private test predictions on both FEVER and HotpotQA . As can be seen in Table TABREF8, with the proposed hierarchical system design, the whole pipeline system achieves new start-of-the-art on HotpotQA with large-margin improvements on all the metrics. More specifically, the biggest improvement comes from the EM for the supporting fact which in turn leads to doubling of the joint EM on previous best results. The scores for answer predictions are also higher than all previous best results with $\sim $8 absolute points increase on EM and $\sim $9 absolute points on F1. All the improvements are consistent between test and dev set evaluation. Similarly for FEVER, we showed F1 for evidence, the Label Accuracy, and the FEVER Score (same as benchmark evaluation) for models in Table TABREF9. Our system obtained substantially higher scores than all previously published results with a $\sim $4 and $\sim $3 points absolute improvement on Label Accuracy and FEVER Score. In particular, the system gains 74.62 on the evidence F1, 22 points greater that of the second system, demonstrating its ability on semantic retrieval. Previous systems BIBREF24, BIBREF4 on HotpotQA treat supporting fact retrieval (sentence-level retrieval) just as an auxiliary task for providing extra model explainability. In nie2019combining, although they used a similar three-stage system for FEVER, they only applied one neural retrieval module at sentence-level which potentially weaken its retrieval ability. Both of these previous best systems are different from our fully hierarchical pipeline approach. These observations lead to the assumption that the performance gain comes mainly from the hierarchical retrieval and its positive effects on downstream. Therefore, to validate the system design decisions in Sec SECREF3 and reveal the importance of semantic retrieval towards downstream, we conducted a series of ablation and analysis experiments on all the modules. We started by examining the necessity of both paragraph and sentence retrieval and give insights on why both of them matters. ### Analysis and Ablations
Intuitively, both the paragraph-level and sentence-level retrieval sub-module help speeding up the downstream processing. More importantly, since downstream modules were trained by sampled data from upstream modules, both of neural retrieval sub-modules also play an implicit but important role in controlling the immediate retrieval distribution i.e. the distribution of set $\mathbf {P_N}$ and set $\mathbf {S}$ (as shown in Fig. FIGREF2), and providing better inference data and training data for downstream modules. ### Analysis and Ablations ::: Ablation Studies ::: Setups:
To reveal the importance of neural retrieval modules at both paragraph and sentence level for maintaining the performance of the overall system, we removed either of them and examine the consequences. Because the removal of a module in the pipeline might change the distribution of the input of the downstream modules, we re-trained all the downstream modules accordingly. To be specific, in the system without the paragraph-level neural retrieval module, we re-trained the sentence-level retrieval module with negative sentences directly sampled from the term-based retrieval set and then also re-trained the downstream QA or verification module. In the system without the sentence-level neural retrieval module, we re-train the downstream QA or verification module by sampling data from both ground truth set and retrieved set directly from the paragraph-level module. We tested the simplified systems on both FEVER and HotpotQA. ### Analysis and Ablations ::: Ablation Studies ::: Results:
Table TABREF13 and TABREF14 shows the ablation results for the two neural retrieval modules at both paragraph and sentence level on HotpotQA and FEVER. To begin with, we can see that removing paragraph-level retrieval module significantly reduces the precision for sentence-level retrieval and the corresponding F1 on both tasks. More importantly, this loss of retrieval precision also led to substantial decreases for all the downstream scores on both QA and verification task in spite of their higher upper-bound and recall scores. This indicates that the negative effects on downstream module induced by the omission of paragraph-level retrieval can not be amended by the sentence-level retrieval module, and focusing semantic retrieval merely on improving the recall or the upper-bound of final score will risk jeopardizing the performance of the overall system. Next, the removal of sentence-level retrieval module induces a $\sim $2 point drop on EM and F1 score in the QA task, and a $\sim $15 point drop on FEVER Score in the verification task. This suggests that rather than just enhance explainability for QA, the sentence-level retrieval module can also help pinpoint relevant information and reduce the noise in the evidence that might otherwise distract the downstream comprehension module. Another interesting finding is that without sentence-level retrieval module, the QA module suffered much less than the verification module; conversely, the removal of paragraph-level retrieval neural induces a 11 point drop on answer EM comparing to a $\sim $9 point drop on Label Accuracy in the verification task. This seems to indicate that the downstream QA module relies more on the upstream paragraph-level retrieval whereas the verification module relies more on the upstream sentence-level retrieval. Finally, we also evaluate the F1 score on FEVER for each classification label and we observe a significant drop of F1 on Not Enough Info category without retrieval module, meaning that semantic retrieval is vital for the downstream verification module's discriminative ability on Not Enough Info label. ### Analysis and Ablations ::: Sub-Module Change Analysis
To further study the effects of upstream semantic retrieval towards downstream tasks, we change training or inference data between intermediate layers and then examine how this modification will affect the downstream performance. ### Analysis and Ablations ::: Sub-Module Change Analysis ::: Effects of Paragraph-level Retrieval
We fixed $h_p=0$ (the value achieving the best performance) and re-trained all the downstream parameters and track their performance as $k_p$ (the number of selected paragraph) being changed from 1 to 12. The increasing of $k_p$ means a potential higher coverage of the answer but more noise in the retrieved facts. Fig. FIGREF17 shows the results. As can be seen that the EM scores for supporting fact retrieval, answer prediction, and joint performance increase sharply when $k_p$ is changed from 1 to 2. This is consistent with the fact that at least two paragraphs are required to ask each question in HotpotQA. Then, after the peak, every score decrease as $k_p$ becomes larger except the recall of supporting fact which peaks when $k_p=4$. This indicates that even though the neural sentence-level retrieval module poccesses a certain level of ability to select correct facts from noisier upstream information, the final QA module is more sensitive to upstream data and fails to maintain the overall system performance. Moreover, the reduction on answer EM and joint EM suggests that it might be risky to give too much information for downstream modules with a unit of a paragraph. ### Analysis and Ablations ::: Sub-Module Change Analysis ::: Effects of Sentence-level Retrieval
Similarly, to study the effects of neural sentence-level retrieval module towards downstream QA and verification modules, we fixed $k_s$ to be 5 and set $h_s$ ranging from 0.1 to 0.9 with a 0.1 interval. Then, we re-trained the downstream QA and verification modules with different $h_s$ value and experimented on both HotpotQA and FEVER. Question Answering: Fig. FIGREF18 shows the trend of performance. Intuitively, the precision increase while the recall decrease as the system becomes more strict about the retrieved sentences. The EM score for supporting fact retrieval and joint performance reaches their highest value when $h_s=0.5$, a natural balancing point between precision and recall. More interestingly, the EM score for answer prediction peaks when $h_s=0.2$ and where the recall is higher than the precision. This misalignment between answer prediction performance and retrieval performance indicates that unlike the observation at paragraph-level, the downstream QA module is able to stand a certain amount of noise at sentence-level and benefit from a higher recall. Fact Verification: Fig. FIGREF19 shows the trends for Label Accuracy, FEVER Score, and Evidence F1 by modifying upstream sentence-level threshold $h_s$. We observed that the general trend is similar to that of QA task where both the label accuracy and FEVER score peak at $h_s=0.2$ whereas the retrieval F1 peaks at $h_s=0.5$. Note that, although the downstream verification could take advantage of a higher recall, the module is more sensitive to sentence-level retrieval comparing to the QA module in HotpotQA. More detailed results are in the Appendix. ### Analysis and Ablations ::: Answer Breakdown
We further sample 200 examples from HotpotQA and manually tag them according to several common answer types BIBREF4. The proportion of different answer types is shown in Figure FIGREF24. The performance of the system on each answer type is shown in Table TABREF23. The most frequent answer type is 'Person' (24%) and the least frequent answer type is 'Event' (2%). It is also interesting to note that the model performs the best in Yes/No questions as shown in Table TABREF23, reaching an accuracy of 70.6%. ### Analysis and Ablations ::: Examples
Fig. FIGREF26 shows an example that is correctly handled by the full pipeline system but not by the system without paragraph-level retrieval module. We can see that it is very difficult to filter the distracting sentence after sentence-level either by the sentence retrieval module or the QA module. Above findings in both FEVER and HotpotQA bring us some important guidelines for MRS: (1) A paragraph-level retrieval module is imperative; (2) Downstream task module is able to undertake a certain amount of noise from sentence-level retrieval; (3) Cascade effects on downstream task might be caused by modification at paragraph-level retrieval. ### Conclusion
We proposed a simple yet effective hierarchical pipeline system that achieves state-of-the-art results on two MRS tasks. Ablation studies demonstrate the importance of semantic retrieval at both paragraph and sentence levels in the MRS system. The work can give general guidelines on MRS modeling and inspire future research on the relationship between semantic retrieval and downstream comprehension in a joint setting. ### Acknowledgments
We thank the reviewers for their helpful comments and Yicheng Wang for useful comments. This work was supported by awards from Verisk, Google, Facebook, Salesforce, and Adobe (plus Amazon and Google GPU cloud credits). The views, opinions, and/or findings contained in this article are those of the authors and should not be interpreted as representing the official views or policies, either expressed or implied, of the funding agency. ### Training Details
The hyper-parameters were chosen based on the performance of the system on the dev set. The hyper-parameters search space is shown in Table TABREF27 and the learning rate was set to $10^{-5}$ in all experiments. ### Term-Based Retrieval Details ::: FEVER
We used the same key-word matching method in nie2019combining to get a candidate set for each query. We also used TF-IDF BIBREF20 method to get top-5 related documents for each query. Then, the two sets were combined to get final term-based retrieval set for FEVER. The mean and standard deviation of the number of the retrieved paragraph in the merged set were 8.06 and 4.88. ### Term-Based Retrieval Details ::: HotpotQA
We first used the same procedure on FEVER to get an initial candidate set for each query in HotpotQA. Because HotpotQA requires at least 2-hop reasoning for each query, we then extract all the hyperlinked documents from the retrieved documents in the initial candidate set, rank them with TF-IDF BIBREF20 score and then select top-5 most related documents and add them to the candidate set. This gives the final term-based retrieval set for HotpotQA. The mean and standard deviation of the number of the retrieved paragraph for each query in HotpotQA were 39.43 and 16.05. ### Detailed Results
The results of sentence-level retrieval and downstream QA with different values of $h_s$ on HotpotQA are in Table TABREF28. The results of sentence-level retrieval and downstream verification with different values of $h_s$ on FEVER are in Table TABREF34. The results of sentence-level retrieval and downstream QA with different values of $k_p$ on HotpotQA are in Table TABREF35. ### Examples and Case Study
We further provide examples, case study and error analysis for the full pipeline system. The examples are shown from Tables TABREF37, TABREF38, TABREF39, TABREF40, TABREF41. The examples show high diversity on the semantic level and the error occurs often due to the system's failure of extracting precise (either wrong, surplus or insufficient) information from KB. Figure 1: System Overview: blue dotted arrows indicate the inference flow and the red solid arrows indicate the training flow. Grey rounded rectangles are neural modules with different functionality. The two retrieval modules were trained with all positive examples from annotated ground truth set and negative examples sampled from the direct upstream modules. Thus, the distribution of negative examples is subjective to the quality of the upstream module. Table 1: Results of systems on HOTPOTQA. Table 2: Performance of systems on FEVER. “F1” indicates the sentence-level evidence F1 score. “LA” indicates Label Acc. without considering the evidence prediction. “FS”=FEVER Score (Thorne et al., 2018) Table 3: Ablation over the paragraph-level and sentence-level neural retrieval sub-modules on HOTPOTQA. Table 4: Ablation over the paragraph-level and sentence-level neural retrieval sub-modules on FEVER. “LA”=Label Accuracy; “FS”=FEVER Score; “Orcl.” is the oracle upperbound of FEVER Score assuming all downstream modules are perfect. “L-F1 (S/R/N)” means the classification f1 scores on the three verification labels: SUPPORT, REFUTE, and NOT ENOUGH INFO. Figure 2: The results of EM for supporting fact, answer prediction and joint score, and the results of supporting fact precision and recall with different values of kp at paragraph-level retrieval on HOTPOTQA. Table 5: System performance on different answer types. “PN”= Proper Noun Figure 3: The results of EM for supporting fact, answer prediction and joint score, and the results of supporting fact precision and recall with different values of hs at sentence-level retrieval on HOTPOTQA. Figure 4: The results of Label Accuracy, FEVER Score, and Evidence F1 with different values of hs at sentence-level retrieval on FEVER. Figure 5: Proportion of answer types. Table 6: Hyper-parameter selection for the full pipeline system. h and k are the retrieval filtering hyperparameters mentioned in the main paper. P-level and S-level indicate paragraph-level and sentence-level respectively. “{}” means values enumerated from a set. “[]” means values enumerated from a range with interval=0.1 “BS.”=Batch Size “# E.”=Number of Epochs Table 7: Detailed Results of downstream sentence-level retrieval and question answering with different values of hs on HOTPOTQA. Table 8: Results with different hs on FEVER. Table 9: Detailed Results of downstream sentence-level retrieval and question answering with different values of kp on HOTPOTQA. Table 10: HotpotQA correct prediction with sufficient evidence. Table 11: HotpotQA incorrect prediction with insufficient/wrong evidence. Table 12: HotpotQA incorrect prediction caused by extra incorrect information. Table 15: FEVER incorrect prediction due to extra wrong evidence
|
This seems to indicate that the downstream QA module relies more on the upstream paragraph-level retrieval whereas the verification module relies more on the upstream sentence-level retrieval.
|
What methods are tested in PIEWi?
|
### Introduction
Spelling error correction is a fundamental NLP task. Most language processing applications benefit greatly from being provided clean texts for their best performance. Human users of computers also often expect competent help in making spelling of their texts correct. Because of the lack of tests of many common spelling correction methods for Polish, it is useful to establish how they perform in a simple scenario. We constrain ourselves to the pure task of isolated correction of non-word errors. They are traditionally separated in error correction literature BIBREF0 . Non-word errors are here incorrect word forms that not only differ from what was intended, but also do not constitute another, existing word themselves. Much of the initial research on error correction focused on this simple task, tackled without means of taking the context of the nearest words into account. It is true that, especially in the case of neural networks, it is often possible and desirable to combine problems of error detection, correction and context awareness into one task trained with a supervised training procedure. In language correction research for English language also grammatical and regular spelling errors have been treated uniformly with much success BIBREF1 . However, when more traditional methods are used, because of their predictability and interpretability for example, one can mix and match various approaches to dealing with the subproblems of detection, correction and context handling (often equivalent to employing some kind of a language model). We call it a modular approach to building spelling error correction systems. There is recent research where this paradigm was applied, interestingly, to convolutional networks trained separately for various subtasks BIBREF2 . In similar setups it is more useful to assess abilities of various solutions in isolation. The exact architecture of a spelling correction system should depend on characteristics of texts it will work on. Similar considerations eliminated from our focus handcrafted solutions for the whole spelling correction pipeline, primarily the LanguageTool BIBREF3 . Its performance in fixing spelling of Polish tweets was already tested BIBREF4 . For our purposes it would be given an unfair advantage, since it is a rule-based system making heavy use of words in context of the error. ### Problems of spelling correction for Polish
Published work on language correction for Polish dates back at least to 1970s, when simplest Levenshtein distance solutions were used for cleaning mainframe inputs BIBREF5 , BIBREF6 . Spelling correction tests described in literature have tended to focus on one approach applied to a specific corpus. Limited examples include works on spellchecking mammography reports and tweets BIBREF7 , BIBREF4 . These works emphasized the importance of tailoring correction systems to specific problems of corpora they are applied to. For example, mammography reports suffer from poor typing, which in this case is a repetitive work done in relative hurry. Tweets, on the other hand, tend to contain emoticons and neologisms that can trick solutions based on rules and dictionaries, such as LanguageTool. The latter is, by itself, fairly well suited for Polish texts, since a number of extensions to the structure of this application was inspired by problems with morphology of Polish language BIBREF3 . These existing works pointed out more general, potentially useful qualities specific to spelling errors in Polish language texts. It is, primarily, the problem of leaving out diacritical signs, or, more rarely, adding them in wrong places. This phenomenon stems from using a variant of the US keyboard layout, where combinations of AltGr with some alphabetic keys produces characters unique to Polish. When the user forgets or neglects to press the AltGr key, typos such as writing *olowek instead of ołówek appear. In fact, BIBREF4 managed to get substantial performance on Twitter corpus by using this ”diacritical swapping” alone. ### Baseline methods
The methods that we evaluated are baselines are the ones we consider to be basic and with moderate potential of yielding particularly good results. Probably the most straightforward approach to error correction is selecting known words from a dictionary that are within the smallest edit distance from the error. We used the Levenshtein distance metric BIBREF8 implemented in Apache Lucene library BIBREF9 . It is a version of edit distance that treats deletions, insertions and replacements as adding one unit distance, without giving a special treatment to character swaps. The SGJP – Grammatical Dictionary of Polish BIBREF10 was used as the reference vocabulary. Another simple approach is the aforementioned diacritical swapping, which is a term that we introduce here for referring to a solution inspired by the work of BIBREF4 . Namely, from the incorrect form we try to produce all strings obtainable by either adding or removing diacritical marks from characters. We then exclude options that are not present in SGJP, and select as the correction the one within the smallest edit distance from the error. It is possible for the number of such diacritically-swapped options to become very big. For example, the token Modlin-Zegrze-Pultusk-Różan-Ostrołęka-Łomża-Osowiec (taken from PlEWi corpus of spelling errors, see below) can yield over INLINEFORM0 states with this method, such as Módłiń-Żęgrzę-Pułtuśk-Roźąń-Óśtróleką-Lómzą-Óśówięć. The actual correction here is just fixing the ł in Pułtusk. Hence we only try to correct in this way tokens that are shorter than 17 characters. ### Vector distance
A promising method, adapted from work on correcting texts by English language learners BIBREF11 , expands on the concept of selecting a correction nearest to the spelling error according to some notion of distance. Here, the Levenshtein distance is used in a weighted sum to cosine distance between word vectors. This is based on the observation that trained vectors models of distributional semantics contain also representations of spelling errors, if they were not pruned. Their representations tend to be similar to those of their correct counterparts. For example, the token enginir will appear in similar contexts as engineer, and therefore will be assigned a similar vector embedding. The distance between two tokens INLINEFORM0 and INLINEFORM1 is thus defined as INLINEFORM2 Here INLINEFORM0 is just Levenshtein distance between strings, and INLINEFORM1 – cosine distance between vectors. INLINEFORM2 denotes the word vector for INLINEFORM3 . Both distance metrics are in our case roughly in the range [0,1] thanks to the scaling of edit distance performed automatically by Apache Lucene. We used a pretrained set of word embeddings of Polish BIBREF12 , obtained with the flavor word2vec procedure using skipgrams and negative sampling BIBREF13 . ### Recurrent neural networks
Another powerful approach, if conceptually simple in linguistic terms, is using a character-based recurrent neural network. Here, we test uni- and bidirectional Long Short-Term Memory networks BIBREF14 that are fed characters of the error as their input and are expected to output its correct form, character after character. This is similar to traditional solutions conceptualizing the spelling error as a chain of characters, which are used as evidence to predict the most likely chain of replacements (original characters). This was done with n-gram methods, Markov chains and other probabilistic models BIBREF15 . Since nowadays neural networks enjoy a large awareness as an element of software infrastructure, with actively maintained packages readily available, their evaluation seems to be the most practically useful. We used the PyTorch BIBREF16 implementation of LSTM in particular. The bidirectional version BIBREF17 of LSTM reads the character chains forward and backwards at the same time. Predictions from networks running in both directions are averaged. In order to provide the network an additional, broad picture peek at the whole error form we also evaluated a setup where the internal state of LSTM cells, instead of being initialized randomly, is computed from an ELMo embedding BIBREF18 of the token. The ELMo embedder is capable of integrating linguistic information carried by the whole form (probably often not much in case of errors), as well as the string as a character chain. The latter is processed with a convolutional neural network. How this representation is constructed is informed by the whole corpus on which the embedder was trained. The pretrained ELMo model that we used BIBREF19 was trained on Wikipedia and Common Crawl corpora of Polish. The ELMo embedding network outputs three layers as matrices, which are supposed to reflect subsequent compositional layers of language, from phonetic phenomena at the bottom to lexical ones at the top. A weighted sum of these layers is computed, with weights trained along with the LSTM error-correcting network. Then we apply a trained linear transformation, followed by INLINEFORM0 non-linearity: INLINEFORM1 (applied cellwise) in order to obtain the initial setting of parameters for the main LSTM. Our ELMo-augmented LSTM is bidirectional. ### Experimental setup
PlEWi BIBREF20 is an early version of WikEd BIBREF21 error corpus, containing error type annotations allowing us to select only non-word errors for evaluation. Specifically, PlEWi supplied 550,755 [error, correction] pairs, from which 298,715 were unique. The corpus contains data extracted from histories of page versions of Polish Wikipedia. An algorithm designed by the corpus author determined where the changes were correcting spelling errors, as opposed to expanding content and disagreements among Wikipedia editors. The corpus features texts that are descriptive rather than conversational, contain relatively many proper names and are more likely to have been at least skimmed by the authors before submitting for online publication. Error cases provided by PlEWi are, therefore, not a balanced representation of spelling errors in written Polish language. PlEWi does have the advantage of scale in comparison to existing literature, such as BIBREF4 operating on a set of only 740 annotated errors in tweets. All methods were tested on a test subset of 25% of cases, with 75% left for training (where needed) and 5% for development. The methods that required training – namely recurrent neural networks – had their loss measured as cross-entropy loss measure between correct character labels and predictions. This value was minimized with Adam algorithm BIBREF22 . The networks were trained for 35 epochs. ### Results
The experimental results are presented in Table TABREF4 . Diacritic swapping showed a remarkably poor performance, despite promising mentions in existing literature. This might be explained by the already mentioned feature of Wikipedia edits, which can be expected to be to some degree self-reviewed before submission. This can very well limit the number of most trivial mistakes. On the other hand, the vector distance method was able to bring a discernible improvement over pure Levenshtein distance, comparable even with the most basic LSTM. It is possible that assigning more fine-tuned weights to edit distance and semantic distance would make the quality of predictions even higher. The idea of using vector space measurements explicitly can be also expanded if we were to consider the problem of contextualizing corrections. For example, the semantic distance of proposed corrections to the nearest words is likely to carry much information about their appropriateness. Looking from another angle, searching for words that seem semantically off in context may be a good heuristic for detecting errors that are not nonword (that is, they lead to wrong forms appearing in text which are nevertheless in-vocabulary). The good performance of recurrent network methods is hardly a surprise, given observed effectiveness of neural networks in many NLP tasks in the recent decade. It seems that bidirectional LSTM augmented with ELMo may already hit the limit for correcting Polish spelling errors without contextual information. While it improves accuracy in comparison to LSTM initialized withrandom noise, it makes the test cross-entropy slightly worse, which hints at overfitting. The perplexity measures actually increase sharply for more sophisticated architectures. Perplexity should show how little probability is assigned by the model to true answers. We measure it as INLINEFORM0 where INLINEFORM0 is a sequence of INLINEFORM1 characters, forming the correct version of the word, and INLINEFORM2 is the estimated probability of the INLINEFORM3 th character, given previous predicted characters and the incorrect form. The observed increase of perplexity for increasingly accurate models is most likely due to more refined predicted probability distributions, which go beyond just assigning the bulk of probability to the best answer. Interesting insights can be gained from weights assigned by optimization to layers of ELMo network, which are taken as the word form embedding (Table TABREF5 ). The first layer, and the one that is nearest to input of the network, is given relatively the least importance, while the middle one dominates both others taken together. This suggests that in error correction, at least for Polish, the middle level of morphemes and other characteristic character chunks is more important than phenomena that are low-level or tied to some specific words. This observation should be taken into account in further research on practical solutions for spelling correction. ### Conclusion
Among the methods tested the bidirectional LSTM, especially initialized by ELMo embeddings, offers the best accuracy and raw performance. Adding ELMo to a straightforward PyTorch implementation of LSTM may be easier now than at the time of performing our tests, as since then the authors of ELMoForManyLangs package BIBREF19 improved their programmatic interface. However, if a more interpretable and explainable output is required, some version of vector distance combined with edit distance may be the best direction. It should be noted that this method produces multiple candidate corrections with their similarity scores, as opposed to only one “best guess“ correction that can be obtained from a character-based LSTM. This is important in applications where it is up to humans to the make the final decision, and they are only to be aided by a machine. It is desirable for further reasearch to expand the corpus material into a wider and more representative set of texts. Nevertheless, the solution for any practical case has to be tailored to its characteristic error patterns. Works on language correction for English show that available corpora can be ”boosted” BIBREF1 , i.e. expanded by generating new errors consistent with a generative model inferred from the data. This may greatly aid in developing models that are dependent on learning from error corpora. A deliberate omission in this paper are the elements accompanying most real-word error correction solutions. Some fairly obvious approaches to integrating evidence from context include n-grams and Markov chains, although the possibility of using measurements in spaces of semantic vectors was already mentioned in this article. Similarly, non-word errors can be easily detected with comparing tokens against reference vocabulary, but in practice one should have ways of detecting mistakes masquerading as real words and fixing bad segmentation (tokens that are glued together or improperly separated). Testing how performant are various methods for dealing with these problems in Polish language is left for future research. Table 1: Test results for all the methods used. The loss measure is cross-entropy. Table 2: Discovered optimal weights for summing layers of ELMo embedding for initializing an error-correcting LSTM. The layers are numbered from the one that directly processes character and word input to the most abstract one.
|
Levenshtein distance metric BIBREF8, diacritical swapping, Levenshtein distance is used in a weighted sum to cosine distance between word vectors, ELMo-augmented LSTM
|
How do Lowry and the Exec feel about the Venusians?
A. Lowry is hoping the Earth immigrants will easily defeat the Venusians, but the Exec doesn't want immigration.
B. They both believe that the immigrants from Earth will easily conquer them.
C. The Exec hates them, but Lowry feels bad for them.
D. They both despise the Venusians because of their un-human-like features.
|
DOUBLECROSS by JAMES Mac CREIGH Revolt was brewing on Venus, led by the descendant of the first Earthmen to land. Svan was the leader making the final plans—plotting them a bit too well. [Transcriber's Note: This etext was produced from Planet Stories Winter 1944. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] The Officer of the Deck was pleased as he returned to the main lock. There was no reason why everything shouldn't have been functioning perfectly, of course, but he was pleased to have it confirmed, all the same. The Executive Officer was moodily smoking a cigarette in the open lock, staring out over the dank Venusian terrain at the native town. He turned. "Everything shipshape, I take it!" he commented. The OD nodded. "I'll have a blank log if this keeps up," he said. "Every man accounted for except the delegation, cargo stowed, drivers ready to lift as soon as they come back." The Exec tossed away his cigarette. " If they come back." "Is there any question?" The Exec shrugged. "I don't know, Lowry," he said. "This is a funny place. I don't trust the natives." Lowry lifted his eyebrows. "Oh? But after all, they're human beings, just like us—" "Not any more. Four or five generations ago they were. Lord, they don't even look human any more. Those white, flabby skins—I don't like them." "Acclimation," Lowry said scientifically. "They had to acclimate themselves to Venus's climate. They're friendly enough." The Exec shrugged again. He stared at the wooden shacks that were the outskirts of the native city, dimly visible through the ever-present Venusian mist. The native guard of honor, posted a hundred yards from the Earth-ship, stood stolidly at attention with their old-fashioned proton-rifles slung over their backs. A few natives were gazing wonderingly at the great ship, but made no move to pass the line of guards. "Of course," Lowry said suddenly, "there's a minority who are afraid of us. I was in town yesterday, and I talked with some of the natives. They think there will be hordes of immigrants from Earth, now that we know Venus is habitable. And there's some sort of a paltry underground group that is spreading the word that the immigrants will drive the native Venusians—the descendants of the first expedition, that is—right down into the mud. Well—" he laughed—"maybe they will. After all, the fittest survive. That's a basic law of—" The annunciator over the open lock clanged vigorously, and a metallic voice rasped: "Officer of the Deck! Post Number One! Instruments reports a spy ray focused on the main lock!" Lowry, interrupted in the middle of a word, jerked his head back and stared unbelievingly at the tell-tale next to the annunciator. Sure enough, it was glowing red—might have been glowing for minutes. He snatched at the hand-phone dangling from the wall, shouted into it. "Set up a screen! Notify the delegation! Alert a landing party!" But even while he was giving orders, the warning light flickered suddenly and went out. Stricken, Lowry turned to the Exec. The Executive Officer nodded gloomily. He said, "You see!" "You see?" Svan clicked off the listening-machine and turned around. The five others in the room looked apprehensive. "You see?" Svan repeated. "From their own mouths you have heard it. The Council was right." The younger of the two women sighed. She might have been beautiful, in spite of her dead-white skin, if there had been a scrap of hair on her head. "Svan, I'm afraid," she said. "Who are we to decide if this is a good thing? Our parents came from Earth. Perhaps there will be trouble at first, if colonists come, but we are of the same blood." Svan laughed harshly. " They don't think so. You heard them. We are not human any more. The officer said it." The other woman spoke unexpectedly. "The Council was right," she agreed. "Svan, what must we do?" Svan raised his hand, thoughtfully. "One moment. Ingra, do you still object?" The younger woman shrank back before the glare in his eyes. She looked around at the others, found them reluctant and uneasy, but visibly convinced by Svan. "No," she said slowly. "I do not object." "And the rest of us? Does any of us object?" Svan eyed them, each in turn. There was a slow but unanimous gesture of assent. "Good," said Svan. "Then we must act. The Council has told us that we alone will decide our course of action. We have agreed that, if the Earth-ship returns, it means disaster for Venus. Therefore, it must not return." An old man shifted restlessly. "But they are strong, Svan," he complained. "They have weapons. We cannot force them to stay." Svan nodded. "No. They will leave. But they will never get back to Earth." "Never get back to Earth?" the old man gasped. "Has the Council authorized—murder?" Svan shrugged. "The Council did not know what we would face. The Councilmen could not come to the city and see what strength the Earth-ship has." He paused dangerously. "Toller," he said, "do you object?" Like the girl, the old man retreated before his eyes. His voice was dull. "What is your plan?" he asked. Svan smiled, and it was like a dark flame. He reached to a box at his feet, held up a shiny metal globe. "One of us will plant this in the ship. It will be set by means of this dial—" he touched a spot on the surface of the globe with a pallid finger—"to do nothing for forty hours. Then—it will explode. Atomite." He grinned triumphantly, looking from face to face. The grin faded uncertainly as he saw what was in their eyes—uncertainty, irresolution. Abruptly he set the bomb down, savagely ripped six leaves off a writing tablet on the table next him. He took a pencil and made a mark on one of them, held it up. "We will let chance decide who is to do the work," he said angrily. "Is there anyone here who is afraid? There will be danger, I think...." No answer. Svan jerked his head. "Good," he said. "Ingra, bring me that bowl." Silently the girl picked up an opaque glass bowl from the broad arm of her chair. It had held Venus-tobacco cigarettes; there were a few left. She shook them out and handed the bowl to Svan, who was rapidly creasing the six fatal slips. He dropped them in the bowl, stirred it with his hand, offered it to the girl. "You first, Ingra," he said. She reached in mechanically, her eyes intent on his, took out a slip and held it without opening it. The bowl went the rounds, till Svan himself took the last. All eyes were on him. No one had looked at their slips. Svan, too, had left his unopened. He sat at the table, facing them. "This is the plan," he said. "We will go, all six of us, in my ground car, to look at the Earth-ship. No one will suspect—the whole city has been to see it already. One will get out, at the best point we can find. It is almost dusk now. He can hide, surely, in the vegetation. The other five will start back. Something will go wrong with the car—perhaps it will run off the road, start to sink in the swamp. The guards will be called. There will be commotion—that is easy enough, after all; a hysterical woman, a few screams, that's all there is to it. And the sixth person will have his chance to steal to the side of the ship. The bomb is magnetic. It will not be noticed in the dark—they will take off before sunrise, because they must travel away from the sun to return—in forty hours the danger is removed." There was comprehension in their eyes, Svan saw ... but still that uncertainty. Impatiently, he crackled: "Look at the slips!" Though he had willed his eyes away from it, his fingers had rebelled. Instinctively they had opened the slip, turned it over and over, striving to detect if it was the fatal one. They had felt nothing.... And his eyes saw nothing. The slip was blank. He gave it but a second's glance, then looked up to see who had won the lethal game of chance. Almost he was disappointed. Each of the others had looked in that same second. And each was looking up now, around at his neighbors. Svan waited impatiently for the chosen one to announce it—a second, ten seconds.... Then gray understanding came to him. A traitor! his subconscious whispered. A coward! He stared at them in a new light, saw their indecision magnified, became opposition. Svan thought faster than ever before in his life. If there was a coward, it would do no good to unmask him. All were wavering, any might be the one who had drawn the fatal slip. He could insist on inspecting every one, but—suppose the coward, cornered, fought back? In fractions of a second, Svan had considered the evidence and reached his decision. Masked by the table, his hand, still holding the pencil, moved swiftly beneath the table, marked his own slip. In the palm of his hand, Svan held up the slip he had just marked in secret. His voice was very tired as he said, "I will plant the bomb." The six conspirators in Svan's old ground car moved slowly along the main street of the native town. Two Earth-ship sailors, unarmed except for deceptively flimsy-looking pistols at their hips, stood before the entrance to the town's Hall of Justice. "Good," said Svan, observing them. "The delegation is still here. We have ample time." He half turned in the broad front seat next to the driver, searching the faces of the others in the car. Which was the coward? he wondered. Ingra? Her aunt? One of the men? The right answer leaped up at him. They all are , he thought. Not one of them understands what this means. They're afraid. He clamped his lips. "Go faster, Ingra," he ordered the girl who was driving. "Let's get this done with." She looked at him, and he was surprised to find compassion in her eyes. Silently she nodded, advanced the fuel-handle so that the clumsy car jolted a trace more rapidly over the corduroy road. It was quite dark now. The car's driving light flared yellowishly in front of them, illuminating the narrow road and the pale, distorted vegetation of the jungle that surrounded them. Svan noticed it was raining a little. The present shower would deepen and intensify until midnight, then fall off again, to halt before morning. But before then they would be done. A proton-bolt lanced across the road in front of them. In the silence that followed its thunderous crash, a man's voice bellowed: "Halt!" The girl, Ingra, gasped something indistinguishable, slammed on the brakes. A Venusian in the trappings of the State Guard advanced on them from the side of the road, proton-rifle held ready to fire again. "Where are you going?" he growled. Svan spoke up. "We want to look at the Earth-ship," he said. He opened the door beside him and stepped out, careless of the drizzle. "We heard it was leaving tonight," he continued, "and we have not seen it. Is that not permitted?" The guard shook his head sourly. "No one is allowed near the ship. The order was just issued. It is thought there is danger." Svan stepped closer, his teeth bared in what passed for a smile. "It is urgent," he purred. His right hand flashed across his chest in a complicated gesture. "Do you understand?" Confusion furrowed the guard's hairless brows, then was replaced by a sudden flare of understanding—and fear. "The Council!" he roared. "By heaven, yes, I understand! You are the swine that caused this—" He strove instinctively to bring the clumsy rifle up, but Svan was faster. His gamble had failed; there was only one course remaining. He hurled his gross white bulk at the guard, bowled him over against the splintery logs of the road. The proton-rifle went flying, and Svan savagely tore at the throat of the guard. Knees, elbows and claw-like nails—Svan battered at the astonished man with every ounce of strength in his body. The guard was as big as Svan, but Svan had the initial advantage ... and it was only a matter of seconds before the guard lay unconscious, his skull a mass of gore at the back where Svan had ruthlessly pounded it against the road. Svan grunted as his fingers constricted brutally. Svan rose, panting, stared around. No one else was in sight, save the petrified five and the ground car. Svan glared at them contemptuously, then reached down and heaved on the senseless body of the guard. Over the shoulder of the road the body went, onto the damp swampland of the jungle. Even while Svan watched the body began to sink. There would be no trace. Svan strode back to the car. "Hurry up," he gasped to the girl. "Now there is danger for all of us, if they discover he is missing. And keep a watch for other guards." Venus has no moon, and no star can shine through its vast cloud layer. Ensign Lowry, staring anxiously out through the astro-dome in the bow of the Earth-ship, cursed the blackness. "Can't see a thing," he complained to the Exec, steadily writing away at the computer's table. "Look—are those lights over there?" The Exec looked up wearily. He shrugged. "Probably the guards. Of course, you can't tell. Might be a raiding party." Lowry, stung, looked to see if the Exec was smiling, but found no answer in his stolid face. "Don't joke about it," he said. "Suppose something happens to the delegation?" "Then we're in the soup," the Exec said philosophically. "I told you the natives were dangerous. Spy-rays! They've been prohibited for the last three hundred years." "It isn't all the natives," Lowry said. "Look how they've doubled the guard around us. The administration is co-operating every way they know how. You heard the delegation's report on the intercom. It's this secret group they call the Council." "And how do you know the guards themselves don't belong to it?" the Exec retorted. "They're all the same to me.... Look, your light's gone out now. Must have been the guard. They're on the wrong side to be coming from the town, anyhow...." Svan hesitated only a fraction of a second after the girl turned the lights out and stopped the car. Then he reached in the compartment under the seat. If he took a little longer than seemed necessary to get the atomite bomb out of the compartment, none of the others noticed. Certainly it did not occur to them that there had been two bombs in the compartment, though Svan's hand emerged with only one. He got out of the car, holding the sphere. "This will do for me," he said. "They won't be expecting anyone to come from behind the ship—we were wise to circle around. Now, you know what you must do?" Ingra nodded, while the others remained mute. "We must circle back again," she parroted. "We are to wait five minutes, then drive the car into the swamp. We will create a commotion, attract the guards." Svan, listening, thought: It's not much of a plan. The guards would not be drawn away. I am glad I can't trust these five any more. If they must be destroyed, it is good that their destruction will serve a purpose. Aloud, he said, "You understand. If I get through, I will return to the city on foot. No one will suspect anything if I am not caught, because the bomb will not explode until the ship is far out in space. Remember, you are in no danger from the guards." From the guards , his mind echoed. He smiled. At least, they would feel no pain, never know what happened. With the amount of atomite in that bomb in the compartment, they would merely be obliterated in a ground-shaking crash. Abruptly he swallowed, reminded of the bomb that was silently counting off the seconds. "Go ahead," he ordered. "I will wait here." "Svan." The girl, Ingra, leaned over to him. Impulsively she reached for him, kissed him. "Good luck to you, Svan," she said. "Good luck," repeated the others. Then silently the electric motor of the car took hold. Skilfully the girl backed it up, turned it around, sent it lumbering back down the road. Only after she had traveled a few hundred feet by the feel of the road did she turn the lights on again. Svan looked after them. The kiss had surprised him. What did it mean? Was it an error that the girl should die with the others? There was an instant of doubt in his steel-shackled mind, then it was driven away. Perhaps she was loyal, yet certainly she was weak. And since he could not know which was the one who had received the marked slip, and feared to admit it, it was better they all should die. He advanced along the midnight road to where the ground rose and the jungle plants thinned out. Ahead, on an elevation, were the rain-dimmed lights of the Earth-ship, set down in the center of a clearing made by its own fierce rockets. Svan's mist-trained eyes spotted the circling figures of sentries, and knew that these would be the ship's own. They would not be as easily overcome as the natives, not with those slim-shafted blasters they carried. Only deceit could get him to the side of the ship. Svan settled himself at the side of the road, waiting for his chance. He had perhaps three minutes to wait; he reckoned. His fingers went absently to the pouch in his wide belt, closed on the slip of paper. He turned it over without looking at it, wondering who had drawn the first cross, and been a coward. Ingra? One of the men? He became abruptly conscious of a commotion behind him. A ground car was racing along the road. He spun around and was caught in the glare of its blinding driving-light, as it bumped to a slithering stop. Paralyzed, he heard the girl's voice. "Svan! They're coming! They found the guard's rifle, and they're looking for us! Thirty Earthmen, Svan, with those frightful guns. They fired at us, but we got away and came for you. We must flee!" He stared unseeingly at the light. "Go away!" he croaked unbelievingly. Then his muscles jerked into action. The time was almost up—the bomb in the car— "Go away!" he shrieked, and turned to run. His fists clenched and swinging at his side, he made a dozen floundering steps before something immense pounded at him from behind. He felt himself lifted from the road, sailing, swooping, dropping with annihilating force onto the hard, charred earth of the clearing. Only then did he hear the sound of the explosion, and as the immense echoes died away he began to feel the pain seeping into him from his hideously racked body.... The Flight Surgeon rose from beside him. "He's still alive," he said callously to Lowry, who had just come up. "It won't last long, though. What've you got there?" Lowry, a bewildered expression on his beardless face, held out the two halves of a metallic sphere. Dangling ends of wires showed where a connection had been broken. "He had a bomb," he said. "A magnetic-type, delayed-action atomite bomb. There must have been another in the car, and it went off. They—they were planning to bomb us." "Amazing," the surgeon said dryly. "Well, they won't do any bombing now." Lowry was staring at the huddled, mutilated form of Svan. He shuddered. The surgeon, seeing the shudder, grasped his shoulder. "Better them than us," he said. "It's poetic justice if I ever saw it. They had it coming...." He paused thoughtfully, staring at a piece of paper between his fingers. "This is the only part I don't get," he said. "What's that?" Lowry craned his neck. "A piece of paper with a cross on it? What about it?" The surgeon shrugged. "He had it clenched in his hand," he said. "Had the devil of a time getting it loose from him." He turned it over slowly, displayed the other side. "Now what in the world would he be doing carrying a scrap of paper with a cross marked on both sides?"
|
C. The Exec hates them, but Lowry feels bad for them.
|
Which word best describes Nat?
A. dishonest
B. respectable
C. enthusiastic
D. partier
|
I am a Nucleus By STEPHEN BARR Illustrated by GAUGHAN [Transcriber's Note: This etext was produced from Galaxy Science Fiction February 1957. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] No doubt whatever about it, I had the Indian sign on me ... my comfortably untidy world had suddenly turned into a monstrosity of order! When I got home from the office, I was not so much tired as beaten down, but the effect is similar. I let myself into the apartment, which had an absentee-wife look, and took a cold shower. The present downtown temperature, according to the radio, was eighty-seven degrees, but according to my Greenwich Village thermometer, it was ninety-six. I got dressed and went into the living room, and wished ardently that my wife Molly were here to tell me why the whole place looked so woebegone. What do they do, I asked myself, that I have left undone? I've vacuumed the carpet, I've dusted and I've straightened the cushions.... Ah! The ashtrays. I emptied them, washed them and put them back, but still the place looked wife-deserted. It had been a bad day; I had forgotten to wind the alarm clock, so I'd had to hurry to make a story conference at one of the TV studios I write for. I didn't notice the impending rain storm and had no umbrella when I reached the sidewalk, to find myself confronted with an almost tropical downpour. I would have turned back, but a taxi came up and a woman got out, so I dashed through the rain and got in. "Madison and Fifty-fourth," I said. "Right," said the driver, and I heard the starter grind, and then go on grinding. After some futile efforts, he turned to me. "Sorry, Mac. You'll have to find another cab. Good hunting." If possible, it was raining still harder. I opened my newspaper over my hat and ran for the subway: three blocks. Whizzing traffic held me up at each crossing and I was soaked when I reached the platform, just in time to miss the local. After an abnormal delay, I got one which exactly missed the express at Fourteenth Street. The same thing happened at both ends of the crosstown shuttle, but I found the rain had stopped when I got out at Fifty-first and Lexington. As I walked across to Madison Avenue, I passed a big excavation where they were getting ready to put up a new office building. There was the usual crowd of buffs watching the digging machines and, in particular, a man with a pneumatic drill who was breaking up some hard-packed clay. While I looked, a big lump of it fell away, and for an instant I was able to see something that looked like a chunk of dirty glass, the size of an old-fashioned hatbox. It glittered brilliantly in the sunlight, and then his chattering drill hit it. There was a faint bang and the thing disintegrated. It knocked him on his back, but he got right up and I realized he was not hurt. At the moment of the explosion—if so feeble a thing can be called one—I felt something sting my face and, on touching it, found blood on my hand. I mopped at it with my handkerchief but, though slight, the bleeding would not stop, so I went into a drugstore and bought some pink adhesive which I put on the tiny cut. When I got to the studio, I found that I had missed the story conference. During the day, by actual count, I heard the phrase "I'm just spitballing" eight times, and another Madison Avenue favorite, "The whole ball of wax," twelve times. However, my story had been accepted without change because nobody had noticed my absence from the conference room. There you have what is known as the Advertising World, the Advertising game or the advertising racket, depending upon which rung of the ladder you have achieved. The subway gave a repeat performance going home, and as I got to the apartment house we live in, the cop on the afternoon beat was standing there talking to the doorman. He said, "Hello, Mr. Graham. I guess you must have just have missed it at your office building." I looked blank and he explained, "We just heard it a little while ago: all six elevators in your building jammed at the same time. Sounds crazy. I guess you just missed it." Anything can happen in advertising, I thought. "That's right, Danny, I just missed it," I said, and went on in. Psychiatry tells us that some people are accident-prone; I, on the other hand, seemed recently to be coincidence-prone, fluke-happy, and except for the alarm clock, I'd had no control over what had been going on. I went into our little kitchen to make a drink and reread the directions Molly had left, telling me how to get along by myself until she got back from her mother's in Oyster Bay, a matter of ten days. How to make coffee, how to open a can, whom to call if I took sick and such. My wife used to be a trained nurse and she is quite convinced that I cannot take a breath without her. She is right, but not for the reasons she supposes. I opened the refrigerator to get some ice and saw another notice: "When you take out the Milk or Butter, Put it Right Back. And Close the Door, too." Intimidated, I took my drink into the living room and sat down in front of the typewriter. As I stared at the novel that was to liberate me from Madison Avenue, I noticed a mistake and picked up a pencil. When I put it down, it rolled off the desk, and with my eyes on the manuscript, I groped under the chair for it. Then I looked down. The pencil was standing on its end. There, I thought to myself, is that one chance in a million we hear about, and picked up the pencil. I turned back to my novel and drank some of the highball in hopes of inspiration and surcease from the muggy heat, but nothing came. I went back and read the whole chapter to try to get a forward momentum, but came to a dead stop at the last sentence. Damn the heat, damn the pencil, damn Madison Avenue and advertising. My drink was gone and I went back to the kitchen and read Molly's notes again to see if they would be like a letter from her. I noticed one that I had missed, pinned to the door of the dumbwaiter: "Garbage picked up at 6:30 AM so the idea is to Put it Here the Night Before. I love you." What can you do when the girl loves you? I made another drink and went and stared out of the living room window at the roof opposite. The Sun was out again and a man with a stick was exercising his flock of pigeons. They wheeled in a circle, hoping to be allowed to perch, but were not allowed to. Pigeons fly as a rule in formation and turn simultaneously, so that their wings all catch the sunlight at the same time. I was thinking about this decorative fact when I saw that as they were making a turn, they seemed to bunch up together. By some curious chance, they all wanted the same place in the sky to turn in, and several collided and fell. The man was as surprised as I and went to one of the dazed birds and picked it up. He stood there shaking his head from side to side, stroking its feathers. My speculations about this peculiar aerial traffic accident were interrupted by loud voices in the hallway. Since our building is usually very well behaved, I was astonished to hear what sounded like an incipient free-for-all, and among the angry voices I recognized that of my neighbor, Nat, a very quiet guy who works on a newspaper and has never, to my knowledge, given wild parties, particularly in the late afternoon. "You can't say a thing like that to me!" I heard him shout. "I tell you I got that deck this afternoon and they weren't opened till we started to play!" Several other loud voices started at the same time. "Nobody gets five straight-flushes in a row!" "Yeah, and only when you were dealer!" The tone of the argument was beginning to get ugly, and I opened the door to offer Nat help if he needed it. There were four men confronting him, evidently torn between the desire to make an angry exit and the impulse to stay and beat him up. His face was furiously red and he looked stunned. "Here!" he said, holding out a deck of cards, "For Pete's sake, look at 'em yourselves if you think they're marked!" The nearest man struck them up from his hand. "Okay, Houdini! So they're not marked! All I know is five straight...." His voice trailed away. He and the others stared at the scattered cards on the floor. About half were face down, as might be expected, and the rest face up—all red. Someone must have rung, because at that moment the elevator arrived and the four men, with half frightened, incredulous looks, and in silence, got in and were taken down. My friend stood looking at the neatly arranged cards. "Judas!" he said, and started to pick them up. "Will you look at that! My God, what a session...." I helped him and said to come in for a drink and tell me all about it, but I had an idea what I would hear. After a while, he calmed down, but he still seemed dazed. "Never seen anything to equal it," he said. "Wouldn't have believed it. Those guys didn't believe it. Every round normal, nothing unusual about the hands—three of a kind, a low straight, that sort of thing and one guy got queens over tens, until it gets to be my deal. Brother! Straight flush to the king—every time! And each time, somebody else has four aces...." He started to sweat again, so I got up to fix him another drink. There was one quart of club soda left, but when I tried to open it, the top broke and glass chips got into the bottle. "I'll have to go down for more soda," I said. "I'll come, too. I need air." At the delicatessen on the corner, the man gave me three bottles in what must have been a wet bag, because as he handed them to me over the top of the cold-meat display, the bottom gave and they fell onto the tile floor. None of them broke, although the fall must have been from at least five feet. Nat was too wound up in his thoughts to notice and I was getting used to miracles. We left the proprietor with his mouth open and met Danny, the cop, looking in at the door, also with his mouth open. On the sidewalk, a man walking in front of Nat stooped suddenly to tie his shoe and Nat, to avoid bumping him, stepped off the curb and a taxi swerved to avoid Nat. The street was still wet and the taxi skidded, its rear end lightly flipping the front of one of those small foreign cars, which was going rather fast. It turned sideways and, without any side-slip, went right up the stoop of a brownstone opposite, coming to rest with its nose inside the front door, which a man opened at that moment. The sight of this threw another driver into a skid, and when he and the taxi had stopped sliding around, they were face to face, arranged crosswise to the street. This gave them exactly no room to move either forward or backward, for the car had its back to a hydrant and the taxi to a lamp. Although rather narrow, this is a two-way street, and in no time at all, traffic was stacked up from both directions as far as the avenues. Everyone was honking his horn. Danny was furious—more so when he tried to put through a call to his station house from the box opposite. It was out of order. Upstairs, the wind was blowing into the apartment and I closed the windows, mainly to shut out the tumult and the shouting. Nat had brightened up considerably. "I'll stay for one more drink and then I'm due at the office," he said. "You know, I think this would make an item for the paper." He grinned and nodded toward the pandemonium. When he was gone, I noticed it was getting dark and turned on the desk lamp. Then I saw the curtains. They were all tied in knots, except one. That was tied in three knots. All right , I told myself, it was the wind. But I felt the time had come for me to get expert advice, so I went to the phone to call McGill. McGill is an assistant professor of mathematics at a university uptown and lives near us. He is highly imaginative, but we believe he knows everything. When I picked up the receiver, the line sounded dead and I thought, more trouble. Then I heard a man cough and I said hello. McGill's voice said, "Alec? You must have picked up the receiver just as we were connected. That's a damn funny coincidence." "Not in the least," I said. "Come on over here. I've got something for you to work on." "Well, as a matter of fact, I was calling up to ask you and Molly—" "Molly's away for the week. Can you get over here quick? It's urgent." "At once," he said, and hung up. While I waited, I thought I might try getting down a few paragraphs of my novel—perhaps something would come now. It did, but as I came to a point where I was about to put down the word "agurgling," I decided it was too reminiscent of Gilbert and Sullivan, and stopped at the letter "R." Then I saw that I had unaccountably hit all four keys one step to the side of the correct ones, and tore out the page, with my face red. This was absolutely not my day. "Well," McGill said, "nothing you've told me is impossible or supernatural. Just very, very improbable. In fact, the odds against that poker game alone would lead me to suspect Nat, well as I know him. It's all those other things...." He got up and walked over to the window and looked at the hot twilight while I waited. Then he turned around; he had a look of concern. "Alec, you're a reasonable guy, so I don't think you'll take offense at what I'm going to say. What you have told me is so impossibly unlikely, and the odds against it so astronomical, that I must take the view that you're either stringing me or you're subject to a delusion." I started to get up and expostulate, but he motioned me back. "I know, but don't you see that that is far more likely than...." He stopped and shook his head. Then he brightened. "I have an idea. Maybe we can have a demonstration." He thought for a tense minute and snapped his fingers. "Have you any change on you?" "Why, yes," I said. "Quite a bit." I reached into my pocket. There must have been nearly two dollars in silver and pennies. "Do you think they'll each have the same date, perhaps?" "Did you accumulate all that change today?" "No. During the week." He shook his head. "In that case, no. Discounting the fact that you could have prearranged it, if my dim provisional theory is right, that would be actually impossible. It would involve time-reversal. I'll tell you about it later. No, just throw down the change. Let's see if they all come up heads." I moved away from the carpet and tossed the handful of coins onto the floor. They clattered and bounced—and bounced together—and stacked themselves into a neat pile. I looked at McGill. His eyes were narrowed. Without a word, he took a handful of coins from his own pocket and threw them. These coins didn't stack. They just fell into an exactly straight line, the adjacent ones touching. "Well," I said, "what more do you want?" "Great Scott," he said, and sat down. "I suppose you know that there are two great apparently opposite principles governing the Universe—random and design. The sands on the beach are an example of random distribution and life is an example of design. The motions of the particles of a gas are what we call random, but there are so many of them, we treat them statistically and derive the Second Law of Thermodynamics—quite reliable. It isn't theoretically hard-and-fast; it's just a matter of extreme probability. Now life, on the other hand, seems not to depend on probability at all; actually, it goes against it. Or you might say it is certainly not an accidental manifestation." "Do you mean," I asked in some confusion, "that some form of life is controlling the coins and—the other things?" He shook his head. "No. All I mean is that improbable things usually have improbable explanations. When I see a natural law being broken, I don't say to myself, 'Here's a miracle.' I revise my version of the book of rules. Something—I don't know what—is going on, and it seems to involve probability, and it seems to center around you. Were you still in that building when the elevators stuck? Or near it?" "I guess I must have been. It happened just after I left." "Hm. You're the center, all right. But why?" "Center of what?" I asked. "I feel as though I were the center of an electrical storm. Something has it in for me!" McGill grinned. "Don't be superstitious. And especially don't be anthropomorphic." "Well, if it's the opposite of random, it's got to be a form of life." "On what basis? All we know for certain is that random motions are being rearranged. A crystal, for example, is not life, but it's a non-random arrangement of particles.... I wonder." He had a faraway, frowning look. I was beginning to feel hungry and the drinks had worn off. "Let's go out and eat," I said, "There's not a damn thing in the kitchen and I'm not allowed to cook. Only eggs and coffee." We put on our hats and went down to the street. From either end, we could hear wrecking trucks towing away the stalled cars. There were, by this time, a number of harassed cops directing the maneuver and we heard one of them say to Danny, "I don't know what the hell's going on around here. Every goddam car's got something the matter with it. They can't none of them back out for one reason or another. Never seen anything like it." Near us, two pedestrians were doing a curious little two-step as they tried to pass one another; as soon as one of them moved aside to let the other pass, the other would move to the same side. They both had embarrassed grins on their faces, but before long their grins were replaced by looks of suspicion and then determination. "All right, smart guy!" they shouted in unison, and barged ahead, only to collide. They backed off and threw simultaneous punches which met in mid-air. Then began one of the most remarkable bouts ever witnessed—a fight in which fist hit fist but never anything else, until both champions backed away undefeated, muttering identical excuses and threats. Danny appeared at that moment. His face was dripping. "You all right, Mr. Graham?" he asked. "I don't know what's going on around here, but ever since I came on this afternoon, things are going crazy. Bartley!" he shouted—he could succeed as a hog-caller. "Bring those dames over here!" Three women in a confused wrangle, with their half-open umbrellas intertwined, were brought across the street, which meant climbing over fenders. Bartley, a fine young patrolman, seemed self-conscious; the ladies seemed not to be. "All right, now, Mrs. Mac-Philip!" one of them said. "Leave go of my umbrella and we'll say no more about it!" "And so now it's Missus Mac-Philip, is it?" said her adversary. The third, a younger one with her back turned to us, her umbrella also caught in the tangle, pulled at it in a tentative way, at which the other two glared at her. She turned her head away and tried to let go, but the handle was caught in her glove. She looked up and I saw it was Molly. My nurse-wife. "Oh, Alec!" she said, and managed to detach herself. "Are you all right?" Was I all right! "Molly! What are you doing here?" "I was so worried, and when I saw all this, I didn't know what to think." She pointed to the stalled cars. "Are you really all right?" "Of course I'm all right. But why...." "The Oyster Bay operator said someone kept dialing and dialing Mother's number and there wasn't anyone on the line, so then she had it traced and it came from our phone here. I kept calling up, but I only got a busy signal. Oh, dear, are you sure you're all right?" I put my arm around her and glanced at McGill. He had an inward look. Then I caught Danny's eye. It had a thoughtful, almost suspicious cast to it. "Trouble does seem to follow you, Mr. Graham," was all he said. When we got upstairs, I turned to McGill. "Explain to Molly," I said. "And incidentally to me. I'm not properly briefed yet." He did so, and when he got to the summing up, I had the feeling she was a jump ahead of him. "In other words, you think it's something organic?" "Well," McGill said, "I'm trying to think of anything else it might be. I'm not doing so well," he confessed. "But so far as I can see," Molly answered, "it's mere probability, and without any over-all pattern." "Not quite. It has a center. Alec is the center." Molly looked at me with a curious expression for a moment. "Do you feel all right, darling?" she asked me. I nodded brightly. "You'll think this silly of me," she went on to McGill, "but why isn't it something like an overactive poltergeist?" "Pure concept," he said. "No genuine evidence." "Magnetism?" "Absolutely not. For one thing, most of the objects affected weren't magnetic—and don't forget magnetism is a force, not a form of energy, and a great deal of energy has been involved. I admit the energy has mainly been supplied by the things themselves, but in a magnetic field, all you'd get would be stored kinetic energy, such as when a piece of iron moves to a magnet or a line of force. Then it would just stay there, like a rundown clock weight. These things do a lot more than that—they go on moving." "Why did you mention a crystal before? Why not a life-form?" "Only an analogy," said McGill. "A crystal resembles life in that it has a definite shape and exhibits growth, but that's all. I'll agree this—thing—has no discernible shape and motion is involved, but plants don't move and amebas have no shape. Then a crystal feeds, but it does not convert what it feeds on; it merely rearranges it into a non-random pattern. In this case, it's rearranging random motions and it has a nucleus and it seems to be growing—at least in what you might call improbability." Molly frowned. "Then what is it? What's it made of?" "I should say it was made of the motions. There's a similar idea about the atom. Another thing that's like a crystal is that it appears to be forming around a nucleus not of its own material—the way a speck of sand thrown into a supersaturated solution becomes the nucleus of crystallization." "Sounds like the pearl in an oyster," Molly said, and gave me an impertinent look. "Why," I asked McGill, "did you say the coins couldn't have the same date? I mean apart from the off chance I got them that way." "Because I don't think this thing got going before today and everything that's happened can all be described as improbable motions here and now. The dates were already there, and to change them would require retroactive action, reversing time. That's out, in my book. That telephone now—" The doorbell rang. We were not surprised to find it was the telephone repairman. He took the set apart and clucked like a hen. "I guess you dropped it on the floor, mister," he said with strong disapproval. "Certainly not," I said. "Is it broken?" "Not exactly broken , but—" He shook his head and took it apart some more. McGill went over and they discussed the problem in undertones. Finally the man left and Molly called her mother to reassure her. McGill tried to explain to me what had happened with the phone. "You must have joggled something loose. And then you replaced the receiver in such a way that the contact wasn't quite open." "But for Pete's sake, Molly says the calls were going on for a long time! I phoned you only a short time ago and it must have taken her nearly two hours to get here from Oyster Bay." "Then you must have done it twice and the vibrations in the floor—something like that—just happened to cause the right induction impulses. Yes, I know how you feel," he said, seeing my expression. "It's beginning to bear down." Molly was through telephoning and suggested going out for dinner. I was so pleased to see her that I'd forgotten all about being hungry. "I'm in no mood to cook," she said. "Let's get away from all this." McGill raised an eyebrow. "If all this, as you call it, will let us." In the lobby, we ran into Nat, looking smug in a journalistic way. "I've been put on the story—who could be better?—I live here. So far, I don't quite get what's been happening. I've been talking to Danny, but he didn't say much. I got the feeling he thinks you're involved in some mystical, Hibernian way. Hello, McGill, what's with you?" "He's got a theory," said Molly. "Come and eat with us and he'll tell you all about it." Since we decided on an air-conditioned restaurant nearby on Sixth Avenue, we walked. The jam of cars didn't seem to be any less than before and we saw Danny again. He was talking to a police lieutenant, and when he caught sight of us, he said something that made the lieutenant look at us with interest. Particularly at me. "If you want your umbrella, Mrs. Graham," Danny said, "it's at the station house. What there's left of it, that is." Molly thanked him and there was a short pause, during which I felt the speculative regard of the lieutenant. I pulled out a packet of cigarettes, which I had opened, as always, by tearing off the top. I happened to have it upside down and all the cigarettes fell out. Before I could move my foot to obliterate what they had spelled out on the sidewalk, the two cops saw it. The lieutenant gave me a hard look, but said nothing. I quickly kicked the insulting cigarettes into the gutter. When we got to the restaurant, it was crowded but cool—although it didn't stay cool for long. We sat down at a side table near the door and ordered Tom Collinses as we looked at the menu. Sitting at the next table were a fat lady, wearing a very long, brilliant green evening gown, and a dried-up sour-looking man in a tux. When the waiter returned, they preempted him and began ordering dinner fussily: cold cuts for the man, and vichyssoise, lobster salad and strawberry parfait for the fat lady. I tasted my drink. It was most peculiar; salt seemed to have been used instead of sugar. I mentioned this and my companions tried theirs, and made faces. The waiter was concerned and apologetic, and took the drinks back to the bar across the room. The bartender looked over at us and tasted one of the drinks. Then he dumped them in his sink with a puzzled expression and made a new batch. After shaking this up, he set out a row of glasses, put ice in them and began to pour. That is to say he tilted the shaker over the first one, but nothing came out. He bumped it against the side of the bar and tried again. Still nothing. Then he took off the top and pried into it with his pick, his face pink with exasperation. I had the impression that the shaker had frozen solid. Well, ice is a crystal, I thought to myself. The other bartender gave him a fresh shaker, but the same thing happened, and I saw no more because the customers sitting at the bar crowded around in front of him, offering advice. Our waiter came back, baffled, saying he'd have the drinks in a moment, and went to the kitchen. When he returned, he had madame's vichyssoise and some rolls, which he put down, and then went to the bar, where the audience had grown larger. Molly lit a cigarette and said, "I suppose this is all part of it, Alec. Incidentally, it seems to be getting warmer in here." It was, and I had the feeling the place was quieter—a background noise had stopped. It dawned on me that I no longer heard the faint hum of the air-conditioner over the door, and as I started to say so, I made a gesture toward it. My hand collided with Molly's when she tapped her cigarette over the ashtray, and the cigarette landed in the neighboring vichyssoise. "Hey! What's the idea?" snarled the sour-looking man. "I'm terribly sorry," I said. "It was an accident. I—" "Throwing cigarettes at people!" the fat lady said. "I really didn't mean to," I began again, getting up. There must have been a hole in the edge of their tablecloth which one of my cuff buttons caught in, because as I stepped out from between the closely set tables, I pulled everything—tablecloth, silver, water glasses, ashtrays and the vichyssoise-à-la-nicotine—onto the floor. The fat lady surged from the banquette and slapped me meatily. The man licked his thumb and danced as boxers are popularly supposed to do. The owner of the place, a man with thick black eyebrows, hustled toward us with a determined manner. I tried to explain what had happened, but I was outshouted, and the owner frowned darkly.
|
B. respectable
|
What did Charles probably realize at the end?
A. He could have stopped the plague
B. There were more people alive that he hadn't found
C. There was an alien on the Empire State Building
D. He was the last person because of his last name
|
"Phone Me in Central Park" By JAMES McCONNELL There should be an epitaph for every man, big or little, but a really grand and special one for Loner Charlie. [Transcriber's Note: This etext was produced from Planet Stories Fall 1954. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Charles turned over on his side to look at her. She lay quietly in the other bed, the most beautiful woman he had ever seen. She was blonde to perfection, exquisitely shaped, and the rich promise of her body was exposed to his view. "Why?" he thought as he looked at her. "Why did it have to happen like this?" The whole thing was still like a dream to him, and as yet he couldn't decide whether it was a good or a bad dream. A year ago she had been unattainable, a face to conjure with in erotic dreams, far beyond his ken. A year ago she had been a public idol, the most popular actress of the day. And he had been a nobody, full of a nobody's idle hopes and schemes. And now he was lying in the bed next to hers in her swank Manhattan apartment in the most exclusive hotel in town. The unrealness of the situation overwhelmed him. His mind was a picture of confused thoughts. Meanings and answers to his questions slithered out of his reach. "God," he said. It was not an exclamation, nor yet an expletive. It was a mere statement of fact. A thought teased at him. Charles looked at the woman again and decided that she still looked beautiful in spite of the harshness of the room's lighting. He touched buttons by the edge of the bed and the illumination quieted to a soft glow, wrapping her in a radiant halo. Charles smiled wanly and got up. He stood by the bed looking at her. "I could have fallen in love with you once. A year ago, perhaps, or longer. But not now. Not now." He turned away and walked to the window. "Now the world is dead. The whole world is dead." New York lay quietly below him. It was the hour of indecision when day has not quite made up its mind to leave and night has not yet attacked in force. The streetlights were already on, making geometric patterns through the dusk of Central Park. Some of the billboards were shining, their relays activated by darkness-sensitized solenoids. A reddish-orange pallor hung from the sky. It had been very pleasant that afternoon. She had given of herself freely, warmly, and Charles had accepted. But then he had known that she would. It was not him, it was the circumstances. Under the circumstances, she would have given herself to any man— "Why did it have to be her—or me? Why should it have to happen to anybody! Why!" She would have given herself to any man— His thoughts beat a rapid crescendo, activating emotions, stimulating sensations of angry rage. He wanted to cry, to weep angry tears of protest. To any man, WHO HAPPENED TO BE THE LAST MAN ON EARTH! Charles picked up a heavy book end off the table and crashed it through the thick pane of window glass. A gust of wind from the outside breezed through the shattered opening, attacking his olfactory patch with the retching smell of decaying flesh. Charles ignored it. Even smells had lost their customary meanings. He felt the rage build up inside again, tearing at his viscera. His stomach clenched up like an angry fist. "But I don't want to be the last man alive!" he shouted. "I don't know what to do! I don't know where to go, how to act! I just don't know—" A paroxysm of sobbing shook his body. Trembling, he dropped to his knees, his head against the cold firmness of the sill, his hands clutched tightly around the jagged edges of the window pane. In spite of the sharp pain that raced through his system, in spite of the bright, warm, red stream that trickled down his face, he knelt by the window for several minutes. " Maybe I'm not the last! " The thought struck him with suddenness, promisingly, edged with swelling comfort to fill his emptiness. Charles got up slowly, noticing for the first time that his fingers were badly cut. He wrapped a handkerchief around them and forgot them. He had to know—he had to find out. As he turned to leave, he noticed again the woman lying in radiant state upon the bed. He walked to her side and leaned over, kissing her gently on the forehead. As he straightened up, his leg caught against her arm, pushing it slightly. The woman's arm slipped from its position and dangled from the edge of the bed like a crazy pendulum. Charles picked it up and folded it across her now cold breasts. He started to pull the sheet over her nude form, then stopped, smiling at his conventionality. After all, it didn't make any difference now. The phonograph was near the door. On sudden impulse he switched it on, turned the volume up full, and in grim jest left it playing Rachmaninoff's Isle of the Dead on full automatic. The music haunted him down the hall to the elevator that he had to run himself. The lobby was littered with debris, human and otherwise. Charles ignored it. The street that led towards the Bureau of Vital Statistics was a mess of desolate carnage. Charles overlooked it. Shop fronts smashed, stores looted, gyro-cars wrecked, proud buildings defaced. "That was it," he said to himself. "Pride. We called this the 'Proud Era.' Everything was better and bigger and nicer to have. Buildings were taller, men were healthier, most of the problems of humanity seemed licked, or nearly so. It was a time of free power, each small unit of population, each section of town operating on perpetual, ever-lasting, automatic atomic piles. "We were free. We seemed, almost, to have accomplished something. The world was running well. No wonder we called it the 'Proud Era.' Life was fun, just a bowl of cherries, until...." Two years ago the animals had started dying. Strangely enough the rats had gone first, to anybody's notice. Sales of poison dropped, scientific laboratories chained to a perpetual rodent-cycle began to complain bitterly. Then the lovers who hunted out and haunted the lonely lanes through the countryside began to remark that the locusts were late that year. The Southern states joyously reported that mosquito control was working to an unprecedented degree. The largest cotton crop ever was forecast and rumors from Mexico had it that no one had died from scorpion bite in several weeks. A month later the meat animals, the birds and the household pets began dropping as rapidly as the flies which had dropped earlier. Congress was called into special session, as were all of the national governments around the world. The U.N. met at emergency sessions to cope with the situation. The president of the world-wide Society for the Prevention of Cruelty to Animals committed suicide. Within a year it was obvious to everyone that man was the only animal left on earth. The panic which had begun with the death of the animals was quieted somewhat by the fact that humans seemed immune to the pandemic. But the lakes full of dead fish caused a great stink and residents along the coasts began to move inland. Sales of perfumes and deodorants soared. Then just one year ago, the first human became infected with the strange malady. Within six months, half of the world's population was gone. Less than a month ago no more than a few thousand people remained in New York. And now.... "I've got to find out," Charles told himself. He meant it, of course, but in a sense he was afraid—afraid that his trip to the Bureau might give him an answer he didn't dare listen to. "But I've got to try." He walked on down the bloody street. Before the plague the Bureau of Vital Statistics had been one of man's crowning achievements. Housed as it was in a huge metallic globe of a building, it contained computers which kept exact account of every human on earth. Compulsory registration and the classification of each individual by means of the discrete patterns of his brain waves had accomplished for man what no ordinary census could have. The machine knew who was alive, who was dead, and where everybody was. Once a year the Bureau issued The Index, an exact accounting of Earth's four billion inhabitants. Four billion names and addresses, compressed into microprint, a tremendous achievement even for the "Proud Era." In all of his life, Charles had never once glanced at The Index. The average person had little necessity to do so since the Bureau information service would answer questions free of charge at any time. Reaching the gigantic building, Charles pushed aside the body of a young man and walked into the main foyer. Passing behind once-guarded doors, he entered the giant computer room and paused in admiration. Only once, before the plague, had he seen the interior of this room. But he still remembered it and he still recalled the powerful emotional experience it had been those many years ago. All children had to have a brain-wave recording made by the Bureau during the first month of their life. And again at the age of 10 each child returned to the Bureau for a recheck. It was for this latter recording that Charles had come to the Bureau some twenty-two years before and a friendly guard had let him peep briefly into the computer room. The impression of intense activity, of organized confusion, of mechanical wonder had remained with him the rest of his life. "So different now," he thought, surveying the room. "Now it's empty, so empty." The machine seemed to reflect the stillness, the very deadness of the world. The silence became unbearable. Charles walked to the master control panel. With newly acquired dexterity he switched the computer screens on and watched them glow to life. All around the world sensitive receiving stations pulsed to activity, sending out searching fingers, hunting for elusive patterns of neutral energy, mapping and tabulating the results. The main computer screen dominated one wall of the room. Other smaller screens clustered around it. On these screens could be graphed the population of any and every part of the globe. An illuminated counter immediately above it would give the numerical strength of the area being sampled while the screen would show population density by individual pinpoints of light that merged to form brightness patterns. "I'll try New York first," he said to himself, knowing that he was a coward, afraid to check the whole world from the start. "I'll start with New York and work up." Charles activated the switches that would flash a schematic map of New York on the screen. "There's bound to be somebody else left here. After all, there were at least twenty of us just a couple of days ago." And one of them, a beautiful woman, had invited him up to her apartment, not because she liked him, but because.... The main screen focused itself, the patterns shifting into a recognizable perceptual image. "Why, it was just yesterday (or was it the day before?) that ten of us, at least, met here to check the figures. There were lots of us alive then." Including the blond young woman who had died just this afternoon.... Charles stopped talking and forced his eyes upwards. Peripheral vision caught first the vague outlines of the lower part of the map. His eyes continued to move, slowly, reluctantly. They caught the over-all relief of Greater New York City—and then concentrated on the single, shining dot at the very heart of the map—and he understood. His eyes stabbed quickly for the counter above the screen. One. He gasped. The counter read one . Charles was by himself, the last person alive in all of New York City. He began to tremble violently. The silence of the room began to press quickly in on him. His frantic fingers searched for the computer controls. New York State. One. The entire United States. One. The western hemisphere, including islands. (Was that a point of light in Brazil? No. Just a ghost image). One. The Pacific area, Asia, Australia, Asia Minor, Russia and the Near East, Africa and then Europe. England! There was a light in England! Someone else still lived! The counter clicked forward. Two! His trembling stopped. He breathed again. "Of course. London was at least as populous as New York City before the plague. It's only logical that—" He stopped. For even as he spoke, the light winked out! The counter clicked again. One. Alone. Alone! Charles screamed. The bottom dropped out from under him! Why? Such a simple question, but in those three letters lay the essence of human nature. Why. The drive of curiosity. Stronger, in a way, than the so-called "basic" drives: hunger, thirst, sex, shelter, warmth, companionship, elimination. Certainly more decisive in the history of the race. Man began to think, to differentiate himself from the other animals, when he first asked the question: "Why?" But thinking about "why" didn't answer the question itself, Charles thought. He looked around him. He was sitting on a bench in Central Park, alone except for a few stray corpses. But the park was fairly free of bodies. "You've got about ten minutes warning," he said to himself. "I guess that most people wanted to die inside of something—inside of anything. Not out in the unprotected open." The silence was like a weight hanging around his neck. Not an insect noise, not the chirp of a bird, not the sound of a car nor the scream of a plane. Not even a breeze to whisper among the leaves, he thought. Civilization equals life equals noise. Silence equals.... Why. His mind kept returning to the question. Of all the people on earth, me. The last. Why me? Average, that's what he was. Height: 5'11". Weight: 165. Age: 32. Status: Married, once upon a time. The Norm, with no significant departures, all down the line. Church member, but not a good one. Could that be it? Could the most normal be the most perfect? Had he led the best of all possible lives? Was that it? Had God, in His infinite wisdom and mercy, spared his life, saved him, singled him out because he was most nearly a saint, most nearly Christ-like, most nearly.... Lies—His mind snapped back to reality. He half smiled. Saint? Christ? The Second Coming? He was no saint. Charles sighed. What about—? Chance. That was it! The laws of probability, the bell-shaped curve, normal distribution, rectilinear regression. More people per square foot in New York than elsewhere. The first person who died was from New York, so the last person who gave way to the disease should come from here too. Spin the wheel; throw the dice; toss the coin. So simple to explain by the laws of chance. No need for any underlying assumptions about good and evil, no need for teleological arguments concerning cause and effect. Simply explain it by chance. Somebody had to be the last to go and that was— "No," Charles said, standing up in the quiet of the spring evening. "No, chance won't do it. No man can reckon with chance. The mind rejects such things. There must be something beyond mere accident. There must be!" He sighed slowly. "So now I'm a hermit, whether or not I like it," he said in derision to the gravel path as he walked along it. "A hermit in the midst of a city of millions of—No, I forgot. There aren't any more people, are there?" It was hard to realize, even now. "A hermit, alone—and I haven't even got a cave...." Charles stopped walking suddenly. No cave, he thought. No place to sleep out the long one, no place to rest while time came to change things around and make them for the better. No place to hide. And suddenly it was the most important thing in life to him to find his "cave." It took him almost an hour to find the proper tools, and better than two hours more of hard, nighttime work to get the hole dug to his satisfaction. It took almost three hours to find the right sort of casket, durable but not too heavy for one man to handle. He carted it out to a grassy plot close to the center of the park where the grave was. He let the coffin down slowly into the depression, then piled up loose dirt on the sloping sides of the hole so that the rain would wash it down over him. "I can't very well bury myself," he said. "I guess it will rain after I'm gone." He looked carefully down at the metallic container. Wait now. There was something wrong, something missing. It was—oh, yes, he caught it. It was the stone. There wasn't any stone to go at the head of the grave. "I'll have to fix that." A sheet of metal, bent double, served for the monument proper. A nearby tool shed yielded up a can of paint and a brush. By the glow of one of the streetlights Charles worked out the inscription. "It ought to be something impressive," he thought out loud. "Something fitting the occasion." What did one say on these situations? There was so little chance to practice up for things like this. But it ought to be good, it ought to be proper. "'In this now hallowed corner of the planet Earth—' No. That sounds too ... too...." Make it simple, he thought. And he finally wrote: HERE LIES THE BODY OF THE LAST MAN ON EARTH Yes. That was it. Simple. Let whoever came afterwards figure out the rest. Let them decide. He smiled and finished the painting. Charles was hungry. He got up and started for one of the restaurants near the park. Later on, when there was more time, he'd find a piece of granite and move it to the plot. He could spend his free time carving on it, copying the inscription. He would make it into a real shrine; maybe he would practice up a bit and try to carve a statue to go with the stone. Somehow, though, since things were ready and it didn't make too much difference, it seemed to Charles that he'd probably have a long time to wait. "Maybe it's just a disease, and I'm immune. I was immune to smallpox. The vaccination never took. That's probably it." He smiled. Strange, but now he wanted very much to go on living, alone or not. There were things he could do, ways to keep occupied. He wouldn't mind it so much. But he wanted more and more desperately with each passing second to retain his foothold on the tenuous path of physical existence. The tantalizing thought of "why" puzzled its way back into his mind. But it seemed less pressing now that he had almost come to the conclusion that he would live for a long time. Later, in a few days perhaps, he would think about it. In a little while he'd have plenty of opportunity for hunting down the answer. This seemed good to him, for now he thought he almost had the answer, if there were an answer. He thought he had seen the solution peering out at him from the recesses of his mind, and he didn't like the expression on its face. Better to forget. Charles reached the broad boulevard. There was a large cafe just across from him, its front window caved in by a large truck. He stumbled and almost fell as he stepped from the curb. "Look at me, nervous as a cat." He was trembling noticeably as he started across the street. "I—" He started to say something, to think something. But some hidden part of his mind clamped down, obscuring the thought, rejecting the concept. The tremor turned to a shake before he reached the far curb, and the first burst of wild pain came as he laid his shoulder against the door to the restaurant. This was the way the plague began, but—His mind quickly repressed the idea. It couldn't be the plague. He was immune! Another burst of pulsating, shattering pain crashed through his body, tearing down the defenses of his mind, putting an end of his thoughts of immunity. Colors flared before his eyes, a persistent, irresistible susurrus flooded his ears. He wanted to protest, but there was no one to listen to him. He appealed to every divinity he knew, all the time knowing it would be useless. His body, out of his voluntary control, tried to run off in all directions at once. Charles struggled to end his body's disorganized responses, to channelize all his energy into one direction. His mind came back into action. He set up his goal; everything else seemed irrelevant: he had to get back to the park, to his hermit's cave, to his long, narrow home. He couldn't die until then. Ten minutes. He was allotted ten minutes before the end. It could have been ten years or ten seconds, for now objective time meant nothing to him. It was not a matter of measuring seconds and minutes. It was a matter of forgetting time and measuring space. He concentrated on the grave; he forced his body to become an unwilling machine. While he could, he walked, forcing himself on. When his legs gave way, he crawled. When his knees buckled, he rolled. When his stomach protested, he vomited. It made no difference. Charles refused to think. Machines, especially half-broken machines, do not think; they only work. Sweating, straining, bleeding, retching, he pushed himself towards his goal, trying to add one final touch of grace and custom to the rude irrationalness of it all. His eyes gave out a few feet from the pit. He felt his way towards it. Convulsions shook his body like a cat shakes a captive mouse. He humped his body forward between the seizures, hands outstretched, searching for the grave. And then he was upon it. One arm reached out for grass, and clutched bare space instead. He was home. He gathered energy from his final reservoirs of strength for one final movement that would throw him headlong into the shallow grave. He tensed his muscles, pulled his limbs up under him and started to roll into the hole. Instantly the thought struck him with paralyzing devastation. The answer to it all poked its face out from the recesses of his mind and sapped the last bit of his energy, corroding his nerves and dying muscles. Now he knew, and the knowing was the end of it. He collapsed at the edge of the pit. Only one arm hung loosely down into it, swinging senseless in the air, pointing accusingly at the empty coffin. The world will end, not with a bang, nor with a whimper, but with the last man's anguished cry at the unreasonableness of it all. Charles screamed. The large, invisible, ovular being that hung suspended over the Empire State Building rested from its exertion. Soon it was approached by another of its kind. "It is finished?" asked the second. "Yes. Just now. I am resting." "I can feel the emptiness of it." "It was very good. Where were you?" "On the next planet out. No beauty to it at all; no system. How was yours?" "Beautiful," said the first. "It went according to the strictest semantic relationship following the purest mathematical principles. They made it easy for me." "Good." "Well, where to now?" "There's another system about four thoughts away. We're due there soon." "All right. Let's go." "What's that you have there?" "Oh, this?" replied the first. "It's a higher neural order compendium the Things here made up. It's what I used." "You can't take it with you, you know. They don't allow souvenirs." "I know." "Well?" "All right, all right. You're so good, see if you can compute the scatter probability." The first being moved imperceptably and the heavy plastoid binding of the book disappeared. The thousands of pages dropped softly, caught at the wind like hungry sails, separated, and pulled by the fingers of gravity, went their disparate ways. Here a page scuttled into a broken window of the Chrysler Building (read the names: Aabat, Aabbs, Aabbt). Here a page landed upright on the head of one of the library lions and sloughed softly to the ground (read the names: Looman, Loomana, Loomanabsky). Here another page crept in between the cracks of a pier on the riverfront, dropping gently to the caressing eddies of the water (read the names: Smith, Smitha, Smitj). And here two pages danced down into Central Park, pirouetted, promenaded, and finally came to rest against a propped-up piece of metal (read the names: Whit, Whita, Whitacomb). It was not until the dusty morning sun stirred up the breezes that they fluttered down into the shallow hole beneath, unnoticed. The writing on the metal, until then partially obscured by the papers, became legible: HERE LIES THE BODY OF THE LAST MAN ON EARTH— CHARLES J. ZZYZST GO TO HELL!
|
D. He was the last person because of his last name
|
Considering the data in the balance sheet, what is Block's (formerly known as Square) FY2016 working capital ratio? Define working capital ratio as total current assets divided by total current liabilities. Round your answer to two decimal places.
|
Evidence 0:
SQUARE,INC.
CONSOLIDATEDBALANCESHEETS
(In thousands, except share and per share data)
December31,
2016
2015
Assets
Currentassets:
Cashandcashequivalents
$
452,030 $
461,329
Short-terminvestments
59,901
Restrictedcash
22,131
13,537
Settlementsreceivable
321,102
142,727
Customerfundsheld
43,574
9,446
Loansheldforsale
42,144
604
Merchantcashadvancereceivable,net
4,212
36,473
Othercurrentassets
56,331
41,447
Totalcurrentassets
1,001,425
705,563
Propertyandequipment,net
88,328
87,222
Goodwill
57,173
56,699
Acquiredintangibleassets,net
19,292
26,776
Long-terminvestments
27,366
Restrictedcash
14,584
14,686
Otherassets
3,194
3,826
Totalassets
$
1,211,362 $
894,772
LiabilitiesandStockholdersEquity
Currentliabilities:
Accountspayable
$
12,602 $
18,869
Customerspayable
388,058
215,365
Customerfundsobligation
43,574
9,446
Accruedtransactionlosses
20,064
17,176
Accruedexpenses
39,543
44,401
Othercurrentliabilities
73,623
28,945
Totalcurrentliabilities
577,464
334,202
Debt(Note11)
Otherliabilities
57,745
52,522
Totalliabilities
635,209
386,724
Commitmentsandcontingencies(Note16)
Stockholdersequity:
Preferredstock,$0.0000001parvalue:100,000,000sharesauthorizedatDecember31,2016andDecember31,2015.None
issuedandoutstandingatDecember31,2016andDecember31,2015.
ClassAcommonstock,$0.0000001parvalue:1,000,000,000sharesauthorizedatDecember31,2016andDecember31,2015;
198,746,620and31,717,133issuedandoutstandingatDecember31,2016andDecember31,2015,respectively.
ClassBcommonstock,$0.0000001parvalue:500,000,000sharesauthorizedatDecember31,2016andDecember31,2015;
165,800,756and303,232,312issuedandoutstandingatDecember31,2016andDecember31,2015,respectively.
Additionalpaid-incapital
1,357,381
1,116,882
Accumulatedothercomprehensiveloss
(1,989)
(1,185)
Accumulateddeficit
(779,239)
(607,649)
Totalstockholdersequity
576,153
508,048
Totalliabilitiesandstockholdersequity
$
1,211,362 $
894,772
Seeaccompanyingnotestoconsolidatedfinancialstatements.
68
|
1.73
|
How long were Parker, Queazy and Starre floating around in space while unconcious?
A. Three days
B. Three days
C. One week
D. Three weeks
|
COSMIC YO-YO By ROSS ROCKLYNNE "Want an asteroid in your backyard? We supply cheap. Trouble also handled without charge." Interplanetary Hauling Company. (ADVT.) [Transcriber's Note: This etext was produced from Planet Stories Summer 1945. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Bob Parker, looking through the photo-amplifiers at the wedge-shaped asteroid, was plainly flabbergasted. Not in his wildest imaginings had he thought they would actually find what they were looking for. "Cut the drive!" he yelled at Queazy. "I've got it, right on the nose. Queazy, my boy, can you imagine it? We're in the dough. Not only that, we're rich! Come here!" Queazy discharged their tremendous inertia into the motive-tubes in such a manner that the big, powerful ship was moving at the same rate as the asteroid below—47.05 miles per second. He came slogging back excitedly, put his eyes to the eyepiece. He gasped, and his big body shook with joyful ejaculations. "She checks down to the last dimension," Bob chortled, working with slide-rule and logarithm tables. "Now all we have to do is find out if she's made of tungsten, iron, quartz crystals, and cinnabar! But there couldn't be two asteroids of that shape anywhere else in the Belt, so this has to be it!" He jerked a badly crumpled ethergram from his pocket, smoothed it out, and thumbed his nose at the signature. "Whee! Mr. Andrew S. Burnside, you owe us five hundred and fifty thousand dollars!" Queazy straightened. A slow, likeable smile wreathed his tanned face. "Better take it easy," he advised, "until I land the ship and we use the atomic whirl spectroscope to determine the composition of the asteroid." "Have it your way," Bob Parker sang, happily. He threw the ethergram to the winds and it fell gently to the deck-plates. While Queazy—so called because his full name was Quentin Zuyler—dropped the ship straight down to the smooth surface of the asteroid, and clamped it tight with magnetic grapples, Bob flung open the lazarette, brought out two space-suits. Moments later, they were outside the ship, with star-powdered infinity spread to all sides. In the ship, the ethergram from Andrew S. Burnside, of Philadelphia, one of the richest men in the world, still lay on the deck-plates. It was addressed to: Mr. Robert Parker, President Interplanetary Hauling & Moving Co., 777 Main Street, Satterfield City, Fontanaland, Mars. The ethergram read: Received your advertising literature a week ago. Would like to state that yes I would like an asteroid in my back yard. Must meet following specifications: 506 feet length, long enough for wedding procession; 98 feet at base, tapering to 10 feet at apex; 9-12 feet thick; topside smooth-plane, underside rough-plane; composed of iron ore, tungsten, quartz crystals, and cinnabar. Must be in my back yard before 11:30 A.M. my time, for important wedding June 2, else order is void. Will pay $5.00 per ton. Bob Parker had received that ethergram three weeks ago. And if The Interplanetary Hauling & Moving Co., hadn't been about to go on the rocks (chiefly due to the activities of Saylor & Saylor, a rival firm) neither Bob nor Queazy would have thought of sending an answering ethergram to Burnside stating that they would fill the order. It was, plainly, a hair-brained request. And yet, if by some chance there was such a rigidly specified asteroid, their financial worries would be over. That they had actually discovered the asteroid, using their mass-detectors in a weight-elimination process, seemed like an incredible stroke of luck. For there are literally millions of asteroids in the asteroid belt, and they had been out in space only three weeks. The "asteroid in your back yard" idea had been Bob Parker's originally. Now it was a fad that was sweeping Earth, and Burnside wasn't the first rich man who had decided to hold a wedding on top of an asteroid. Unfortunately, other interplanetary moving companies had cashed in on that brainstorm, chiefly the firm of the Saylor brothers—which persons Bob Parker intended to punch in the nose some day. And would have before this if he hadn't been lanky and tall while they were giants. Now that he and Queazy had found the asteroid, they were desperate to get it to its destination, for fear that the Saylor brothers might get wind of what was going on, and try to beat them out of their profits. Which was not so far-fetched, because the firm of Saylor & Saylor made no pretense of being scrupulous. Now they scuffed along the smooth-plane topside of the asteroid, the magnets in their shoes keeping them from stepping off into space. They came to the broad base of the asteroid-wedge, walked over the edge and "down" the twelve-foot thickness. Here they squatted, and Bob Parker happily clamped the atomic-whirl spectroscope to the rough surface. By the naked eye, they could see iron ore, quartz crystals, cinnabar, but he had the spectroscope and there was no reason why he shouldn't use it. He satisfied himself as to the exterior of the asteroid, and then sent the twin beams deep into its heart. The beams crossed, tore atoms from molecules, revolved them like an infinitely fine powder. The radiations from the sundered molecules traveled back up the beams to the atomic-whirl spectroscope. Bob watched a pointer which moved slowly up and up—past tungsten, past iridium, past gold— Bob Parker said, in astonishment, "Hell! There's something screwy about this business. Look at that point—" Neither he nor Queazy had the opportunity to observe the pointer any further. A cold, completely disagreeable feminine voice said, "May I ask what you interlopers are doing on my asteroid?" Bob started so badly that the spectroscope's settings were jarred and the lights in its interior died. Bob twisted his head around as far as he could inside the "aquarium"—the glass helmet, and found himself looking at a space-suited girl who was standing on the edge of the asteroid "below." "Ma'am," said Bob, blinking, "did you say something?" Queazy made a gulping sound and slowly straightened. He automatically reached up as if he would take off his hat and twist it in his hands. "I said," remarked the girl, "that you should scram off of my asteroid. And quit poking around at it with that spectroscope. I've already taken a reading. Cinnabar, iron ore, quartz crystals, tungsten. Goodbye." Bob's nose twitched as he adjusted his glasses, which he wore even inside his suit. He couldn't think of anything pertinent to say. He knew that he was slowly working up a blush. Mildly speaking, the girl was beautiful, and though only her carefully made-up face was visible—cool blue eyes, masterfully coiffed, upswept, glinting brown hair, wilful lips and chin—Bob suspected the rest of her compared nicely. Her expression darkened as she saw the completely instinctive way he was looking at her and her radioed-voice rapped out, "Now you two boys go and play somewhere else! Else I'll let the Interplanetary Commission know you've infringed the law. G'bye!" She turned and disappeared. Bob awoke from his trance, shouted desperately, "Hey! Wait! You! " He and Queazy caught up with her on the side of the asteroid they hadn't yet examined. It was a rough plane, completing the rigid qualifications Burnside had set down. "Wait a minute," Bob Parker begged nervously. "I want to make some conversation, lady. I'm sure you don't understand the conditions—" The girl turned and drew a gun from a holster. It was a spasticizer, and it was three times as big as her gloved hand. "I understand conditions better than you do," she said. "You want to move this asteroid from its orbit and haul it back to Earth. Unfortunately, this is my home, by common law. Come back in a month. I don't expect to be here then." "A month!" Parker burst the word out. He started to sweat, then his face became grim. He took two slow steps toward the girl. She blinked and lost her composure and unconsciously backed up two steps. About twenty steps away was her small dumbbell-shaped ship, so shiny and unscarred that it reflected starlight in highlights from its curved surface. A rich girl's ship, Bob Parker thought angrily. A month would be too late! He said grimly, "Don't worry. I don't intend to pull any rough stuff. I just want you to listen to reason. You've taken a whim to stay on an asteroid that doesn't mean anything to you one way or another. But to us—to me and Queazy here—it means our business. We got an order for this asteroid. Some screwball millionaire wants it for a backyard wedding see? We get five hundred and fifty thousand dollars for it! If we don't take this asteroid to Earth before June 2, we go back to Satterfield City and work the rest of our lives in the glass factories. Don't we, Queazy?" Queazy said simply, "That's right, miss. We're in a spot. I assure you we didn't expect to find someone living here." The girl holstered her spasticizer, but her completely inhospitable expression did not change. She put her hands on the bulging hips of her space-suit. "Okay," she said. "Now I understand the conditions. Now we both understand each other. G'bye again. I'm staying here and—" she smiled sweetly "—it may interest you to know that if I let you have the asteroid you'll save your business, but I'll meet a fate worse than death! So that's that." Bob recognized finality when he saw it. "Come on, Queazy," he said fuming. "Let this brat have her way. But if I ever run across her without a space-suit on I'm going to give her the licking of her life, right where it'll do the most good!" He turned angrily, but Queazy grabbed his arm, his mouth falling open. He pointed off into space, beyond the girl. "What's that?" he whispered. "What's wha— Oh! " Bob Parker's stomach caved in. A few hundred feet away, floating gently toward the asteroid, came another ship—a ship a trifle bigger than their own. The girl turned, too. They heard her gasp. In another second, Bob was standing next to her. He turned the audio-switch to his headset off, and spoke to the girl by putting his helmet against hers. "Listen to me, miss," he snapped earnestly, when she tried to draw away. "Don't talk by radio. That ship belongs to the Saylor brothers! Oh, Lord, that this should happen! Somewhere along the line, we've been double-crossed. Those boys are after this asteroid too, and they won't hesitate to pull any rough stuff. We're in this together, understand? We got to back each other up." The girl nodded dumbly. Suddenly she seemed to be frightened. "It's—it's very important that this—this asteroid stay right where it is," she said huskily. "What—what will they do?" Bob Parker didn't answer. The big ship had landed, and little blue sparks crackled between the hull and the asteroid as the magnetic clamps took hold. A few seconds later, the airlocks swung down, and five men let themselves down to the asteroid's surface and stood surveying the three who faced them. The two men in the lead stood with their hands on their hips; their darkish, twin faces were grinning broadly. "A pleasure," drawled Wally Saylor, looking at the girl. "What do you think of this situation Billy?" "It's obvious," drawled Billy Saylor, rocking back and forth on his heels, "that Bob Parker and company have double-crossed us. We'll have to take steps." The three men behind the Saylor twins broke into rough, chuckling laughter. Bob Parker's gorge rose. "Scram," he said coldly. "We've got an ethergram direct from Andrew S. Burnside ordering this asteroid." "So have we," Wally Saylor smiled—and his smile remained fixed, dangerous. He started moving forward, and the three men in back came abreast, forming a semi-circle which slowly closed in. Bob Parker gave back a step, as he saw their intentions. "We got here first," he snapped harshly. "Try any funny stuff and we'll report you to the Interplanetary Commission!" It was Bob Parker's misfortune that he didn't carry a weapon. Each of these men carried one or more, plainly visible. But he was thinking of the girl's spasticizer—a paralyzing weapon. He took a hair-brained chance, jerked the spasticizer from the girl's holster and yelled at Queazy. Queazy got the idea, urged his immense body into motion. He hurled straight at Billy Saylor, lifted him straight off the asteroid and threw him away, into space. He yelled with triumph. At the same time, the spasticizer Bob held was shot cleanly out of his hand by Wally Saylor. Bob roared, started toward Wally Saylor, knocked the smoking gun from his hand with a sweeping arm. Then something crushing seemed to hit him in the stomach, grabbing at his solar plexus. He doubled up, gurgling with agony. He fell over on his back, and his boots were wrenched loose from their magnetic grip. Vaguely, before the flickering points of light in his brain subsided to complete darkness, he heard the girl's scream of rage—then a scream of pain. What had happened to Queazy he didn't know. He felt so horribly sick, he didn't care. Then—lights out. Bob Parker came to, the emptiness of remote starlight in his face. He opened his eyes. He was slowly revolving on an axis. Sometimes the Sun swept across his line of vision. A cold hammering began at the base of his skull, a sensation similar to that of being buried alive. There was no asteroid, no girl, no Queazy. He was alone in the vastness of space. Alone in a space-suit. "Queazy!" he whispered. "Queazy! I'm running out of air!" There was no answer from Queazy. With sick eyes, Bob studied the oxygen indicator. There was only five pounds pressure. Five pounds! That meant he had been floating around out here—how long? Days at least—maybe weeks! It was evident that somebody had given him a dose of spastic rays, enough to screw up every muscle in his body to the snapping point, putting him in such a condition of suspended animation that his oxygen needs were small. He closed his eyes, trying to fight against panic. He was glad he couldn't see any part of his body. He was probably scrawny. And he was hungry! "I'll starve," he thought. "Or suffocate to death first!" He couldn't keep himself from taking in great gulps of air. Minutes, then hours passed. He was breathing abnormally, and there wasn't enough air in the first place. He pleaded continually for Queazy, hoping that somehow Queazy could help, when probably Queazy was in the same condition. He ripped out wild curses directed at the Saylor brothers. Murderers, both of them! Up until this time, he had merely thought of them as business rivals. If he ever got out of this— He groaned. He never would get out of it! After another hour, he was gasping weakly, and yellow spots danced in his eyes. He called Queazy's name once more, knowing that was the last time he would have strength to call it. And this time the headset spoke back! Bob Parker made a gurgling sound. A voice came again, washed with static, far away, burbling, but excited. Bob made a rattling sound in his throat. Then his eyes started to close, but he imagined that he saw a ship, shiny and small, driving toward him, growing in size against the backdrop of the Milky Way. He relapsed, a terrific buzzing in his ears. He did not lose consciousness. He heard voices, Queazy's and the girl's, whoever she was. Somebody grabbed hold of his foot. His "aquarium" was unbuckled and good air washed over his streaming face. The sudden rush of oxygen to his brain dizzied him. Then he was lying on a bunk, and gradually the world beyond his sick body focussed in his clearing eyes and he knew he was alive—and going to stay that way, for awhile anyway. "Thanks, Queazy," he said huskily. Queazy was bending over him, his anxiety clearing away from his suddenly brightening face. "Don't thank me," he whispered. "We'd have both been goners if it hadn't been for her. The Saylor brothers left her paralyzed like us, and when she woke up she was on a slow orbit around her ship. She unstrapped her holster and threw it away from her and it gave her enough reaction to reach the ship. She got inside and used the direction-finder on the telaudio and located me first. The Saylors scattered us far and wide." Queazy's broad, normally good-humored face twisted blackly. "The so and so's didn't care if we lived or died." Bob saw the girl now, standing a little behind Queazy, looking down at him curiously, but unhappily. Her space-suit was off. She was wearing lightly striped blue slacks and blue silk blouse and she had a paper flower in her hair. Something in Bob's stomach caved in as his eyes widened on her. The girl said glumly, "I guess you men won't much care for me when you find out who I am and what I've done. I'm Starre Lowenthal—Andrew S. Burnside's granddaughter!" Bob came slowly to his feet, and matched Queazy's slowly growing anger. "Say that again?" he snapped. "This is some kind of dirty trick you and your grandfather cooked up?" "No!" she exclaimed. "No. My grandfather didn't even know there was an asteroid like this. But I did, long before he ordered it from you—or from the Saylor brothers. You see—well, my granddad's about the stubbornest old hoot-owl in this universe! He's always had his way, and when people stand in his way, that's just a challenge to him. He's been badgering me for years to marry Mac, and so has Mac—" "Who's Mac?" Queazy demanded. "My fiancé, I guess," she said helplessly. "He's one of my granddad's protégés. Granddad's always financing some likely young man and giving him a start in life. Mac has become pretty famous for his Mercurian water-colors—he's an artist. Well, I couldn't hold out any longer. If you knew my grandfather, you'd know how absolutely impossible it is to go against him when he's got his mind set! I was just a mass of nerves. So I decided to trick him and I came out to the asteroid belt and picked out an asteroid that was shaped so a wedding could take place on it. I took the measurements and the composition, then I told my grandfather I'd marry Mac if the wedding was in the back yard on top of an asteroid with those measurements and made of iron ore, tungsten, and so forth. He agreed so fast he scared me, and just to make sure that if somebody did find the asteroid in time they wouldn't be able to get it back to Earth, I came out here and decided to live here. Asteroids up to a certain size belong to whoever happens to be on them, by common law.... So I had everything figured out—except," she added bitterly, "the Saylor brothers! I guess Granddad wanted to make sure the asteroid was delivered, so he gave the order to several companies." Bob swore under his breath. He went reeling across to a port, and was gratified to see his and Queazy's big interplanetary hauler floating only a few hundred feet away. He swung around, looked at Queazy. "How long were we floating around out there?" "Three weeks, according to the chronometer. The Saylor boys gave us a stiff shot." " Ouch! " Bob groaned. Then he looked at Starre Lowenthal with determination. "Miss, pardon me if I say that this deal you and your granddad cooked up is plain screwy! With us on the butt end. But I'm going to put this to you plainly. We can catch up with the Saylor brothers even if they are three weeks ahead of us. The Saylor ship and ours both travel on the HH drive—inertia-less. But the asteroid has plenty of inertia, and so they'll have to haul it down to Earth by a long, spiraling orbit. We can go direct and probably catch up with them a few hundred thousand miles this side of Earth. And we can have a fling at getting the asteroid back!" Her eyes sparkled. "You mean—" she cried. Then her attractive face fell. "Oh," she said. " Oh! And when you get it back, you'll land it." "That's right," Bob said grimly. "We're in business. For us, it's a matter of survival. If the by-product of delivering the asteroid is your marriage—sorry! But until we do get the asteroid back, we three can work as a team if you're willing. We'll fight the other problem out later. Okay?" She smiled tremulously. "Okay, I guess." Queazy looked from one to another of them. He waved his hand scornfully at Bob. "You're plain nuts," he complained. "How do you propose to go about convincing the Saylor brothers they ought to let us have the asteroid back? Remember, commercial ships aren't allowed to carry long-range weapons. And we couldn't ram the Saylor brothers' ship—not without damaging our own ship just as much. Go ahead and answer that." Bob looked at Queazy dismally. "The old balance-wheel," he groaned at Starre. "He's always pulling me up short when I go off half-cocked. All I know is, that maybe we'll get a good idea as we go along. In the meantime, Starre—ahem—none of us has eaten in three weeks...?" Starre got the idea. She smiled dazzlingly and vanished toward the galley. Bob Parker was in love with Starre Lowenthal. He knew that after five days out, as the ship hurled itself at breakneck speed toward Earth; probably that distracting emotion was the real reason he couldn't attach any significance to Starre's dumbbell-shaped ship, which trailed astern, attached by a long cable. Starre apparently knew he was in love with her, too, for on the fifth day Bob was teaching her the mechanics of operating the hauler, and she gently lifted his hand from a finger-switch. "Even I know that isn't the control to the Holloway vacuum-feeder, Bob. That switch is for the—ah—the anathern tube, you told me. Right?" "Right," he said unsteadily. "Anyway, Starre, as I was saying, this ship operates according to the reverse Fitzgerald Contraction Formula. All moving bodies contract in the line of motion. What Holloway and Hammond did was to reverse that universal law. They caused the contraction first—motion had to follow! The gravitonic field affects every atom in the ship with the same speed at the same time. We could go from zero speed to our top speed of two thousand miles a second just like that!" He snapped his fingers. "No acceleration effects. This type of ship, necessary in our business, can stop flat, back up, ease up, move in any direction, and the passengers wouldn't have any feeling of motion at—Oh, hell!" Bob groaned, the serious glory of her eyes making him shake. He took her hand. "Starre," he said desperately, "I've got to tell you something—" She jerked her hand away. "No," she exclaimed in an almost frightened voice. "You can't tell me. There's—there's Mac," she finished, faltering. "The asteroid—" "You have to marry him?" Her eyes filled with tears. "I have to live up to the bargain." "And ruin your whole life," he ground out. Suddenly, he turned back to the control board, quartered the vision plate. He pointed savagely to the lower left quarter, which gave a rearward view of the dumbbell ship trailing astern. "There's your ship, Starre." He jabbed his finger at it. "I've got a feeling—and I can't put the thought into concrete words—that somehow the whole solution of the problem of grabbing the asteroid back lies there. But how? How? " Starre's blue eyes followed the long cable back to where it was attached around her ship's narrow midsection. She shook her head helplessly. "It just looks like a big yo-yo to me." "A yo-yo?" "Yes, a yo-yo. That's all." She was belligerent. "A yo-yo !" Bob Parker yelled the word and almost hit the ceiling, he got out of the chair so fast. "Can you imagine it! A yo-yo!" He disappeared from the room. "Queazy!" he shouted. " Queazy, I've got it! " It was Queazy who got into his space-suit and did the welding job, fastening two huge supra-steel "eyes" onto the dumbbell-shaped ship's narrow midsection. Into these eyes cables which trailed back to two winches in the big ship's nose were inserted, welded fast, and reinforced. The nose of the hauler was blunt, perfectly fitted for the job. Bob Parker practiced and experimented for three hours with this yo-yo of cosmic dimensions, while Starre and Queazy stood over him bursting into strange, delighted squeals of laughter whenever the yo-yo reached the end of its double cable and started rolling back up to the ship. Queazy snapped his fingers. "It'll work!" His gray eyes showed satisfaction. "Now, if only the Saylor brothers are where we calculated!" They weren't where Bob and Queazy had calculated, as they had discovered the next day. They had expected to pick up the asteroid on their mass-detectors a few hundred thousand miles outside of the Moon's orbit. But now they saw the giant ship attached like a leech to the still bigger asteroid—inside the Moon's orbit! A mere two hundred thousand miles from Earth! "We have to work fast," Bob stammered, sweating. He got within naked-eye distance of the Saylor brothers' ship. Below, Earth was spread out, a huge crescent shape, part of the Eastern hemisphere vaguely visible through impeding clouds and atmosphere. The enemy ship was two miles distant, a black shadow occulting part of the brilliant sky. It was moving along a down-spiraling path toward Earth. Queazy's big hand gripped his shoulder. "Go to it, Bob!" Bob nodded grimly. He backed the hauler up about thirty miles, then sent it forward again, directly toward the Saylor brothers' ship at ten miles per second. And resting on the blunt nose of the ship was the "yo-yo." There was little doubt the Saylors' saw their approach. But, scornfully, they made no attempt to evade. There was no possible harm the oncoming ship could wreak. Or at least that was what they thought, for Bob brought the hauler's speed down to zero—and Starre Lowenthal's little ship, possessing its own inertia, kept on moving! It spun away from the hauler's blunt nose, paying out two rigid lengths of cable behind it as it unwound, hurled itself forward like a fantastic spinning cannon ball. "It's going to hit!" The excited cry came from Starre. But Bob swore. The dumbbell ship reached the end of its cables, falling a bare twenty feet short of completing its mission. It didn't stop spinning, but came winding back up the cable, at the same terrific speed with which it had left. Bob sweated, having only fractions of seconds in which to maneuver for the "yo-yo" could strike a fatal blow at the hauler too. It was ticklish work completely to nullify the "yo-yo's" speed. Bob used exactly the same method of catching the "yo-yo" on the blunt nose of the ship as a baseball player uses to catch a hard-driven ball in his glove—namely, by matching the ball's speed and direction almost exactly at the moment of impact. And now Bob's hours of practice paid dividends, for the "yo-yo" came to rest snugly, ready to be released again. All this had happened in such a short space of time that the Saylor brothers must have had only a bare realization of what was going on. But by the time the "yo-yo" was flung at them again, this time with better calculations, they managed to put the firmly held asteroid between them and the deadly missile. But it was clumsy evasion, for the asteroid was several times as massive as the ship which was towing it, and its inertia was great. And as soon as the little ship came spinning back to rest, Bob flung the hauler to a new vantage point and again the "yo-yo" snapped out. And this time—collision! Bob yelled as he saw the stern section of the Saylor brothers' ship crumple like tissue paper crushed between the hand. The dumbbell-shaped ship, smaller, and therefore stauncher due to the principle of the arch, wound up again, wobbling a little. It had received a mere dent in its starboard half. Starre was chortling with glee. Queazy whispered, "Attaboy, Bob! This time we'll knock 'em out of the sky!" The "yo-yo" came to rest and at the same moment a gong rang excitedly. Bob knew what that meant. The Saylor brothers were trying to establish communication. Queazy was across the room in two running strides. He threw in the telaudio and almost immediately, Wally Saylor's big body built up in the plate. Wally Saylor's face was quivering with wrath. "What do you damned fools think you're trying to do?" he roared. "You've crushed in our stern section. You've sliced away half of our stern jets. Air is rushing out! You'll kill us!" "Now," Bob drawled, "you're getting the idea." "I'll inform the Interplanetary Commission!" screamed Saylor. " If you're alive," Bob snarled wrathfully. "And you won't be unless you release the asteroid." "I'll see you in Hades first!" "Hades," remarked Bob coldly, "here you come!" He snapped the hauler into its mile-a-second speed again, stopped it at zero. And the "yo-yo" went on its lone, destructive sortie. For a fraction of a second Wally Saylor exhibited the countenance of a doomed man. In the telaudio plate, he whirled, and diminished in size with a strangled yell. The "yo-yo" struck again, but Bob Parker maneuvered its speed in such a manner that it struck in the same place as before, but not as heavily, then rebounded and came spinning back with perfect, sparkling precision. And even before it snugged itself into its berth, it was apparent that the Saylor brothers had given up. Like a wounded terrier, their ship shook itself free of the asteroid, hung in black space for a second, then vanished with a flaming puff of released gravitons from its still-intact jets. The battle was won!
|
D. Three weeks
|
What was the one thing William admitted to doing?
A. stealing while at school
B. stealing from the church
C. doing drugs
D. lying to people
|
Charity Case By JIM HARMON Illustrated by DICK FRANCIS [Transcriber's Note: This etext was produced from Galaxy Science Fiction December 1959. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Certainly I see things that aren't there and don't say what my voice says—but how can I prove that I don't have my health? When he began his talk with "You got your health, don't you?" it touched those spots inside me. That was when I did it. Why couldn't what he said have been "The best things in life are free, buddy" or "Every dog has his day, fellow" or "If at first you don't succeed, man"? No, he had to use that one line. You wouldn't blame me. Not if you believe me. The first thing I can remember, the start of all this, was when I was four or five somebody was soiling my bed for me. I absolutely was not doing it. I took long naps morning and evening so I could lie awake all night to see that it wouldn't happen. It couldn't happen. But in the morning the bed would sit there dispassionately soiled and convict me on circumstantial evidence. My punishment was as sure as the tide. Dad was a compact man, small eyes, small mouth, tight clothes. He was narrow but not mean. For punishment, he locked me in a windowless room and told me to sit still until he came back. It wasn't so bad a punishment, except that when Dad closed the door, the light turned off and I was left there in the dark. Being four or five, I didn't know any better, so I thought Dad made it dark to add to my punishment. But I learned he didn't know the light went out. It came back on when he unlocked the door. Every time I told him about the light as soon as I could talk again, but he said I was lying. One day, to prove me a liar, he opened and closed the door a few times from outside. The light winked off and on, off and on, always shining when Dad stuck his head inside. He tried using the door from the inside, and the light stayed on, no matter how hard he slammed the door. I stayed in the dark longer for lying about the light. Alone in the dark, I wouldn't have had it so bad if it wasn't for the things that came to me. They were real to me. They never touched me, but they had a little boy. He looked the way I did in the mirror. They did unpleasant things to him. Because they were real, I talked about them as if they were real, and I almost earned a bunk in the home for retarded children until I got smart enough to keep the beasts to myself. My mother hated me. I loved her, of course. I remember her smell mixed up with flowers and cookies and winter fires. I remember she hugged me on my ninth birthday. The trouble came from the notes written in my awkward hand that she found, calling her names I didn't understand. Sometimes there were drawings. I didn't write those notes or make those drawings. My mother and father must have been glad when I was sent away to reform school after my thirteenth birthday party, the one no one came to. The reform school was nicer. There were others there who'd had it about like me. We got along. I didn't watch their shifty eyes too much, or ask them what they shifted to see. They didn't talk about my screams at night. It was home. My trouble there was that I was always being framed for stealing. I didn't take any of those things they located in my bunk. Stealing wasn't in my line. If you believe any of this at all, you'll see why it couldn't be me who did the stealing. There was reason for me to steal, if I could have got away with it. The others got money from home to buy the things they needed—razor blades, candy, sticks of tea. I got a letter from Mom or Dad every now and then before they were killed, saying they had sent money or that it was enclosed, but somehow I never got a dime of it. When I was expelled from reform school, I left with just one idea in mind—to get all the money I could ever use for the things I needed and the things I wanted. It was two or three years later that I skulked into Brother Partridge's mission on Durbin Street. The preacher and half a dozen men were singing Onward Christian Soldiers in the meeting room. It was a drafty hall with varnished camp chairs. I shuffled in at the back with my suitcoat collar turned up around my stubbled jaw. I made my hand shaky as I ran it through my knotted hair. Partridge was supposed to think I was just a bum. As an inspiration, I hugged my chest to make him think I was some wino nursing a flask full of Sneaky Pete. All I had there was a piece of copper alloy tubing inside a slice of plastic hose for taking care of myself, rolling sailors and the like. Who had the price of a bottle? Partridge didn't seem to notice me, but I knew that was an act. I knew people were always watching every move I made. He braced his red-furred hands on the sides of his auctioneer's stand and leaned his splotched eagle beak toward us. "Brothers, this being Thanksgiving, I pray the good Lord that we all are truly thankful for all that we have received. Amen." Some skin-and-bones character I didn't know struggled out of his seat, amening. I could see he had a lot to be thankful for—somewhere he had received a fix. "Brothers," Partridge went on after enjoying the interruption with a beaming smile, "you shall all be entitled to a bowl of turkey soup prepared by Sister Partridge, a generous supply of sweet rolls and dinner rolls contributed by the Early Morning Bakery of this city, and all the coffee you can drink. Let us march out to The Stars and Stripes Forever , John Philip Sousa's grand old patriotic song." I had to laugh at all those bums clattering the chairs in front of me, scampering after water soup and stale bread. As soon as I got cleaned up, I was going to have dinner in a good restaurant, and I was going to order such expensive food and leave such a large tip for the waiter and send one to the chef that they were going to think I was rich, and some executive with some brokerage firm would see me and say to himself, "Hmm, executive material. Just the type we need. I beg your pardon, sir—" just like the razor-blade comic-strip ads in the old magazines that Frankie the Pig sells three for a quarter. I was marching. Man, was I ever marching, but the secret of it was I was only marking time the way we did in fire drills at the school. They passed me, every one of them, and marched out of the meeting room into the kitchen. Even Partridge made his way down from the auctioneer's stand like a vulture with a busted wing and darted through his private door. I was alone, marking time behind the closed half of double doors. One good breath and I raced past the open door and flattened myself to the wall. Crockery was ringing and men were slurping inside. No one had paid any attention to me. That was pretty odd. People usually watch my every move, but a man's luck has to change sometime, doesn't it? Following the wallboard, I went down the side of the room and behind the last row of chairs, closer, closer, and halfway up the room again to the entrance—the entrance and the little wooden box fastened to the wall beside it. The box was old and made out of some varnished wood. There was a slot in the top. There wasn't any sign anywhere around it, but you knew it wasn't a mailbox. My hand went flat on the top of the box. One finger at a time drew up and slipped into the slot. Index, fore, third, little. I put my thumb in my palm and shoved. My hand went in. There were coins inside. I scooped them up with two fingers and held them fast with the other two. Once I dropped a dime—not a penny, milled edge—and I started to reach for it. No, don't be greedy. I knew I would probably lose my hold on all the coins if I tried for that one. I had all the rest. It felt like about two dollars, or close to it. Then I found the bill. A neatly folded bill in the box. Somehow I knew all along it would be there. I tried to read the numbers on the bill with my fingertips, but I couldn't. It had to be a one. Who drops anything but a one into a Skid Row collection box? But still there were tourists, slummers. They might leave a fifty or even a hundred. A hundred! Yes, it felt new, crisp. It had to be a hundred. A single would be creased or worn. I pulled my hand out of the box. I tried to pull my hand out of the box. I knew what the trouble was, of course. I was in a monkey trap. The monkey reaches through the hole for the bait, and when he gets it in his hot little fist, he can't get his hand out. He's too greedy to let go, so he stays there, caught as securely as if he were caged. I was a man, not a monkey. I knew why I couldn't get my hand out. But I couldn't lose that money, especially that century bill. Calm, I ordered myself. Calm. The box was fastened to the vertical tongue-and-groove laths of the woodwork, not the wall. It was old lumber, stiffened by a hundred layers of paint since 1908. The paint was as thick and strong as the boards. The box was fastened fast. Six-inch spike nails, I guessed. Calmly, I flung my whole weight away from the wall. My wrist almost cracked, but there wasn't even a bend in the box. Carefully, I tried to jerk my fist straight up, to pry off the top of the box. It was as if the box had been carved out of one solid piece of timber. It wouldn't go up, down, left or right. But I kept trying. While keeping a lookout for Partridge and somebody stepping out of the kitchen for a pull on a bottle, I spotted the clock for the first time, a Western Union clock high up at the back of the hall. Just as I seen it for the first time, the electricity wound the spring motor inside like a chicken having its neck wrung. The next time I glanced at the clock, it said ten minutes had gone by. My hand still wasn't free and I hadn't budged the box. "This," Brother Partridge said, "is one of the most profound experiences of my life." My head hinged until it lined my eyes up with Brother Partridge. The pipe hung heavy in my pocket, but he was too far from me. "A vision of you at the box projected itself on the crest of my soup," the preacher explained in wonderment. I nodded. "Swimming right in there with the dead duck." "Cold turkey," he corrected. "Are you scoffing at a miracle?" "People are always watching me, Brother," I said. "So now they do it even when they aren't around. I should have known it would come to that." The pipe was suddenly a weight I wanted off me. I would try robbing a collection box, knowing positively that I would get caught, but I wasn't dumb enough to murder. Somebody, somewhere, would be a witness to it. I had never got away with anything in my life. I was too smart to even try anything but the little things. "I may be able to help you," Brother Partridge said, "if you have faith and a conscience." "I've got something better than a conscience," I told him. Brother Partridge regarded me solemnly. "There must be something special about you, for your apprehension to come through miraculous intervention. But I can't imagine what." "I always get apprehended somehow, Brother," I said. "I'm pretty special." "Your name?" "William Hagle." No sense lying. I had been booked and printed before. Partridge prodded me with his bony fingers as if making sure I was substantial. "Come. Let's sit down, if you can remove your fist from the money box." I opened up my fingers and let the coins ring inside the box and I drew out my hand. The bill stuck to the sweat on my fingers and slid out along with the digits. A one, I decided. I had got into trouble for a grubby single. It wasn't any century. I had been kidding myself. I unfolded the note. Sure enough, it wasn't a hundred-dollar bill, but it was a twenty, and that was almost the same thing to me. I creased it and put it back into the slot. As long as it stalled off the cops, I'd talk to Partridge. We took a couple of camp chairs and I told him the story of my life, or most of it. It was hard work on an empty stomach; I wished I'd had some of that turkey soup. Then again I was glad I hadn't. Something always happened to me when I thought back over my life. The same thing. The men filed out of the kitchen, wiping their chins, and I went right on talking. After some time Sister Partridge bustled in and snapped on the overhead lights and I kept talking. The brother still hadn't used the phone to call the cops. "Remarkable," Partridge finally said when I got so hoarse I had to take a break. "One is almost— almost —reminded of Job. William, you are being punished for some great sin. Of that, I'm sure." "Punished for a sin? But, Brother, I've always had it like this, as long as I can remember. What kind of a sin could I have committed when I was fresh out of my crib?" "William, all I can tell you is that time means nothing in Heaven. Do you deny the transmigration of souls?" "Well," I said, "I've had no personal experience—" "Of course you have, William! Say you don't remember. Say you don't want to remember. But don't say you have no personal experience!" "And you think I'm being punished for something I did in a previous life?" He looked at me in disbelief. "What else could it be?" "I don't know," I confessed. "I certainly haven't done anything that bad in this life." "William, if you atone for this sin, perhaps the horde of locusts will lift from you." It wasn't much of a chance, but I was unused to having any at all. I shook off the dizziness of it. "By the Lord Harry, Brother, I'm going to give it a try!" I cried. "I believe you," Partridge said, surprised at himself. He ambled over to the money box on the wall. He tapped the bottom lightly and a box with no top slid out of the slightly larger box. He reached in, fished out the bill and presented it to me. "Perhaps this will help in your atonement," he said. I crumpled it into my pocket fast. Not meaning to sound ungrateful, I'm pretty sure he hadn't noticed it was a twenty. And then the bill seemed to lie there, heavy, a lead weight. It would have been different if I had managed to get it out of the box myself. You know how it is. Money you haven't earned doesn't seem real to you. There was something I forgot to mention so far. During the year between when I got out of the reformatory and the one when I tried to steal Brother Partridge's money, I killed a man. It was all an accident, but killing somebody is reason enough to get punished. It didn't have to be a sin in some previous life, you see. I had gotten my first job in too long, stacking boxes at the freight door of Baysinger's. The drivers unloaded the stuff, but they just dumped it off the truck. An empty rear end was all they wanted. The freight boss told me to stack the boxes inside, neat and not too close together. I stacked boxes the first day. I stacked more the second. The third day I went outside with my baloney and crackers. It was warm enough even for November. Two of them, dressed like Harvard seniors, caps and striped duffer jackets, came up to the crate I was dining off. "Work inside, Jack?" the taller one asked. "Yeah," I said, chewing. "What do you do, Jack?" the fatter one asked. "Stack boxes." "Got a union card?" I shook my head. "Application?" "No," I said. "I'm just helping out during Christmas." "You're a scab, buddy," Long-legs said. "Don't you read the papers?" "I don't like comic strips," I said. They sighed. I think they hated to do it, but I was bucking the system. Fats hit me high. Long-legs hit me low. I blew cracker crumbs into their faces. After that, I just let them go. I know how to take a beating. That's one thing I knew. Then lying there, bleeding to myself, I heard them talking. I heard noises like make an example of him and do something permanent and I squirmed away across the rubbish like a polite mouse. I made it around a corner of brick and stood up, hurting my knee on a piece of brown-splotched pipe. There were noises on the other angle of the corner and so I tested if the pipe was loose and it was. I closed my eyes and brought the pipe up and then down. It felt as if I connected, but I was so numb, I wasn't sure until I unscrewed my eyes. There was a big man in a heavy wool overcoat and gray homburg spread on a damp centerfold from the News . There was a pick-up slip from the warehouse under the fingers of one hand, and somebody had beaten his brains out. The police figured it was part of some labor dispute, I guess, and they never got to me. I suppose I was to blame anyway. If I hadn't been alive, if I hadn't been there to get beaten up, it wouldn't have happened. I could see the point in making me suffer for it. There was a lot to be said for looking at it like that. But there was nothing to be said for telling Brother Partridge about the accident, or murder, or whatever had happened that day. Searching myself after I left Brother Partridge, I finally found a strip of gray adhesive tape on my side, out of the fuzzy area. Making the twenty the size of a thick postage stamp, I peeled back the tape and put the folded bill on the white skin and smoothed the tape back. There was only one place for me to go now. I headed for the public library. It was only about twenty blocks, but not having had anything to eat since the day before, it enervated me. The downstairs washroom was where I went first. There was nobody there but an old guy talking urgently to a kid with thick glasses, and somebody building a fix in one of the booths. I could see charred matches dropping down on the floor next to his tennis shoes, and even a few grains of white stuff. But he managed to hold still enough to keep from spilling more from the spoon. I washed my hands and face, smoothed my hair down, combing it with my fingers. Going over my suit with damp toweling got off a lot of the dirt. I put my collar on the outside of my jacket and creased the wings with my thumbnail so it would look more like a sports shirt. It didn't really. I still looked like a bum, but sort of a neat, non-objectionable bum. The librarian at the main desk looked sympathetically hostile, or hostilely sympathetic. "I'd like to get into the stacks, miss," I said, "and see some of the old newspapers." "Which newspapers?" the old girl asked stiffly. I thought back. I couldn't remember the exact date. "Ones for the first week in November last year." "We have the Times microfilmed. I would have to project them for you." "I didn't want to see the Times ," I said, fast. "Don't you have any newspapers on paper?" I didn't want her to see what I wanted to read up on. "We have the News , bound, for last year." I nodded. "That's the one I wanted to see." She sniffed and told me to follow her. I didn't rate a cart to my table, I guess, or else the bound papers weren't supposed to come out of the stacks. The cases of books, row after row, smelled good. Like old leather and good pipe tobacco. I had been here before. In this world, it's the man with education who makes the money. I had been reading the Funk & Wagnalls Encyclopedia. So far I knew a lot about Mark Antony, Atomic Energy, Boron, Brussels, Catapults, Demons, and Divans. I guess I had stopped to look around at some of the titles, because the busy librarian said sharply, "Follow me." I heard my voice say, "A pleasure. What about after work?" I didn't say it, but I was used to my voice independently saying things. Her neck got to flaming, but she walked stiffly ahead. She didn't say anything. She must be awful mad, I decided. But then I got the idea she was flushed with pleasure. I'm pretty ugly and I looked like a bum, but I was young. You had to grant me that. She waved a hand at the rows of bound News and left me alone with them. I wasn't sure if I was allowed to hunt up a table to lay the books on or not, so I took the volume for last year and laid it on the floor. That was the cleanest floor I ever saw. It didn't take me long to find the story. The victim was a big man, because the story was on the second page of the Nov. 4 edition. I started to tear the page out, then only memorized the name and home address. Somebody was sure to see me and I couldn't risk trouble just now. I stuck the book back in line and left by the side door. I went to a dry-cleaner, not the cheapest place I knew, because I wouldn't be safe with the change from a twenty in that neighborhood. My suit was cleaned while I waited. I paid a little extra and had it mended. Funny thing about a suit—it's almost never completely shot unless you just have it ripped off you or burned up. It wasn't exactly in style, but some rich executives wore suits out of style that they had paid a lot of money for. I remembered Fredric March's double-breasted in Executive Suite while Walter Pidgeon and the rest wore Ivy Leagues. Maybe I would look like an eccentric executive. I bought a new shirt, a good used pair of shoes, and a dime pack of single-edged razor blades. I didn't have a razor, but anybody with nerve can shave with a single-edge blade and soap and water. The clerk took my two bucks in advance and I went up to my room. I washed out my socks and underwear, took a bath, shaved and trimmed my hair and nails with the razor blade. With some soap on my finger, I scrubbed my teeth. Finally I got dressed. Everything was all right except that I didn't have a tie. They had them, a quarter a piece, where I got the shoes. It was only six blocks—I could go back. But I didn't want to wait. I wanted to complete the picture. The razor blade sliced through the pink bath towel evenly. I cut out a nice modern-style tie, narrow, with some horizontal stripes down at the bottom. I made a tight, thin knot. It looked pretty good. I was ready to leave, so I started for the door. I went back. I had almost forgotten my luggage. The box still had three unwrapped blades in it. I pocketed it. I hefted the used blade, dulled by all the work it had done. You can run being economical into stinginess. I tossed it into the wastebasket. I had five hamburgers and five cups of coffee. I couldn't finish all of the French fries. "Mac," I said to the fat counterman, who looked like all fat countermen, "give me a Milwaukee beer." He stopped polishing the counter in front of his friend. "Milwaukee, Wisconsin, or Milwaukee, Oregon?" "Wisconsin." He didn't argue. It was cold and bitter. All beer is bitter, no matter what they say on TV. I like beer. I like the bitterness of it. It felt like another, but I checked myself. I needed a clear head. I thought about going back to the hotel for some sleep; I still had the key in my pocket (I wasn't trusting it to any clerk). No, I had had sleep on Thanksgiving, bracing up for trying the lift at Brother Partridge's. Let's see, it was daylight outside again, so this was the day after Thanksgiving. But it had only been sixteen or twenty hours since I had slept. That was enough. I left the money on the counter for the hamburgers and coffee and the beer. There was $7.68 left. As I passed the counterman's friend on his stool, my voice said, "I think you're yellow." He turned slowly, his jaw moving further away from his brain. I winked. "It was just a bet for me to say that to you. I won two bucks. Half of it is yours." I held out the bill to him. His paw closed over the money and punched me on the biceps. Too hard. He winked back. "It's okay." I rubbed my shoulder, marching off fast, and I counted my money. With my luck, I might have given the counterman's friend the five instead of one of the singles. But I hadn't. I now had $6.68 left. "I still think you're yellow," my voice said. It was my voice, but it didn't come from me. There were no words, no feeling of words in my throat. It just came out of the air the way it always did. I ran. Harold R. Thompkins, 49, vice-president of Baysinger's, was found dead behind the store last night. His skull had been crushed by a vicious beating with a heavy implement, Coroner McClain announced in preliminary verdict. Tompkins, who resided at 1467 Claremont, Edgeway, had been active in seeking labor-management peace in the recent difficulties.... I had read that a year before. The car cards on the clanking subway and the rumbling bus didn't seem nearly so interesting to me. Outside the van, a tasteful sign announced the limits of the village of Edgeway, and back inside, the monsters of my boyhood went bloomp at me. I hadn't seen anything like them in years. The slimy, scaly beasts were slithering over the newspaper holders, the ad card readers, the girl watchers as the neat little carbon-copy modern homes breezed past the windows. I ignored the devils and concentrated on reading the withered, washed-out political posters on the telephone poles. My neck ached from holding it so stiff, staring out through the glass. More than that, I could feel the jabberwocks staring at me. You know how it is. You can feel a stare with the back of your neck and between your eyes. They got one brush of a gaze out of me. The things abruptly started their business, trying to act casually as if they hadn't been waiting for me to look at them at all. They had a little human being of some sort. It was the size of a small boy, like the small boy who looked like me that they used to destroy when I was locked up with them in the dark. Except this was a man, scaled down to child's size. He had sort of an ugly, worried, tired, stupid look and he wore a shiny suit with a piece of a welcome mat or something for a necktie. Yeah, it was me. I really knew it all the time. They began doing things to the midget me. I didn't even lift an eyebrow. They couldn't do anything worse to the small man than they had done to the young boy. It was sort of nostalgic watching them, but I really got bored with all that violence and killing and killing the same kill over and over. Like watching the Saturday night string of westerns in a bar. The sunlight through the window was yellow and hot. After a time, I began to dose. The shrieks woke me up. For the first time, I could hear the shrieks of the monster's victim and listen to their obscene droolings. For the very first time in my life. Always before it had been all pantomime, like Charlie Chaplin. Now I heard the sounds of it all. They say it's a bad sign when you start hearing voices. I nearly panicked, but I held myself in the seat and forced myself to be rational about it. My own voice was always saying things everybody could hear but which I didn't say. It wasn't any worse to be the only one who could hear other things I never said. I was as sane as I ever was. There was no doubt about that. But a new thought suddenly impressed itself on me. Whatever was punishing me for my sin was determined that I turn back before reaching 1467 Claremont.
|
B. stealing from the church
|
What isn't true about Charlie?
A. he was a great space traveler
B. he regretted the life he chose
C. he drugged himself to watch Ben graduate
D. he was sick with lung-rot
|
Spacemen Die at Home By EDWARD W. LUDWIG Illustrated by THORNE [Transcriber's Note: This etext was produced from Galaxy Science Fiction October 1951. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] One man's retreat is another's prison ... and it takes a heap of flying to make a hulk a home! Forty days of heaven and forty nights of hell. That's the way it's been, Laura. But how can I make you understand? How can I tell you what it's like to be young and a man and to dream of reaching the stars? And yet, at the same time, to be filled with a terrible, gnawing fear—a fear locked in my mind during the day and bursting out like an evil jack-in-the-box at night. I must tell you, Laura. Perhaps if I start at the beginning, the very beginning.... It was the Big Day. All the examinations, the physicals and psychos, were over. The Academy, with its great halls and classrooms and laboratories, lay hollow and silent, an exhausted thing at sleep after spawning its first-born. For it was June in this year of 1995, and we were the graduating class of the U. S. Academy of Interplanetary Flight. The first graduating class, Laura. That's why it was so important, because we were the first . We sat on a little platform, twenty-five of us. Below us was a beach of faces, most of them strange, shining like pebbles in the warm New Mexican sunlight. They were the faces of mothers and fathers and grandparents and kid brothers and sisters—the people who a short time ago had been only scrawled names on letters from home or words spoken wistfully at Christmas. They were the memory-people who, to me, had never really existed. But today they had become real, and they were here and looking at us with pride in their eyes. A voice was speaking, deep, sure, resonant. "... these boys have worked hard for six years, and now they're going to do a lot of big things. They're going to bring us the metals and minerals that we desperately need. They're going to find new land for our colonists, good rich land that will bear food and be a home for our children. And perhaps most important of all, they'll make other men think of the stars and look up at them and feel humility—for mankind needs humility." The speaker was Robert Chandler, who'd brought the first rocket down on Mars just five years ago, who'd established the first colony there, and who had just returned from his second hop to Venus. Instead of listening to his words, I was staring at his broad shoulders and his dark, crew-cut hair and his white uniform which was silk-smooth and skin-tight. I was worshiping him and hating him at the same time, for I was thinking: He's already reached Mars and Venus. Let him leave Jupiter and the others alone! Let us be the first to land somewhere! Let us be the first! Mickey Cameron, sitting next to me, dug an elbow into my ribs. "I don't see 'em, Ben," he whispered. "Where do you suppose they are?" I blinked. "Who?" "My folks." That was something I didn't have to worry about. My parents had died in a strato-jet crash when I was four, so I hadn't needed many of those "You are cordially invited" cards. Just one, which I'd sent to Charlie Taggart. Stardust Charlie, we called him, although I never knew why. He was a veteran of Everson's first trip to the Moon nearly twenty-five years ago, and he was still at it. He was Chief Jetman now on the Lunar Lady , a commercial ore ship on a shuttle between Luna City and White Sands. I remembered how, as a kid, I'd pestered him in the Long Island Spaceport, tagging after him like a puppy, and how he'd grown to like me until he became father, mother, and buddy all in one to me. And I remembered, too, how his recommendation had finally made me a cadet. My gaze wandered over the faces, but I couldn't find Charlie's. It wasn't surprising. The Lunar Lady was in White Sands now, but liberties, as Charlie said, were as scarce as water on Mars. It doesn't matter , I told myself. Then Mickey stiffened. "I see 'em, Ben! There in the fifth row!" Usually Mickey was the same whether in a furnace-hot engine room or a garden party, smiling, accepting whatever the world offered. But now a tenseness and an excitement had gripped even him. I was grateful that he was beside me; we'd been a good team during those final months at the Academy and I knew we'd be a good team in space. The Universe was mighty big, but with two of us to face it together, it would be only half as big. And then it seemed that all the proud faces were looking at us as if we were gods. A shiver went through my body. Though it was daytime, I saw the stars in my mind's vision, the great shining balls of silver, each like a voice crying out and pleading to be explored, to be touched by the sons of Earth. They expect a lot from us. They expect us to make a new kind of civilization and a better place out of Earth. They expect all this and a hell of a lot more. They think there's nothing we can't do. I felt very small and very humble. I was scared. Damned scared. At last it was over, and the proud faces descended upon us in a huge, babbling wave. Then I saw him. Good old Stardust Charlie. His wizened little body was shuffling down an aisle, his eyes shining like a child's. He'd been sandwiched, evidently, in one of the rear rows. But he wasn't the Charlie I'd seen a year ago. He'd become gaunt and old, and he walked with an unnatural stiffness. He looked so old that it was hard to believe he'd once been young. He scratched his mop of steel-gray hair and grinned. "You made it, boy," he chortled, "and by Jupiter, we'll celebrate tonight. Yes, siree, I got twenty-four hours, and we'll celebrate as good spacemen should!" Then Mickey strode up to us. He was his normal, boyish self again, walking lightly, his blond, curly-haired skull swaying as if in rhythm with some silent melody. And you, Laura, were with him. "Meet the Brat," he said. "My sister Laura." I stared almost rudely. You were like a doll lost in the immensity of your fluffy pink dress. Your hair was long and transformed into a golden froth where sunlight touched it. But your eyes were the eyes of a woman, glowing like dark stars and reflecting a softness, a gentleness that I'd never seen in eyes before. "I'm happy to meet you, Ben," you said. "I've heard of no one else for the past year." A tide of heat crept up from my collar. I stuttered through an introduction of Charlie. You and Mickey looked strangely at Charlie, and I realized that old Stardust was not a cadet's notion of the ideal spaceman. Charlie scorned the skin-tight uniforms of the government service and wore a shiny black suit that was a relic of Everson's early-day Moon Patrol. His tie was clumsily knotted, and a button on his coat was missing. And the left side of his face was streaked with dark scar tissue, the result of an atomic blowup on one of the old Moon ships. I was so accustomed to the scars, I was seldom aware of them; but others, I knew, would find them ugly. You were kind. You shook hands and said, softly: "It's a privilege to meet you, Charlie. Just think—one of Everson's men, one of the first to reach the Moon!" Charlie gulped helplessly, and Mickey said: "Still going to spend the weekend with us, aren't you, Ben?" I shook my head. "Charlie has only twenty-four hours liberty. We're planning to see the town tonight." "Why don't you both come with us?" you asked. "Our folks have their own plane, so it would be no problem. And we've got a big guest room. Charlie, wouldn't you like a home-cooked meal before going back to the Moon?" Charlie's answer was obscured by a sudden burst of coughing. I knew that he'd infinitely prefer to spend his liberty sampling Martian fizzes and Plutonian zombies. But this night seemed too sacred for Charlie's kind of celebration. "We'd really like to come," I said. On our way to the 'copter parking field, Dean Dawson passed us. He was a tall, willowy man, spectacled, looking the way an academy professor should look. "Ben," he called, "don't forget that offer. Remember you've got two months to decide." "No, thanks," I answered. "Better not count on me." A moment later Mickey said, frowning, "What was he talking about, Ben? Did he make you an offer?" I laughed. "He offered me a job here at the Academy teaching astrogation. What a life that would be! Imagine standing in a classroom for forty years when I've got the chance to—" I hesitated, and you supplied the right words: "When you've got the chance to be the first to reach a new planet. That's what most of you want, isn't it? That's what Mickey used to want." I looked at you as if you were Everson himself, because you seemed to understand the hunger that could lie in a man's heart. Then your last words came back and jabbed me: "That's what Mickey used to want." " Used to want?" I asked. "What do you mean?" You bit your lip, not answering. "What did she mean, Mickey?" Mickey looked down at his feet. "I didn't want to tell you yet, Ben. We've been together a long time, planning to be on a rocket. But—" "Yes?" "Well, what does it add up to? You become a spaceman and wear a pretty uniform. You wade through the sands of Mars and the dust of Venus. If you're lucky, you're good for five, maybe ten years. Then one thing or another gets you. They don't insure rocketmen, you know." My stomach was full of churning, biting ice. "What are you trying to say, Mickey?" "I've thought about it a long time. They want me for Cargo Supervisor of White Sands Port." He raised his hand to stop me. "I know. It's not so exciting. I'll just live a lot longer. I'm sorry, Ben." I couldn't answer. It was as if someone had whacked the back of my knees with the blast of a jet. "It doesn't change anything, Ben—right now, I mean. We can still have a good weekend." Charlie was muttering under his breath, smoldering like a bomb about to reach critical mass. I shook my head dazedly at him as we got to the 'copter. "Sure," I said to Mickey, "we can still have a good weekend." I liked your folks, Laura. There was no star-hunger in them, of course. They were simple and solid and settled, like green growing things, deep-rooted, belonging to Earth. They were content with a home that was cool on this warm summer night, with a 'copter and a tri-dimensional video, and a handsome automatic home that needed no servants or housework. Stardust Charlie was as comfortable as a Martian sand-monkey in a shower, but he tried courageously to be himself. At the dinner table he stared glassily at nothing and grated, "Only hit Mars once, but I'll never forget the kid who called himself a medic. Skipper started coughing, kept it up for three days. Whoopin' cough, the medic says, not knowin' the air had chemicals that turned to acid in your lungs. I'd never been to Mars before, but I knew better'n that. Hell, I says, that ain't whoopin' cough, that's lung-rot." That was when your father said he wasn't so hungry after all. Afterward, you and I walked onto the terrace, into the moonlit night, to watch for crimson-tailed continental rockets that occasionally streaked up from White Sands. We gazed for a few seconds up into the dark sky, and then you said: "Charlie is funny, isn't he? He's nice and I'm glad he's here, but he's sort of funny." "He's an old-time spaceman. You didn't need much education in those days, just a lot of brawn and a quick mind. It took guts to be a spaceman then." "But he wasn't always a spaceman. Didn't he ever have a family?" I smiled and shook my head. "If he had, he never mentioned it. Charlie doesn't like to be sentimental, at least not on the outside. As far as I know, his life began when he took off for the Moon with Everson." You stared at me strangely, almost in a sacred kind of way. I knew suddenly that you liked me, and my heart began to beat faster. There was silence. You were lovely, your soft hair like strands of gold, and there were flecks of silver in your dark eyes. Somehow I was afraid. I had the feeling that I shouldn't have come here. You kept looking at me until I had to ask: "What are you thinking, Laura?" You laughed, but it was a sad, fearful laugh. "No, I shouldn't be thinking it. You'd hate me if I told you, and I wouldn't want that." "I could never hate you." "It—it's about the stars," you said very softly. "I understand why you want to go to them. Mickey and I used to dream about them when we were kids. Of course I was a girl, so it was just a game to me. But once I dreamed of going to England. Oh, it was going to be so wonderful. I lived for months, just thinking about it. "One summer we went. I had fun. I saw the old buildings and castles, and the spaceports and the Channel Tube. But after it was over, I realized England wasn't so different from America. Places seem exciting before you get to them, and afterward they're not really." I frowned. "And you mean it might be the same with the stars? You think maybe I haven't grown up yet?" Anxiety darkened your features. "No, it'd be good to be a spaceman, to see the strange places and make history. But is it worth it? Is it worth the things you'd have to give up?" I didn't understand at first, and I wanted to ask, "Give up what ?" Then I looked at you and the promise in your eyes, and I knew. All through the years I'd been walking down a single, narrow path. Government boarding school, the Academy, my eyes always upward and on the stars. Now I'd stumbled into a cross-roads, beholding a strange new path that I'd never noticed before. You can go into space , I thought, and try to do as much living in ten years as normal men do in fifty. You can be like Everson, who died in a Moon crash at the age of 36, or like a thousand others who lie buried in Martian sand and Venusian dust. Or, if you're lucky, like Charlie—a kind of human meteor streaking through space, eternally alone, never finding a home. Or there's the other path. To stay on this little prison of an Earth in cool, comfortable houses. To be one of the solid, rooted people with a wife and kids. To be one of the people who live long enough to grow old, who awake to the song of birds instead of rocket grumblings, who fill their lungs with the clean rich air of Earth instead of poisonous dust. "I'm sorry," you said. "I didn't mean to make you sad, Ben." "It's all right," I said, clenching my fists. "You made sense—a lot of sense." The next morning Charlie said good-bye in our room. He rubbed his scarred face nervously as he cleared his throat with a series of thin, tight coughs. Then he pointed to a brown, faded tin box lying on the bed. "I'm leavin' that for you. It's full of old stuff, souvenirs mostly. Thought maybe you'd like to have 'em." I scowled, not understanding. "Why, Charlie? What for?" He shrugged as if afraid he might be accused of sentimentality. "Oh, it's just that I've been dodgin' meteors now for twenty-five years. That's a long time, boy. Ain't one spaceman in a thousand that lucky. Some of these days, I won't be so lucky." I tried to laugh. "You're good for another twenty-five years, Charlie." He shook his head stiffly, staring at nothing. "Maybe. Anyway, I'm gonna get off the Shuttle this time, make one more trip to Mars. Tell you what. There's a little stone cafe on Mars, the Space Rat , just off Chandler Field on the Grand Canal. When you get to Mars, take a look inside. I'll probably be there." He coughed again, a deep, rasping cough that filled his eyes with tears. "Not used to this Earth air," he muttered. "What I need's some Martian climate." Suddenly that cough frightened me. It didn't seem normal. I wondered, too, about his stiff movements and glassy stare. It was as if he were drugged. I shook the thought away. If Charlie was sick, he wouldn't talk about going to Mars. The medics wouldn't let him go even as far as Luna. We watched him leave, you and Mickey and I. "When will you be back?" you asked. Charlie's hard face contorted itself into a gargoylish grin. "Maybe a couple of months, maybe a couple of years. You know spacemen." Then he waved and strode away, a strange, gray, withered gnome of a man. I wanted him to say something, to tell me the secret that would kill the doubt worming through my brain. But he rounded a corner, still grinning and waving, and then he was gone. That afternoon Mickey showed me his room. It was more like a boy's room than a spaceman's. In it were all the little things that kids treasure—pennants, models of Everson's two ships, a tennis trophy, books, a home-made video. I began to realize how important a room like this could be to a boy. I could imagine, too, the happiness that parents felt as they watched their children grow to adulthood. I'd missed something. My folks were shadow-people, my impressions of them drawn half from ancient photos, half from imagination. For me, it had been a cold, automatic kind of life, the life of dormitories and routines and rules. I'd been so blinded by the brilliancy of my dreams, I hadn't realized I was different. My folks were killed in a rocket crash. If it weren't for rockets, I'd have lived the kind of life a kid should live. Mickey noticed my frown. "What's the matter, Ben? Still sore? I feel like a heel, but I'm just not like you and Charlie, I guess. I—" "No, I understand, Mickey. I'm not sore, really." "Listen, then. You haven't accepted any offer yet, have you?" "No. I got a couple of possibilities. Could get a berth on the Odyssey , the new ship being finished at Los Angeles. They want me, too, for the Moon Patrol, but that's old stuff, not much better than teaching. I want to be in deep space." "Well, how about staying with us till you decide? Might as well enjoy Earth life while you can. Okay?" I felt like running from the house, to forget that it existed. I wanted someone to tell me one of the old stories about space, a tale of courage that would put fuel on dying dreams. But I wanted, also, to be with you, Laura, to see your smile and the flecks of silver in your eyes and the way your nose turned upward ever so slightly when you laughed. You see, I loved you already, almost as much as I loved the stars. And I said, slowly, my voice sounding unfamiliar and far away, "Sure, I'll stay, Mickey. Sure." Forty days of joy, forty nights of fear and indecision. We did all the little things, like watching the rockets land at White Sands and flying down to the Gulf to swim in cool waters. You tried, unsuccessfully, to teach me to dance, and we talked about Everson and Charlie and the Moon and the stars. You felt you had to give the stars all the beauty and promise of a child's dream, because you knew that was what I wanted. One morning I thought, Why must I make a choice? Why can't I have both you and the stars? Would that be asking too much? All day the thought lay in my mind like fire. That evening I asked you to marry me. I said it very simply: "Laura, I want you to be my wife." You looked up at Venus, and you were silent for a long while, your face flushed. Then you murmured, "I—I want to marry you, Ben, but are you asking me to marry a spaceman or a teacher?" "Can't a spaceman marry, too?" "Yes, a spaceman can marry, but what would it be like? Don't you see, Ben? You'd be like Charlie. Gone for maybe two months, maybe two years. Then you'd have a twenty-four hour liberty—and I'd have what?" Somehow I'd expected words like these, but still they hurt. "I wouldn't have to be a spaceman forever. I could try it for a couple of years, then teach." "Would you, Ben? Would you be satisfied with just seeing Mars? Wouldn't you want to go on to Jupiter and Saturn and Uranus and on and on?" Your voice was choked, and even in the semi-darkness I saw tears glittering in your eyes. "Do you think I'd dare have children, Ben? Mickey told me what happened on the Cyclops . There was a leak in the atomic engines. The ship was flooded with radiation—just for a second. It didn't seem serious. The men had no burns. But a year later the captain had a child. And it was—" "I know, Laura. Don't say it." You had to finish. "It was a monster." That night I lay awake, the fears and doubts too frantic to let me sleep. You've got to decide now , I told myself. You can't stay here. You've got to make a choice. The teaching job was still open. The spot on the Odyssey was still open—and the big ship, it was rumored, was equipped to make it all the way to Pluto. You can take Dean Dawson's job and stay with Laura and have kids and a home and live to see what happens in this world sixty years from now. Or you can see what's on the other side of the mountain. You can be a line in a history book. I cursed. I knew what Charlie would say. He'd say, "Get the hell out of there, boy. Don't let a fool woman make a sucker out of you. Get out there on the Odyssey where you belong. We got a date on Mars, remember? At the Space Rat , just off Chandler Field on the Grand Canal." That's what he'd say. And yet I wanted you, Laura. I wanted to be with you, always. "Oh God," I moaned, "what shall I do?" Next morning the door chimes pealed, and you went to the door and brought back the audiogram. It was addressed to me; I wondered who could be sending me a message. I pressed the stud on the little gray cylinder, and a rasping, automatic voice droned: "Luna City, Luna, July 27, 1995. Regret to inform you of death of Charles Taggart, Chief Jetman...." Then there was a Latin name which was more polite than the word "lung-rot" and the metallic phrase, "This message brought to you by courtesy of United Nations Earth-Luna Communication Corps." I stood staring at the cylinder. Charles Taggart was dead. Charles Taggart was Charlie. Stardust Charlie. My heart thudded crazily against my chest. It couldn't be! Not Charlie! The audiogram had lied! I pressed the stud again. "... regret to inform you of death of Charles ..." I hurled the cylinder at the wall. It thudded, fell, rolled. The broken voice droned on. You ran to it, shut it off. "I'm sorry, Ben, so terribly—" Without answering, I walked into my room. I knew it was true now. I remembered Charlie's coughing, his gaunt features, his drugged gaze. The metallic words had told the truth. I sat for a long time on my bed, crying inside, but staring dry-eyed at Charlie's faded tin box. Then, finally, I fingered his meager possessions—a few wrinkled photos, some letters, a small black statue of a forgotten Martian god, a gold service medal from the Moon Patrol. This was what remained of Charlie after twenty-five years in space. It was a bitter bargain. A statue instead of a wife, yellowed letters instead of children, a medal instead of a home. It'd be a great future , I thought. You'd dream of sitting in a dingy stone dive on the Grand Canal with sand-wasps buzzing around smoky, stinking candles. A bottle of luchu juice and a couple of Martian girls with dirty feet for company. And a sudden cough that would be the first sign of lung-rot. To hell with it! I walked into your living room and called Dean Dawson on the visiphone. I accepted that job teaching. And now, Laura, it's nearly midnight. You're in your room, sleeping, and the house is silent. It's hard to tell you, to make you understand, and that is why I am writing this. I looked through Charlie's box again, more carefully this time, reading the old letters and studying the photographs. I believe now that Charlie sensed my indecision, that he left these things so that they could tell me what he could not express in words. And among the things, Laura, I found a ring. A wedding ring. In that past he never talked about, there was a woman—his wife. Charlie was young once, his eyes full of dreams, and he faced the same decision that I am facing. Two paths were before him, but he tried to travel both. He later learned what we already know—that there can be no compromise. And you know, too, which path he finally chose. Do you know why he had to drug himself to watch me graduate? So he could look at me, knowing that I would see the worlds he could never live to see. Charlie didn't leave just a few trinkets behind him. He left himself, Laura, for he showed me that a boy's dream can also be a man's dream. He made his last trip to Luna when he knew he was going to die. Heaven knows how he escaped a checkup. Maybe the captain understood and was kind—but that doesn't matter now. Do you know why he wanted to reach Mars? Do you know why he didn't want to die in the clean, cool air of Earth? It was because he wanted to die nearer home. His home, Laura, was the Universe, where the ship was his house, the crew his father, mother, brothers, the planets his children. You say that the beauty of the other side of the mountain vanishes after you reach it. But how can one ever be sure until the journey is made? Could I or Charlie or the thousand before us bear to look upon a star and think, I might have gone there; I could have been the first ? We said, too, that the life of a spaceman is lonely. Yet how could one be lonely when men like Charlie roam the spaceways? Charlie wanted me to himself that night after graduation. He wanted us to celebrate as spacemen should, for he knew that this would be his last night on Earth. It might have seemed an ugly kind of celebration to you, but he wanted it with all his heart, and we robbed him of it. Because of these things, Laura, I will be gone in the morning. Explain the best you can to Mickey and to your parents and Dean Dawson. Right now I've got a date that I'm going to keep—at a dingy stone cafe on Mars, the Space Rat , just off Chandler Field on the Grand Canal. Stardust Charlie will be there; he'll go with me in memory to whatever part of the Galaxy I may live to reach. And so will you, Laura. I have two wedding rings with me—his wife's ring and yours.
|
B. he regretted the life he chose
|
Where is the Farm?
A. New Jersey
B. Illinois
C. Pennsylvania
D. Connecticut
|
BRAMBLE BUSH BY ALAN E. NOURSE [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, August 1957. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] There was a man in our town, and he was wondrous wise; He jumped into a bramble bush and scratched out both his eyes. And when he saw what he had done, with all his might and main He jumped into another bush and scratched them in again. MOTHER GOOSE Dr. David Lessing found Jack Dorffman and the boy waiting in his office when he arrived at the Hoffman Center that morning. Dorffman looked as though he'd been running all night. There were dark pouches under his eyes; his heavy unshaven face seemed to sag at every crease. Lessing glanced sharply at his Field Director and sank down behind his desk with a sigh. "All right, Jack—what's wrong?" "This kid is driving me nuts," said Dorffman through clenched teeth. "He's gone completely hay-wire. Nobody's been able to get near him for three weeks, and now at six o'clock this morning he decides he's leaving the Farm. I talk to him, I sweat him down, I do everything but tie him to the bed, and I waste my time. He's leaving the Farm. Period." "So you bring him down here," said Lessing sourly. "The worst place he could be, if something's really wrong." He looked across at the boy. "Tommy? Come over and sit down." There was nothing singular about the boy's appearance. He was thin, with a pale freckled face and the guileless expression of any normal eight-year-old as he blinked across the desk at Lessing. The awkward grey monitor-helmet concealed a shock of sandy hair. He sat with a mute appeal in his large grey eyes as Lessing flipped the reader-switch and blinked in alarm at the wildly thrashing pattern on the tape. The boy was terrorized. He was literally pulsating with fear. Lessing sat back slowly. "Tell me about it, Tommy," he said gently. "I don't want to go back to the Farm," said the boy. "Why?" "I just don't. I hate it there." "Are you frightened?" The boy bit his lip and nodded slowly. "Of me? Of Dr. Dorffman?" "No. Oh, no!" "Then what?" Again the mute appeal in the boy's eyes. He groped for words, and none came. Finally he said, "If I could only take this off—" He fingered the grey plastic helmet. "You think that would make you feel better?" "It would, I know it would." Lessing shook his head. "I don't think so, Tommy. You know what the monitor is for, don't you?" "It stops things from going out." "That's right. And it stops things from going in. It's an insulator. You need it badly. It would hurt you a great deal if you took it off, away from the Farm." The boy fought back tears. "But I don't want to go back there—" The fear-pattern was alive again on the tape. "I don't feel good there. I never want to go back." "Well, we'll see. You can stay here for a while." Lessing nodded at Dorffman and stepped into an adjoining room with him. "You say this has been going on for three weeks ?" "I'm afraid so. We thought it was just a temporary pattern—we see so much of that up there." "I know, I know." Lessing chewed his lip. "I don't like it. We'd better set up a battery on him and try to spot the trouble. And I'm afraid you'll have to set it up. I've got that young Melrose from Chicago to deal with this morning—the one who's threatening to upset the whole Conference next month with some crazy theories he's been playing with. I'll probably have to take him out to the Farm to shut him up." Lessing ran a hand through sparse grey hair. "See what you can do for the boy downstairs." "Full psi precautions?" asked Dorffman. "Certainly! And Jack—in this case, be sure of it. If Tommy's in the trouble I think he's in, we don't dare risk a chance of Adult Contact now. We could end up with a dead boy on our hands." Two letters were waiting on Lessing's desk that morning. The first was from Roberts Bros., announcing another shift of deadline on the book, and demanding the galley proofs two weeks earlier than scheduled. Lessing groaned. As director of psionic research at the Hoffman Medical Center, he had long since learned how administrative detail could suck up daytime hours. He knew that his real work was at the Farm—yet he hadn't even been to the Farm in over six weeks. And now, as the book approached publication date, Lessing wondered if he would ever really get back to work again. The other letter cheered him a bit more. It bore the letterhead of the International Psionics Conference: Dear Dr. Lessing: In recognition of your position as an authority on human Psionic behavior patterns, we would be gratified to schedule you as principle speaker at the Conference in Chicago on October 12th. A few remarks in discussion of your forthcoming book would be entirely in order— They were waiting for it, then! He ran the galley proofs into the scanner excitedly. They knew he had something up his sleeve. His earlier papers had only hinted at the direction he was going—but the book would clear away the fog. He scanned the title page proudly. "A Theory of Psionic Influence on Infant and Child Development." A good title—concise, commanding, yet modest. They would read it, all right. And they would find it a light shining brightly in the darkness, a guide to the men who were floundering in the jungle of a strange and baffling new science. For they were floundering. When they were finally forced to recognize that this great and powerful force did indeed exist in human minds, with unimaginable potential if it could only be unlocked, they had plunged eagerly into the search, and found themselves in a maddening bramble bush of contradictions and chaos. Nothing worked, and everything worked too well. They were trying to study phenomena which made no sense, observing things that defied logic. Natural laws came crashing down about their ears as they stood sadly by and watched things happen which natural law said could never happen. They had never been in this jungle before, nor in any jungle remotely like it. The old rules didn't work here, the old methods of study failed. And the more they struggled, the thicker and more impenetrable the bramble bush became— But now David Lessing had discovered a pathway through that jungle, a theory to work by— At his elbow the intercom buzzed. "A gentleman to see you," the girl said. "A Dr. Melrose. He's very impatient, sir." He shut off the scanner and said, "Send him in, please." Dr. Peter Melrose was tall and thin, with jet black hair and dark mocking eyes. He wore a threadbare sport coat and a slouch. He offered Lessing a bony hand, then flung himself into a chair as he stared about the office in awe. "I'm really overwhelmed," he said after a moment. "Within the stronghold of psionic research at last. And face to face with the Master in the trembling flesh!" Lessing frowned. "Dr. Melrose, I don't quite understand—" "Oh, it's just that I'm impressed," the young man said airily. "Of course, I've seen old dried-up Authorities before—but never before a brand spanking new one, just fresh out of the pupa, so to speak!" He touched his forehead in a gesture of reverence. "I bow before the Oracle. Speak, oh Motah, live forever! Cast a pearl at my feet!" "If you've come here to be insulting," Lessing said coldly, "you're just wasting time." He reached for the intercom switch. "I think you'd better wait before you do that," Melrose said sharply, "because I'm planning to take you apart at the Conference next month unless I like everything I see and hear down here today. And if you don't think I can do it, you're in for quite a dumping." Lessing sat back slowly. "Tell me—just what, exactly, do you want?" "I want to hear this fairy tale you're about to publish in the name of 'Theory'," Melrose said. "I want to see this famous Farm of yours up in Connecticut and see for myself how much pressure these experimental controls you keep talking about will actually bear. But mostly, I want to see just what in psionic hell you're so busy making yourself an Authority about." There was no laughter in the man's sharp brown eyes. "You couldn't touch me with a ten foot pole at this conference," snapped Lessing. The other man grinned. "Try me! We shook you up a little bit last year, but you didn't seem to get the idea." "Last year was different." Lessing scowled. "As for our 'fairy tale', we happen to have a staggering body of evidence that says that it's true." "If the papers you've already published are a preview, we think it's false as Satan." "And our controls are above suspicion." "So far, we haven't found any way to set up logical controls," said Melrose. "We've done a lot of work on it, too." "Oh, yes—I've heard about your work. Not bad, really. A little misdirected, is all." "According to your Theory, that is." "Wildly unorthodox approach to psionics—but at least you're energetic enough." "We haven't been energetic enough to find an orthodox approach that got us anywhere. We doubt if you have, either. But maybe we're all wrong." Melrose grinned unpleasantly. "We're not unreasonable, your Majesty. We just ask to be shown. If you dare, that is." Lessing slammed his fist down on the desk angrily. "Have you got the day to take a trip?" "I've got 'til New Year." Lessing shouted for his girl. "Get Dorffman up here. We're going to the Farm this afternoon." The girl nodded, then hesitated. "But what about your lunch?" "Bother lunch." He gave Melrose a sidelong glare. "We've got a guest here who's got a lot of words he's going to eat for us...." Ten minutes later they rode the elevator down to the transit levels and boarded the little shuttle car in the terminal below the Hoffman Center. They sat in silence as the car dipped down into the rapid-transit channels beneath the great city, swinging northward in the express circuit through Philadelphia and Camden sectors, surfacing briefly in Trenton sector, then dropping underground once again for the long pull beneath Newark, Manhattan and Westchester sectors. In less than twenty minutes the car surfaced on a Parkway channel and buzzed north and east through the verdant Connecticut countryside. "What about Tommy?" Lessing asked Dorffman as the car sped along through the afternoon sun. "I just finished the prelims. He's not cooperating." Lessing ground his teeth. "I should be running him now instead of beating the bushes with this—" He broke off to glare at young Melrose. Melrose grinned. "I've heard you have quite a place up here." "It's—unconventional, at any rate," Lessing snapped. "Well, that depends on your standards. Sounds like a country day school, from what I've heard. According to your papers, you've even used conventional statistical analysis on your data from up here." "Until we had to throw it out. We discovered that what we were trying to measure didn't make sense in a statistical analysis." "Of course, you're sure you were measuring something ." "Oh, yes. We certainly were." "Yet you said that you didn't know what." "That's right," said Lessing. "We don't." "And you don't know why your instruments measure whatever they're measuring." The Chicago man's face was thoughtful. "In fact, you can't really be certain that your instruments are measuring the children at all. It's not inconceivable that the children might be measuring the instruments , eh?" Lessing blinked. "It's conceivable." "Mmmm," said Melrose. "Sounds like a real firm foundation to build a theory on." "Why not?" Lessing growled. "It wouldn't be the first time the tail wagged the dog. The psychiatrists never would have gotten out of their rut if somebody hadn't gotten smart and realized that one of their new drugs worked better in combatting schizophrenia when the doctor took the medicine instead of the patient. That was quite a wall to climb." "Yes, wasn't it," mused Melrose, scratching his bony jaw. "Only took them seventy years to climb it, thanks to a certain man's theories. I wonder how long it'll take psionics to crawl out of the pit you're digging for it?" "We're not digging any pit," Lessing exploded angrily. "We're exploring—nothing more. A phenomenon exists. We've known that, one way or another, for centuries. The fact that it doesn't seem to be bound by the same sort of natural law we've observed elsewhere doesn't mean that it isn't governed by natural law. But how can we define the law? How can we define the limits of the phenomenon, for that matter? We can't work in the dark forever—we've got to have a working hypothesis to guide us." "So you dreamed up this 'tadpole' idea," said Melrose sourly. "For a working hypothesis—yes. We've known for a long time that every human being has extrasensory potential to one degree or another. Not just a few here and there—every single one. It's a differentiating quality of the human mind. Just as the ability to think logically in a crisis instead of giving way to panic is a differentiating quality." "Fine," said Melrose. "Great. We can't prove that, of course, but I'll play along." Lessing glared at him. "When we began studying this psi-potential, we found out some curious things. For one thing, it seemed to be immensely more powerful and active in infants and children than in adults. Somewhere along the line as a child grows up, something happens. We don't know what. We do know that the child's psi-potential gradually withdraws deeper and deeper into his mind, burying itself farther and farther out of reach, just the way a tadpole's tail is absorbed deeper and deeper into the growing frog until there just isn't any tail any more." Lessing paused, packing tobacco into his pipe. "That's why we have the Farm—to try to discover why. What forces that potential underground? What buries it so deeply that adult human beings can't get at it any more?" "And you think you have an answer," said Melrose. "We think we might be near an answer. We have a theory that explains the available data." The shuttle car bounced sharply as it left the highway automatics. Dorffman took the controls. In a few moments they were skimming through the high white gates of the Farm, slowing down at the entrance to a long, low building. "All right, young man—come along," said Lessing. "I think we can show you our answer." In the main office building they donned the close-fitting psionic monitors required of all personnel at the Farm. They were of a hard grey plastic material, with a network of wiring buried in the substance, connected to a simple pocket-sized power source. "The major problem," Lessing said, "has been to shield the children from any external psionic stimuli, except those we wished to expose them to. Our goal is a perfectly controlled psi environment. The monitors are quite effective—a simple Renwick scrambler screen." "It blocks off all types of psi activity?" asked Melrose. "As far as we can measure, yes." "Which may not be very far." Jack Dorffman burst in: "What Dr. Lessing is saying is that they seem effective for our purposes." "But you don't know why," added Melrose. "All right, we don't know why. Nobody knows why a Renwick screen works—why blame us?" They were walking down the main corridor and out through an open areaway. Behind the buildings was a broad playground. A baseball game was in progress in one corner; across the field a group of swings, slides, ring bars and other playground paraphernalia was in heavy use. The place was teeming with youngsters, all shouting in a fury of busy activity. Occasionally a helmeted supervisor hurried by; one waved to them as she rescued a four-year-old from the parallel bars. They crossed into the next building, where classes were in progress. "Some of our children are here only briefly," Lessing explained as they walked along, "and some have been here for years. We maintain a top-ranking curriculum—your idea of a 'country day school' wasn't so far afield at that—with scholarships supported by Hoffman Center funds. Other children come to us—foundlings, desertees, children from broken homes, children of all ages from infancy on. Sometimes they stay until they have reached college age, or go on to jobs. As far as psionics research is concerned, we are not trying to be teachers. We are strictly observers. We try to place the youngsters in positions where they can develope what potential they have— without the presence of external psionic influences they would normally be subject to. The results have been remarkable." He led them into a long, narrow room with chairs and ash trays, facing a wide grey glass wall. The room fell into darkness, and through the grey glass they could see three children, about four years old, playing in a large room. "They're perfectly insulated from us," said Lessing. "A variety of recording instruments are working. And before you ask, Dr. Melrose, they are all empirical instruments, and they would all defy any engineer's attempts to determine what makes them go. We don't know what makes them go, and we don't care—they go. That's all we need. Like that one, for instance—" In the corner a flat screen was flickering, emitting a pale green fluorescent light. It hung from the wall by two plastic rods which penetrated into the children's room. There was no sign of a switch, nor a power source. As the children moved about, the screen flickered. Below it, a recording-tape clicked along in little spurts and starts of activity. "What are they doing?" Melrose asked after watching the children a few moments. "Those three seem to work as a team, somehow. Each one, individually, had a fairly constant recordable psi potential of about seventeen on the arbitrary scale we find useful here. Any two of them scale in at thirty-four to thirty-six. Put the three together and they operate somewhere in the neighborhood of six hundred on the same scale." Lessing smiled. "This is an isolated phenomenon—it doesn't hold for any other three children on the Farm. Nor did we make any effort to place them together—they drew each other like magnets. One of our workers spent two weeks trying to find out why the instruments weren't right. It wasn't the instruments, of course." Lessing nodded to an attendant, and peered around at Melrose. "Now, I want you to watch this very closely." He opened a door and walked into the room with the children. The fluorescent screen continued to flicker as the children ran to Lessing. He inspected the block tower they were building, and stooped down to talk to them, his lips moving soundlessly behind the observation wall. The children laughed and jabbered, apparently intrigued by the game he was proposing. He walked to the table and tapped the bottom block in the tower with his thumb. The tower quivered, and the screen blazed out with green light, but the tower stood. Carefully Lessing jogged all the foundation blocks out of place until the tower hung in midair, clearly unsupported. The children watched it closely, and the foundation blocks inched still further out of place.... Then, quite casually, Lessing lifted off his monitor. The children continued staring at the tower as the screen gave three or four violent bursts of green fire and went dark. The block tower fell with a crash. Moments later Lessing was back in the observation room, leaving the children busily putting the tower back together. There was a little smile on his lips as he saw Melrose's face. "Perhaps you're beginning to see what I'm driving at," he said slowly. "Yes," said Melrose. "I think I'm beginning to see." He scratched his jaw. "You think that it's adult psi-contact that drives the child's potential underground—that somehow adult contact acts like a damper, a sort of colossal candle-snuffer." "That's what I think," said Lessing. "How do you know those children didn't make you take off your monitor?" Lessing blinked. "Why should they?" "Maybe they enjoy the crash when the blocks fall down." "But that wouldn't make any difference, would it? The blocks still fall down." Melrose paced down the narrow room. "This is very good," he said suddenly, his voice earnest. "You have fine facilities here, good workers. And in spite of my flippancy, Dr. Lessing, I have never imagined for a moment that you were not an acute observer and a careful, highly imaginative worker. But suppose I told you, in perfect faith, that we have data that flatly contradicts everything you've told me today. Reproducible data, utterly incompatable with yours. What would you say to that?" "I'd say you were wrong," said Lessing. "You couldn't have such data. According to the things I am certain are true, what you're saying is sheer nonsense." "And you'd express that opinion in a professional meeting?" "I would." "And as an Authority on psionic behavior patterns," said Melrose slowly, "you would kill us then and there. You would strangle us professionally, discredit anything we did, cut us off cold." The tall man turned on him fiercely. "Are you blind, man? Can't you see what danger you're in? If you publish your book now, you will become an Authority in a field where the most devastating thing that could possibly happen would be— the appearance of an Authority ." Lessing and Dorffman rode back to the Hoffman Center in grim silence. At first Lessing pretended to work; finally he snapped off the tape recorder in disgust and stared out the shuttle-car window. Melrose had gone on to Idlewild to catch a jet back to Chicago. It was a relief to see him go, Lessing thought, and tried to force the thin, angry man firmly out of his mind. But somehow Melrose wouldn't force. "Stop worrying about it," Dorffman urged. "He's a crackpot. He's crawled way out on a limb, and now he's afraid your theory is going to cut it off under him. Well, that's his worry, not yours." Dorffman's face was intense. "Scientifically, you're on unshakeable ground. Every great researcher has people like Melrose sniping at him. You just have to throw them off and keep going." Lessing shook his head. "Maybe. But this field of work is different from any other, Jack. It doesn't follow the rules. Maybe scientific grounds aren't right at all, in this case." Dorffman snorted. "Surely there's nothing wrong with theorizing—" "He wasn't objecting to the theory. He's afraid of what happens after the theory." "So it seems. But why?" "Have you ever considered what makes a man an Authority?" "He knows more about his field than anybody else does." "He seems to, you mean. And therefore, anything he says about it carries more weight than what anybody else says. Other workers follow his lead. He developes ideas, formulates theories—and then defends them for all he's worth ." "But why shouldn't he?" "Because a man can't fight for his life and reputation and still keep his objectivity," said Lessing. "And what if he just happens to be wrong? Once he's an Authority the question of what's right and what's wrong gets lost in the shuffle. It's what he says that counts." "But we know you're right," Dorffman protested. "Do we?" "Of course we do! Look at our work! Look at what we've seen on the Farm." "Yes, I know." Lessing's voice was weary. "But first I think we'd better look at Tommy Gilman, and the quicker we look, the better—" A nurse greeted them as they stepped off the elevator. "We called you at the Farm, but you'd already left. The boy—" She broke off helplessly. "He's sick, Doctor. He's sicker than we ever imagined." "What happened?" "Nothing exactly—happened. I don't quite know how to describe it." She hurried them down the corridor and opened a door into a large children's playroom. "See what you think." The boy sat stolidly in the corner of the room. He looked up as they came in, but there was no flicker of recognition or pleasure on his pale face. The monitor helmet was still on his head. He just sat there, gripping a toy fire engine tightly in his hands. Lessing crossed the room swiftly. "Tommy," he said. The boy didn't even look at him. He stared stupidly at the fire engine. "Tommy!" Lessing reached out for the toy. The boy drew back in terror, clutching it to his chest. "Go away," he choked. "Go away, go away—" When Lessing persisted the boy bent over swiftly and bit him hard on the hand. Lessing sat down on the table. "Tommy, listen to me." His voice was gentle. "I won't try to take it again. I promise." "Go away." "Do you know who I am?" Tommy's eyes shifted haltingly to Lessing's face. He nodded. "Go away." "Why are you afraid, Tommy?" "I hurt. My head hurts. I hurt all over. Go away." "Why do you hurt?" "I—can't get it—off," the boy said. The monitor , Lessing thought suddenly. Something had suddenly gone horribly wrong—could the boy really be sensing the source of the trouble? Lessing felt a cold knot gather in the pit of his stomach. He knew what happened when adult psi-contact struck a psi-high youngster's mind. He had seen it a hundred times at the Farm. But even more—he had felt it in his own mind, bursting from the child. Like a violent physical blow, the hate and fear and suspicion and cruelty buried and repressed in the adult mind, crushing suddenly into the raw receptors of the child's mind like a smothering fog—it was a fearful thing. A healthy youngster could survive it, even though the scar remained. But this youngster was sick— And yet an animal instinctively seeks its own protection . With trembling fingers Lessing reached out and opened the baffle-snap on the monitor. "Take it off, Tommy," he whispered. The boy blinked in amazement, and pulled the grey helmet from his head. Lessing felt the familiar prickly feeling run down his scalp as the boy stared at him. He could feel deep in his own mind the cold chill of terror radiating from the boy. Then, suddenly, it began to fade. A sense of warmth—peace and security and comfort—swept in as the fear faded from the boy's face. The fire engine clattered to the floor. They analyzed the tapes later, punching the data cards with greatest care, filing them through the machines for the basic processing and classification that all their data underwent. It was late that night when they had the report back in their hands. Dorffman stared at it angrily. "It's obviously wrong," he grated. "It doesn't fit. Dave, it doesn't agree with anything we've observed before. There must be an error." "Of course," said Lessing. "According to the theory. The theory says that adult psi-contact is deadly to the growing child. It smothers their potential through repeated contact until it dries up completely. We've proved that, haven't we? Time after time. Everything goes according to the theory—except Tommy. But Tommy's psi-potential was drying up there on the Farm, until the distortion was threatening the balance of his mind. Then he made an adult contact, and we saw how he bloomed." Lessing sank down to his desk wearily. "What are we going to do, Jack? Formulate a separate theory for Tommy?" "Of course not," said Dorffman. "The instruments were wrong. Somehow we misread the data—" "Didn't you see his face ?" Lessing burst out. "Didn't you see how he acted ? What do you want with an instrument reading?" He shook his head. "It's no good, Jack. Something different happened here, something we'd never counted on. It's something the theory just doesn't allow for." They sat silently for a while. Then Dorffman said: "What are you going to do?" "I don't know," said Lessing. "Maybe when we fell into this bramble bush we blinded ourselves with the urge to classify—to line everything up in neat rows like pins in a paper. Maybe we were so blind we missed the path altogether." "But the book is due! The Conference speech—" "I think we'll make some changes in the book," Lessing said slowly. "It'll be costly—but it might even be fun. It's a pretty dry, logical presentation of ideas, as it stands. Very austere and authoritarian. But a few revisions could change all that—" He rubbed his hands together thoughtfully. "How about it, Jack? Do we have nerve enough to be laughed at? Do you think we could stand a little discredit, making silly asses of ourselves? Because when I finish this book, we'll be laughed out of existence. There won't be any Authority in psionics for a while—and maybe that way one of the lads who's really sniffing out the trail will get somebody to listen to him! "Get a pad, get a pencil! We've got work to do. And when we finish, I think we'll send a carbon copy out Chicago way. Might even persuade that puppy out there to come here and work for me—"
|
D. Connecticut
|
Why isn’t Retief satisfied when the Groaci finally show him the missing cruiser?
A. Retief believes the cruiser they show him is a decoy. The real missing cruiser was at least twenty-tons, which is much larger than the ship the Groacians reveal.
B. Retief believes the cruiser they show him isn’t human made at all, meaning the real cruiser is still out there.
C. Retief believes the cruiser they show him is a replica, meaning the real cruiser is still out there.
D. Retief believes the cruiser they show him is a decoy. The real missing cruiser was a battle ship, while the cruiser they show him is of the domestic variety.
|
THE MADMAN FROM EARTH BY KEITH LAUMER You don't have to be crazy to be an earth diplomat—but on Groac it sure helps! [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, March 1962. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] I "The Consul for the Terrestrial States," Retief said, "presents his compliments, et cetera, to the Ministry of Culture of the Groacian Autonomy, and with reference to the Ministry's invitation to attend a recital of interpretive grimacing, has the honor to express regret that he will be unable—" "You can't turn this invitation down," Administrative Assistant Meuhl said flatly. "I'll make that 'accepts with pleasure'." Retief exhaled a plume of cigar smoke. "Miss Meuhl," he said, "in the past couple of weeks I've sat through six light-concerts, four attempts at chamber music, and god knows how many assorted folk-art festivals. I've been tied up every off-duty hour since I got here—" "You can't offend the Groaci," Miss Meuhl said sharply. "Consul Whaffle would never have been so rude." "Whaffle left here three months ago," Retief said, "leaving me in charge." "Well," Miss Meuhl said, snapping off the dictyper. "I'm sure I don't know what excuse I can give the Minister." "Never mind the excuses," Retief said. "Just tell him I won't be there." He stood up. "Are you leaving the office?" Miss Meuhl adjusted her glasses. "I have some important letters here for your signature." "I don't recall dictating any letters today, Miss Meuhl," Retief said, pulling on a light cape. "I wrote them for you. They're just as Consul Whaffle would have wanted them." "Did you write all Whaffle's letters for him, Miss Meuhl?" "Consul Whaffle was an extremely busy man," Miss Meuhl said stiffly. "He had complete confidence in me." "Since I'm cutting out the culture from now on," Retief said, "I won't be so busy." "Well!" Miss Meuhl said. "May I ask where you'll be if something comes up?" "I'm going over to the Foreign Office Archives." Miss Meuhl blinked behind thick lenses. "Whatever for?" Retief looked thoughtfully at Miss Meuhl. "You've been here on Groac for four years, Miss Meuhl. What was behind the coup d'etat that put the present government in power?" "I'm sure I haven't pried into—" "What about that Terrestrial cruiser? The one that disappeared out this way about ten years back?" "Mr. Retief, those are just the sort of questions we avoid with the Groaci. I certainly hope you're not thinking of openly intruding—" "Why?" "The Groaci are a very sensitive race. They don't welcome outworlders raking up things. They've been gracious enough to let us live down the fact that Terrestrials subjected them to deep humiliation on one occasion." "You mean when they came looking for the cruiser?" "I, for one, am ashamed of the high-handed tactics that were employed, grilling these innocent people as though they were criminals. We try never to reopen that wound, Mr. Retief." "They never found the cruiser, did they?" "Certainly not on Groac." Retief nodded. "Thanks, Miss Meuhl," he said. "I'll be back before you close the office." Miss Meuhl's face was set in lines of grim disapproval as he closed the door. The pale-featured Groacian vibrated his throat-bladder in a distressed bleat. "Not to enter the Archives," he said in his faint voice. "The denial of permission. The deep regret of the Archivist." "The importance of my task here," Retief said, enunciating the glottal dialect with difficulty. "My interest in local history." "The impossibility of access to outworlders. To depart quietly." "The necessity that I enter." "The specific instructions of the Archivist." The Groacian's voice rose to a whisper. "To insist no longer. To give up this idea!" "OK, Skinny, I know when I'm licked," Retief said in Terran. "To keep your nose clean." Outside, Retief stood for a moment looking across at the deeply carved windowless stucco facades lining the street, then started off in the direction of the Terrestrial Consulate General. The few Groacians on the street eyed him furtively, veered to avoid him as he passed. Flimsy high-wheeled ground cars puffed silently along the resilient pavement. The air was clean and cool. At the office, Miss Meuhl would be waiting with another list of complaints. Retief studied the carving over the open doorways along the street. An elaborate one picked out in pinkish paint seemed to indicate the Groacian equivalent of a bar. Retief went in. A Groacian bartender was dispensing clay pots of alcoholic drink from the bar-pit at the center of the room. He looked at Retief and froze in mid-motion, a metal tube poised over a waiting pot. "To enjoy a cooling drink," Retief said in Groacian, squatting down at the edge of the pit. "To sample a true Groacian beverage." "To not enjoy my poor offerings," the Groacian mumbled. "A pain in the digestive sacs; to express regret." "To not worry," Retief said, irritated. "To pour it out and let me decide whether I like it." "To be grappled in by peace-keepers for poisoning of—foreigners." The barkeep looked around for support, found none. The Groaci customers, eyes elsewhere, were drifting away. "To get the lead out," Retief said, placing a thick gold-piece in the dish provided. "To shake a tentacle." "The procuring of a cage," a thin voice called from the sidelines. "The displaying of a freak." Retief turned. A tall Groacian vibrated his mandibles in a gesture of contempt. From his bluish throat coloration, it was apparent the creature was drunk. "To choke in your upper sac," the bartender hissed, extending his eyes toward the drunk. "To keep silent, litter-mate of drones." "To swallow your own poison, dispenser of vileness," the drunk whispered. "To find a proper cage for this zoo-piece." He wavered toward Retief. "To show this one in the streets, like all freaks." "Seen a lot of freaks like me, have you?" Retief asked, interestedly. "To speak intelligibly, malodorous outworlder," the drunk said. The barkeep whispered something, and two customers came up to the drunk, took his arms and helped him to the door. "To get a cage!" the drunk shrilled. "To keep the animals in their own stinking place." "I've changed my mind," Retief said to the bartender. "To be grateful as hell, but to have to hurry off now." He followed the drunk out the door. The other Groaci released him, hurried back inside. Retief looked at the weaving alien. "To begone, freak," the Groacian whispered. "To be pals," Retief said. "To be kind to dumb animals." "To have you hauled away to a stockyard, ill-odored foreign livestock." "To not be angry, fragrant native," Retief said. "To permit me to chum with you." "To flee before I take a cane to you!" "To have a drink together—" "To not endure such insolence!" The Groacian advanced toward Retief. Retief backed away. "To hold hands," Retief said. "To be palsy-walsy—" The Groacian reached for him, missed. A passer-by stepped around him, head down, scuttled away. Retief backed into the opening to a narrow crossway and offered further verbal familiarities to the drunken local, who followed, furious. Retief backed, rounded a corner into a narrow alley-like passage, deserted, silent ... except for the following Groacian. Retief stepped around him, seized his collar and yanked. The Groacian fell on his back. Retief stood over him. The downed native half-rose; Retief put a foot against his chest and pushed. "To not be going anywhere for a few minutes," Retief said. "To stay right here and have a nice long talk." II "There you are!" Miss Meuhl said, eyeing Retief over her lenses. "There are two gentlemen waiting to see you. Groacian gentlemen." "Government men, I imagine. Word travels fast." Retief pulled off his cape. "This saves me the trouble of paying another call at the Foreign Ministry." "What have you been doing? They seem very upset, I don't mind telling you." "I'm sure you don't. Come along. And bring an official recorder." Two Groaci wearing heavy eye-shields and elaborate crest ornaments indicative of rank rose as Retief entered the room. Neither offered a courteous snap of the mandibles, Retief noted. They were mad, all right. "I am Fith, of the Terrestrial Desk, Ministry of Foreign Affairs, Mr. Consul," the taller Groacian said, in lisping Terran. "May I present Shluh, of the Internal Police?" "Sit down, gentlemen," Retief said. They resumed their seats. Miss Meuhl hovered nervously, then sat on the edge of a comfortless chair. "Oh, it's such a pleasure—" she began. "Never mind that," Retief said. "These gentlemen didn't come here to sip tea today." "So true," Fith said. "Frankly, I have had a most disturbing report, Mr. Consul. I shall ask Shluh to recount it." He nodded to the police chief. "One hour ago," The Groacian said, "a Groacian national was brought to hospital suffering from serious contusions. Questioning of this individual revealed that he had been set upon and beaten by a foreigner. A Terrestrial, to be precise. Investigation by my department indicates that the description of the culprit closely matches that of the Terrestrial Consul." Miss Meuhl gasped audibly. "Have you ever heard," Retief said, looking steadily at Fith, "of a Terrestrial cruiser, the ISV Terrific , which dropped from sight in this sector nine years ago?" "Really!" Miss Meuhl exclaimed, rising. "I wash my hands—" "Just keep that recorder going," Retief snapped. "I'll not be a party—" "You'll do as you're told, Miss Meuhl," Retief said quietly. "I'm telling you to make an official sealed record of this conversation." Miss Meuhl sat down. Fith puffed out his throat indignantly. "You reopen an old wound, Mr. Consul. It reminds us of certain illegal treatment at Terrestrial hands—" "Hogwash," Retief said. "That tune went over with my predecessors, but it hits a sour note with me." "All our efforts," Miss Meuhl said, "to live down that terrible episode! And you—" "Terrible? I understand that a Terrestrial task force stood off Groac and sent a delegation down to ask questions. They got some funny answers, and stayed on to dig around a little. After a week they left. Somewhat annoying to the Groaci, maybe—at the most. If they were innocent." "IF!" Miss Meuhl burst out. "If, indeed!" Fith said, his weak voice trembling. "I must protest your—" "Save the protests, Fith. You have some explaining to do. And I don't think your story will be good enough." "It is for you to explain! This person who was beaten—" "Not beaten. Just rapped a few times to loosen his memory." "Then you admit—" "It worked, too. He remembered lots of things, once he put his mind to it." Fith rose; Shluh followed suit. "I shall ask for your immediate recall, Mr. Consul. Were it not for your diplomatic immunity, I should do more—" "Why did the government fall, Fith? It was just after the task force paid its visit, and before the arrival of the first Terrestrial diplomatic mission." "This is an internal matter!" Fith cried, in his faint Groacian voice. "The new regime has shown itself most amiable to you Terrestrials. It has outdone itself—" "—to keep the Terrestrial consul and his staff in the dark," Retief said. "And the same goes for the few terrestrial businessmen you've visaed. This continual round of culture; no social contacts outside the diplomatic circle; no travel permits to visit out-lying districts, or your satellite—" "Enough!" Fith's mandibles quivered in distress. "I can talk no more of this matter—" "You'll talk to me, or there'll be a task force here in five days to do the talking," Retief said. "You can't!" Miss Meuhl gasped. Retief turned a steady look on Miss Meuhl. She closed her mouth. The Groaci sat down. "Answer me this one," Retief said, looking at Shluh. "A few years back—about nine, I think—there was a little parade held here. Some curious looking creatures were captured. After being securely caged, they were exhibited to the gentle Groaci public. Hauled through the streets. Very educational, no doubt. A highly cultural show. "Funny thing about these animals. They wore clothes. They seemed to communicate with each other. Altogether it was a very amusing exhibit. "Tell me, Shluh, what happened to those six Terrestrials after the parade was over?" Fith made a choked noise and spoke rapidly to Shluh in Groacian. Shluh retracted his eyes, shrank down in his chair. Miss Meuhl opened her mouth, closed it and blinked rapidly. "How did they die?" Retief snapped. "Did you murder them, cut their throats, shoot them or bury them alive? What amusing end did you figure out for them? Research, maybe? Cut them open to see what made them yell...." "No!" Fith gasped. "I must correct this terrible false impression at once." "False impression, hell," Retief said. "They were Terrans! A simple narco-interrogation would get that out of any Groacian who saw the parade." "Yes," Fith said weakly. "It is true, they were Terrestrials. But there was no killing." "They're alive?" "Alas, no. They ... died." Miss Meuhl yelped faintly. "I see," Retief said. "They died." "We tried to keep them alive, of course. But we did not know what foods—" "Didn't take the trouble to find out, either, did you?" "They fell ill," Fith said. "One by one...." "We'll deal with that question later," Retief said. "Right now, I want more information. Where did you get them? Where did you hide the ship? What happened to the rest of the crew? Did they 'fall ill' before the big parade?" "There were no more! Absolutely, I assure you!" "Killed in the crash landing?" "No crash landing. The ship descended intact, east of the city. The ... Terrestrials ... were unharmed. Naturally, we feared them. They were strange to us. We had never before seen such beings." "Stepped off the ship with guns blazing, did they?" "Guns? No, no guns—" "They raised their hands, didn't they? Asked for help. You helped them; helped them to death." "How could we know?" Fith moaned. "How could you know a flotilla would show up in a few months looking for them, you mean? That was a shock, wasn't it? I'll bet you had a brisk time of it hiding the ship, and shutting everybody up. A close call, eh?" "We were afraid," Shluh said. "We are a simple people. We feared the strange creatures from the alien craft. We did not kill them, but we felt it was as well they ... did not survive. Then, when the warships came, we realized our error. But we feared to speak. We purged our guilty leaders, concealed what had happened, and ... offered our friendship. We invited the opening of diplomatic relations. We made a blunder, it is true, a great blunder. But we have tried to make amends...." "Where is the ship?" "The ship?" "What did you do with it? It was too big to just walk off and forget. Where is it?" The two Groacians exchanged looks. "We wish to show our contrition," Fith said. "We will show you the ship." "Miss Meuhl," Retief said. "If I don't come back in a reasonable length of time, transmit that recording to Regional Headquarters, sealed." He stood, looked at the Groaci. "Let's go," he said. Retief stooped under the heavy timbers shoring the entry to the cavern. He peered into the gloom at the curving flank of the space-burned hull. "Any lights in here?" he asked. A Groacian threw a switch. A weak bluish glow sprang up. Retief walked along the raised wooden catwalk, studying the ship. Empty emplacements gaped below lensless scanner eyes. Littered decking was visible within the half-open entry port. Near the bow the words 'IVS Terrific B7 New Terra' were lettered in bright chrome duralloy. "How did you get it in here?" Retief asked. "It was hauled here from the landing point, some nine miles distant," Fith said, his voice thinner than ever. "This is a natural crevasse. The vessel was lowered into it and roofed over." "How did you shield it so the detectors didn't pick it up?" "All here is high-grade iron ore," Fith said, waving a member. "Great veins of almost pure metal." Retief grunted. "Let's go inside." Shluh came forward with a hand-lamp. The party entered the ship. Retief clambered up a narrow companionway, glanced around the interior of the control compartment. Dust was thick on the deck, the stanchions where acceleration couches had been mounted, the empty instrument panels, the litter of sheared bolts, scraps of wire and paper. A thin frosting of rust dulled the exposed metal where cutting torches had sliced away heavy shielding. There was a faint odor of stale bedding. "The cargo compartment—" Shluh began. "I've seen enough," Retief said. Silently, the Groacians led the way back out through the tunnel and into the late afternoon sunshine. As they climbed the slope to the steam car, Fith came to Retief's side. "Indeed, I hope that this will be the end of this unfortunate affair," he said. "Now that all has been fully and honestly shown—" "You can skip all that," Retief said. "You're nine years late. The crew was still alive when the task force called, I imagine. You killed them—or let them die—rather than take the chance of admitting what you'd done." "We were at fault," Fith said abjectly. "Now we wish only friendship." "The Terrific was a heavy cruiser, about twenty thousand tons." Retief looked grimly at the slender Foreign Office official. "Where is she, Fith? I won't settle for a hundred-ton lifeboat." Fith erected his eye stalks so violently that one eye-shield fell off. "I know nothing of ... of...." He stopped. His throat vibrated rapidly as he struggled for calm. "My government can entertain no further accusations, Mr. Consul," he said at last. "I have been completely candid with you, I have overlooked your probing into matters not properly within your sphere of responsibility. My patience is at an end." "Where is that ship?" Retief rapped out. "You never learn, do you? You're still convinced you can hide the whole thing and forget it. I'm telling you you can't." "We return to the city now," Fith said. "I can do no more." "You can and you will, Fith," Retief said. "I intend to get to the truth of this matter." Fith spoke to Shluh in rapid Groacian. The police chief gestured to his four armed constables. They moved to ring Retief in. Retief eyed Fith. "Don't try it," he said. "You'll just get yourself in deeper." Fith clacked his mandibles angrily, eye stalks canted aggressively toward the Terrestrial. "Out of deference to your diplomatic status, Terrestrial, I shall ignore your insulting remarks," Fith said in his reedy voice. "Let us now return to the city." Retief looked at the four policemen. "I see your point," he said. Fith followed him into the car, sat rigidly at the far end of the seat. "I advise you to remain very close to your consulate," Fith said. "I advise you to dismiss these fancies from your mind, and to enjoy the cultural aspects of life at Groac. Especially, I should not venture out of the city, or appear overly curious about matters of concern only to the Groacian government." In the front seat, Shluh looked straight ahead. The loosely-sprung vehicle bobbed and swayed along the narrow highway. Retief listened to the rhythmic puffing of the motor and said nothing. III "Miss Meuhl," Retief said, "I want you to listen carefully to what I'm going to tell you. I have to move rapidly now, to catch the Groaci off guard." "I'm sure I don't know what you're talking about," Miss Meuhl snapped, her eyes sharp behind the heavy lenses. "If you'll listen, you may find out," Retief said. "I have no time to waste, Miss Meuhl. They won't be expecting an immediate move—I hope—and that may give me the latitude I need." "You're still determined to make an issue of that incident!" Miss Meuhl snorted. "I really can hardly blame the Groaci. They are not a sophisticated race; they had never before met aliens." "You're ready to forgive a great deal, Miss Meuhl. But it's not what happened nine years ago I'm concerned with. It's what's happening now. I've told you that it was only a lifeboat the Groaci have hidden out. Don't you understand the implication? That vessel couldn't have come far. The cruiser itself must be somewhere near by. I want to know where!" "The Groaci don't know. They're a very cultured, gentle people. You can do irreparable harm to the reputation of Terrestrials if you insist—" "That's my decision," Retief said. "I have a job to do and we're wasting time." He crossed the room to his desk, opened a drawer and took out a slim-barreled needler. "This office is being watched. Not very efficiently, if I know the Groaci. I think I can get past them all right." "Where are you going with ... that?" Miss Meuhl stared at the needler. "What in the world—" "The Groaci won't waste any time destroying every piece of paper in their files relating to this thing. I have to get what I need before it's too late. If I wait for an official Inquiry Commission, they'll find nothing but blank smiles." "You're out of your mind!" Miss Meuhl stood up, quivering with indignation. "You're like a ... a...." "You and I are in a tight spot, Miss Meuhl. The logical next move for the Groaci is to dispose of both of us. We're the only ones who know what happened. Fith almost did the job this afternoon, but I bluffed him out—for the moment." Miss Meuhl emitted a shrill laugh. "Your fantasies are getting the better of you," she gasped. "In danger, indeed! Disposing of me! I've never heard anything so ridiculous." "Stay in this office. Close and safe-lock the door. You've got food and water in the dispenser. I suggest you stock up, before they shut the supply down. Don't let anyone in, on any pretext whatever. I'll keep in touch with you via hand-phone." "What are you planning to do?" "If I don't make it back here, transmit the sealed record of this afternoon's conversation, along with the information I've given you. Beam it through on a mayday priority. Then tell the Groaci what you've done and sit tight. I think you'll be all right. It won't be easy to blast in here and anyway, they won't make things worse by killing you. A force can be here in a week." "I'll do nothing of the sort! The Groaci are very fond of me! You ... Johnny-come-lately! Roughneck! Setting out to destroy—" "Blame it on me if it will make you feel any better," Retief said, "but don't be fool enough to trust them." He pulled on a cape, opened the door. "I'll be back in a couple of hours," he said. Miss Meuhl stared after him silently as he closed the door. It was an hour before dawn when Retief keyed the combination to the safe-lock and stepped into the darkened consular office. He looked tired. Miss Meuhl, dozing in a chair, awoke with a start. She looked at Retief, rose and snapped on a light, turned to stare. "What in the world—Where have you been? What's happened to your clothing?" "I got a little dirty. Don't worry about it." Retief went to his desk, opened a drawer and replaced the needler. "Where have you been?" Miss Meuhl demanded. "I stayed here—" "I'm glad you did," Retief said. "I hope you piled up a supply of food and water from the dispenser, too. We'll be holed up here for a week, at least." He jotted figures on a pad. "Warm up the official sender. I have a long transmission for Regional Headquarters." "Are you going to tell me where you've been?" "I have a message to get off first, Miss Meuhl," Retief said sharply. "I've been to the Foreign Ministry," he added. "I'll tell you all about it later." "At this hour? There's no one there...." "Exactly." Miss Meuhl gasped. "You mean you broke in? You burgled the Foreign Office?" "That's right," Retief said calmly. "Now—" "This is absolutely the end!" Miss Meuhl said. "Thank heaven I've already—" "Get that sender going, woman!" Retief snapped. "This is important." "I've already done so, Mr. Retief!" Miss Meuhl said harshly. "I've been waiting for you to come back here...." She turned to the communicator, flipped levers. The screen snapped aglow, and a wavering long-distance image appeared. "He's here now," Miss Meuhl said to the screen. She looked at Retief triumphantly. "That's good," Retief said. "I don't think the Groaci can knock us off the air, but—" "I have done my duty, Mr. Retief," Miss Meuhl said. "I made a full report to Regional Headquarters last night, as soon as you left this office. Any doubts I may have had as to the rightness of that decision have been completely dispelled by what you've just told me." Retief looked at her levelly. "You've been a busy girl, Miss Meuhl. Did you mention the six Terrestrials who were killed here?" "That had no bearing on the matter of your wild behavior! I must say, in all my years in the Corps, I've never encountered a personality less suited to diplomatic work." The screen crackled, the ten-second transmission lag having elapsed. "Mr. Retief," the face on the screen said, "I am Counsellor Pardy, DSO-1, Deputy Under-secretary for the region. I have received a report on your conduct which makes it mandatory for me to relieve you administratively, vice Miss Yolanda Meuhl, DAO-9. Pending the findings of a Board of Inquiry, you will—" Retief reached out and snapped off the communicator. The triumphant look faded from Miss Meuhl's face. "Why, what is the meaning—" "If I'd listened any longer, I might have heard something I couldn't ignore. I can't afford that, at this moment. Listen, Miss Meuhl," Retief went on earnestly, "I've found the missing cruiser." "You heard him relieve you!" "I heard him say he was going to, Miss Meuhl. But until I've heard and acknowledged a verbal order, it has no force. If I'm wrong, he'll get my resignation. If I'm right, that suspension would be embarrassing all around." "You're defying lawful authority! I'm in charge here now." Miss Meuhl stepped to the local communicator. "I'm going to report this terrible thing to the Groaci at once, and offer my profound—" "Don't touch that screen," Retief said. "You go sit in that corner where I can keep an eye on you. I'm going to make a sealed tape for transmission to Headquarters, along with a call for an armed task force. Then we'll settle down to wait." Retief ignored Miss Meuhl's fury as he spoke into the recorder. The local communicator chimed. Miss Meuhl jumped up, staring at it. "Go ahead," Retief said. "Answer it." A Groacian official appeared on the screen. "Yolanda Meuhl," he said without preamble, "for the Foreign Minister of the Groacian Autonomy, I herewith accredit you as Terrestrial Consul to Groac, in accordance with the advices transmitted to my government direct from the Terrestrial Headquarters. As consul, you are requested to make available for questioning Mr. J. Retief, former consul, in connection with the assault on two peace keepers and illegal entry into the offices of the Ministry for Foreign Affairs." "Why, why," Miss Meuhl stammered. "Yes, of course. And I do want to express my deepest regrets—" Retief rose, went to the communicator, assisted Miss Meuhl aside. "Listen carefully, Fith," he said. "Your bluff has been called. You don't come in and we don't come out. Your camouflage worked for nine years, but it's all over now. I suggest you keep your heads and resist the temptation to make matters worse than they are." "Miss Meuhl," Fith said, "a peace squad waits outside your consulate. It is clear you are in the hands of a dangerous lunatic. As always, the Groaci wish only friendship with the Terrestrials, but—" "Don't bother," Retief said. "You know what was in those files I looked over this morning." Retief turned at a sound behind him. Miss Meuhl was at the door, reaching for the safe-lock release.... "Don't!" Retief jumped—too late. The door burst inward. A crowd of crested Groaci pressed into the room, pushed Miss Meuhl back, aimed scatter guns at Retief. Police Chief Shluh pushed forward. "Attempt no violence, Terrestrial," he said. "I cannot promise to restrain my men." "You're violating Terrestrial territory, Shluh," Retief said steadily. "I suggest you move back out the same way you came in." "I invited them here," Miss Meuhl spoke up. "They are here at my express wish." "Are they? Are you sure you meant to go this far, Miss Meuhl? A squad of armed Groaci in the consulate?" "You are the consul, Miss Yolanda Meuhl," Shluh said. "Would it not be best if we removed this deranged person to a place of safety?" "You're making a serious mistake, Shluh," Retief said. "Yes," Miss Meuhl said. "You're quite right, Mr. Shluh. Please escort Mr. Retief to his quarters in this building—" "I don't advise you to violate my diplomatic immunity, Fith," Retief said. "As chief of mission," Miss Meuhl said quickly, "I hereby waive immunity in the case of Mr. Retief." Shluh produced a hand recorder. "Kindly repeat your statement, Madam, officially," he said. "I wish no question to arise later." "Don't be a fool, woman," Retief said. "Don't you see what you're letting yourself in for? This would be a hell of a good time for you to figure out whose side you're on." "I'm on the side of common decency!" "You've been taken in. These people are concealing—" "You think all women are fools, don't you, Mr. Retief?" She turned to the police chief and spoke into the microphone he held up. "That's an illegal waiver," Retief said. "I'm consul here, whatever rumors you've heard. This thing's coming out into the open, whatever you do. Don't add violation of the Consulate to the list of Groacian atrocities." "Take the man," Shluh said.
|
A. Retief believes the cruiser they show him is a decoy. The real missing cruiser was at least twenty-tons, which is much larger than the ship the Groacians reveal.
|
As per Mrs. Mayer's surgical report, what complication was encountered during the VAC change?
Choose the correct answer from the following options:
A. Hemorrhage
B. Infection
C. Extracapsular spread of the tumor
D. Adhesion formation
E. Anaphylactic reaction to anesthesia
|
### Patient Report 0
**Dear colleague, **
We report to you about Mrs. Linda Mayer, born on 01/12/1948, who
presented to our outpatient clinic on 07/13/19.
**Diagnoses:**
- BIRADS IV, recommended biopsy during breast diagnostics.
- Left breast carcinoma: iT1b; iN0; MX; ER: 12/12; PR: 2/12; Her-2:
neg; Ki67: 15%.
**Other Diagnoses: **
- Status post apoplexy
- Status post cataract surgery
- Status post right hip total hip replacement (THR)
- Pemphigus vulgaris under azathioprine therapy
- Osteoporosis
- Obesity with a BMI of 35
- Undergoing immunosuppressive therapy with prednisolone
**Family History:**
- Sister deceased at age 39 from breast cancer.
- Mother and grandmother (maternal and paternal) were diagnosed with
breast cancer.
**Medical History:** The CT thorax report indicates the presence of
inflammatory foci, warranting further follow-up. The relevant data was
documented and presented during the tumor conference. Subsequently, a
telephone conversation was conducted with the patient to discuss the
next steps.
**Tumor board decision from 07/13/2019:**
**Imaging: **
1) MRI examination detected a unifocal lesion on the left external
aspect, measuring approximately 2.4 cm in size.
2) CT scan (thorax/abdomen 07/12/2019) revealed a previously known
liver lesion, likely a hemangioma. No evidence of metastases was
identified. Nonspecific, small foci were observed in the lungs,
likely indicative of post-inflammatory changes.
**Recommendations:**
1. If no metastasis (M0): Fast-track BRCA testing is recommended.
2. If BRCA testing returns negative: Proceed with a selective excision
of the left breast after ultrasound-guided fine needle marking and
sentinel lymph node biopsy on the left side. Additionally, perform
Endopredict analysis on the surgical specimen.
**Current Medication: **
**Medication** **Dosage** **Route** **Frequency**
------------------------------- ------------ ----------- ---------------
Aspirin 100mg Oral 1-0-0
Simvastatin (Zocor) 40mg Oral 0-1-0
Haloperidol (Haldol) 100mg Oral ½-0-½
Zopiclone (Imovane) 7.5mg Oral 0-0-1
Trazodone (Desyrel) 100mg Oral 0-0-½-
Calcium Supplement (Caltrate) 500mg Oral 1-0-1
Nystatin (Bio-Statin) As advised Oral 1-1-1-1
Pantoprazole (Protonix) 40mg Oral 1-0-0
Prednisolone (Prelone) 40mg Oral As advised
Tramadol/Naloxone (Ultram) 50/4mg Oral 1-0-1
Acyclovir (Zovirax) 800mg Oral 1-1-1
**Mammography and Tomosynthesis from 07/8/2019:**
[Findings]{.underline}**: **During the inspection and palpation, no
significant findings were noted on either side. Some areas with higher
mammographic density were observed, which slightly limited the
assessment. However, during the initial examination, a small
architectural irregularity was identified on the outer left side. This
irregularity appeared as a small, roundish compression measuring
approximately 6mm and was visible only in the medio-lateral oblique
image, with a nipple distance of 8cm. Apart from this discovery, there
were no other suspicious focal findings on either side. No clustered or
irregular microcalcifications were detected. Additionally, a long-term,
unchanged observation noted some asymmetry with denser breast tissue
present on both sides, particularly on the outer aspects. Sonographic
evaluation posed challenges due to the mixed echogenic glandular tissue.
As a possible corresponding feature to the questionable architectural
irregularity on the outer left side, a blurred, echo-poor area with a
vertical alignment measuring about 7x5mm was identified. Importantly, no
other suspicious focal findings were observed, and there was no evidence
of enlarged lymph nodes in the axilla on both sides.
[Assessment]{.underline}**:** The observed finding on the left side
presents an uncertain nature, categorized as BIRADS IVb. In contrast,
the finding on the right side appears benign, categorized as BIRADS II.
To gain a more conclusive understanding of the left-sided finding, we
recommend a histological assessment through a sonographically guided
high-speed punch biopsy. An appointment has been scheduled with the
patient to proceed with this biopsy and obtain a definitive
diagnosis.Formularbeginn
Formularende**Current Recommendations:**\
A fast-track decision will be made regarding tumor genetics, and the
patient will be notified of the appointment via telephone. The patient
should bring the pathology blocks from Fairview Clinic on the day of
blood collection for genetic testing, along with a referral for an
Endopredict test. A multidisciplinary team meeting will be convened
after the Endopredict test and genetic testing results are available. If
there is persistence or worsening of symptoms, we strongly advise the
patient to seek immediate re-evaluation. Additionally, outside of
regular office hours, the patient can seek assistance at the emergency
care unit in case of emergency.
**MRI from 07/11/2019:**
[Technique:]{.underline} Breast MRI (3T scanner) with dedicated mammary
surface coil:
[Findings:]{.underline} The overall contrast enhancement was observed
bilaterally to evaluate the Grade II findings. There was low to moderate
small-spotted contrast enhancement with slightly limited assessability.
The contrast dynamics revealed a patchy, confluent, blurred, and
elongated contrast enhancement, corresponding to the primary lesion,
which measured approximately 2.4 cm on the lower left exterior. Single
spicules were noted, and the lesion appeared hypointense in T1w imaging.
No suspicious focal findings with contrast enhancement were detected on
the right side. Small axillary lymph nodes were observed on the left
side, but they did not appear suspicious based on MR morphology.
Additionally, there were no suspicious lymph nodes on the right side.
[Assessment:]{.underline} An unifocal primary lesion measuring
approximately 2.4 cm in diameter was identified on the lower left
exterior. It exhibited patchy confluent enhancement and architectural
disturbance, with single spicules. No evidence of suspicious lymph nodes
was found. The left side is categorized as BIRADS 6, indicating a high
suspicion of malignancy, while the right side is categorized as BIRADS
2, indicating a benign finding.
### Patient Report 1
**Dear colleague, **
We are writing to provide you with an update on the medical condition of
Mrs. Linda Mayer, born on 01/12/1948, who attended our outpatient clinic
on 08/02/2019.
**Diagnoses:**
- Vacuum-assisted biopsy-confirmed ductal carcinoma in situ (DCIS) of
the right breast (17mm)
- Histological grade G3, estrogen receptor (ER) and progesterone
receptor (PR) negative.
- Postmenopausal for the past eight years.
- Previous surgical history includes an appendectomy.
- Allergies: Hay fever
**Current Presentation**: The patient sought consultation following a
confirmed diagnosis of DCIS (Ductal Carcinoma In Situ) in the right
breast, which was determined through a vacuum-assisted biopsy.
**Physical Examination**: Upon physical examination, there is evidence
of a post-intervention hematoma located in the upper right quadrant of
the right breast. However, the clip from the biopsy is not clearly
visible. A sonographic examination of the right axilla reveals no
abnormalities.
**Current Recommendations:**
- Imaging studies have been conducted.
- A case presentation is scheduled for our mammary conference
tomorrow.
- Subsequently, planning for surgery will commence, including the
evaluation of sentinel lymph nodes following a right mastectomy and
axillary lymph node dissection.
### Patient Report 2
**Dear colleague, **
We are writing to provide an update regarding Mrs. Linda Mayer, born on
01/12/1948, who received outpatient care at our facility on 08/29/2019.
**Diagnoses:**
- Vacuum-assisted biopsy-confirmed ductal carcinoma in situ (DCIS) of
the right breast, measuring 17mm in size, classified as Grade 3, and
testing negative for estrogen receptors (ER) and progesterone
receptors (PR).
- Mrs. Mayer has been postmenopausal for eight years.
- Notable allergy: Hay fever
**Tumor Board Decision:** Mammography imaging revealed a clip associated
with a focal finding in the right breast adjacent to calcifications.
[Recommendation]{.underline}: Proceed with sentinel lymph node
evaluation after right mastectomy, including clip localization on the
right side.
**Current Presentation**: During the patient\'s recent outpatient visit,
an extensive pre-operative consultation was conducted. This discussion
covered the indications for the surgery, details of the surgical
process, potential alternative options, as well as general and specific
risks associated with the procedure. These risks included the
possibility of an aesthetically suboptimal outcome and the chance of
encountering an R1 situation. The patient did not have any further
questions and provided written consent for the procedure.
**Physical Examination:** Both breasts appear normal upon inspection and
palpation. The right axilla shows no abnormalities.
**Medical History:** Mrs. Linda Mayer presented to our clinic with a
vacuum biopsy-confirmed DCIS of the right breast for therapeutic
intervention. The decision for surgery was reached following a
comprehensive review by our interdisciplinary breast board. After an
extensive discussion of the procedure\'s scope, associated risks, and
alternative options, the patient provided informed consent for the
proposed surgery.
**Preoperative Procedure:** Sonographic and mammographic fine needle
marking of the remaining findings and the clip in the right breast.
**Surgical Report:** Team time-out conducted with colleagues of
anesthesia. Patient positioned in the supine position. Surgical site
disinfection and sterile draping. Marking of the incision site.
A semicircular incision was made laterally on the right breast.
Visualization and dissection along the marking wire towards the marked
finding. Excision of the marked findings, with a safety margin of
approximately 1-2 cm. The excised specimen measured approximately 4 x 5
x 3 cm. Markings using standard protocol (green thread cranially, blue
thread ventrally). The excised specimen was sent for preparation
radiography. Hemostasis was meticulously ensured. Insertion of a 10Ch
Blake drain into the segmental cavity, followed by suturing.
Verification of a blood-dry wound cavity. Preparation radiography
included the marked area and the marking wires. The excised material was
transferred to our pathology colleagues for histological examination.
Subdermal and intracutaneous sutures with Monocryl 3/0 in a continuous
manner. Application of Steristrips and dressing. Instruments, swabs, and
cloths were accounted for per the nurse\'s checklist. The patient was
correctly positioned throughout the operation. The anesthesiologic
course was without significant problems. A thorax compression bandage
was applied in the operating room as a preventive measure against
bleeding.
**Postoperative Procedure:** Pain management, thrombosis prophylaxis,
application of a pressure dressing, drainage under suction.
**Examinations:** **Digital Mammography performed on 08/29/2019**
[Clinical indication]{.underline}: DCIS right
[Question]{.underline}: Please send specimen + Mx-FNM
**Findings**: Sonographically guided wire marking of the maximum
microcalcification group measuring about 12 mm. Local hematoma cavity
and inset clip marking directly cranial to the finding. Stitch direction
from lateral to medial. The wire is positioned with the tip caudal to
the clip in close proximity to the microcalcification. Additional
marking of the focal localization on the skin. Documentation of the wire
course in two planes.
- Telephone discussion of findings with the surgeon.
- Preparation radiography and preparation sonography are recommended.
- Marking wire and suspicious focal findings centrally included in the
preparation.
- Intraoperative report of findings has been conveyed to the surgeon.
**Current Recommendations:**
- Scheduled for inpatient admission on ward 22 tomorrow.
- Right breast mastectomy with sentinel lymph node evaluation.
### Patient Report 3
**Dear colleague, **
We are writing to update you on the clinical course of Mrs. Linda Mayer,
born on 01/12/1948, who was under our inpatient care from 08/30/2019 to
09/12/2019.
**Diagnosis:** Vacuum-assisted biopsy confirmed Ductal Carcinoma In Situ
(DCIS) in the right breast, measuring 17mm, Grade 3, ER/PR negative.
**Tumor Board Decision (07/13/2019):**
[Imaging:]{.underline} Clip identified in focal lesion in the right
breast, adjacent to calcifications.
[Recommendation]{.underline}**:** Spin Echo following fine-needle
localization with mammography-guided control of the clip in the right
breast.
[Subsequent Recommendation (08/27/2019):]{.underline} Radiation therapy
to the right breast. Regular follow-up is advised.
**Medical History:** Ms. Linda Mayer presented to our facility on
08/30/2019 for the aforementioned surgical procedure. After a
comprehensive discussion regarding the surgical plan, potential risks,
and possible complications, the patient consented to proceed. The
surgery was executed without complications on 09/01/2019. The
postoperative course was unremarkable, allowing for Ms. Mayer\'s
discharge on 09/12/2019 in stable condition and with no signs of wound
irritation.
**Histopathological Findings (09/01/2019):**
The resected segment from the right breast showed a maximum necrotic
zone of 1.6 cm with foreign body reaction, chronic resorptive
inflammation, fibrosis, and residual hemorrhage. These findings
primarily correspond to the pre-biopsy site. Surrounding this were areas
of DCIS with solid and cribriform growth patterns and comedonecrosis,
WHO Grade 3, Nuclear Grade 3, with a reconstructed extent of 3.5 cm.
Resection margins were as follows: ventral 0.15 cm, caudal 0.2 cm,
dorsal 0.4 cm, with remaining margins exceeding 0.5 cm. TNM
Classification (8th Edition, 2017): pTis (DCIS), R0, G3. Additional
immunohistochemical studies are underway to determine hormone receptor
status; a supplementary report will follow.
**Postoperative Plan:**
The patient was educated on standard postoperative care and the
importance of immediate re-evaluation for any persistent or worsening
symptoms. Radiation therapy to the right breast is planned, along with
regular follow-up appointments.
Should you have any questions or require further clarification, we are
readily available. For urgent concerns outside of regular office hours,
emergency care is available at the Emergency Department.
**Internal Histopathological Findings Report**
**Clinical Data:** DCIS in the right breast (17 mm), Grade 3, ER/PR
negative.
**Macroscopic Examination:**
The resected mammary segment from the right breast, marked with dual
threads and containing a fine-needle marker inserted ventro-laterally,
measures 4.5 x 5.5 x 3 cm (HxWxD) and weighs 35 grams. The specimen was
sectioned from medial to lateral into 14 lamellae. The cut surface
predominantly shows yellowish, lobulated mammary parenchyma with sparse
striated whitish glandular components. A DCIS-suspected area, up to 2.1
cm in size, is evident caudally and centro-ventrally (from lamellae
4-10), displaying both reddish-hemorrhagic and whitish-nodular
indurations. Minimal distances from the suspicious area to the resection
margins are as follows: cranial 2 cm, caudal 0.2 cm, dorsal 0.2 cm,
ventral 0.1 cm, medial 1.6 cm, lateral 2.5 cm. The suspect area was
completely embedded. Ink markings: green/cranial, yellow/caudal,
blue/ventral, black/dorsal.
**Microscopic Examination:**
Histological sections of the mammary parenchyma reveal fibro-lipomatous
stroma and glandular lobules with a two-layered epithelial lining. In
lamellae 3-6 and 11, solid and cribriform epithelial proliferations are
evident. Cells are cuboidal with variably enlarged, predominantly
moderately pleomorphic, round to oval nuclei. Comedo-like necroses are
occasionally observed in secondary lumina. Microscopic distances to the
deposition margins are consistent with the macroscopic findings. The
surrounding stroma in lamellae 6-9 shows extensive geographic adipose
tissue necrosis, multinucleated foreign body-type giant cells, foamy
cell macrophages, collagen fiber proliferation, and fresh hemorrhages.
**Supplemental Immunohistochemical Findings
(09/04/2019):** **Microscopy:** In the meantime, the material was
further processed as announced.
Here, the previously described intraductal epithelial growths, each with
negative staining reaction for the estrogen and progesterone receptor
(with regular external and internal control reaction).
**Critical Findings:**
Resected mammary segment with paracentral, max. 1.6 cm necrotic zone
with foreign body reaction, chronic resorptive. Chronic resorptive
inflammation, fibrosis, and hemorrhage remnants (primarily corresponding
to the pre-biopsy site), and surrounding portions of ductal carcinoma in
situ. Ductal carcinoma in situ, solid and rib-shaped growth type with
comedonecrosis, WHO grade 3, nuclear grade 3. The resection was locally
complete with the following Safety margins: ventral 0.15 cm, caudal 0.2
cm, dorsal 0.4 cm, and the remaining sedimentation margins more than 0.5
cm.
TNM classification (8th edition 2017): pTis (DCIS), R0, G3.
[Hormone receptor status:]{.underline}
- Estrogen receptor: negative (0%).
- Progesterone receptor: negative (0%).
### Patient Report 4
**Dear colleague, **
We are writing to provide an update regarding Mrs. Linda Mayer, born on
01/12/1948, who received outpatient treatment on 27/09/2019.
**Diagnoses**: Left breast carcinoma; iT1c; iN0; MX; ER:12/12; PR:2/12;
Her-2: neg; Ki67:15%, BRCA 2 mutation.
**Other Diagnoses**:
- Hailey-Hailey disease - currently regressing under prednisolone.
- History of apoplexy in 2016 with no residuals
- Depressive episodes
- Right hip total hip replacement
- History of left adnexectomy in 1980 due to extrauterine pregnancy
- Tubal sterilization in 1988.
- Uterine curettage (Abrasio) in 2004
- Hysterectomy in 2005
**Allergies**: Hay fever
**Imaging**:
- CT revealed a cystic lesion in the liver, not suspicious for
metastasis. Granulomatous, post-inflammatory changes in the lung.
- An MRI of the left breast showed a unifocal lesion on the outer left
side with a 2.4 cm extension.
**Histology: **Gene score of 6.5, indicating a high-risk profile (pT2 or
pN1) if BRCA negative.
**Recommendation**: If BRCA negative, SE left mamma after ultrasound-FNM
with correlation in Mx and SLNB on the left.
**Current Presentation**: Mrs. Linda Mayer presented for pre-operative
evaluation for left mastectomy. BRCA testing confirmed a BRCA2 mutation,
warranting bilateral subcutaneous mastectomy and SLNB on the left.
Reconstruction with implants and mesh is planned, along with a breast
lift as requested by the patient.
**Macroscopy:**
**Left Subcutaneous Mastectomy (Blue/Ventral, Green/Cranial):**
- Specimen Size: 17 x 15 x 6 cm (Height x Width x Depth), Weight: 410
g
- Description: Dual filament-labeled subcutaneous mastectomy specimen
- Specimen Workup: 27 lamellae from lateral to medial
- Tumor-Suspect Area (Lamellae 17-21): Max. 1.6 cm, white dermal,
partly blurred
- Margins from Tumor Area: Ventral 0.1 cm, Caudal 1 cm, Dorsal 1.2 cm,
Cranial \> 5 cm, Lateral \> 5 cm, Medial \> 2 cm
- Remaining Mammary Parenchyma: Predominantly yellowish lipomatous
with focal nodular appearance
- Ink Markings: Cranial/Green, Caudal/Yellow, Ventral/Blue,
Dorsal/Black
- A: Lamella 17 - Covers dorsal and caudal
- B: Lamella 18 - Covers ventral
- C: Lamella 19 - Covers ventral
- D: Blade 21 - Covers ventral
- E: Lamella 20 - Reference cranial
- F: Lamella 16 - Immediately laterally following mammary
parenchyma
- G: Blade 22 - Reference immediately medial following mammary
tissue
- H: Lamella 12 - Central section
- I: Lamella 8 - Documented section top/outside
- J: Lamella 3 - Vestigial section below/outside
- K: Lamella 21 - White-nodular imposing area
- L: Lamella 8 - Further section below/outside with nodular area
- M: Lateral border lamella perpendicularly
- N: Medial border lamella perpendicular (Exemplary)
**Second Sentinel Lymph Node on the Left:**
- Specimen: Maximum of 6 cm of fat tissue resectate with 1 to 2 cm of
lymph nodes and smaller nodular indurations.
- A, B: One lymph node each divided
- C: Further nodular indurations
**Palpable Lymph Nodes Level I:**
- Specimen: One max. 4.5 cm large fat resectate with nodular
indurations up to 1.5 cm in size
- A: One nodular induration divided
- B: Further nodular indurated portions
**Right Subcutaneous Mastectomy:**
- Specimen: Double thread-labeled 450 g subcutaneous mastectomy
specimen
- Assumed Suture Markings: Blue (Ventral) and Green (Cranial)
- Dorsal Fascia Intact
- [Specimen Preparation:]{.underline} 16 lamellae from medial to
lateral
- Predominantly yellowish lobulated with streaky, beige, impinging
strands of tissue
- Isolated hemorrhages in the parenchyma
- Ink Markings: Green = Cranial, Yellow = Caudal, Blue = Ventral,
Black = Dorsal
<!-- -->
- A: Medial border lamella perpendicular (Exemplary)
- B: Lamella 5 with reference ventrally (below inside)
- C: Lamella 8 with reference ventrally (below inside)
- D: Lamella 6 with ventral and dorsal reference (upper inside)
- E: Blade 8 with ventral and dorsal cover (top inside)
- F: Blade 11 with cover dorsal and caudal (bottom outside)
- G: Blade 13 with dorsal cover (bottom outside)
- H: Blade 10 with ventral and dorsal cover (top outside)
- I: Lamella 14 with reference cranial and dorsal and bleeding in
(upper outer)
- J: Lateral border lamella perpendicular (Exemplary)
**Microscopy:**
1\) In the tumor-suspicious area, a blurred large fibrosis zone with
star-shaped extensions is visible. Intercalated are single-cell and
stranded epithelial cells with a high nuclear-cytoplasmic ratio. The
nuclei are monomorphic with finely dispersed chromatin, at most, very
isolated mitoses. Adjacent distended glandular ducts with a discohesive
cell proliferate with the same cytomorphology. Sporadically, preexistent
glandular ducts are sheared disc-like by the infiltrative tumor cells.
Samples from the nodular area of lamella 21 show areas of cell-poor
hyaline sclerosis with partly ectatically dilated glandular ducts.
2\) Second lymph node with partial infiltrates of the neoplasia described
above. The cells here are relatively densely packed. Somewhat increased
mitoses. In the lymph nodes, iron deposition is also in the sinus
histiocytes.
3\) Lymph nodes with partly sparse iron deposition. No epithelial foreign
infiltrates.
4\) Regular mammary gland parenchyma. No tumor infiltrates. Part of the
glandular ducts are slightly cystically dilated.
**Preliminary Critical Findings Report: **
Left breast carcinoma measuring max 1.6 cm diagnosed as moderately
differentiated invasive lobular carcinoma, B.R.E. score 6 (3+2+1, G2).
Presence of tumor-associated and peritumoral lobular carcinoma in situ.
Resection status indicates locally complete excision of both invasive
and non-invasive carcinoma; minimal margins as follows: ventral \<0.1
cm, caudal 0.2 cm, dorsal 0.8 cm, remaining margins ≥0.5 cm. Nodal
status reveals max 0.25 cm metastasis in 1/5 nodes, 0/2 additional
nodes, without extracapsular spread. Right mammary gland from
subcutaneous mastectomy shows tumor-free parenchyma.
**TNM classification (8th ed. 2017):** pT1c, pTis (LCIS), pN1a, G2, L0,
V0, Pn0, R0. Investigations to determine tumor biology were initiated.
Addendum follows.
**Supplementary findings on 10/07/2019**
Editing: immunohistochemistry:** **
Estrogen receptor, Progesterone receptor, Her2neu, MIB-1 (block 1D).
**Critical Findings Report:** Breast carcinoma on the left with a 1.6 cm
invasive lobular carcinoma, moderately differentiated, with a B.R.E.
score of 6 (3+2+1, G2). Additionally, tumor-associated and peritumoral
lobular carcinoma in situ are noted. Resection status confirms locally
complete excision of both invasive and non-invasive carcinomas; minimal
resection margins are ventral \<0.1 cm, caudal (LCIS) 0.2 cm, dorsal 0.8
cm, and all other margins ≥0.5 cm. Nodal assessment reveals a single
metastasis with a maximum dimension of 0.25 cm among 7 lymph nodes,
specifically found in 1/5 nodes, with no additional metastasis in 0/2
nodes and no extracapsular extension. Contralateral right mammary gland
from subcutaneous mastectomy is tumor-free.
Tumor biology of the invasive carcinoma demonstrates strong positive
estrogen receptor expression in 100% of tumor cells, strong positive
progesterone receptor expression in 1% of tumor cells, negative HER2/neu
status (Score 1+), and a Ki67 (MIB-1) proliferation index of 25%.
**TNM classification (8th Edition 2017):** pT1c, pTis (LCIS), pN1a (1/7
ECE-, sn), G2, L0, V0, Pn0, R0.
**Surgery Report (Vac Change + Irrigation)**: Indication for VAC change.
After a detailed explanation of the procedure, its risks, and
alternatives, the patient agrees to the proposed procedure.
The course of surgery: Proper positioning in a supine position. Removal
of the VAC sponge. A foul odor appears from the wound cavity. Careful
disinfection of the surgical area. Sterile draping. Detailed inspection
of the wound conditions. Wound debridement with removal of fibrin
coatings and freshening of the wound. Resection of necrotic material in
places with sharp spoon. Followed by extensive Irrigation of the entire
wound bed and wound edges using 1 l Polyhexanide solution. Renewed VAC
sponge application according to standard.
**Postoperative procedure**: Pain medication, thrombosis prophylaxis,
continuation of antibiotic therapy. In the case of abundant
Staphylococcus aureus and isolated Pseudomosas in the smear and still
clinical suspected infection, extension of antibiotic treatment to
Meropenem.
**Surgery Report: Implant Placement**
**Type of Surgery:** Implant placement and wound closure.
**Report:** After infection and VAC therapy, clean smears and planning
of reinsertion. Informed consent. Intraoperative consults: Anesthesia.
**Course of Surgery:** Team time out. Removal VAC sponge. Disinfection
and covering. Irrigation of the wound cavity with Serasept. Blust
irrigation. Fixation cranially and laterally with 4 fixation sutures
with Vircryl 2-0. Choice of trial implant. Temporary insertion. Control
in sitting and lying positions. Choice of the implant. Repeated
disinfection. Change of gloves. Insertion of the implant into the
pocket. Careful hemostasis. Insertion of a Blake drain into the wound
cavity. Suturing of the drainage. Subcutaneous sutures with Monocryl
3-0.
**Type of Surgery:** Prophylactic open Laparoscopy, extensive
adhesiolysis
**Type of Anesthesia:** ITN
**Report:** Patient presented for prophylactic right adnexectomy in the
course of hysterectomy and left adnexectomy due to genetic burden.
Intraoperatively, secondary wound closure was to be performed in the
case of a right mammary wound weeping more than one year
postoperatively. The patient agreed to the planned procedure in writing
after receiving detailed information about the extent, the risks, and
the alternatives.
**Course of the Operation:** Team time out with anesthesia colleagues.
Flat lithotomy positioning, disinfection, and sterile draping. Placement
of permanent transurethral catheter. Subumbilical incision and
dissection onto the fascia. Opening of the fascia and suturing of the
same. Exposure of the peritoneum and opening of the same. Insertion of
the 10-mm optic trocar. Insertion of three additional trocars into the
lower abdomen (left and center right, each 5mm; right 10mm). The
following situation is seen: when the camera is inserted from the
umbilical region, an extensive adhesion is seen. Only by changing the
camera to the right lower bay is extensive adhesiolysis possible. The
omentum is fused with the peritoneum and the serosa of the uterus. Upper
abdomen as far as visible inconspicuous.
After hysterectomy and adnexectomy on the left side, adnexa on the right
side atrophic and inconspicuous. The peritoneum is smooth as far as can
be seen.
Visualization of the right adnexa and the suspensory ligament of ovary.
Coagulation of the suspensory ligament of ovary ligament after
visualization of the ureter on the same side. Stepwise dissection of the
adnexa from the pelvic wall.
Recovery via endobag. Hemostasis. Inspection of the situs.
Removal of instrumentation under vision and draining of
pneumoperitoneum.
Closure of the abdominal fascia at the umbilicus and right lower
abdomen. Suturing of the skin with Monocryl 3/0. Compression bandage at
each trocar insertion site. Inspection of the right mamma. In the area
of the surgical scar laterally/externally, 2-3 small epithelium-lined
pore-like openings are visible; here, on pressure, discharge of rather
viscous/sebaceous, non-odorous, or purulent fluid. No dehiscence is
visible, suspected. fistula ducts to the implant cavity. After
consultation with the mamma surgeon, a two-stage procedure was planned
for the treatment of the fistula tracts. Correct positioning and
inconspicuous anesthesiological course. Instrumentation, swabs, and
cloths complete according to the operating room nurse. Postoperative
procedures include analgesia, mobilization, thrombosis prophylaxis, and
waiting for histology.
**Internal Histopathological Report**
[Clinical information/question]{.underline}: Fistula formation mammary
right. Dignity?
[Macroscopy]{.underline}**:** Skin spindle from scar mammary right: fix.
a 2.4 cm long, stranded skin-subcutaneous excidate. Lamellation and
complete embedding.
[Processing]{.underline}**:** 1 block, HE
[Microscopy]{.underline}**:** Histologic skin/subcutaneous
cross-sections with overlay by a multilayered keratinizing squamous
epithelium. The dermis with few inset regular skin adnexal structures,
sparse to moderately dense mononuclear-dominated inflammatory
infiltrates, and proliferation of cell-poor, fiber-rich collagenous
connective tissue.
**Critical Findings Report:**
Skin spindle on scar mamma right: skin/subcutaneous resectate with
fibrosis and chronic inflammation. To ensure that all findings are
recorded, the material will be further processed. A follow-up report
will follow.
[Microscopy]{.underline}**:** In the meantime, the material was further
processed as announced. The van Gieson stain showed extensive
proliferation of collagenous and, in some places elastic fibers. Also in
the additional immunohistochemical staining against no evidence of
atypical epithelial infiltrates.
**Lab results upon Discharge:**
**Parameter** **Results** **Reference Range**
-------------------------------- ------------- ---------------------
Sodium 141 mEq/L 132-146 mEq/L
Potassium 4.2 mEq/L 3.4-4.5 mEq/L
Creatinine 0.82 mg/dL 0.50-0.90 mg/dL
Estimated GFR (eGFR CKD-EPI) \>90 \-
Total Bilirubin 0.21 mg/dL \< 1.20 mg/dL
Albumin 4.09 g/dL 3.5-5.2 g/dL
CRP 7.8 mg/L \< 5.0 mg/L
Haptoglobin 108 mg/dL 30-200 mg/dL
Ferritin 24 µg/L 13-140 µg/L
ALT 24 U/L \< 31 U/L
AST 37 U/L \< 35 U/L
Gamma-GT 27 U/L 5-36 U/L
Lactate Dehydrogenase 244 U/L 135-214 U/L
25-OH-Vitamin D3 91.7 nmol/L 50.0-150.0 nmol/L
Hemoglobin 11.1 g/dL 12.0-15.6 g/dL
Hematocrit 40.0% 35.5-45.5%
Red Blood Cells 3.5 M/uL 3.9-5.2 M/uL
White Blood Cells 2.41 K/uL 3.90-10.50 K/uL
Platelets 142 K/uL 150-370 K/uL
MCV 73.0 fL 80.0-99.0 fL
MCH 23.9 pg 27.0-33.5 pg
MCHC 32.7 g/dL 31.5-36.0 g/dL
MPV 10.7 fL 7.0-12.0 fL
RDW-CV 14.8% 11.5-15.0%
Absolute Neutrophils 1.27 K/uL 1.50-7.70 K/uL
Absolute Immature Granulocytes 0.000 K/uL \< 0.050 K/uL
Absolute Lymphocytes 0.67 K/uL 1.10-4.50 K/uL
Absolute Monocytes 0.34 K/uL 0.10-0.90 K/uL
Absolute Eosinophils 0.09 K/uL 0.02-0.50 K/uL
Absolute Basophils 0.04 K/uL 0.00-0.20 K/uL
Free Hemoglobin 5.00 mg/dL \< 20.00 mg/dL
### Patient Report 5
**Dear colleague, **
We would like to provide an update on Mrs. Linda Mayer, born on
01/12/1948, who received inpatient care at our facility from 01/01/2021
to 01/14/2021.
**Diagnosis:** Hailey-Hailey disease.
- Upon admission, the patient was under treatment with Acitretin 25mg.
**Other Diagnoses**:
- History of apoplexy in 2016 with no residuals
- Depressive episodes
- Right hip total hip replacement
- History of left adnexectomy in 1980 die to extrauterine pregnancy
- Tubal sterilization in 1988.
- Uterine curettage in 2004
- Hysterectomy in 2005
**Medical History:** Mrs. Linda Mayer was referred to our hospital for
the management of Hailey-Hailey disease after assessment in our
outpatient clinic. She reported a worsening of painful skin erosions on
her neck and inner thighs over a span of approximately 3 weeks.
Itchiness was not reported. Prior attempts at treatment, including the
topical use of Fucicort, Prednisolone with Octenidine, and Polidocanol
gel, had provided limited relief. She denied any other physical
complaints, dyspnea, B symptoms, infections, or irregularities in stool
and micturition.
Her history revealed the initial onset of Hailey-Hailey disease,
initially presenting as itching followed by skin erosions, which
subsequently healed with scarring. The diagnosis was established at the
Fairview Clinic. Previous therapeutic interventions included systemic
cortisone shock therapy, as-needed application of Fucicort ointment, and
axillary laser therapy.
**Family History:**
- Father: Hailey-Hailey Disease (M. Hailey-Hailey)
- Mother and Sister: Breast carcinoma
**Psychosocial History:** Socially, Ms. Linda Mayer is described as a
retiree, having previously worked as a nurse.
**Physical Examination on Admission:**
Height: 16 cm, Body Weight: 80.0 kg, BMI: 29.7
**Physical Examination Findings:**
Generally stable condition with increased nutritional status. Her
consciousness was unremarkable, and cranial mobility was free. Ocular
mobility was regular, with prompt pupillary reflexes to accommodation
and light. She exhibited a normal heart rate, and cardiac and pulmonary
examinations were unremarkable. No heart murmurs were detected. Renal
bed and spine were not palpable. Further internal and orienting
neurological examinations revealed no pathological findings.
**Skin Findings on Admission:** Sharp erosions, approximately 10x10 cm
in size, with a livid-erythematous base, partly crusty, were observed on
the neck and proximal inner thighs.
In the axillary regions on both sides, there were marginal,
livid-erythematous, well-demarcated plaques interspersed with scarring
strands, more pronounced on the right side.
Skin type II.
Mucous membranes appeared normal. Dermographism was noted to be ruber.
**Medication ** **Dosage** **Frequency**
------------------------------ ------------ -------------------------------
Prednisolone (Deltasone) 5 mg 1.5-0-0-0-0-0
Aspirin (Bayer) 100 mg 0-1-0-0-0-0
Simvastatin (Zocor) 40 mg 0-0-0-0-1
Pantoprazole (Protonix) 45.1 mg 1-0-0-0-0
Acitretin (Soriatane) 25 mg 1-0-0-0-0
Tetrabenazine (Xenazine) 111 mg 0.25-0.25-0.25-0.25-0.25-0.25
Letrozole (Femara) 2.5 mg 0-0-1-0
Risedronate Sodium (Actonel) 35 mg 1-0-0-0-0
Acetaminophen (Tylenol) 500 mg 0-1-0-1
Naloxone (Narcan) 8.8 mg 1-0-1-0
Eszopiclone (Lunesta) 7.5 mg 0-0-1-0
**Other Findings:** MRSA Smears:
- Nasal Smear: Normal flora, no MRSA.
- Throat Swab: Normal flora, no MRSA.
- Non-lesional Skin Smear: Normal flora.
- Lesional Skin Swab: Abundant Pseudomonas aeruginosa, abundant
Klebsiella oxytoca, and abundant Serratia sp., sensitive to
piperacillin-tazobactam.
**Therapy and Progression:** Mrs. Linda Mayer was admitted on 01/01/2021
as an inpatient for a refractory exacerbation of previously diagnosed
Hailey-Hailey disease. On admission, both bacteriological and
mycological smears were conducted, which indicated abundant levels of
Pseudomonas aeruginosa, Klebsiella oxytoca, and Serratia sp. Lab tests
showed a CRP level of 2.83 mg/dL and a leukocyte count of 8.8 G/L.
Initial topical therapy consisted of Zinc oxide ointment, Clotrimazole
paste, and Triamcinolone Acetonide shake lotion. Treatment was modified
on 01/04/2021 to include Clotrimazole (Lotrimin) paste in the mornings
and methylprednisolone emulsion in the evenings. Starting on 01/08,
eosin aqueous solution was introduced for application on the thighs,
serving antiseptic and drying purposes. A hydrophilic prednicarbate
cream at 0.25% concentration, combined with octenidine at 0.1%, was
applied to the neck and thighs twice daily, also starting on 01/08. For
showering, octenidine-based wash lotion was utilized. Additionally, Mrs.
Linda Mayer received an emulsifying ointment as part of her treatment.
### Patient Report 6
**Dear colleague, **
We are providing an update on our patient Mrs. Linda Mayer, born on
01/12/1948, who presented to our outpatient clinic on 09/22/2021.
**Diagnoses:** M. Hailey-Hailey
**Medical History:**
- Diagnosis of M. Hailey-Hailey at the Fairview Clinic
<!-- -->
- Treatment involved systemic steroid shock therapy, laser therapy,
and the initiation of Acitretin in October 2021, with no observed
improvement.
<!-- -->
- A dermabrasion procedure was scheduled on 03/18/2021, during a
previous inpatient admission.
- Acitretin 25mg has been administered daily, with favorable outcomes
noted when using Triamcinolone/Triclosan or Prednisolone +
Octenidine.
- A history of mastectomy with Vacuum-Assisted Closure (VAC) has
resulted in breast erosion.
**Skin Findings:**
- Erythematous and partially mottled lesions have been identified in
the axillary and inguinal regions, with some scarring observed in
the axillary area.
- On 04/28/2021, somewhat erosive plaques were noted in the inguinal
regions.
- As of 05/05/2021 discrete erosions are currently present on both
forearms.
**Current Recommendations:**
- Inpatient admission is scheduled for September 2021.
- The prescribed treatment plan includes topical prednicarbate
(Dermatop) 0.25% with Octenidine 0.1%, per NRF 11.145, in a 50g
container, to be applied once daily for 1-2 weeks.
- Hydrocortisone 5% in a suitable base, 200g, is to be applied daily.
- The regimen also includes prednicarbate (Dermatop) combined with
Octenidine.
- Acitretin will be continued temporarily.
- A follow-up appointment in the outpatient clinic is scheduled for
three months from now.
- Discontinuation of Acitretin.
- It is recommended to avoid the use of compresses on the erosions to
prevent constant trauma.
- Topical therapy with petrolatum-based wound ointment and sterile
compresses.
|
Infection
|
How often do Bachus vines mature and what is the significance of that timeline?
A. Every 18 years a vintage is held, which is a kind of celebration of art.
B. Every 12 years a vintage is held, which also serves as a cultural festival that encourage young people to procreate.
C. Every 18 years a vintage is held, which serves as a kind of celebration of life for both young and old people.
D. Every 12 years a vintage is held, wherein the young people are made to harvest all the grapes.
|
CULTURAL EXCHANGE BY KEITH LAUMER It was a simple student exchange—but Retief gave them more of an education than they expected! [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, September 1962. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] I Second Secretary Magnan took his green-lined cape and orange-feathered beret from the clothes tree. "I'm off now, Retief," he said. "I hope you'll manage the administrative routine during my absence without any unfortunate incidents." "That seems a modest enough hope," Retief said. "I'll try to live up to it." "I don't appreciate frivolity with reference to this Division," Magnan said testily. "When I first came here, the Manpower Utilization Directorate, Division of Libraries and Education was a shambles. I fancy I've made MUDDLE what it is today. Frankly, I question the wisdom of placing you in charge of such a sensitive desk, even for two weeks. But remember. Yours is purely a rubber-stamp function." "In that case, let's leave it to Miss Furkle. I'll take a couple of weeks off myself. With her poundage, she could bring plenty of pressure to bear." "I assume you jest, Retief," Magnan said sadly. "I should expect even you to appreciate that Bogan participation in the Exchange Program may be the first step toward sublimation of their aggressions into more cultivated channels." "I see they're sending two thousand students to d'Land," Retief said, glancing at the Memo for Record. "That's a sizable sublimation." Magnan nodded. "The Bogans have launched no less than four military campaigns in the last two decades. They're known as the Hoodlums of the Nicodemean Cluster. Now, perhaps, we shall see them breaking that precedent and entering into the cultural life of the Galaxy." "Breaking and entering," Retief said. "You may have something there. But I'm wondering what they'll study on d'Land. That's an industrial world of the poor but honest variety." "Academic details are the affair of the students and their professors," Magnan said. "Our function is merely to bring them together. See that you don't antagonize the Bogan representative. This will be an excellent opportunity for you to practice your diplomatic restraint—not your strong point, I'm sure you'll agree." A buzzer sounded. Retief punched a button. "What is it, Miss Furkle?" "That—bucolic person from Lovenbroy is here again." On the small desk screen, Miss Furkle's meaty features were compressed in disapproval. "This fellow's a confounded pest. I'll leave him to you, Retief," Magnan said. "Tell him something. Get rid of him. And remember: here at Corps HQ, all eyes are upon you." "If I'd thought of that, I'd have worn my other suit," Retief said. Magnan snorted and passed from view. Retief punched Miss Furkle's button. "Send the bucolic person in." A tall broad man with bronze skin and gray hair, wearing tight trousers of heavy cloth, a loose shirt open at the neck and a short jacket, stepped into the room. He had a bundle under his arm. He paused at sight of Retief, looked him over momentarily, then advanced and held out his hand. Retief took it. For a moment the two big men stood, face to face. The newcomer's jaw muscles knotted. Then he winced. Retief dropped his hand and motioned to a chair. "That's nice knuckle work, mister," the stranger said, massaging his hand. "First time anybody ever did that to me. My fault though. I started it, I guess." He grinned and sat down. "What can I do for you?" Retief said. "You work for this Culture bunch, do you? Funny. I thought they were all ribbon-counter boys. Never mind. I'm Hank Arapoulous. I'm a farmer. What I wanted to see you about was—" He shifted in his chair. "Well, out on Lovenbroy we've got a serious problem. The wine crop is just about ready. We start picking in another two, three months. Now I don't know if you're familiar with the Bacchus vines we grow...?" "No," Retief said. "Have a cigar?" He pushed a box across the desk. Arapoulous took one. "Bacchus vines are an unusual crop," he said, puffing the cigar alight. "Only mature every twelve years. In between, the vines don't need a lot of attention, so our time's mostly our own. We like to farm, though. Spend a lot of time developing new forms. Apples the size of a melon—and sweet—" "Sounds very pleasant," Retief said. "Where does the Libraries and Education Division come in?" Arapoulous leaned forward. "We go in pretty heavy for the arts. Folks can't spend all their time hybridizing plants. We've turned all the land area we've got into parks and farms. Course, we left some sizable forest areas for hunting and such. Lovenbroy's a nice place, Mr. Retief." "It sounds like it, Mr. Arapoulous. Just what—" "Call me Hank. We've got long seasons back home. Five of 'em. Our year's about eighteen Terry months. Cold as hell in winter; eccentric orbit, you know. Blue-black sky, stars visible all day. We do mostly painting and sculpture in the winter. Then Spring; still plenty cold. Lots of skiing, bob-sledding, ice skating; and it's the season for woodworkers. Our furniture—" "I've seen some of your furniture," Retief said. "Beautiful work." Arapoulous nodded. "All local timbers too. Lots of metals in our soil and those sulphates give the woods some color, I'll tell you. Then comes the Monsoon. Rain—it comes down in sheets. But the sun's getting closer. Shines all the time. Ever seen it pouring rain in the sunshine? That's the music-writing season. Then summer. Summer's hot. We stay inside in the daytime and have beach parties all night. Lots of beach on Lovenbroy; we're mostly islands. That's the drama and symphony time. The theatres are set up on the sand, or anchored off-shore. You have the music and the surf and the bonfires and stars—we're close to the center of a globular cluster, you know...." "You say it's time now for the wine crop?" "That's right. Autumn's our harvest season. Most years we have just the ordinary crops. Fruit, grain, that kind of thing; getting it in doesn't take long. We spend most of the time on architecture, getting new places ready for the winter or remodeling the older ones. We spend a lot of time in our houses. We like to have them comfortable. But this year's different. This is Wine Year." Arapoulous puffed on his cigar, looked worriedly at Retief. "Our wine crop is our big money crop," he said. "We make enough to keep us going. But this year...." "The crop isn't panning out?" "Oh, the crop's fine. One of the best I can remember. Course, I'm only twenty-eight; I can't remember but two other harvests. The problem's not the crop." "Have you lost your markets? That sounds like a matter for the Commercial—" "Lost our markets? Mister, nobody that ever tasted our wines ever settled for anything else!" "It sounds like I've been missing something," said Retief. "I'll have to try them some time." Arapoulous put his bundle on the desk, pulled off the wrappings. "No time like the present," he said. Retief looked at the two squat bottles, one green, one amber, both dusty, with faded labels, and blackened corks secured by wire. "Drinking on duty is frowned on in the Corps, Mr. Arapoulous," he said. "This isn't drinking . It's just wine." Arapoulous pulled the wire retainer loose, thumbed the cork. It rose slowly, then popped in the air. Arapoulous caught it. Aromatic fumes wafted from the bottle. "Besides, my feelings would be hurt if you didn't join me." He winked. Retief took two thin-walled glasses from a table beside the desk. "Come to think of it, we also have to be careful about violating quaint native customs." Arapoulous filled the glasses. Retief picked one up, sniffed the deep rust-colored fluid, tasted it, then took a healthy swallow. He looked at Arapoulous thoughtfully. "Hmmm. It tastes like salted pecans, with an undercurrent of crusted port." "Don't try to describe it, Mr. Retief," Arapoulous said. He took a mouthful of wine, swished it around his teeth, swallowed. "It's Bacchus wine, that's all. Nothing like it in the Galaxy." He pushed the second bottle toward Retief. "The custom back home is to alternate red wine and black." Retief put aside his cigar, pulled the wires loose, nudged the cork, caught it as it popped up. "Bad luck if you miss the cork," Arapoulous said, nodding. "You probably never heard about the trouble we had on Lovenbroy a few years back?" "Can't say that I did, Hank." Retief poured the black wine into two fresh glasses. "Here's to the harvest." "We've got plenty of minerals on Lovenbroy," Arapoulous said, swallowing wine. "But we don't plan to wreck the landscape mining 'em. We like to farm. About ten years back some neighbors of ours landed a force. They figured they knew better what to do with our minerals than we did. Wanted to strip-mine, smelt ore. We convinced 'em otherwise. But it took a year, and we lost a lot of men." "That's too bad," Retief said. "I'd say this one tastes more like roast beef and popcorn over a Riesling base." "It put us in a bad spot," Arapoulous went on. "We had to borrow money from a world called Croanie. Mortgaged our crops. Had to start exporting art work too. Plenty of buyers, but it's not the same when you're doing it for strangers." "Say, this business of alternating drinks is the real McCoy," Retief said. "What's the problem? Croanie about to foreclose?" "Well, the loan's due. The wine crop would put us in the clear. But we need harvest hands. Picking Bacchus grapes isn't a job you can turn over to machinery—and anyway we wouldn't if we could. Vintage season is the high point of living on Lovenbroy. Everybody joins in. First, there's the picking in the fields. Miles and miles of vineyards covering the mountain sides, and crowding the river banks, with gardens here and there. Big vines, eight feet high, loaded with fruit, and deep grass growing between. The wine-carriers keep on the run, bringing wine to the pickers. There's prizes for the biggest day's output, bets on who can fill the most baskets in an hour.... The sun's high and bright, and it's just cool enough to give you plenty of energy. Come nightfall, the tables are set up in the garden plots, and the feast is laid on: roast turkeys, beef, hams, all kinds of fowl. Big salads. Plenty of fruit. Fresh-baked bread ... and wine, plenty of wine. The cooking's done by a different crew each night in each garden, and there's prizes for the best crews. "Then the wine-making. We still tramp out the vintage. That's mostly for the young folks but anybody's welcome. That's when things start to get loosened up. Matter of fact, pretty near half our young-uns are born after a vintage. All bets are off then. It keeps a fellow on his toes though. Ever tried to hold onto a gal wearing nothing but a layer of grape juice?" "Never did," Retief said. "You say most of the children are born after a vintage. That would make them only twelve years old by the time—" "Oh, that's Lovenbroy years; they'd be eighteen, Terry reckoning." "I was thinking you looked a little mature for twenty-eight," Retief said. "Forty-two, Terry years," Arapoulous said. "But this year it looks bad. We've got a bumper crop—and we're short-handed. If we don't get a big vintage, Croanie steps in. Lord knows what they'll do to the land. Then next vintage time, with them holding half our grape acreage—" "You hocked the vineyards?" "Yep. Pretty dumb, huh? But we figured twelve years was a long time." "On the whole," Retief said, "I think I prefer the black. But the red is hard to beat...." "What we figured was, maybe you Culture boys could help us out. A loan to see us through the vintage, enough to hire extra hands. Then we'd repay it in sculpture, painting, furniture—" "Sorry, Hank. All we do here is work out itineraries for traveling side-shows, that kind of thing. Now, if you needed a troop of Groaci nose-flute players—" "Can they pick grapes?" "Nope. Anyway, they can't stand the daylight. Have you talked this over with the Labor Office?" "Sure did. They said they'd fix us up with all the electronics specialists and computer programmers we wanted—but no field hands. Said it was what they classified as menial drudgery; you'd have thought I was trying to buy slaves." The buzzer sounded. Miss Furkle's features appeared on the desk screen. "You're due at the Intergroup Council in five minutes," she said. "Then afterwards, there are the Bogan students to meet." "Thanks." Retief finished his glass, stood. "I have to run, Hank," he said. "Let me think this over. Maybe I can come up with something. Check with me day after tomorrow. And you'd better leave the bottles here. Cultural exhibits, you know." II As the council meeting broke up, Retief caught the eye of a colleague across the table. "Mr. Whaffle, you mentioned a shipment going to a place called Croanie. What are they getting?" Whaffle blinked. "You're the fellow who's filling in for Magnan, over at MUDDLE," he said. "Properly speaking, equipment grants are the sole concern of the Motorized Equipment Depot, Division of Loans and Exchanges." He pursed his lips. "However, I suppose there's no harm in telling you. They'll be receiving heavy mining equipment." "Drill rigs, that sort of thing?" "Strip mining gear." Whaffle took a slip of paper from a breast pocket, blinked at it. "Bolo Model WV/1 tractors, to be specific. Why is MUDDLE interested in MEDDLE's activities?" "Forgive my curiosity, Mr. Whaffle. It's just that Croanie cropped up earlier today. It seems she holds a mortgage on some vineyards over on—" "That's not MEDDLE's affair, sir," Whaffle cut in. "I have sufficient problems as Chief of MEDDLE without probing into MUDDLE'S business." "Speaking of tractors," another man put in, "we over at the Special Committee for Rehabilitation and Overhaul of Under-developed Nations' General Economies have been trying for months to get a request for mining equipment for d'Land through MEDDLE—" "SCROUNGE was late on the scene," Whaffle said. "First come, first served. That's our policy at MEDDLE. Good day, gentlemen." He strode off, briefcase under his arm. "That's the trouble with peaceful worlds," the SCROUNGE committeeman said. "Boge is a troublemaker, so every agency in the Corps is out to pacify her. While my chance to make a record—that is, assist peace-loving d'Land—comes to naught." He shook his head. "What kind of university do they have on d'Land?" asked Retief. "We're sending them two thousand exchange students. It must be quite an institution." "University? D'Land has one under-endowed technical college." "Will all the exchange students be studying at the Technical College?" "Two thousand students? Hah! Two hundred students would overtax the facilities of the college." "I wonder if the Bogans know that?" "The Bogans? Why, most of d'Land's difficulties are due to the unwise trade agreement she entered into with Boge. Two thousand students indeed!" He snorted and walked away. Retief stopped by the office to pick up a short cape, then rode the elevator to the roof of the 230-story Corps HQ building and hailed a cab to the port. The Bogan students had arrived early. Retief saw them lined up on the ramp waiting to go through customs. It would be half an hour before they were cleared through. He turned into the bar and ordered a beer. A tall young fellow on the next stool raised his glass. "Happy days," he said. "And nights to match." "You said it." He gulped half his beer. "My name's Karsh. Mr. Karsh. Yep, Mr. Karsh. Boy, this is a drag, sitting around this place waiting...." "You meeting somebody?" "Yeah. Bunch of babies. Kids. How they expect—Never mind. Have one on me." "Thanks. You a Scoutmaster?" "I'll tell you what I am. I'm a cradle-robber. You know—" he turned to Retief—"not one of those kids is over eighteen." He hiccupped. "Students, you know. Never saw a student with a beard, did you?" "Lots of times. You're meeting the students, are you?" The young fellow blinked at Retief. "Oh, you know about it, huh?" "I represent MUDDLE." Karsh finished his beer, ordered another. "I came on ahead. Sort of an advance guard for the kids. I trained 'em myself. Treated it like a game, but they can handle a CSU. Don't know how they'll act under pressure. If I had my old platoon—" He looked at his beer glass, pushed it back. "Had enough," he said. "So long, friend. Or are you coming along?" Retief nodded. "Might as well." At the exit to the Customs enclosure, Retief watched as the first of the Bogan students came through, caught sight of Karsh and snapped to attention, his chest out. "Drop that, mister," Karsh snapped. "Is that any way for a student to act?" The youth, a round-faced lad with broad shoulders, grinned. "Heck, no," he said. "Say, uh, Mr. Karsh, are we gonna get to go to town? We fellas were thinking—" "You were, hah? You act like a bunch of school kids! I mean ... no! Now line up!" "We have quarters ready for the students," Retief said. "If you'd like to bring them around to the west side, I have a couple of copters laid on." "Thanks," said Karsh. "They'll stay here until take-off time. Can't have the little dears wandering around loose. Might get ideas about going over the hill." He hiccupped. "I mean they might play hookey." "We've scheduled your re-embarkation for noon tomorrow. That's a long wait. MUDDLE's arranged theater tickets and a dinner." "Sorry," Karsh said. "As soon as the baggage gets here, we're off." He hiccupped again. "Can't travel without our baggage, y'know." "Suit yourself," Retief said. "Where's the baggage now?" "Coming in aboard a Croanie lighter." "Maybe you'd like to arrange for a meal for the students here." "Sure," Karsh said. "That's a good idea. Why don't you join us?" Karsh winked. "And bring a few beers." "Not this time," Retief said. He watched the students, still emerging from Customs. "They seem to be all boys," he commented. "No female students?" "Maybe later," Karsh said. "You know, after we see how the first bunch is received." Back at the MUDDLE office, Retief buzzed Miss Furkle. "Do you know the name of the institution these Bogan students are bound for?" "Why, the University at d'Land, of course." "Would that be the Technical College?" Miss Furkle's mouth puckered. "I'm sure I've never pried into these details." "Where does doing your job stop and prying begin, Miss Furkle?" Retief said. "Personally, I'm curious as to just what it is these students are travelling so far to study—at Corps expense." "Mr. Magnan never—" "For the present. Miss Furkle, Mr. Magnan is vacationing. That leaves me with the question of two thousand young male students headed for a world with no classrooms for them ... a world in need of tractors. But the tractors are on their way to Croanie, a world under obligation to Boge. And Croanie holds a mortgage on the best grape acreage on Lovenbroy." "Well!" Miss Furkle snapped, small eyes glaring under unplucked brows. "I hope you're not questioning Mr. Magnan's wisdom!" "About Mr. Magnan's wisdom there can be no question," Retief said. "But never mind. I'd like you to look up an item for me. How many tractors will Croanie be getting under the MEDDLE program?" "Why, that's entirely MEDDLE business," Miss Furkle said. "Mr. Magnan always—" "I'm sure he did. Let me know about the tractors as soon as you can." Miss Furkle sniffed and disappeared from the screen. Retief left the office, descended forty-one stories, followed a corridor to the Corps Library. In the stacks he thumbed through catalogues, pored over indices. "Can I help you?" someone chirped. A tiny librarian stood at his elbow. "Thank you, ma'am," Retief said. "I'm looking for information on a mining rig. A Bolo model WV tractor." "You won't find it in the industrial section," the librarian said. "Come along." Retief followed her along the stacks to a well-lit section lettered ARMAMENTS. She took a tape from the shelf, plugged it into the viewer, flipped through and stopped at a squat armored vehicle. "That's the model WV," she said. "It's what is known as a continental siege unit. It carries four men, with a half-megaton/second firepower." "There must be an error somewhere," Retief said. "The Bolo model I want is a tractor. Model WV M-1—" "Oh, the modification was the addition of a bulldozer blade for demolition work. That must be what confused you." "Probably—among other things. Thank you." Miss Furkle was waiting at the office. "I have the information you wanted," she said. "I've had it for over ten minutes. I was under the impression you needed it urgently, and I went to great lengths—" "Sure," Retief said. "Shoot. How many tractors?" "Five hundred." "Are you sure?" Miss Furkle's chins quivered. "Well! If you feel I'm incompetent—" "Just questioning the possibility of a mistake, Miss Furkle. Five hundred tractors is a lot of equipment." "Was there anything further?" Miss Furkle inquired frigidly. "I sincerely hope not," Retief said. III Leaning back in Magnan's padded chair with power swivel and hip-u-matic concontour, Retief leafed through a folder labelled "CERP 7-602-Ba; CROANIE (general)." He paused at a page headed Industry. Still reading, he opened the desk drawer, took out the two bottles of Bacchus wine and two glasses. He poured an inch of wine into each and sipped the black wine meditatively. It would be a pity, he reflected, if anything should interfere with the production of such vintages.... Half an hour later he laid the folder aside, keyed the phone and put through a call to the Croanie Legation. He asked for the Commercial Attache. "Retief here, Corps HQ," he said airily. "About the MEDDLE shipment, the tractors. I'm wondering if there's been a slip up. My records show we're shipping five hundred units...." "That's correct. Five hundred." Retief waited. "Ah ... are you there, Retief?" "I'm still here. And I'm still wondering about the five hundred tractors." "It's perfectly in order. I thought it was all settled. Mr. Whaffle—" "One unit would require a good-sized plant to handle its output," Retief said. "Now Croanie subsists on her fisheries. She has perhaps half a dozen pint-sized processing plants. Maybe, in a bind, they could handle the ore ten WV's could scrape up ... if Croanie had any ore. It doesn't. By the way, isn't a WV a poor choice as a mining outfit? I should think—" "See here, Retief! Why all this interest in a few surplus tractors? And in any event, what business is it of yours how we plan to use the equipment? That's an internal affair of my government. Mr. Whaffle—" "I'm not Mr. Whaffle. What are you going to do with the other four hundred and ninety tractors?" "I understood the grant was to be with no strings attached!" "I know it's bad manners to ask questions. It's an old diplomatic tradition that any time you can get anybody to accept anything as a gift, you've scored points in the game. But if Croanie has some scheme cooking—" "Nothing like that, Retief. It's a mere business transaction." "What kind of business do you do with a Bolo WV? With or without a blade attached, it's what's known as a continental siege unit." "Great Heavens, Retief! Don't jump to conclusions! Would you have us branded as warmongers? Frankly—is this a closed line?" "Certainly. You may speak freely." "The tractors are for transshipment. We've gotten ourselves into a difficult situation, balance-of-payments-wise. This is an accommodation to a group with which we have rather strong business ties." "I understand you hold a mortgage on the best land on Lovenbroy," Retief said. "Any connection?" "Why ... ah ... no. Of course not, ha ha." "Who gets the tractors eventually?" "Retief, this is unwarranted interference!" "Who gets them?" "They happen to be going to Lovenbroy. But I scarcely see—" "And who's the friend you're helping out with an unauthorized transshipment of grant material?" "Why ... ah ... I've been working with a Mr. Gulver, a Bogan representative." "And when will they be shipped?" "Why, they went out a week ago. They'll be half way there by now. But look here, Retief, this isn't what you're thinking!" "How do you know what I'm thinking? I don't know myself." Retief rang off, buzzed the secretary. "Miss Furkle, I'd like to be notified immediately of any new applications that might come in from the Bogan Consulate for placement of students." "Well, it happens, by coincidence, that I have an application here now. Mr. Gulver of the Consulate brought it in." "Is Mr. Gulver in the office? I'd like to see him." "I'll ask him if he has time." "Great. Thanks." It was half a minute before a thick-necked red-faced man in a tight hat walked in. He wore an old-fashioned suit, a drab shirt, shiny shoes with round toes and an ill-tempered expression. "What is it you wish?" he barked. "I understood in my discussions with the other ... ah ... civilian there'd be no further need for these irritating conferences." "I've just learned you're placing more students abroad, Mr. Gulver. How many this time?" "Two thousand." "And where will they be going?" "Croanie. It's all in the application form I've handed in. Your job is to provide transportation." "Will there be any other students embarking this season?" "Why ... perhaps. That's Boge's business." Gulver looked at Retief with pursed lips. "As a matter of fact, we had in mind dispatching another two thousand to Featherweight." "Another under-populated world—and in the same cluster, I believe," Retief said. "Your people must be unusually interested in that region of space." "If that's all you wanted to know, I'll be on my way. I have matters of importance to see to." After Gulver left, Retief called Miss Furkle in. "I'd like to have a break-out of all the student movements that have been planned under the present program," he said. "And see if you can get a summary of what MEDDLE has been shipping lately." Miss Furkle compressed her lips. "If Mr. Magnan were here, I'm sure he wouldn't dream of interfering in the work of other departments. I ... overheard your conversation with the gentleman from the Croanie Legation—" "The lists, Miss Furkle." "I'm not accustomed," Miss Furkle said, "to intruding in matters outside our interest cluster." "That's worse than listening in on phone conversations, eh? But never mind. I need the information, Miss Furkle." "Loyalty to my Chief—" "Loyalty to your pay-check should send you scuttling for the material I've asked for," Retief said. "I'm taking full responsibility. Now scat." The buzzer sounded. Retief flipped a key. "MUDDLE, Retief speaking...." Arapoulous's brown face appeared on the desk screen. "How-do, Retief. Okay if I come up?" "Sure, Hank. I want to talk to you." In the office, Arapoulous took a chair. "Sorry if I'm rushing you, Retief," he said. "But have you got anything for me?" Retief waved at the wine bottles. "What do you know about Croanie?" "Croanie? Not much of a place. Mostly ocean. All right if you like fish, I guess. We import our seafood from there. Nice prawns in monsoon time. Over a foot long." "You on good terms with them?" "Sure, I guess so. Course, they're pretty thick with Boge." "So?" "Didn't I tell you? Boge was the bunch that tried to take us over here a dozen years back. They'd've made it too, if they hadn't had a lot of bad luck. Their armor went in the drink, and without armor they're easy game." Miss Furkle buzzed. "I have your lists," she said shortly. "Bring them in, please." The secretary placed the papers on the desk. Arapoulous caught her eye and grinned. She sniffed and marched from the room. "What that gal needs is a slippery time in the grape mash," Arapoulous observed. Retief thumbed through the papers, pausing to read from time to time. He finished and looked at Arapoulous. "How many men do you need for the harvest, Hank?" Retief inquired. Arapoulous sniffed his wine glass and looked thoughtful. "A hundred would help," he said. "A thousand would be better. Cheers." "What would you say to two thousand?" "Two thousand? Retief, you're not fooling?" "I hope not." He picked up the phone, called the Port Authority, asked for the dispatch clerk. "Hello, Jim. Say, I have a favor to ask of you. You know that contingent of Bogan students. They're traveling aboard the two CDT transports. I'm interested in the baggage that goes with the students. Has it arrived yet? Okay, I'll wait." Jim came back to the phone. "Yeah, Retief, it's here. Just arrived. But there's a funny thing. It's not consigned to d'Land. It's ticketed clear through to Lovenbroy." "Listen, Jim," Retief said. "I want you to go over to the warehouse and take a look at that baggage for me." Retief waited while the dispatch clerk carried out the errand. The level in the two bottles had gone down an inch when Jim returned to the phone. "Hey, I took a look at that baggage, Retief. Something funny going on. Guns. 2mm needlers, Mark XII hand blasters, power pistols—" "It's okay, Jim. Nothing to worry about. Just a mix-up. Now, Jim, I'm going to ask you to do something more for me. I'm covering for a friend. It seems he slipped up. I wouldn't want word to get out, you understand. I'll send along a written change order in the morning that will cover you officially. Meanwhile, here's what I want you to do...." Retief gave instructions, then rang off and turned to Arapoulous. "As soon as I get off a couple of TWX's, I think we'd better get down to the port, Hank. I think I'd like to see the students off personally."
|
B. Every 12 years a vintage is held, which also serves as a cultural festival that encourage young people to procreate.
|
Where is the Hoffman Medical Center?
A. Newark
B. Westchester
C. Philadelphia
D. Trenton
|
BRAMBLE BUSH BY ALAN E. NOURSE [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, August 1957. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] There was a man in our town, and he was wondrous wise; He jumped into a bramble bush and scratched out both his eyes. And when he saw what he had done, with all his might and main He jumped into another bush and scratched them in again. MOTHER GOOSE Dr. David Lessing found Jack Dorffman and the boy waiting in his office when he arrived at the Hoffman Center that morning. Dorffman looked as though he'd been running all night. There were dark pouches under his eyes; his heavy unshaven face seemed to sag at every crease. Lessing glanced sharply at his Field Director and sank down behind his desk with a sigh. "All right, Jack—what's wrong?" "This kid is driving me nuts," said Dorffman through clenched teeth. "He's gone completely hay-wire. Nobody's been able to get near him for three weeks, and now at six o'clock this morning he decides he's leaving the Farm. I talk to him, I sweat him down, I do everything but tie him to the bed, and I waste my time. He's leaving the Farm. Period." "So you bring him down here," said Lessing sourly. "The worst place he could be, if something's really wrong." He looked across at the boy. "Tommy? Come over and sit down." There was nothing singular about the boy's appearance. He was thin, with a pale freckled face and the guileless expression of any normal eight-year-old as he blinked across the desk at Lessing. The awkward grey monitor-helmet concealed a shock of sandy hair. He sat with a mute appeal in his large grey eyes as Lessing flipped the reader-switch and blinked in alarm at the wildly thrashing pattern on the tape. The boy was terrorized. He was literally pulsating with fear. Lessing sat back slowly. "Tell me about it, Tommy," he said gently. "I don't want to go back to the Farm," said the boy. "Why?" "I just don't. I hate it there." "Are you frightened?" The boy bit his lip and nodded slowly. "Of me? Of Dr. Dorffman?" "No. Oh, no!" "Then what?" Again the mute appeal in the boy's eyes. He groped for words, and none came. Finally he said, "If I could only take this off—" He fingered the grey plastic helmet. "You think that would make you feel better?" "It would, I know it would." Lessing shook his head. "I don't think so, Tommy. You know what the monitor is for, don't you?" "It stops things from going out." "That's right. And it stops things from going in. It's an insulator. You need it badly. It would hurt you a great deal if you took it off, away from the Farm." The boy fought back tears. "But I don't want to go back there—" The fear-pattern was alive again on the tape. "I don't feel good there. I never want to go back." "Well, we'll see. You can stay here for a while." Lessing nodded at Dorffman and stepped into an adjoining room with him. "You say this has been going on for three weeks ?" "I'm afraid so. We thought it was just a temporary pattern—we see so much of that up there." "I know, I know." Lessing chewed his lip. "I don't like it. We'd better set up a battery on him and try to spot the trouble. And I'm afraid you'll have to set it up. I've got that young Melrose from Chicago to deal with this morning—the one who's threatening to upset the whole Conference next month with some crazy theories he's been playing with. I'll probably have to take him out to the Farm to shut him up." Lessing ran a hand through sparse grey hair. "See what you can do for the boy downstairs." "Full psi precautions?" asked Dorffman. "Certainly! And Jack—in this case, be sure of it. If Tommy's in the trouble I think he's in, we don't dare risk a chance of Adult Contact now. We could end up with a dead boy on our hands." Two letters were waiting on Lessing's desk that morning. The first was from Roberts Bros., announcing another shift of deadline on the book, and demanding the galley proofs two weeks earlier than scheduled. Lessing groaned. As director of psionic research at the Hoffman Medical Center, he had long since learned how administrative detail could suck up daytime hours. He knew that his real work was at the Farm—yet he hadn't even been to the Farm in over six weeks. And now, as the book approached publication date, Lessing wondered if he would ever really get back to work again. The other letter cheered him a bit more. It bore the letterhead of the International Psionics Conference: Dear Dr. Lessing: In recognition of your position as an authority on human Psionic behavior patterns, we would be gratified to schedule you as principle speaker at the Conference in Chicago on October 12th. A few remarks in discussion of your forthcoming book would be entirely in order— They were waiting for it, then! He ran the galley proofs into the scanner excitedly. They knew he had something up his sleeve. His earlier papers had only hinted at the direction he was going—but the book would clear away the fog. He scanned the title page proudly. "A Theory of Psionic Influence on Infant and Child Development." A good title—concise, commanding, yet modest. They would read it, all right. And they would find it a light shining brightly in the darkness, a guide to the men who were floundering in the jungle of a strange and baffling new science. For they were floundering. When they were finally forced to recognize that this great and powerful force did indeed exist in human minds, with unimaginable potential if it could only be unlocked, they had plunged eagerly into the search, and found themselves in a maddening bramble bush of contradictions and chaos. Nothing worked, and everything worked too well. They were trying to study phenomena which made no sense, observing things that defied logic. Natural laws came crashing down about their ears as they stood sadly by and watched things happen which natural law said could never happen. They had never been in this jungle before, nor in any jungle remotely like it. The old rules didn't work here, the old methods of study failed. And the more they struggled, the thicker and more impenetrable the bramble bush became— But now David Lessing had discovered a pathway through that jungle, a theory to work by— At his elbow the intercom buzzed. "A gentleman to see you," the girl said. "A Dr. Melrose. He's very impatient, sir." He shut off the scanner and said, "Send him in, please." Dr. Peter Melrose was tall and thin, with jet black hair and dark mocking eyes. He wore a threadbare sport coat and a slouch. He offered Lessing a bony hand, then flung himself into a chair as he stared about the office in awe. "I'm really overwhelmed," he said after a moment. "Within the stronghold of psionic research at last. And face to face with the Master in the trembling flesh!" Lessing frowned. "Dr. Melrose, I don't quite understand—" "Oh, it's just that I'm impressed," the young man said airily. "Of course, I've seen old dried-up Authorities before—but never before a brand spanking new one, just fresh out of the pupa, so to speak!" He touched his forehead in a gesture of reverence. "I bow before the Oracle. Speak, oh Motah, live forever! Cast a pearl at my feet!" "If you've come here to be insulting," Lessing said coldly, "you're just wasting time." He reached for the intercom switch. "I think you'd better wait before you do that," Melrose said sharply, "because I'm planning to take you apart at the Conference next month unless I like everything I see and hear down here today. And if you don't think I can do it, you're in for quite a dumping." Lessing sat back slowly. "Tell me—just what, exactly, do you want?" "I want to hear this fairy tale you're about to publish in the name of 'Theory'," Melrose said. "I want to see this famous Farm of yours up in Connecticut and see for myself how much pressure these experimental controls you keep talking about will actually bear. But mostly, I want to see just what in psionic hell you're so busy making yourself an Authority about." There was no laughter in the man's sharp brown eyes. "You couldn't touch me with a ten foot pole at this conference," snapped Lessing. The other man grinned. "Try me! We shook you up a little bit last year, but you didn't seem to get the idea." "Last year was different." Lessing scowled. "As for our 'fairy tale', we happen to have a staggering body of evidence that says that it's true." "If the papers you've already published are a preview, we think it's false as Satan." "And our controls are above suspicion." "So far, we haven't found any way to set up logical controls," said Melrose. "We've done a lot of work on it, too." "Oh, yes—I've heard about your work. Not bad, really. A little misdirected, is all." "According to your Theory, that is." "Wildly unorthodox approach to psionics—but at least you're energetic enough." "We haven't been energetic enough to find an orthodox approach that got us anywhere. We doubt if you have, either. But maybe we're all wrong." Melrose grinned unpleasantly. "We're not unreasonable, your Majesty. We just ask to be shown. If you dare, that is." Lessing slammed his fist down on the desk angrily. "Have you got the day to take a trip?" "I've got 'til New Year." Lessing shouted for his girl. "Get Dorffman up here. We're going to the Farm this afternoon." The girl nodded, then hesitated. "But what about your lunch?" "Bother lunch." He gave Melrose a sidelong glare. "We've got a guest here who's got a lot of words he's going to eat for us...." Ten minutes later they rode the elevator down to the transit levels and boarded the little shuttle car in the terminal below the Hoffman Center. They sat in silence as the car dipped down into the rapid-transit channels beneath the great city, swinging northward in the express circuit through Philadelphia and Camden sectors, surfacing briefly in Trenton sector, then dropping underground once again for the long pull beneath Newark, Manhattan and Westchester sectors. In less than twenty minutes the car surfaced on a Parkway channel and buzzed north and east through the verdant Connecticut countryside. "What about Tommy?" Lessing asked Dorffman as the car sped along through the afternoon sun. "I just finished the prelims. He's not cooperating." Lessing ground his teeth. "I should be running him now instead of beating the bushes with this—" He broke off to glare at young Melrose. Melrose grinned. "I've heard you have quite a place up here." "It's—unconventional, at any rate," Lessing snapped. "Well, that depends on your standards. Sounds like a country day school, from what I've heard. According to your papers, you've even used conventional statistical analysis on your data from up here." "Until we had to throw it out. We discovered that what we were trying to measure didn't make sense in a statistical analysis." "Of course, you're sure you were measuring something ." "Oh, yes. We certainly were." "Yet you said that you didn't know what." "That's right," said Lessing. "We don't." "And you don't know why your instruments measure whatever they're measuring." The Chicago man's face was thoughtful. "In fact, you can't really be certain that your instruments are measuring the children at all. It's not inconceivable that the children might be measuring the instruments , eh?" Lessing blinked. "It's conceivable." "Mmmm," said Melrose. "Sounds like a real firm foundation to build a theory on." "Why not?" Lessing growled. "It wouldn't be the first time the tail wagged the dog. The psychiatrists never would have gotten out of their rut if somebody hadn't gotten smart and realized that one of their new drugs worked better in combatting schizophrenia when the doctor took the medicine instead of the patient. That was quite a wall to climb." "Yes, wasn't it," mused Melrose, scratching his bony jaw. "Only took them seventy years to climb it, thanks to a certain man's theories. I wonder how long it'll take psionics to crawl out of the pit you're digging for it?" "We're not digging any pit," Lessing exploded angrily. "We're exploring—nothing more. A phenomenon exists. We've known that, one way or another, for centuries. The fact that it doesn't seem to be bound by the same sort of natural law we've observed elsewhere doesn't mean that it isn't governed by natural law. But how can we define the law? How can we define the limits of the phenomenon, for that matter? We can't work in the dark forever—we've got to have a working hypothesis to guide us." "So you dreamed up this 'tadpole' idea," said Melrose sourly. "For a working hypothesis—yes. We've known for a long time that every human being has extrasensory potential to one degree or another. Not just a few here and there—every single one. It's a differentiating quality of the human mind. Just as the ability to think logically in a crisis instead of giving way to panic is a differentiating quality." "Fine," said Melrose. "Great. We can't prove that, of course, but I'll play along." Lessing glared at him. "When we began studying this psi-potential, we found out some curious things. For one thing, it seemed to be immensely more powerful and active in infants and children than in adults. Somewhere along the line as a child grows up, something happens. We don't know what. We do know that the child's psi-potential gradually withdraws deeper and deeper into his mind, burying itself farther and farther out of reach, just the way a tadpole's tail is absorbed deeper and deeper into the growing frog until there just isn't any tail any more." Lessing paused, packing tobacco into his pipe. "That's why we have the Farm—to try to discover why. What forces that potential underground? What buries it so deeply that adult human beings can't get at it any more?" "And you think you have an answer," said Melrose. "We think we might be near an answer. We have a theory that explains the available data." The shuttle car bounced sharply as it left the highway automatics. Dorffman took the controls. In a few moments they were skimming through the high white gates of the Farm, slowing down at the entrance to a long, low building. "All right, young man—come along," said Lessing. "I think we can show you our answer." In the main office building they donned the close-fitting psionic monitors required of all personnel at the Farm. They were of a hard grey plastic material, with a network of wiring buried in the substance, connected to a simple pocket-sized power source. "The major problem," Lessing said, "has been to shield the children from any external psionic stimuli, except those we wished to expose them to. Our goal is a perfectly controlled psi environment. The monitors are quite effective—a simple Renwick scrambler screen." "It blocks off all types of psi activity?" asked Melrose. "As far as we can measure, yes." "Which may not be very far." Jack Dorffman burst in: "What Dr. Lessing is saying is that they seem effective for our purposes." "But you don't know why," added Melrose. "All right, we don't know why. Nobody knows why a Renwick screen works—why blame us?" They were walking down the main corridor and out through an open areaway. Behind the buildings was a broad playground. A baseball game was in progress in one corner; across the field a group of swings, slides, ring bars and other playground paraphernalia was in heavy use. The place was teeming with youngsters, all shouting in a fury of busy activity. Occasionally a helmeted supervisor hurried by; one waved to them as she rescued a four-year-old from the parallel bars. They crossed into the next building, where classes were in progress. "Some of our children are here only briefly," Lessing explained as they walked along, "and some have been here for years. We maintain a top-ranking curriculum—your idea of a 'country day school' wasn't so far afield at that—with scholarships supported by Hoffman Center funds. Other children come to us—foundlings, desertees, children from broken homes, children of all ages from infancy on. Sometimes they stay until they have reached college age, or go on to jobs. As far as psionics research is concerned, we are not trying to be teachers. We are strictly observers. We try to place the youngsters in positions where they can develope what potential they have— without the presence of external psionic influences they would normally be subject to. The results have been remarkable." He led them into a long, narrow room with chairs and ash trays, facing a wide grey glass wall. The room fell into darkness, and through the grey glass they could see three children, about four years old, playing in a large room. "They're perfectly insulated from us," said Lessing. "A variety of recording instruments are working. And before you ask, Dr. Melrose, they are all empirical instruments, and they would all defy any engineer's attempts to determine what makes them go. We don't know what makes them go, and we don't care—they go. That's all we need. Like that one, for instance—" In the corner a flat screen was flickering, emitting a pale green fluorescent light. It hung from the wall by two plastic rods which penetrated into the children's room. There was no sign of a switch, nor a power source. As the children moved about, the screen flickered. Below it, a recording-tape clicked along in little spurts and starts of activity. "What are they doing?" Melrose asked after watching the children a few moments. "Those three seem to work as a team, somehow. Each one, individually, had a fairly constant recordable psi potential of about seventeen on the arbitrary scale we find useful here. Any two of them scale in at thirty-four to thirty-six. Put the three together and they operate somewhere in the neighborhood of six hundred on the same scale." Lessing smiled. "This is an isolated phenomenon—it doesn't hold for any other three children on the Farm. Nor did we make any effort to place them together—they drew each other like magnets. One of our workers spent two weeks trying to find out why the instruments weren't right. It wasn't the instruments, of course." Lessing nodded to an attendant, and peered around at Melrose. "Now, I want you to watch this very closely." He opened a door and walked into the room with the children. The fluorescent screen continued to flicker as the children ran to Lessing. He inspected the block tower they were building, and stooped down to talk to them, his lips moving soundlessly behind the observation wall. The children laughed and jabbered, apparently intrigued by the game he was proposing. He walked to the table and tapped the bottom block in the tower with his thumb. The tower quivered, and the screen blazed out with green light, but the tower stood. Carefully Lessing jogged all the foundation blocks out of place until the tower hung in midair, clearly unsupported. The children watched it closely, and the foundation blocks inched still further out of place.... Then, quite casually, Lessing lifted off his monitor. The children continued staring at the tower as the screen gave three or four violent bursts of green fire and went dark. The block tower fell with a crash. Moments later Lessing was back in the observation room, leaving the children busily putting the tower back together. There was a little smile on his lips as he saw Melrose's face. "Perhaps you're beginning to see what I'm driving at," he said slowly. "Yes," said Melrose. "I think I'm beginning to see." He scratched his jaw. "You think that it's adult psi-contact that drives the child's potential underground—that somehow adult contact acts like a damper, a sort of colossal candle-snuffer." "That's what I think," said Lessing. "How do you know those children didn't make you take off your monitor?" Lessing blinked. "Why should they?" "Maybe they enjoy the crash when the blocks fall down." "But that wouldn't make any difference, would it? The blocks still fall down." Melrose paced down the narrow room. "This is very good," he said suddenly, his voice earnest. "You have fine facilities here, good workers. And in spite of my flippancy, Dr. Lessing, I have never imagined for a moment that you were not an acute observer and a careful, highly imaginative worker. But suppose I told you, in perfect faith, that we have data that flatly contradicts everything you've told me today. Reproducible data, utterly incompatable with yours. What would you say to that?" "I'd say you were wrong," said Lessing. "You couldn't have such data. According to the things I am certain are true, what you're saying is sheer nonsense." "And you'd express that opinion in a professional meeting?" "I would." "And as an Authority on psionic behavior patterns," said Melrose slowly, "you would kill us then and there. You would strangle us professionally, discredit anything we did, cut us off cold." The tall man turned on him fiercely. "Are you blind, man? Can't you see what danger you're in? If you publish your book now, you will become an Authority in a field where the most devastating thing that could possibly happen would be— the appearance of an Authority ." Lessing and Dorffman rode back to the Hoffman Center in grim silence. At first Lessing pretended to work; finally he snapped off the tape recorder in disgust and stared out the shuttle-car window. Melrose had gone on to Idlewild to catch a jet back to Chicago. It was a relief to see him go, Lessing thought, and tried to force the thin, angry man firmly out of his mind. But somehow Melrose wouldn't force. "Stop worrying about it," Dorffman urged. "He's a crackpot. He's crawled way out on a limb, and now he's afraid your theory is going to cut it off under him. Well, that's his worry, not yours." Dorffman's face was intense. "Scientifically, you're on unshakeable ground. Every great researcher has people like Melrose sniping at him. You just have to throw them off and keep going." Lessing shook his head. "Maybe. But this field of work is different from any other, Jack. It doesn't follow the rules. Maybe scientific grounds aren't right at all, in this case." Dorffman snorted. "Surely there's nothing wrong with theorizing—" "He wasn't objecting to the theory. He's afraid of what happens after the theory." "So it seems. But why?" "Have you ever considered what makes a man an Authority?" "He knows more about his field than anybody else does." "He seems to, you mean. And therefore, anything he says about it carries more weight than what anybody else says. Other workers follow his lead. He developes ideas, formulates theories—and then defends them for all he's worth ." "But why shouldn't he?" "Because a man can't fight for his life and reputation and still keep his objectivity," said Lessing. "And what if he just happens to be wrong? Once he's an Authority the question of what's right and what's wrong gets lost in the shuffle. It's what he says that counts." "But we know you're right," Dorffman protested. "Do we?" "Of course we do! Look at our work! Look at what we've seen on the Farm." "Yes, I know." Lessing's voice was weary. "But first I think we'd better look at Tommy Gilman, and the quicker we look, the better—" A nurse greeted them as they stepped off the elevator. "We called you at the Farm, but you'd already left. The boy—" She broke off helplessly. "He's sick, Doctor. He's sicker than we ever imagined." "What happened?" "Nothing exactly—happened. I don't quite know how to describe it." She hurried them down the corridor and opened a door into a large children's playroom. "See what you think." The boy sat stolidly in the corner of the room. He looked up as they came in, but there was no flicker of recognition or pleasure on his pale face. The monitor helmet was still on his head. He just sat there, gripping a toy fire engine tightly in his hands. Lessing crossed the room swiftly. "Tommy," he said. The boy didn't even look at him. He stared stupidly at the fire engine. "Tommy!" Lessing reached out for the toy. The boy drew back in terror, clutching it to his chest. "Go away," he choked. "Go away, go away—" When Lessing persisted the boy bent over swiftly and bit him hard on the hand. Lessing sat down on the table. "Tommy, listen to me." His voice was gentle. "I won't try to take it again. I promise." "Go away." "Do you know who I am?" Tommy's eyes shifted haltingly to Lessing's face. He nodded. "Go away." "Why are you afraid, Tommy?" "I hurt. My head hurts. I hurt all over. Go away." "Why do you hurt?" "I—can't get it—off," the boy said. The monitor , Lessing thought suddenly. Something had suddenly gone horribly wrong—could the boy really be sensing the source of the trouble? Lessing felt a cold knot gather in the pit of his stomach. He knew what happened when adult psi-contact struck a psi-high youngster's mind. He had seen it a hundred times at the Farm. But even more—he had felt it in his own mind, bursting from the child. Like a violent physical blow, the hate and fear and suspicion and cruelty buried and repressed in the adult mind, crushing suddenly into the raw receptors of the child's mind like a smothering fog—it was a fearful thing. A healthy youngster could survive it, even though the scar remained. But this youngster was sick— And yet an animal instinctively seeks its own protection . With trembling fingers Lessing reached out and opened the baffle-snap on the monitor. "Take it off, Tommy," he whispered. The boy blinked in amazement, and pulled the grey helmet from his head. Lessing felt the familiar prickly feeling run down his scalp as the boy stared at him. He could feel deep in his own mind the cold chill of terror radiating from the boy. Then, suddenly, it began to fade. A sense of warmth—peace and security and comfort—swept in as the fear faded from the boy's face. The fire engine clattered to the floor. They analyzed the tapes later, punching the data cards with greatest care, filing them through the machines for the basic processing and classification that all their data underwent. It was late that night when they had the report back in their hands. Dorffman stared at it angrily. "It's obviously wrong," he grated. "It doesn't fit. Dave, it doesn't agree with anything we've observed before. There must be an error." "Of course," said Lessing. "According to the theory. The theory says that adult psi-contact is deadly to the growing child. It smothers their potential through repeated contact until it dries up completely. We've proved that, haven't we? Time after time. Everything goes according to the theory—except Tommy. But Tommy's psi-potential was drying up there on the Farm, until the distortion was threatening the balance of his mind. Then he made an adult contact, and we saw how he bloomed." Lessing sank down to his desk wearily. "What are we going to do, Jack? Formulate a separate theory for Tommy?" "Of course not," said Dorffman. "The instruments were wrong. Somehow we misread the data—" "Didn't you see his face ?" Lessing burst out. "Didn't you see how he acted ? What do you want with an instrument reading?" He shook his head. "It's no good, Jack. Something different happened here, something we'd never counted on. It's something the theory just doesn't allow for." They sat silently for a while. Then Dorffman said: "What are you going to do?" "I don't know," said Lessing. "Maybe when we fell into this bramble bush we blinded ourselves with the urge to classify—to line everything up in neat rows like pins in a paper. Maybe we were so blind we missed the path altogether." "But the book is due! The Conference speech—" "I think we'll make some changes in the book," Lessing said slowly. "It'll be costly—but it might even be fun. It's a pretty dry, logical presentation of ideas, as it stands. Very austere and authoritarian. But a few revisions could change all that—" He rubbed his hands together thoughtfully. "How about it, Jack? Do we have nerve enough to be laughed at? Do you think we could stand a little discredit, making silly asses of ourselves? Because when I finish this book, we'll be laughed out of existence. There won't be any Authority in psionics for a while—and maybe that way one of the lads who's really sniffing out the trail will get somebody to listen to him! "Get a pad, get a pencil! We've got work to do. And when we finish, I think we'll send a carbon copy out Chicago way. Might even persuade that puppy out there to come here and work for me—"
|
C. Philadelphia
|
How does the war affect the protagonist’s relationship with his wife?
A. She waits at home like they planned, greeting them lovingly.
B. She is transformed into a monster, striking fear in the protagonist.
C. She is killed during the war, her body nowhere to be found.
D. She patiently waits for him at home.
|
HOMECOMING BY MIGUEL HIDALGO What lasts forever? Does love? Does death?... Nothing lasts forever.... Not even forever [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, April 1958. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] The large horse plodded slowly over the shifting sand. The rider was of medium size, with huge, strong hands and seemingly hollow eyes. Strange eyes, alive and aflame. They had no place in the dust-caked, tired body, yet there they were, seeking, always seeking—searching the clear horizon, and never seeming to find what they sought. The horse moved faster now. They were nearing a river; the water would be welcome on tired bodies and dry throats. He spurred his horse, and when they reached the water's edge, he dismounted and unsaddled the horse. Then both man and horse plunged headlong into the waiting torrent, deep into the cool embrace of the clear liquid. They soaked it into their pores and drank deeply of it, feeling life going once more through their veins. Satisfied, they lifted themselves from the water, and the man lay down on the yellow sand of the river bank to sleep. When he awoke, the sun was almost setting. The bright shafts of red light spilled across the sky, making the mountains silent scarlet shadows on the face of the rippling water. Quickly he gathered driftwood, and built a small fire. From his pack he removed some of the coffee he had found in one of the ruined cities. He brought water from the river in the battered coffee-pot he had salvaged, and while he waited for it to boil, he went to his horse, Conqueror, stroking his mane and whispering in his ear. Then he led him silently to a grassy slope where he hobbled him and left him for the night. In the fading light, he ate the hard beef jerky and drank the scalding coffee. Refreshed and momentarily content, he sat staring into the dying fire, seeing the bright glowing coals as living fingers clutching at the wood in consuming embrace, taking all and returning nothing but ashes. Slowly his eyelids yielded. His body sagged, and blood seemed to fill his brain, bathing it in a gentle, warm flood. He slept. His brain slept. But the portion of his brain called memory stirred. It was all alone; all else was at rest. Images began to appear, drawn from inexhaustible files, wherein are kept all thoughts, past, present, and future.... It was the night before he was to go overseas. World War III had been declared, and he had enlisted, receiving his old rank of captain. He was with his wife in the living room of their home. They had put the children to bed—their sons—and now sat on the couch, watching the blazing fire. It was then that he had showed it to her. "I've got something to tell you, and something to show you." He had removed the box from his pocket and opened it. And heard her cry of surprised joy. "Oh, a ring, and it's a diamond, too!" she cried in her rich, happy voice which always seemed to send a thrill through his body. "It's for you; so long as you wear it, I'll come back, even from the dead, if need be. Read the inscription." She held the ring up to the light and read aloud, "It is forever." Then she had slipped the ring on her finger and her arms around him. He held her very close, feeling the warmth from her body flowing into his and making him oblivious to everything except that she was there in his arms and that he was sinking deep, deep into a familiar sea, where he had been many times before but each time found something new and unexplored, some vastly different emotion he could never quite explain. "Wait!" she cried. "I've something for you, too." She took off the locket she wore about her neck and held it up to the shimmering light, letting it spin at the end of its chain. It caught the shadows of the fire and reflected them, greatly magnified, over the room. It was in the shape of a star, encrusted with emeralds, with one large ruby in the center. When he opened it, he found a picture of her in one side, and in the other a picture of the children. He took her in his arms again, and loosened her long, black hair, burying his face in it for a moment. Then he kissed her, and instantly was drawn down into the abyss which seemed to have no beginning or any end. The next morning had been bleak and gray. The mist clung to the wet, sodden ground, and the air was heavy in his lungs. He had driven off in the jeep the army had sent for him, watching her there on the porch until the mist swirled around her feet and she ran back into the house and slammed the door. His cold fingers found the locket, making a little bulge under his uniform, and the touch of it seemed to warm the blood in his veins. Three days later they had landed in Spain, merged with another division, then crossed the Pyrenees into France, and finally to Paris where the fighting had begun. Already the city was a silent graveyard, littered with the rubble of towers and cathedrals which had once been great. Three years later they were on the road to Moscow. Over a thousand miles lay behind, a dead man on every foot of those miles. Yet victory was near. The Russians had not yet used the H-bomb; the threat of annihilation by the retaliation forces had been too great. He had done well in the war, and had been decorated many times for bravery in action. Now he felt the victory that seemed to be in the air, and he had wished it would come quickly, so that he might return to her. Home. The very feel of the word was everything a battle-weary soldier needed to make him fight harder and live longer. Suddenly he had become aware of a droning, wooshing sound above him. It grew louder and louder until he knew what it was. "Heavy bombers!" The alarm had sounded, and the men had headed for their foxholes. But the planes had passed over, the sun glinting on their bellies, reflecting a blinding light. They were bound for bigger, more important targets. When the all-clear had sounded, the men clambered from their shelters. An icy wind swept the field, bringing with it clouds which covered the sun. A strange fear had gripped him then.... Across the Atlantic, over the pole, via Alaska, the great bombers flew. In cities, great and small, the air raid sirens sounded, high screaming noises which had jarred the people from sleep in time to die. The defending planes roared into the sky to intercept the on-rushing bombers. The horrendous battle split the universe. Many bombers fell, victims of fanatical suicide planes, or of missiles that streaked across the sky which none could escape. But too many bombers got through, dropping their deadly cargo upon the helpless cities. And not all the prayers or entreaties to any God had stopped their carnage. First there had been the red flashes that melted buildings into molten streams, and then the great triple-mushroom cloud filled with the poisonous gases that the wind swept away to other cities, where men had not died quickly and mercifully, but had rotted away, leaving shreds of putrid flesh behind to mark the places where they had crawled. The retaliatory forces had roared away to bomb the Russian cities. Few, if any, had returned. Too much blood and life were on their hands. Those who had remained alive had found a resting place on the crown of some distant mountain. Others had preferred the silent peaceful sea, where flesh stayed not long on bones, and only darting fishes and merciful beams of filtered light found their aluminum coffins. The war had ended. To no avail. Neither side had won. Most of the cities and the majority of the population of both countries had been destroyed. Even their governments had vanished, leaving a silent nothingness. The armies that remained were without leaders, without sources of supplies, save what they could forage and beg from an unfriendly people. They were alone now, a group of tired, battered men, for whom life held nothing. Their families had long since died, their bodies turned to dust, their spirits fled on the winds to a new world. Yet these remnants of an army must return—or at least try. Their exodus was just beginning. Somehow he had managed to hold together the few men left from his force. He had always nourished the hope that she might still be alive. And now that the war was over he had to return—had to know whether she was still waiting for him. They had started the long trek. Throughout Europe anarchy reigned. He and his men were alone. All they could do now was fight. Finally they reached the seaport city of Calais. With what few men he had left, he had commandeered a small yacht, and they had taken to the sea. After months of storms and bad luck, they had been shipwrecked somewhere off the coast of Mexico. He had managed to swim ashore, and had been found by a fisherman's family. Many months he had spent swimming and fishing, recovering his strength, inquiring about the United States. The Mexicans had spoken with fear of the land across the Rio Grande. All its great cities had been destroyed, and those that had been only partially destroyed were devoid of people. The land across the Rio Grande had become a land of shadows. The winds were poisoned, and the few people who might have survived, were crazed and maimed by the blasts. Few men had dared cross the Rio Grande into "El Mundo gris de Noviembre"—the November world. Those who had, had never returned. In time he had traveled north until he reached the Rio Grande. He had waded into the muddy waters and somehow landed on the American side. In the November world. It was rightly called. The deserts were long. All plant life had died, leaving to those once great fertile stretches, nothing but the sad, temporal beauty that comes with death. No people had he seen. Only the ruins of what had once been their cities. He had walked through them, and all that he had seen were the small mutant rodents, and all that he had heard was the occasional swish of the wind as it whisked along what might have been dead leaves, but wasn't. He had been on the trail for a long time. His food was nearly exhausted. The mountains were just beginning, and he hoped to find food there. He had not found food, but his luck had been with him. He had found a horse. Not a normal horse, but a mutation. It was almost twice as large as a regular horse. Its skin seemed to shimmer and was like glassy steel to the touch. From the center of its forehead grew a horn, straight out, as the horn of a unicorn. But most startling of all were the animal's eyes which seemed to speak—a silent mental speech, which he could understand. The horse had looked up as he approached it and seemed to say: "Follow me." And he had followed. Over a mountain, until they came to a pass, and finally to a narrow path which led to an old cabin. He had found it empty, but there were cans of food and a rifle and many shells. He had remained there a long time—how long he could not tell, for he could only measure time by the cycles of the sun and the moon. Finally he had taken the horse, the rifle and what food was left, and once again started the long journey home. The farther north he went, the more life seemed to have survived. He had seen great herds of horses like his own, stampeding across the plains, and strange birds which he could not identify. Yet he had seen no human beings. But he knew he was closer now. Closer to home. He recognized the land. How, he did not know, for it was much changed. A sensing, perhaps, of what it had once been. He could not be more than two days' ride away. Once he was through this desert, he would find her, he would be with her once again; all would be well, and his long journey would be over. The images faded. Even memory slept in a flow of warm blood. Body and mind slept into the shadows of the dawn. He awoke and stretched the cramped muscles of his body. At the edge of the water he removed his clothes and stared at himself in the rippling mirror. His muscles were lean and hard, evenly placed throughout the length of his frame. A deep ridge ran down the length of his torso, separating the muscles, making the chest broad. Well satisfied with his body, he plunged into the cold water, deep down, until he thought his lungs would burst; then swiftly returned to the clean air, tingling in every pore. He dried himself and dressed. Conqueror was eating the long grass near the stream. Quickly he saddled him. No time for breakfast. He would ride all day and the next night. And he would be home. Still northward. The hours crawled slower than a dying man. The sun was a torch that pierced his skin, seeming to melt his bones into a burning stream within his body. But day at last gave way to night, and the sun to the moon. The torch became a white pock-marked goddess, with streaming hair called stars. In the moonlight he had not seen the crater until he was at its very edge. Even then he might not have seen it had not the horse stopped suddenly. The wind swirled through its vast emptiness, slapping his face with dusty hands. For a moment he thought he heard voices—mournful, murmuring voices, echoing up from the misty depths. He turned quickly away and did not look back. Night paled into day; day burned into night. There were clouds in the sky now, and a gentle wind caressed the sweat from his tired body. He stopped. There it was! Barely discernible through the moonlight, he saw it. Home. Quickly he dismounted and ran. Now he could see a small light in the window, and he knew they were there. His breath came in hard ragged gulps. At the window he peered in, and as his eyes became accustomed to the inner gloom, he saw how bare the room was. No matter. Now that he was home he would build new furniture, and the house would be even better than it had been before. Then he saw her. She was sitting motionless in a straight wooden chair beside the fireplace, the feeble light cast by the embers veiling her in mauve shadows. He waited, wondering if she were.... Presently she stirred like a restless child in sleep, then moved from the chair to the pile of wood near the hearth, and replenished the fire. The wood caught quickly, sending up long tongues of flame, and forming a bright pool of light around her. His blood froze. The creature illuminated by the firelight was a monster. Large greasy scales covered its face and arms, and there was no hair on its head. Its gums were toothless cavities in a sunken, mumbling mouth. The eyes, turned momentarily toward the window, were empty of life. "No, no!" he cried soundlessly. This was not his house. In his delirium he had only imagined he had found it. He had been searching so long. He would go on searching. He was turning wearily away from the window when the movement of the creature beside the fire held his attention. It had taken a ring from one skeleton-like finger and stood, turning the ring slowly as if trying to decipher some inscription inside it. He knew then. He had come home. Slowly he moved toward the door. A great weakness was upon him. His feet were stones, reluctant to leave the earth. His body was a weed, shriveled by thirst. He grasped the doorknob and clung to it, looking up at the night sky and trying to draw strength from the wind that passed over him. It was no use. There was no strength. Only fear—a kind of fear he had never known. He fumbled at his throat, his fingers crawling like cold worms around his neck until he found the locket and the clasp which had held it safely through endless nightmare days and nights. He slipped the clasp and the locket fell into his waiting hand. As one in a dream, he opened it, and stared at the pictures, now in the dim moonlight no longer faces of those he loved, but grey ghosts from the past. Even the ruby had lost its glow. What had once been living fire was now a dull glob of darkness. "Nothing is forever!" He thought he had shouted the words, but only a thin sound, the sound of leaves ruffled by the wind, came back to him. He closed the locket and fastened the clasp, and hung it on the doorknob. It moved slowly in the wind, back and forth, like a pendulum. "Forever—forever. Only death is forever." He could have sworn he heard the words. He ran. Away from the house. To the large horse with a horn in the center of its forehead, like a unicorn. Once in the saddle, the spurt of strength left him. His shoulders slumped, his head dropped onto his chest. Conqueror trotted away, the sound of his hooves echoing hollowly in the vast emptiness.
|
B. She is transformed into a monster, striking fear in the protagonist.
|
How might the story's conclusion have differed if Phil, in the beginning of the story, had agreed to Mary's wish?
A. The conclusion would likely not have differed -- Phil would lose his sense of purpose and thus his vitality in a relationship
B. Phil would have agreed to Mary's wishes, but left to go on the mission without telling here
C. Phil would eventually come to accept Mary's fear and let go of his dream to go to the moon
D. Phil would have tried to keep a positive attitude and wait his turn for the next mission
|
Transcriber's Note: This etext was produced from Astounding Science Fiction December 1955. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed. BREAKAWAY BY STANLEY GIMBLE Illustrated by Freas She surely got her wish ... but there was some question about getting what she wanted. Phil Conover pulled the zipper of his flight suit up the front of his long, thin body and came into the living room. His face, usually serious and quietly handsome, had an alive, excited look. And the faint lines around his dark, deep-set eyes were accentuated when he smiled at his wife. "All set, honey. How do I look in my monkey suit?" His wife was sitting stiffly on the flowered couch that was still not theirs completely. In her fingers she held a cigarette burned down too far. She said, "You look fine, Phil. You look just right." She managed a smile. Then she leaned forward and crushed the cigarette in the ash tray on the maple coffee table and took another from the pack. He came to her and touched his hands to her soft blond hair, raising her face until she was looking into his eyes. "You're the most beautiful girl I know. Did I ever tell you that?" "Yes, I think so. Yes, I'm sure you did," she said, finishing the ritual; but her voice broke, and she turned her head away. Phil sat beside her and put his arm around her small shoulders. He had stopped smiling. "Honey, look at me," he said. "It isn't going to be bad. Honestly it isn't. We know exactly how it will be. If anything could go wrong, they wouldn't be sending me; you know that. I told you that we've sent five un-manned ships up and everyone came back without a hitch." She turned, facing him. There were tears starting in the corners of her wide, brown eyes, and she brushed them away with her hand. "Phil, don't go. Please don't. They can send Sammy. Sammy doesn't have a wife. Can't he go? They'd understand, Phil. Please!" She was holding his arms tightly with her hands, and the color had drained from her cheeks. "Mary, you know I can't back out now. How could I? It's been three years. You know how much I've wanted to be the first man to go. Nothing would ever be right with me again if I didn't go. Please don't make it hard." He stopped talking and held her to him and stroked the back of her head. He could feel her shoulders shaking with quiet sobs. He released her and stood up. "I've got to get started, Mary. Will you come to the field with me?" "Yes, I'll come to say good-by." She paused and dropped her eyes. "Phil, if you go, I won't be here when you get back—if you get back. I won't be here because I won't be the wife of a space pilot for the rest of my life. It isn't the kind of life I bargained for. No matter how much I love you, I just couldn't take that, Phil. I'm sorry. I guess I'm not the noble sort of wife." She finished and took another cigarette from the pack on the coffee table and put it to her lips. Her hand was trembling as she touched the lighter to the end of the cigarette and drew deeply. Phil stood watching her, the excitement completely gone from his eyes. "I wish you had told me this a long time ago, Mary," Phil said. His voice was dry and low. "I didn't know you felt this way about it." "Yes, you did. I told you how I felt. I told you I could never be the wife of a space pilot. But I don't think I ever really believed it was possible—not until this morning when you said tonight was the take-off. It's so stupid to jeopardize everything we've got for a ridiculous dream!" He sat down on the edge of the couch and took her hands between his. "Mary, listen to me," he said. "It isn't a dream. It's real. There's nothing means anything more to me than you do—you know that. But no man ever had the chance to do what I'm going to do tonight—no man ever. If I backed out now for any reason, I'd never be able to look at the sky again. I'd be through." She looked at him without seeing him, and there was nothing at all in her eyes. "Let's go, if you're still going," she finally said. They drove through the streets of the small town with its small bungalows, each alike. There were no trees and very little grass. It was a new town, a government built town, and it had no personality yet. It existed only because of the huge ship standing poised in the take-off zone five miles away in the desert. Its future as a town rested with the ship, and the town seemed to feel the uncertainty of its future, seemed ready to stop existing as a town and to give itself back to the desert, if such was its destiny. Phil turned the car off the highway onto the rutted dirt road that led across the sand to the field where the ship waited. In the distance they could see the beams of the searchlights as they played across the take-off zone and swept along the top of the high wire fence stretching out of sight to right and left. At the gate they were stopped by the guard. He read Phil's pass, shined his flashlight in their faces, and then saluted. "Good luck, colonel," he said, and shook Phil's hand. "Thanks, sergeant. I'll be seeing you next week," Phil said, and smiled. They drove between the rows of wooden buildings that lined the field, and he parked near the low barbed fence ringing the take-off zone. He turned off the ignition, and sat quietly for a moment before lighting a cigarette. Then he looked at his wife. She was staring through the windshield at the rocket two hundred yards away. Its smooth polished surface gleamed in the spotlight glare, and it sloped up and up until the eye lost the tip against the stars. "She's beautiful, Mary. You've never seen her before, have you?" "No, I've never seen her before," she said. "Hadn't you better go?" Her voice was strained and she held her hands closed tightly in her lap. "Please go now, Phil," she said. He leaned toward her and touched her cheek. Then she was in his arms, her head buried against his shoulder. "Good-by, darling," she said. "Wish me luck, Mary?" he asked. "Yes, good luck, Phil," she said. He opened the car door and got out. The noise of men and machines scurrying around the ship broke the spell of the rocket waiting silently for flight. "Mary, I—" he began, and then turned and strode toward the administration building without looking back. Inside the building it was like a locker room before the big game. The tension stood alone, and each man had the same happy, excited look that Phil had worn earlier. When he came into the room, the noise and bustle stopped. They turned as one man toward him, and General Small came up to him and took his hand. "Hello, Phil. We were beginning to think you weren't coming. You all set, son?" "Yes, sir, I'm all set, I guess," Phil said. "I'd like you to meet the Secretary of Defense, Phil. He's over here by the radar." As they crossed the room, familiar faces smiled, and each man shook his hand or touched his arm. He saw Sammy, alone, by the coffee urn. Sammy waved to him, but he didn't smile. Phil wanted to talk to him, to say something; but there was nothing to be said now. Sammy's turn would come later. "Mr. Secretary," the general said, "this is Colonel Conover. He'll be the first man in history to see the other side of the Moon. Colonel—the Secretary of Defense." "How do you do, sir. I'm very proud to meet you," Phil said. "On the contrary, colonel. I'm very proud to meet you. I've been looking at that ship out there and wondering. I almost wish I were a young man again. I'd like to be going. It's a thrilling thought—man's first adventure into the universe. You're lighting a new dawn of history, colonel. It's a privilege few men have ever had; and those who have had it didn't realize it at the time. Good luck, and God be with you." "Thank you, sir. I'm aware of all you say. It frightens me a little." The general took Phil's arm and they walked to the briefing room. There were chairs set up for the scientists and Air Force officers directly connected with the take-off. They were seated now in a semicircle in front of a huge chart of the solar system. Phil took his seat, and the last minute briefing began. It was a routine he knew by heart. He had gone over and over it a thousand times, and he only half listened now. He kept thinking of Mary outside, alone by the fence. The voice of the briefing officer was a dull hum in his ears. "... And orbit at 18,000-mph. You will then accelerate for the breakaway to 24,900-mph for five minutes and then free-coast for 116 hours until—" Phil asked a few questions about weather and solar conditions. And then the session was done. They rose and looked at each other, the same unanswered questions on each man's face. There were forced smiles and handshakes. They were ready now. "Phil," the general said, and took him aside. "Sir?" "Phil, you're ... you feel all right, don't you, son?" "Yes, sir. I feel fine. Why?" "Phil, I've spent nearly every day with you for three years. I know you better than I know myself in many ways. And I've studied the psychologist's reports on you carefully. Maybe it's just nervousness, Phil, but I think there's something wrong. Is there?" "No, sir. There's nothing wrong," Phil said, but his voice didn't carry conviction. He reached for a cigarette. "Phil, if there is anything—anything at all—you know what it might mean. You've got to be in the best mental and physical condition of your life tonight. You know better than any man here what that means to our success. I think there is something more than just natural apprehension wrong with you. Want to tell me?" Outside, the take-off zone crawled with men and machines at the base of the rocket. For ten hours, the final check-outs had been in progress; and now the men were checking again, on their own time. The thing they had worked toward for six years was ready to happen, and each one felt that he was sending just a little bit of himself into the sky. Beyond the ring of lights and moving men, on the edge of the field, Mary stood. Her hands moved slowly over the top of the fence, twisting the barbs of wire. But her eyes were on the ship. And then they were ready. A small group of excited men came out from the administration building and moved forward. The check-out crews climbed into their machines and drove back outside the take-off zone. And, alone, one man climbed the steel ladder up the side of the rocket—ninety feet into the air. At the top he waved to the men on the ground and then disappeared through a small port. Mary waved to him. "Good-by," she said to herself, but the words stuck tight in her throat. The small group at the base of the ship turned and walked back to the fence. And for an eternity the great ship stood alone, waiting. Then, from deep inside, a rumble came, increasing in volume to a gigantic roar that shook the earth and tore at the ears. Slowly, the first manned rocket to the Moon lifted up and up to the sky. For a long time after the rocket had become a tiny speck of light in the heavens, she stood holding her face in her hands and crying softly to herself. And then she felt the touch of a hand on her arm. She turned. "Phil! Oh, Phil." She held tightly to him and repeated his name over and over. "They wouldn't let me go, Mary," he said finally. "The general would not let me go." She looked at him. His face was drawn tight, and there were tears on his cheeks. "Thank, God," she said. "It doesn't matter, darling. The only thing that matters is you didn't go." "You're right, Mary," he said. His voice was low—so low she could hardly hear him. "It doesn't matter. Nothing matters now." He stood with his hands at his sides, watching her. And then turned away and walked toward the car. THE END
|
A. The conclusion would likely not have differed -- Phil would lose his sense of purpose and thus his vitality in a relationship
|
What two benchmark datasets are used?
|
### Introduction
Task-oriented dialogue system is an important tool to build personal virtual assistants, which can help users to complete most of the daily tasks by interacting with devices via natural language. It's attracting increasing attention of researchers, and lots of works have been proposed in this area BIBREF0, BIBREF1, BIBREF2, BIBREF3, BIBREF4, BIBREF5, BIBREF6, BIBREF7. The existing task-oriented dialogue systems usually consist of four components: (1) natural language understanding (NLU), it tries to identify the intent of a user; (2) dialogue state tracker (DST), it keeps the track of user goals and constraints in every turn; (3) dialogue policy maker (DP), it aims to generate the next available dialogue action; and (4) natural language generator (NLG), it generates a natural language response based on the dialogue action. Among the four components, dialogue policy maker plays a key role in order to complete dialogues effectively, because it decides the next dialogue action to be executed. As far as we know, the dialogue policy makers in most existing task-oriented dialogue systems just use the classifiers of the predefined acts to obtain dialogue policy BIBREF0, BIBREF2, BIBREF4, BIBREF8, BIBREF9. The classification-based dialogue policy learning methods can assign either only a dialogue act and its corresponding parameters BIBREF10, BIBREF2, BIBREF0 or multiple dialogue acts without their corresponding parameters for a dialogue action BIBREF11. However, all these existing methods cannot obtain multiple dialogue acts and their corresponding parameters for a dialogue action at the same time. Intuitively, it will be more reasonable to construct multiple dialogue acts and their corresponding parameters for a dialogue action at the same time. For example, it can be shown that there are 49.4% of turns in the DSTC2 dataset and 61.5% of turns in the Maluuba dataset have multiple dialogue acts and their corresponding parameters as the dialogue action. If multiple dialogue acts and their corresponding parameters can be obtained at the same time, the final response of task-oriented dialogue systems will become more accurate and effective. For example, as shown in Figure FIGREF3, a user wants to get the name of a cheap french restaurant. The correct dialogue policy should generate three acts in current dialogue turn: offer(name=name_slot), inform(food=french) and inform(food=cheap). Thus, the user's real thought may be: “name_slot is a cheap french restaurant". If losing the act offer, the system may generate a response like “There are some french restaurants", which will be far from the user's goal. To address this challenge, we propose a Generative Dialogue Policy model (GDP) by casting the dialogue policy learning problem as a sequence optimization problem. The proposed model generates a series of acts and their corresponding parameters by the learned dialogue policy. Specifically, our proposed model uses a recurrent neural network (RNN) as action decoder to construct dialogue policy maker instead of traditional classifiers. Attention mechanism is used to help the decoder decode dialogue acts and their corresponding parameters, and then the template-based natural language generator uses the results of the dialogue policy maker to choose an appropriate sentence template as the final response to the user. Extensive experiments conducted on two benchmark datasets verify the effectiveness of our proposed method. Our contributions in this work are three-fold. The existing methods cannot construct multiple dialogue acts and their corresponding parameters at the same time. In this paper, We propose a novel generative dialogue policy model to solve the problem. The extensive experiments demonstrate that the proposed model significantly outperforms the state-of-the-art baselines on two benchmarks. We publicly release the source code. ### Related Work
Usually, the existing task-oriented dialogue systems use a pipeline of four separate modules: natural language understanding, dialogue belief tracker, dialogue policy and natural language generator. Among these four modules, dialogue policy maker plays a key role in task-oriented dialogue systems, which generates the next dialogue action. As far as we know, nearly all the existing approaches obtain the dialogue policy by using the classifiers of all predefined dialogue acts BIBREF12, BIBREF13. There are usually two kinds of dialogue policy learning methods. One constructs a dialogue act and its corresponding parameters for a dialogue action. For example, BIBREF0 constructs a simple classifier for all the predefined dialogue acts. BIBREF2 build a complex classifier for some predefined dialogue acts, addtionally BIBREF2 adds two acts for each parameter: one to inform its value and the other to request it. The other obtains the dialogue policy by using multi-label classification to consider multiple dialogue acts without their parameters. BIBREF11 performs multi-label multi-class classification for dialogue policy learning and then the multiple acts can be decided based on a threshold. Based on these classifiers, the reinforcement learning can be used to further update the dialogue policy of task-oriented dialogue systems BIBREF3, BIBREF14, BIBREF9. In the real scene, an correct dialogue action usually consists of multiple dialogue acts and their corresponding parameters. However, it is very hard for existing classification-based dialogue policy maker to achieve this goal. Thus, in this paper we propose a novel generative dialogue policy maker to address this issue by casting the dialogue policy learning problem as a sequence optimization problem. ### Technical Background ::: Encoder-Decoder Seq2Seq Models
Seq2Seq model was first introduced by BIBREF15 for statistical machine translation. It uses two recurrent neural networks (RNN) to solve the sequence-to-sequence mapping problem. One called encoder encodes the user utterance into a dense vector representing its semantics, the other called decoder decodes this vector to the target sentence. Now Seq2Seq framework has already been used in task-oriented dialog systems such as BIBREF4 and BIBREF1, and shows the challenging performance. In the Seq2Seq model, given the user utterance $Q=(x_1, x_2, ..., x_n)$, the encoder squeezes it into a context vector $C$ and then used by decoder to generate the response $R=(y_1, y_2, ..., y_m)$ word by word by maximizing the generation probability of $R$ conditioned on $Q$. The objective function of Seq2Seq can be written as: In particular, the encoder RNN produces the context vector $C$ by doing calculation below: The $h_t$ is the hidden state of the encoder RNN at time step $t$ and $f$ is the non-linear transformation which can be a long-short term memory unit LSTM BIBREF16 or a gated recurrent unit GRU BIBREF15. In this paper, we implement $f$ by using GRU. The decoder RNN generates each word in reply conditioned on the context vector $C$. The probability distribution of candidate words at every time step $t$ is calculated as: The $s_t$ is the hidden state of decoder RNN at time step $t$ and $y_{t-1}$ is the generated word in the reply at time $t-1$ calculated by softmax operations. ### Technical Background ::: Attention Mechanism
Attention mechanisms BIBREF17 have been proved to improved effectively the generation quality for the Seq2Seq framework. In Seq2Seq with attention, each $y_i$ corresponds to a context vector $C_i$ which is calculated dynamically. It is a weighted average of all hidden states of the encoder RNN. Formally, $C_i$ is defined as $C_i=\sum _{j=1}^{n} \alpha _{ij}h_j$, where $\alpha _{ij}$ is given by: where $s_{i-1}$ is the last hidden state of the decoder, the $\eta $ is often implemented as a multi-layer-perceptron (MLP) with tanh as the activation function. ### Generative Dialogue Policy
Figure FIGREF13 shows the overall system architecture of the proposed GDP model. Our model contains five main components: (1) utterance encoder; (2) dialogue belief tracker; (3) dialogue policy maker; (4) knowledge base; (5) template-based natural language generator. Next, we will describe each component of our proposed GDP model in detail. ### Generative Dialogue Policy ::: Notations and Task Formulation
Given the user utterance $U_t$ at turn $t$ and the dialogue context $C_{t-1}$ which contains the result of the dialogue belief tracker at turn $t-1$, the task-oriented dialog system needs to generate user's intents $C_t$ by dialogue belief tracker and then uses this information to get the knowledge base query result $k_t \in \mathbb {R}^k$. Then the model needs to generate the next dialogue action $A_t$ based on $k_t$, $U_t$ and $C_t$. The natural language generator provides the template-based response $R_t$ as the final reply by using $A_t$. The $U_t$ and $C_t$ are the sequences, $k_t$ is a one-hot vector representing the number of the query results. For baselines, in this paper, the $A_t$ is the classification result of the next dialogue action, but in our proposed model it's a sequence which contains multiple acts and their corresponding parameters. ### Generative Dialogue Policy ::: Utterance Encoder
A bidirectional GRU is used to encode the user utterance $U_t$, the last turn response $R_{t-1}$ made by the system and the dialogue context $C_{t-1}$ into a continuous representation. The vector is generated by concatenating the last forward and backward GRU states. $U_t = (w_1, w_2, ..., w_{T_m})$ is the user utterance at turn $t$. $C_{t-1}=(c_1, c_2, ..., c_{T_n})$ is the dialogue context made by dialogue belief tracker at $t-1$ turn. $R_{t-1}$ is the response made by our task-oriented dialogue system at last turn. Then the words of $[C_{t-1}, R_{t-1}, U_t]$ are firstly mapped into an embedding space and further serve as the inputs of each step to the bidirectional GRU. Let $n$ denotes the number of words in the sequence $[C_{t-1}, R_{t-1}, U_t]$. The $\overrightarrow{h_{t^{\prime }}^u}$ and $\overleftarrow{h_{t^{\prime }}^u}$ represent the forward and backward GRU state outputs at time step $t^{\prime }$. The encoder output of timestep $i$ denote as $\overline{h_i^u}$. where $e([C_{t-1}, R_{t-1}, U_t])$ is the embedding of the input sequence, $d_h$ is the hidden size of the GRU. $H_u$ contains the encoder hidden state of each timestep, which will be used by attention mechanism in dialogue policy maker. ### Generative Dialogue Policy ::: Dialogue State Tracker
Dialogue state tracker maintains the state of a conversation and collects the user's goals during the dialogue. Recent work successfully represents this component as discriminative classifiers. BIBREF5 verified that the generation is a better way to model the dialogue state tracker. Specifically, we use a GRU as the generator to decode the $C_t$ of current turn. In order to capture user intent information accurately, the basic attention mechanism is calculated when the decoder decodes the $C_t$ at each step, which is the same as the Eq. (DISPLAY_FORM12). where $m$ is the length of $C_t$, $e(y_i)$ is the embedding of the token, $d_h$ is the hidden size of the GRU and the hidden state at $i$ timestep of the RNN in dialogue state tracker denote as $h_i^d$. The decoded token at step $i$ denotes as $y_i^d$. ### Generative Dialogue Policy ::: Knowledge Base
Knowledge base is a database that stores information about the related task. For example, in the restaurant reservation, a knowledge base stores the information of all the restaurants, such as location and price. After dialogue belief tracker, the $C_t$ will be used as the constraints to search the results in knowledge base. Then the one-hot vector $k_t$ will be produced when the system gets the number of the results. The search result $k_t$ has a great influence on dialogue policy. For example, if the result has multiple matches, the system should request more constraints of the user. In practice, let $k_t$ be an one-hot vector of 20 dimensions to represent the number of query results. Then $k_t$ will be used as the cue for dialogue policy maker. ### Generative Dialogue Policy ::: Dialogue Policy Maker
In task-oriented dialogue systems, supervised classification is a straightforward solution for dialogue policy modeling. However, we observe that classification cannot hold enough information for dialogue policy modeling. The generative approach is another way to model the dialogue policy maker for task-oriented dialogue systems, which generates the next dialogue acts and their corresponding parameters based on the dialogue context word by word. Thus the generative approach converts the dialogue policy learning problem into a sequence optimization problem. The dialogue policy maker generates the next dialogue action $A_t$ based on $k_t$ and $[H_u, H_d]$. Our proposed model uses the GRU as the action decoder to decode the acts and their parameters for the response. Particularly, at step $i$, for decoding $y_i^p$ of $A_t$, the decoder GRU takes the embedding of $y_{i-1}^p$ to generate a hidden vector $h_i^p$. Basic attention mechanism is calculated. where $e$ is the embedding of the token, $c_u$ is the context vector of the input utterance and $c_d$ is the context vector of the dialogue state tracker. $h_i^p$ is the hidden state of the GRU in dialogue policy maker at $i$ timestep. where $y_i^p$ is the token decoded at $i$ timestep. And the final results of dialogue policy maker denote as $A_t$, and the $k$ is the length of it. In our proposed model, the dialogue policy maker can be viewed as a decoder of the seq2seq model conditioned on $[C_{t-1},R_{t-1},U_t]$ and $k_t$. ### Generative Dialogue Policy ::: Nature Language Generator
After getting the dialogue action $A_t$ by the learned dialogue policy maker, the task-oriented dialogue system needs to generate an appropriate response $R_t$ for users. We construct the natural language generator by using template sentences. For each dataset, we extract all the system responses, then we manually modify responses to construct the sentence templates for task-oriented dialogue systems. In our proposed model, the sequence of the acts and parameters $A_t$ will be used for searching appropriate template. However, the classification-based baselines use the categories of acts and their corresponding parameters to search the corresponding template. ### Generative Dialogue Policy ::: Training
In supervised learning, because our proposed model is built in a seq2seq way, the standard cross entropy is adopted as our objective function to train dialogue belief tracker and dialogue policy maker. After supervised learning, the dialogue policy can be further updated by using reinforcement learning. In the context of reinforcement learning, the decoder of dialogue policy maker can be viewed as a policy network, denoted as $\pi _{\theta }(y_j)$ for decoding $y_j$, $\theta $ is the parameters of the decoder. Accordingly, the hidden state created by GRU is the corresponding state, and the choice of the current token $y_j$ is an action. Reward function is also very important for reinforcement learning when decoding every token. To encourage our policy maker to generate correct acts and their corresponding parameters, we set the reward function as follows: once the dialogue acts and their parameters are decoded correctly, the reward is 2; otherwise, the reward is -5; only the label of the dialogue act is decoded correctly but parameters is wrong, the reward is 1; $\lambda $ is a decay parameter. More details are shown in Sec SECREF41. In our proposed model, rewards can only be obtained at the end of decoding $A_t$. In order to get the rewards at each decoding step, we sample some results $A_t$ after choosing $y_j$, and the reward of $y_j$ is set as the average of all the sampled results' rewards. In order to ensure that the model's performance is stable during the fine-tuning phase of reinforcement learning, we freeze the parameters of user utterance and dialogue belief tracker, only the parameters of the dialogue policy maker will be optimized by reinforcement learning. Policy gradient algorithm REINFORCE BIBREF18 is used for pretrained dialogue policy maker: where the $m$ is the length of the decoded action. The objective function $J$ can be optimized by gradient descent. ### Experiments
We evaluate the performance of the proposed model in three aspects: (1) the accuracy of the dialogue state tracker, it aims to show the impact of the dialogue state tracker on the dialogue policy maker; (2) the accuracy of dialogue policy maker, it aims to explain the performance of different methods of constructing dialogue policy; (3) the quality of the final response, it aims to explain the impact of the dialogue policy on the final dialogue response. The evaluation metrics are listed as follows: BPRA: Belief Per-Response Accuracy (BPRA) tests the ability to generate the correct user intents during the dialogue. This metric is used to evaluate the accuracy of dialogue belief tracker BIBREF1. APRA: Action Per-Response Accuracy (APRA) evaluates the per-turn accuracy of the dialogue actions generated by dialogue policy maker. For baselines, APRA evaluates the classification accuracy of the dialogue policy maker. But our model actually generates each individual token of actions, and we consider a prediction to be correct only if every token of the model output matches the corresponding token in the ground truth. BLEU BIBREF19: The metric evaluates the quality of the final response generated by natural language generator. The metric is usually used to measure the performance of the task-oriented dialogue system. We also choose the following metrics to evaluate the efficiency of training the model: $\mathbf {Time_{full}}$: The time for training the whole model, which is important for industry settings. $\mathbf {Time_{DP}}$: The time for training the dialogue policy maker in a task-oriented dialogue system. ### Experiments ::: Datasets
We adopt the DSTC2 BIBREF20 dataset and Maluuba BIBREF21 dataset to evaluate our proposed model. Both of them are the benchmark datasets for building the task-oriented dialog systems. Specifically, the DSTC2 is a human-machine dataset in the single domain of restaurant searching. The Maluuba is a very complex human-human dataset in travel booking domain which contains more slots and values than DSTC2. Detailed slot information in each dataset is shown in Table TABREF34. ### Experiments ::: Baselines
For comparison, we choose two state-of-the-art baselines and their variants. E2ECM BIBREF11: In dialogue policy maker, it adopts a classic classification for skeletal sentence template. In our implement, we construct multiple binary classifications for each act to search the sentence template according to the work proposed by BIBREF11. CDM BIBREF10: This approach designs a group of classifications (two multi-class classifications and some binary classifications) to model the dialogue policy. E2ECM+RL: It fine tunes the classification parameters of the dialogue policy by REINFORCE BIBREF18. CDM+RL: It fine tunes the classification of the act and corresponding parameters by REINFORCE BIBREF18. In order to verify the performance of the dialogue policy maker, the utterance encoder and dialogue belief tracker of our proposed model and baselines is the same, only dialogue policy maker is different. ### Experiments ::: Parameters settings
For all models, the hidden size of dialogue belief tracker and utterance encoder is 350, and the embedding size $d_{emb}$ is set to 300. For our proposed model, the hidden size of decoder in dialogue policy maker is 150. The vocabulary size $|V|$ is 540 for DSTC2 and 4712 for Maluuba. And the size of $k_t$ is set to 20. An Adam optimizer BIBREF22 is used for training our models and baselines, with a learning rate of 0.001 for supervised training and 0.0001 for reinforcement learning. In reinforcement learning, the decay parameter $\lambda $ is set to 0.8. The weight decay is set to 0.001. And early stopping is performed on developing set. ### Experiments ::: Experimental Results
The experimental results of the proposed model and baselines will be analyzed from the following aspects. BPRA Results: As shown in Table TABREF35, most of the models have similar performance on BPRA on these two datasets, which can guarantee a consistent impact on the dialogue policy maker. All the models perform very well in BPRA on DSTC2 dataset. On Maluuba dataset, the BPRA decreases because of the complex domains. We can notice that BPRA of CDM is slightly worse than other models on Maluuba dataset, the reason is that the CDM's dialogue policy maker contains lots of classifications and has the bigger loss than other models because of complex domains, which affects the training of the dialogue belief tracker. APRA Results: Compared with baselines, GDP achieves the best performance in APRA on two datasets. It can be noted that we do not compare with the E2ECM baseline in APRA. E2ECM only uses a simple classifier to recognize the label of the acts and ignores the parameters information. In our experiment, APRA of E2ECM is slightly better than our method. Considering the lack of parameters of the acts, it's unfair for our GDP method. Furthermore, the CDM baseline considers the parameters of the act. But GDP is far better than CDM in supervised learning and reinforcement learning. BLEU Results: GDP significantly outperforms the baselines on BLEU. As mentioned above, E2ECM is actually slightly better than GDP in APRA. But in fact, we can find that the language quality of the response generated by GDP is still better than E2ECM, which proves that lack of enough parameters information makes it difficult to find the appropriate sentence template in NLG. It can be found that the BLEU of all models is very poor on Maluuba dataset. The reason is that Maluuba is a human-human task-oriented dialogue dataset, the utterances are very flexible, the natural language generator for all methods is difficult to generate an accurate utterance based on the context. And DSTC2 is a human-machine dialog dataset. The response is very regular so the effectiveness of NLG will be better than that of Maluuba. But from the results, the GDP is still better than the baselines on Maluuba dataset, which also verifies that our proposed method is more accurate in modeling dialogue policy on complex domains than the classification-based methods. Time and Model Size: In order to obtain more accurate and complete dialogue policy for task-oriented dialogue systems, the proposed model has more parameters on the dialogue policy maker than baselines. As shown in Figure FIGREF44, E2ECM has the minimal dialogue policy parameters because of the simple classification. It needs minimum training time, but the performance of E2ECM is bad. The number of parameters in the CDM model is slightly larger than E2ECM. However, because both of them are classification methods, they all lose some important information about dialogue policy. Therefore, we can see from the experimental results that the quality of CDM's dialogue policy is as bad as E2ECM. The number of dialogue policy maker's parameters in GDP model is much larger than baselines. Although the proposed model need more time to be optimized by supervised learning and reinforcement learning, the performance is much better than all baselines. ### Experiments ::: Case Study
Table TABREF43 illustrates an example of our proposed model and baselines on DSTC2 dataset. In this example, a user's goal is to find a cheap restaurant in the east part of the town. In the current turn, the user wants to get the address of the restaurant. E2ECM chooses the inform and offer acts accurately, but the lack of the inform's parameters makes the final output deviate from the user's goal. CDM generates the parameters of offer successfully, but the lack of the information of inform also leads to a bad result. By contrast, the proposed model GDP can generate all the acts and their corresponding parameters as the dialogue action. Interestingly, the final result of GDP is exactly the same as the ground truth, which verifies that the proposed model is better than the state-of-the-art baselines. ### Conclusion
In this paper, we propose a novel model named GDP. Our proposed model treats the dialogue policy modeling as the generative task instead of the discriminative task which can hold more information for dialogue policy modeling. We evaluate the GDP on two benchmark task-oriented dialogue datasets. Extensive experiments show that GDP outperforms the existing classification-based methods on both action accuracy and BLEU. Figure 1: The examples in DSTC2 dataset, our proposed model can hold more information about dialogue policy than the classification models mentioned above. “MA, w/o P” is the model that chooses multiple acts without corresponding parameters during dialogue police modeling, “w/o MA, P” is the model that chooses only one act and its parameters. Figure 2: GDP overview. The utterance encoder encodes the user utterance, the dialogue context and the last reply of the systems into the dense vector. As for dialogue belief tracker, we use the approach of Lei et al. (2018) to generate dialogue context. Then this information will be used to search the knowledge base. Based on the user’s intents and query results, dialogue policy maker generates the next dialogue action by using our RNN-based proposed method. Table 1: The details of DSTC2 and Maluuba dataset. The Maluuba dataset is more complex than DSTC2, and has some continuous value space such as time and price which is hard to solve for classification model. Table 2: The performance of baselines and proposed model on DSTC2 and Maluuba dataset. T imefull is the time spent on training the whole model, T imeDP is the time spent on training the dialogue policy maker. Table 3: Case Study on DSTC2 dataset. The first column is the Dialogue Context of this case, it contains three parts: (1) Inf is the user’s intent captured by dialogue state tracker; (2) sys is the system response at last turn; (3) user is the user utterance in this turn. The second column to the fifth column has two rows, above is the action made by the learned dialogue policy maker below is the final response made by template-based generator. Figure 3: The number of the parameters. GDP has the bigger model size and more dialogue policy parameters because of the RNN-based dialogue policy maker.
|
DSTC2, Maluuba
|
What traits best describe Searles?
A. Empathetic and beautiful
B. Resourceful and dilligent
C. Original and bold
D. Intelligent and original
|
The Snowball Effect By KATHERINE MacLEAN Illustrated by EMSH [Transcriber's Note: This etext was produced from Galaxy Science Fiction September 1952. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Tack power drives on a sewing circle and you can needle the world into the darndest mess! "All right," I said, "what is sociology good for?" Wilton Caswell, Ph.D., was head of my Sociology Department, and right then he was mad enough to chew nails. On the office wall behind him were three or four framed documents in Latin that were supposed to be signs of great learning, but I didn't care at that moment if he papered the walls with his degrees. I had been appointed dean and president to see to it that the university made money. I had a job to do, and I meant to do it. He bit off each word with great restraint: "Sociology is the study of social institutions, Mr. Halloway." I tried to make him understand my position. "Look, it's the big-money men who are supposed to be contributing to the support of this college. To them, sociology sounds like socialism—nothing can sound worse than that—and an institution is where they put Aunt Maggy when she began collecting Wheaties in a stamp album. We can't appeal to them that way. Come on now." I smiled condescendingly, knowing it would irritate him. "What are you doing that's worth anything?" He glared at me, his white hair bristling and his nostrils dilated like a war horse about to whinny. I can say one thing for them—these scientists and professors always keep themselves well under control. He had a book in his hand and I was expecting him to throw it, but he spoke instead: "This department's analysis of institutional accretion, by the use of open system mathematics, has been recognized as an outstanding and valuable contribution to—" The words were impressive, whatever they meant, but this still didn't sound like anything that would pull in money. I interrupted, "Valuable in what way?" He sat down on the edge of his desk thoughtfully, apparently recovering from the shock of being asked to produce something solid for his position, and ran his eyes over the titles of the books that lined his office walls. "Well, sociology has been valuable to business in initiating worker efficiency and group motivation studies, which they now use in management decisions. And, of course, since the depression, Washington has been using sociological studies of employment, labor and standards of living as a basis for its general policies of—" I stopped him with both raised hands. "Please, Professor Caswell! That would hardly be a recommendation. Washington, the New Deal and the present Administration are somewhat touchy subjects to the men I have to deal with. They consider its value debatable, if you know what I mean. If they got the idea that sociology professors are giving advice and guidance—No, we have to stick to brass tacks and leave Washington out of this. What, specifically, has the work of this specific department done that would make it as worthy to receive money as—say, a heart disease research fund?" He began to tap the corner of his book absently on the desk, watching me. "Fundamental research doesn't show immediate effects, Mr. Halloway, but its value is recognized." I smiled and took out my pipe. "All right, tell me about it. Maybe I'll recognize its value." Prof. Caswell smiled back tightly. He knew his department was at stake. The other departments were popular with donors and pulled in gift money by scholarships and fellowships, and supported their professors and graduate students by research contracts with the government and industry. Caswell had to show a way to make his own department popular—or else. I couldn't fire him directly, of course, but there are ways of doing it indirectly. He laid down his book and ran a hand over his ruffled hair. "Institutions—organizations, that is—" his voice became more resonant; like most professors, when he had to explain something he instinctively slipped into his platform lecture mannerisms, and began to deliver an essay—"have certain tendencies built into the way they happen to have been organized, which cause them to expand or contract without reference to the needs they were founded to serve." He was becoming flushed with the pleasure of explaining his subject. "All through the ages, it has been a matter of wonder and dismay to men that a simple organization—such as a church to worship in, or a delegation of weapons to a warrior class merely for defense against an outside enemy—will either grow insensately and extend its control until it is a tyranny over their whole lives, or, like other organizations set up to serve a vital need, will tend to repeatedly dwindle and vanish, and have to be painfully rebuilt. "The reason can be traced to little quirks in the way they were organized, a matter of positive and negative power feedbacks. Such simple questions as, 'Is there a way a holder of authority in this organization can use the power available to him to increase his power?' provide the key. But it still could not be handled until the complex questions of interacting motives and long-range accumulations of minor effects could somehow be simplified and formulated. In working on the problem, I found that the mathematics of open system, as introduced to biology by Ludwig von Bertalanffy and George Kreezer, could be used as a base that would enable me to develop a specifically social mathematics, expressing the human factors of intermeshing authority and motives in simple formulas. "By these formulations, it is possible to determine automatically the amount of growth and period of life of any organization. The UN, to choose an unfortunate example, is a shrinker type organization. Its monetary support is not in the hands of those who personally benefit by its governmental activities, but, instead, in the hands of those who would personally lose by any extension and encroachment of its authority on their own. Yet by the use of formula analysis—" "That's theory," I said. "How about proof?" "My equations are already being used in the study of limited-size Federal corporations. Washington—" I held up my palm again. "Please, not that nasty word again. I mean, where else has it been put into operation? Just a simple demonstration, something to show that it works, that's all." He looked away from me thoughtfully, picked up the book and began to tap it on the desk again. It had some unreadable title and his name on it in gold letters. I got the distinct impression again that he was repressing an urge to hit me with it. He spoke quietly. "All right, I'll give you a demonstration. Are you willing to wait six months?" "Certainly, if you can show me something at the end of that time." Reminded of time, I glanced at my watch and stood up. "Could we discuss this over lunch?" he asked. "I wouldn't mind hearing more, but I'm having lunch with some executors of a millionaire's will. They have to be convinced that by, 'furtherance of research into human ills,' he meant that the money should go to research fellowships for postgraduate biologists at the university, rather than to a medical foundation." "I see you have your problems, too," Caswell said, conceding me nothing. He extended his hand with a chilly smile. "Well, good afternoon, Mr. Halloway. I'm glad we had this talk." I shook hands and left him standing there, sure of his place in the progress of science and the respect of his colleagues, yet seething inside because I, the president and dean, had boorishly demanded that he produce something tangible. I frankly didn't give a hoot if he blew his lid. My job isn't easy. For a crumb of favorable publicity and respect in the newspapers and an annual ceremony in a silly costume, I spend the rest of the year going hat in hand, asking politely for money at everyone's door, like a well-dressed panhandler, and trying to manage the university on the dribble I get. As far as I was concerned, a department had to support itself or be cut down to what student tuition pays for, which is a handful of over-crowded courses taught by an assistant lecturer. Caswell had to make it work or get out. But the more I thought about it, the more I wanted to hear what he was going to do for a demonstration. At lunch, three days later, while we were waiting for our order, he opened a small notebook. "Ever hear of feedback effects?" "Not enough to have it clear." "You know the snowball effect, though." "Sure, start a snowball rolling downhill and it grows." "Well, now—" He wrote a short line of symbols on a blank page and turned the notebook around for me to inspect it. "Here's the formula for the snowball process. It's the basic general growth formula—covers everything." It was a row of little symbols arranged like an algebra equation. One was a concentric spiral going up, like a cross-section of a snowball rolling in snow. That was a growth sign. I hadn't expected to understand the equation, but it was almost as clear as a sentence. I was impressed and slightly intimidated by it. He had already explained enough so that I knew that, if he was right, here was the growth of the Catholic Church and the Roman Empire, the conquests of Alexander and the spread of the smoking habit and the change and rigidity of the unwritten law of styles. "Is it really as simple as that?" I asked. "You notice," he said, "that when it becomes too heavy for the cohesion strength of snow, it breaks apart. Now in human terms—" The chops and mashed potatoes and peas arrived. "Go on," I urged. He was deep in the symbology of human motives and the equations of human behavior in groups. After running through a few different types of grower and shrinker type organizations, we came back to the snowball, and decided to run the test by making something grow. "You add the motives," he said, "and the equation will translate them into organization." "How about a good selfish reason for the ins to drag others into the group—some sort of bounty on new members, a cut of their membership fee?" I suggested uncertainly, feeling slightly foolish. "And maybe a reason why the members would lose if any of them resigned, and some indirect way they could use to force each other to stay in." "The first is the chain letter principle," he nodded. "I've got that. The other...." He put the symbols through some mathematical manipulation so that a special grouping appeared in the middle of the equation. "That's it." Since I seemed to have the right idea, I suggested some more, and he added some, and juggled them around in different patterns. We threw out a few that would have made the organization too complicated, and finally worked out an idyllically simple and deadly little organization setup where joining had all the temptation of buying a sweepstakes ticket, going in deeper was as easy as hanging around a race track, and getting out was like trying to pull free from a Malayan thumb trap. We put our heads closer together and talked lower, picking the best place for the demonstration. "Abington?" "How about Watashaw? I have some student sociological surveys of it already. We can pick a suitable group from that." "This demonstration has got to be convincing. We'd better pick a little group that no one in his right mind would expect to grow." "There should be a suitable club—" Picture Professor Caswell, head of the Department of Sociology, and with him the President of the University, leaning across the table toward each other, sipping coffee and talking in conspiratorial tones over something they were writing in a notebook. That was us. "Ladies," said the skinny female chairman of the Watashaw Sewing Circle. "Today we have guests." She signaled for us to rise, and we stood up, bowing to polite applause and smiles. "Professor Caswell, and Professor Smith." (My alias.) "They are making a survey of the methods and duties of the clubs of Watashaw." We sat down to another ripple of applause and slightly wider smiles, and then the meeting of the Watashaw Sewing Circle began. In five minutes I began to feel sleepy. There were only about thirty people there, and it was a small room, not the halls of Congress, but they discussed their business of collecting and repairing second hand clothing for charity with the same endless boring parliamentary formality. I pointed out to Caswell the member I thought would be the natural leader, a tall, well-built woman in a green suit, with conscious gestures and a resonant, penetrating voice, and then went into a half doze while Caswell stayed awake beside me and wrote in his notebook. After a while the resonant voice roused me to attention for a moment. It was the tall woman holding the floor over some collective dereliction of the club. She was being scathing. I nudged Caswell and murmured, "Did you fix it so that a shover has a better chance of getting into office than a non-shover?" "I think there's a way they could find for it," Caswell whispered back, and went to work on his equation again. "Yes, several ways to bias the elections." "Good. Point them out tactfully to the one you select. Not as if she'd use such methods, but just as an example of the reason why only she can be trusted with initiating the change. Just mention all the personal advantages an unscrupulous person could have." He nodded, keeping a straight and sober face as if we were exchanging admiring remarks about the techniques of clothes repairing, instead of conspiring. After the meeting, Caswell drew the tall woman in the green suit aside and spoke to her confidentially, showing her the diagram of organization we had drawn up. I saw the responsive glitter in the woman's eyes and knew she was hooked. We left the diagram of organization and our typed copy of the new bylaws with her and went off soberly, as befitted two social science experimenters. We didn't start laughing until our car passed the town limits and began the climb for University Heights. If Caswell's equations meant anything at all, we had given that sewing circle more growth drives than the Roman Empire. Four months later I had time out from a very busy schedule to wonder how the test was coming along. Passing Caswell's office, I put my head in. He looked up from a student research paper he was correcting. "Caswell, about that sewing club business—I'm beginning to feel the suspense. Could I get an advance report on how it's coming?" "I'm not following it. We're supposed to let it run the full six months." "But I'm curious. Could I get in touch with that woman—what's her name?" "Searles. Mrs. George Searles." "Would that change the results?" "Not in the slightest. If you want to graph the membership rise, it should be going up in a log curve, probably doubling every so often." I grinned. "If it's not rising, you're fired." He grinned back. "If it's not rising, you won't have to fire me—I'll burn my books and shoot myself." I returned to my office and put in a call to Watashaw. While I was waiting for the phone to be answered, I took a piece of graph paper and ruled it off into six sections, one for each month. After the phone had rung in the distance for a long time, a servant answered with a bored drawl: "Mrs. Searles' residence." I picked up a red gummed star and licked it. "Mrs. Searles, please." "She's not in just now. Could I take a message?" I placed the star at the thirty line in the beginning of the first section. Thirty members they'd started with. "No, thanks. Could you tell me when she'll be back?" "Not until dinner. She's at the meetin'." "The sewing club?" I asked. "No, sir, not that thing. There isn't any Sewing club any more, not for a long time. She's at the Civic Welfare meeting." Somehow I hadn't expected anything like that. "Thank you," I said and hung up, and after a moment noticed I was holding a box of red gummed stars in my hand. I closed it and put it down on top of the graph of membership in the sewing circle. No more members.... Poor Caswell. The bet between us was ironclad. He wouldn't let me back down on it even if I wanted to. He'd probably quit before I put through the first slow move to fire him. His professional pride would be shattered, sunk without a trace. I remembered what he said about shooting himself. It had seemed funny to both of us at the time, but.... What a mess that would make for the university. I had to talk to Mrs. Searles. Perhaps there was some outside reason why the club had disbanded. Perhaps it had not just died. I called back. "This is Professor Smith," I said, giving the alias I had used before. "I called a few minutes ago. When did you say Mrs. Searles will return?" "About six-thirty or seven o'clock." Five hours to wait. And what if Caswell asked me what I had found out in the meantime? I didn't want to tell him anything until I had talked it over with that woman Searles first. "Where is this Civic Welfare meeting?" She told me. Five minutes later, I was in my car, heading for Watashaw, driving considerably faster than my usual speed and keeping a careful watch for highway patrol cars as the speedometer climbed. The town meeting hall and theater was a big place, probably with lots of small rooms for different clubs. I went in through the center door and found myself in the huge central hall where some sort of rally was being held. A political-type rally—you know, cheers and chants, with bunting already down on the floor, people holding banners, and plenty of enthusiasm and excitement in the air. Someone was making a speech up on the platform. Most of the people there were women. I wondered how the Civic Welfare League could dare hold its meeting at the same time as a political rally that could pull its members away. The group with Mrs. Searles was probably holding a shrunken and almost memberless meeting somewhere in an upper room. There probably was a side door that would lead upstairs. While I glanced around, a pretty girl usher put a printed bulletin in my hand, whispering, "Here's one of the new copies." As I attempted to hand it back, she retreated. "Oh, you can keep it. It's the new one. Everyone's supposed to have it. We've just printed up six thousand copies to make sure there'll be enough to last." The tall woman on the platform had been making a driving, forceful speech about some plans for rebuilding Watashaw's slum section. It began to penetrate my mind dimly as I glanced down at the bulletin in my hands. "Civic Welfare League of Watashaw. The United Organization of Church and Secular Charities." That's what it said. Below began the rules of membership. I looked up. The speaker, with a clear, determined voice and conscious, forceful gestures, had entered the homestretch of her speech, an appeal to the civic pride of all citizens of Watashaw. "With a bright and glorious future—potentially without poor and without uncared-for ill—potentially with no ugliness, no vistas which are not beautiful—the best people in the best planned town in the country—the jewel of the United States." She paused and then leaned forward intensely, striking her clenched hand on the speaker's stand with each word for emphasis. " All we need is more members. Now get out there and recruit! " I finally recognized Mrs. Searles, as an answering sudden blast of sound half deafened me. The crowd was chanting at the top of its lungs: "Recruit! Recruit!" Mrs. Searles stood still at the speaker's table and behind her, seated in a row of chairs, was a group that was probably the board of directors. It was mostly women, and the women began to look vaguely familiar, as if they could be members of the sewing circle. I put my lips close to the ear of the pretty usher while I turned over the stiff printed bulletin on a hunch. "How long has the League been organized?" On the back of the bulletin was a constitution. She was cheering with the crowd, her eyes sparkling. "I don't know," she answered between cheers. "I only joined two days ago. Isn't it wonderful?" I went into the quiet outer air and got into my car with my skin prickling. Even as I drove away, I could hear them. They were singing some kind of organization song with the tune of "Marching through Georgia." Even at the single glance I had given it, the constitution looked exactly like the one we had given the Watashaw Sewing Circle. All I told Caswell when I got back was that the sewing circle had changed its name and the membership seemed to be rising. Next day, after calling Mrs. Searles, I placed some red stars on my graph for the first three months. They made a nice curve, rising more steeply as it reached the fourth month. They had picked up their first increase in membership simply by amalgamating with all the other types of charity organizations in Watashaw, changing the club name with each fusion, but keeping the same constitution—the constitution with the bright promise of advantages as long as there were always new members being brought in. By the fifth month, the League had added a mutual baby-sitting service and had induced the local school board to add a nursery school to the town service, so as to free more women for League activity. But charity must have been completely organized by then, and expansion had to be in other directions. Some real estate agents evidently had been drawn into the whirlpool early, along with their ideas. The slum improvement plans began to blossom and take on a tinge of real estate planning later in the month. The first day of the sixth month, a big two page spread appeared in the local paper of a mass meeting which had approved a full-fledged scheme for slum clearance of Watashaw's shack-town section, plus plans for rehousing, civic building, and rezoning. And good prospects for attracting some new industries to the town, industries which had already been contacted and seemed interested by the privileges offered. And with all this, an arrangement for securing and distributing to the club members alone most of the profit that would come to the town in the form of a rise in the price of building sites and a boom in the building industry. The profit distributing arrangement was the same one that had been built into the organization plan for the distribution of the small profits of membership fees and honorary promotions. It was becoming an openly profitable business. Membership was rising more rapidly now. By the second week of the sixth month, news appeared in the local paper that the club had filed an application to incorporate itself as the Watashaw Mutual Trade and Civic Development Corporation, and all the local real estate promoters had finished joining en masse. The Mutual Trade part sounded to me as if the Chamber of Commerce was on the point of being pulled in with them, ideas, ambitions and all. I chuckled while reading the next page of the paper, on which a local politician was reported as having addressed the club with a long flowery oration on their enterprise, charity, and civic spirit. He had been made an honorary member. If he allowed himself to be made a full member with its contractual obligations and its lures, if the politicians went into this, too.... I laughed, filing the newspaper with the other documents on the Watashaw test. These proofs would fascinate any businessman with the sense to see where his bread was buttered. A businessman is constantly dealing with organizations, including his own, and finding them either inert, cantankerous, or both. Caswell's formula could be a handle to grasp them with. Gratitude alone would bring money into the university in carload lots. The end of the sixth month came. The test was over and the end reports were spectacular. Caswell's formulas were proven to the hilt. After reading the last newspaper reports, I called him up. "Perfect, Wilt, perfect ! I can use this Watashaw thing to get you so many fellowships and scholarships and grants for your department that you'll think it's snowing money!" He answered somewhat disinterestedly, "I've been busy working with students on their research papers and marking tests—not following the Watashaw business at all, I'm afraid. You say the demonstration went well and you're satisfied?" He was definitely putting on a chill. We were friends now, but obviously he was still peeved whenever he was reminded that I had doubted that his theory could work. And he was using its success to rub my nose in the realization that I had been wrong. A man with a string of degrees after his name is just as human as anyone else. I had needled him pretty hard that first time. "I'm satisfied," I acknowledged. "I was wrong. The formulas work beautifully. Come over and see my file of documents on it if you want a boost for your ego. Now let's see the formula for stopping it." He sounded cheerful again. "I didn't complicate that organization with negatives. I wanted it to grow . It falls apart naturally when it stops growing for more than two months. It's like the great stock boom before an economic crash. Everyone in it is prosperous as long as the prices just keep going up and new buyers come into the market, but they all knew what would happen if it stopped growing. You remember, we built in as one of the incentives that the members know they are going to lose if membership stops growing. Why, if I tried to stop it now, they'd cut my throat." I remembered the drive and frenzy of the crowd in the one early meeting I had seen. They probably would. "No," he continued. "We'll just let it play out to the end of its tether and die of old age." "When will that be?" "It can't grow past the female population of the town. There are only so many women in Watashaw, and some of them don't like sewing." The graph on the desk before me began to look sinister. Surely Caswell must have made some provision for— "You underestimate their ingenuity," I said into the phone. "Since they wanted to expand, they didn't stick to sewing. They went from general charity to social welfare schemes to something that's pretty close to an incorporated government. The name is now the Watashaw Mutual Trade and Civic Development Corporation, and they're filing an application to change it to Civic Property Pool and Social Dividend, membership contractual, open to all. That social dividend sounds like a Technocrat climbed on the band wagon, eh?" While I spoke, I carefully added another red star to the curve above the thousand member level, checking with the newspaper that still lay open on my desk. The curve was definitely some sort of log curve now, growing more rapidly with each increase. "Leaving out practical limitations for a moment, where does the formula say it will stop?" I asked. "When you run out of people to join it. But after all, there are only so many people in Watashaw. It's a pretty small town." "They've opened a branch office in New York," I said carefully into the phone, a few weeks later. With my pencil, very carefully, I extended the membership curve from where it was then. After the next doubling, the curve went almost straight up and off the page. Allowing for a lag of contagion from one nation to another, depending on how much their citizens intermingled, I'd give the rest of the world about twelve years. There was a long silence while Caswell probably drew the same graph in his own mind. Then he laughed weakly. "Well, you asked me for a demonstration." That was as good an answer as any. We got together and had lunch in a bar, if you can call it lunch. The movement we started will expand by hook or by crook, by seduction or by bribery or by propaganda or by conquest, but it will expand. And maybe a total world government will be a fine thing—until it hits the end of its rope in twelve years or so. What happens then, I don't know. But I don't want anyone to pin that on me. From now on, if anyone asks me, I've never heard of Watashaw.
|
B. Resourceful and dilligent
|
Which components of QA and QG models are shared during training?
|
### Introduction
Question answering (QA) is the task of automatically producing an answer to a question given a corresponding document. It not only provides humans with efficient access to vast amounts of information, but also acts as an important proxy task to assess machine literacy via reading comprehension. Thanks to the recent release of several large-scale machine comprehension/QA datasets BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 , the field has undergone significant advancement, with an array of neural models rapidly approaching human parity on some of these benchmarks BIBREF5 , BIBREF6 , BIBREF7 . However, previous models do not treat QA as a task of natural language generation (NLG), but of pointing to an answer span within a document. Alongside QA, question generation has also gained increased popularity BIBREF8 , BIBREF9 . The task is to generate a natural-language question conditioned on an answer and the corresponding document. Among its many applications, question generation has been used to improve QA systems BIBREF10 , BIBREF11 , BIBREF12 . A recurring theme among previous studies is to augment existing labeled data with machine-generated questions; to our knowledge, the direct (though implicit) effect of asking questions on answering questions has not yet been explored. In this work, we propose a joint model that both asks and answers questions, and investigate how this joint-training setup affects the individual tasks. We hypothesize that question generation can help models achieve better QA performance. This is motivated partly by observations made in psychology that devising questions while reading can increase scores on comprehension tests BIBREF13 . Our joint model also serves as a novel framework for improving QA performance outside of the network-architectural engineering that characterizes most previous studies. Although the question answering and asking tasks appear symmetric, there are some key differences. First, answering the questions in most existing QA datasets is extractive — it requires selecting some span of text within the document — while question asking is comparatively abstractive — it requires generation of text that may not appear in the document. Furthermore, a (document, question) pair typically specifies a unique answer. Conversely, a typical (document, answer) pair may be associated with multiple questions, since a valid question can be formed from any information or relations which uniquely specify the given answer. To tackle the joint task, we construct an attention-based BIBREF14 sequence-to-sequence model BIBREF15 that takes a document as input and generates a question (answer) conditioned on an answer (question) as output. To address the mixed extractive/abstractive nature of the generative targets, we use the pointer-softmax mechanism BIBREF16 that learns to switch between copying words from the document and generating words from a prescribed vocabulary. Joint training is realized by alternating the input data between question-answering and question-generating examples for the same model. We demonstrate empirically that this model's QA performance on SQuAD, while not state of the art, improves by about 10% with joint training. A key novelty of our joint model is that it can generate (partially) abstractive answers. ### Related Work
Joint-learning on multiple related tasks has been explored previously BIBREF17 , BIBREF18 . In machine translation, for instance, BIBREF18 demonstrated that translation quality clearly improves over models trained with a single language pair when the attention mechanism in a neural translation model is shared and jointly trained on multiple language pairs. In question answering, BIBREF19 proposed one of the first neural models for the SQuAD dataset. SQuAD defines an extractive QA task wherein answers consist of word spans in the corresponding document. BIBREF19 demonstrated that learning to point to answer boundaries is more effective than learning to point sequentially to the tokens making up an answer span. Many later studies adopted this boundary model and achieved near-human performance on the task BIBREF5 , BIBREF6 , BIBREF7 . However, the boundary-pointing mechanism is not suitable for more open-ended tasks, including abstractive QA BIBREF4 and question generation. While “forcing” the extractive boundary model onto abstractive datasets currently yields state-of-the-art results BIBREF5 , this is mainly because current generative models are poor and NLG evaluation is unsolved. Earlier work on question generation has resorted to either rule-based reordering methods BIBREF20 , BIBREF21 , BIBREF22 or slot-filling with question templates BIBREF23 , BIBREF24 , BIBREF25 . These techniques often involve pipelines of independent components that are difficult to tune for final performance measures. Partly to address this limitation, end-to-end-trainable neural models have recently been proposed for question generation in both vision BIBREF26 and language. For example, BIBREF8 used a sequence-to-sequence model with an attention mechanism derived from the encoder states. BIBREF9 proposed a similar architecture but in addition improved model performance through policy gradient techniques. Several neural models with a questioning component have been proposed for the purpose of improving QA models, an objective shared by this study. BIBREF12 devised a semi-supervised training framework that trained a QA model BIBREF27 on both labeled data and artificial data generated by a separate generative component. BIBREF10 used policy gradient with a QA reward to train a sequence-to-sequence paraphrase model to reformulate questions in an existing QA dataset BIBREF2 . The generated questions were then used to further train an existing QA model BIBREF7 . A key distinction of our model is that we harness the process of asking questions to benefit question answering, without training the model to answer the generated questions. ### Model Description
Our proposed model adopts a sequence-to-sequence framework BIBREF15 with an attention mechanism BIBREF14 and a pointer-softmax decoder BIBREF16 . Specifically, the model takes a document (i.e., a word sequence) $D = (w^d_1,\dots ,w^d_{n_d})$ and a condition sequence $C = (w^c_1,\dots ,w^c_{n_c})$ as input, and outputs a target sequence $Y^{\lbrace q,a\rbrace } = (\hat{w}_1,\dots ,\hat{w}_{n_p})$ . The condition corresponds to the question word sequence in answer-generation mode (a-gen), and the answer word sequence in question-generation mode (q-gen). We also attach a binary variable to indicate whether a data-point is intended for a-gen or q-gen. Intuitively, this should help the model learn the two modalities more easily. Empirically, QA performance improves slightly with this addition. ### Encoder
A word $w_i$ in an input sequence is first embedded with an embedding layer into vector ${\bf e}^w_i$ . Character-level information is captured with the final states ${\bf e}^{ch}_i$ of a bidirectional Long Short-Term Memory model BIBREF28 on the character sequences of $w_i$ . The final representation for a word token ${\bf e}_i=\langle {\bf e}^w_i,{\bf e}^{ch}_i\rangle $ concatenates the word- and character-level embeddings. These are subsequently encoded with another BiLSTM into annotation vectors ${\bf h}^d_i$ and ${\bf h}^c_j$ (for the document and the condition sequence, respectively). To better encode the condition, we also extract the encodings of the document words that appear in the condition sequence. This procedure is particularly helpful in q-gen mode, where the condition (answer) sequence is typically extractive. These extracted vectors are then fed into a condition aggregation BiLSTM to produce the extractive condition encoding ${\bf h}^e_k$ . We specifically take the final states of the condition encodings ${\bf h}^c_J$ and ${\bf h}^e_K$ . To account for the different extractive vs. abstractive nature of questions vs. answers, we use ${\bf h}^c_J$ in a-gen mode (for encoding questions) and ${\bf h}^e_K$ in q-gen mode (for encoding answers). ### Decoder
The RNN-based decoder employs the pointer-softmax mechanism BIBREF16 . At each generation step, the decoder decides adaptively whether (a) to generate from a decoder vocabulary or (b) to point to a word in the source sequence (and copy over). Recurrence of the pointing decoder is implemented with two LSTM cells $c_1$ and $c_2$ : $${\bf s}_1^{(t)} & = & c_1({\bf y}^{(t-1)}, {\bf s}_2^{(t-1)})\\
{\bf s}_2^{(t)} & = & c_2({\bf v}^{(t)}, {\bf s}_1^{(t)}),$$ (Eq. 1) where ${\bf s}_1^{(t)}$ and ${\bf s}_2^{(t)}$ are the recurrent states, ${\bf y}^{(t-1)}$ is the embedding of decoder output from the previous time step, and ${\bf v}^{(t)}$ is the context vector (to be defined shortly in Equation ( 2 )). The pointing decoder computes a distribution $\alpha ^{(t)}$ over the document word positions (i.e., a document attention, BIBREF14 ). Each element is defined as: $
\alpha ^{(t)}_i = f({\bf h}^d_i, {\bf h}^c, {\bf h}^e, {\bf s_1}^{(t-1)}),
$ where $f$ is a two-layer MLP with tanh and softmax activation, respectively. The context vector ${\bf v}^{(t)}$ used in Equation () is the sum of the document encoding weighted by the document attention: $${\bf v}^{(t)}=\sum _{i=1}^n \alpha ^{(t)}_i{\bf h}^d_i.$$ (Eq. 2) The generative decoder, on the other hand, defines a distribution over a prescribed decoder vocabulary with a two-layer MLP $g$ : $${\bf o}^{(t)}=g({\bf y}^{(t-1)},{\bf s}_2^{(t)},{\bf v}^{(t)},{\bf h}^c,{\bf h}^e).$$ (Eq. 3) Finally, the switch scalar $s^{(t)}$ at each time step is computed by a three-layer MLP $h$ : $
s^{(t)}=h({\bf s}_2^{(t)},{\bf v}^{(t)},\alpha ^{(t)},{\bf o}^{(t)}),
$ The first two layers of $h$ use tanh activation and the final layer uses sigmoid activation, and highway connections are present between the first and the second layer. We also attach the entropy of the softmax distributions to the input of the final layer, postulating that the quantities should help guide the switching mechanism by indicating the confidence of pointing vs generating. The addition is empirically observed to improve model performance. The resulting switch is used to interpolate the pointing and the generative probabilities for predicting the next word: $
p(\hat{w}_t)\sim s^{(t)} \alpha ^{(t)} + (1-s^{(t)}){\bf o}^{(t)}.
$ ### Training and Inference
The optimization objective for updating the model parameters $\theta $ is to maximize the negative log likelihood of the generated sequences with respect to the training data $\mathcal {D}$ : $
\mathcal {L}=-\sum _{x\in \mathcal {D}}\log p(\hat{w}_t|w_{<t},x;\theta ).
$ Here, $w_{<t}$ corresponds to the embeddings ${\bf y}^{(t-1)}$ in Equation ( 1 ) and ( 3 ). During training, gold targets are used to teacher-force the sequence generation for training, i.e., $w_{<t}=w^{\lbrace q,a\rbrace }_{<t}$ , while during inference, generation is conditioned on the previously generated words, i.e., $w_{<t}=\hat{w}_{<t}$ . For words with multiple occurrence, since their exact references in the document cannot be reiabled determined, we aggregate the probability of these words in the encoder and the pointing decoder (similar to BIBREF29 ). At test time, beam search is used to enhance fluency in the question-generation output. The decoder also keeps an explicit history of previously generated words to avoid repetition in the output. ### Dataset
We conduct our experiments on the SQuAD corpus BIBREF1 , a machine comprehension dataset consisting of over 100k crowd-sourced question-answer pairs on 536 Wikipedia articles. Simple preprocessing is performed, including lower-casing all texts in the dataset and using NLTK BIBREF30 for word tokenization. The test split of SQuAD is hidden from the public. We therefore take 5,158 question-answer pairs (self-contained in 23 Wikipedia articles) from the training set as validation set, and use the official development data to report test results. Note that answers in this dataset are strictly extractive, and we therefore constrain the pointer-softmax module to point at all decoding steps in answer generation mode. ### Baseline Models
We first establish two baselines without multi-task training. Specifically, model A-gen is trained only to generate an answer given a document and a question, i.e., as a conventional QA model. Analogously, model Q-gen is trained only to generate questions from documents and answers. Joint-training (in model JointQA) is realized by feeding answer-generation and question-generation data to the model in an alternating fashion between mini-batches. In addition, we compare answer-generation performance with the sequence model variant of the match-LSTM (mLSTM) model BIBREF19 . As mentioned earlier, in contrast to existing neural QA models that point to the start and end boundaries of extractive answers, this model predicts a sequence of document positions as the answer. This makes it most comparable to our QA setup. Note, however, that our model has the additional capacity to generate abstractively from the decoder vocabulary. ### Quantitative Evaluation
We use F1 and Exact Match (EM, BIBREF1 ) against the gold answer sequences to evaluate answer generation, and BLEU BIBREF31 against the gold question sequences to evaluate question generation. However, existing studies have shown that the task of question generation often exhibits linguistic variance that is semantically admissible; this renders it inappropriate to judge a generated question solely by matching against a gold sequence BIBREF9 . We therefore opt to assess the quality of generated questions $Y^q$ with two pretrained neural models as well: we use a language model to compute the perplexity of $Y^q$ , and a QA model to answer $Y^q$ . We measure the F1 score of the answer produced by this QA model. We choose mLSTM as the pretrained QA model and train it on SQuAD with the same split as mentioned in Section "Dataset" . Performance on the test set (i.e., the official validation set of SQuAD) is 73.78 F1 and 62.7 EM. For the pretrained language model, we train a single-layer LSTM language model on the combination of the text8 corpus, the Quora Question Pairs corpus, and the gold questions from SQuAD. The latter two corpora were included to tailor to our purpose of assessing question fluency, and for this reason, we ignore the semantic equivalence labels in the Quora dataset. Validation perplexity is 67.2 for the pretrained language model. ### Analysis and Discussion
Evaluation results are provided in Table 1 . We see that A-gen performance improves significantly with the joint model: both F1 and EM increase by about 10 percentage points. Performance of q-gen worsens after joint training, but the decrease is relatively small. Furthermore, as pointed out by earlier studies, automatic metrics often do not correlate well with the generation quality assessed by humans BIBREF9 . We thus consider the overall outcome to be positive. Meanwhile, although our model does not perform as well as mLSTM on the QA task, it has the added capability of generating questions. mLSTM uses a more advanced encoder tailored to QA, while our model uses only a bidirectional LSTM for encoding. Our model uses a more advanced decoder based on the pointer-softmax that enables it to generate abstactively and extractively. For a finer grained analysis, we first categorize test set answers based on their entity types, then stratify the QA performance comparison between A-gen and JointQA. The categorization relies on Stanford CoreNLP BIBREF32 to generate constituency parses, POS tags, and NER tags for answer spans (see BIBREF1 for more details). As seen in Figure 1 , the joint model significantly outperforms the single model in all categories. Interestingly, the moving average of the performance gap (dashed curve above bars) exhibits an upward trend as the A-gen model performance decreases across answer types, suggesting that the joint model helps most where the single model performance is weakest. ### Qualitative Examples
Qualitatively, we have observed interesting “shifts” in attention before and after joint training. For example, in the positive case in Table 2 , the gold question asks about the direct object,Nixon, of the verb endorse, but the A-gen model predicts the indirect object, Kennedy, instead. In contrast, the joint model asks about the appositive of vice president during question generation, which presumably “primes” the model attention towards the correct answer Nixon. Analogously in the negative example, QA attention in the joint model appears to be shifted by joint training towards an answer that is incorrect but closer to the generated question. Note that the examples from Table 2 come from the validation set, and it is thus not possible for the joint model to memorize the gold answers from question-generation mode — the priming effect must come from some form of knowledge transfer between q-gen and a-gen via joint training. ### Implementation Details
Implementation details of the proposed model are as follows. The encoder vocabulary indexes all words in the dataset. The decoder vocabulary uses the top 100 words sorted by their frequency in the gold questions in the training data. This encourages the model to generate frequent words (e.g. wh-words and function words) from the decoder vocabulary and copy less frequent ones (e.g., topical words and entities) from the document. The word embedding matrix is initialized with the 300-dimensional GloVe vectors BIBREF33 . The dimensionality of the character representations is 32. The number of hidden units is 384 for both of the encoder/decoder RNN cells. Dropout is applied at a rate of 0.3 to all embedding layers as well as between the hidden states in the encoder/decoder RNNs across time steps. We use adam BIBREF34 as the step rule for optimization with mini-batch size 32. The initial learning rate is $2e-4$ , which is decayed at a rate of 0.5 when the validation loss increases for two consecutive epochs. The model is implemented using Keras BIBREF35 with the Theano BIBREF36 backend. ### Conclusion
We proposed a neural machine comprehension model that can jointly ask and answer questions given a document. We hypothesized that question answering can benefit from synergistic interaction between the two tasks through parameter sharing and joint training under this multitask setting. Our proposed model adopts an attention-based sequence-to-sequence architecture that learns to dynamically switch between copying words from the document and generating words from a vocabulary. Experiments with the model confirm our hypothesis: the joint model outperforms its QA-only counterpart by a significant margin on the SQuAD dataset. Although evaluation scores are still lower than the state-of-the-art results achieved by dedicated QA models, the proposed model nonetheless demonstrates the effectiveness of joint training between QA and question generation, and thus offers a novel perspective and a promising direction for advancing the study of QA. Table 1. Model evaluation on question- and answer-generation. Figure 1. Comparison between A-gen and JointQA stratified by answer types. The dashed curve indicates period-2 moving average of the performance difference between the models. Table 2. Examples of QA behaviour changes possibly induced by joint training. Gold answers correspond to text spans in green. In both the positive and the negative cases, the answers produced by the joint model are highly related (and thus presumably influenced) by the generated questions.
|
parameter sharing
|
What helps Houlihan to focus more intently on his own problem?
A. collaborating with the leprechauns, who speak his same language
B. imagining the pot of gold that awaits him if he is able to solve the equation
C. being outdoors, where his creativity is stimulated
D. venturing outside of the Center, where he is not worried about competition among colleagues
|
Every writer must seek his own Flowery Kingdom in imagination's wide demesne, and if that search can begin and end on Earth his problem has been greatly simplified. In post-war Japan Walt Sheldon has found not only serenity, but complete freedom to write undisturbed about the things he treasures most. A one-time Air Force officer, he has turned to fantasy in his lighter moments, to bring us such brightly sparkling little gems as this. houlihan's equation by ... Walt Sheldon The tiny spaceship had been built for a journey to a star. But its small, mischievous pilots had a rendezvous with destiny—on Earth. I must admit that at first I wasn't sure I was hearing those noises. It was in a park near the nuclear propulsion center—a cool, green spot, with the leaves all telling each other to hush, be quiet, and the soft breeze stirring them up again. I had known precisely such a secluded little green sanctuary just over the hill from Mr. Riordan's farm when I was a boy. Now it was a place I came to when I had a problem to thrash out. That morning I had been trying to work out an equation to give the coefficient of discharge for the matter in combustion. You may call it gas, if you wish, for we treated it like gas at the center for convenience—as it came from the rocket tubes in our engine. Without this coefficient to give us control, we would have lacked a workable equation when we set about putting the first moon rocket around those extraordinary engines of ours, which were still in the undeveloped blueprint stage. I see I shall have to explain this, although I had hoped to get right along with my story. When you start from scratch, matter discharged from any orifice has a velocity directly proportional to the square root of the pressure-head driving it. But when you actually put things together, contractions or expansions in the gas, surface roughness and other factors make the velocity a bit smaller. At the terrible discharge speed of nuclear explosion—which is what the drive amounts to despite the fact that it is simply water in which nuclear salts have been previously dissolved—this small factor makes quite a difference. I had to figure everything into it—diameter of the nozzle, sharpness of the edge, the velocity of approach to the point of discharge, atomic weight and structure— Oh, there is so much of this that if you're not a nuclear engineer yourself it's certain to weary you. Perhaps you had better take my word for it that without this equation—correctly stated, mind you—mankind would be well advised not to make a first trip to the moon. And all this talk of coefficients and equations sits strangely, you might say, upon the tongue of a man named Kevin Francis Houlihan. But I am, after all, a scientist. If I had not been a specialist in my field I would hardly have found myself engaged in vital research at the center. Anyway, I heard these little noises in the park. They sounded like small working sounds, blending in eerily mysterious fashion with a chorus of small voices. I thought at first it might be children at play, but then at the time I was a bit absent-minded. I tiptoed to the edge of the trees, not wanting to deprive any small scalawags of their pleasure, and peered out between the branches. And what do you suppose I saw? Not children, but a group of little people, hard at work. There was a leader, an older one with a crank face. He was beating the air with his arms and piping: "Over here, now! All right, bring those electrical connections over here—and see you're not slow as treacle about it!" There were perhaps fifty of the little people. I was more than startled by it, too. I had not seen little people in—oh, close to thirty years. I had seen them first as a boy of eight, and then, very briefly again, on my tenth birthday. And I had become convinced they could never be seen here in America. I had never seen them so busy, either. They were building something in the middle of the glade. It was long and shiny and upright and a little over five feet in height. "Come along now, people!" said this crotchety one, looking straight at me. "Stop starin' and get to work! You'll not be needin' to mind that man standin' there! You know he can't see nor hear us!" Oh, it was good to hear the rich old tongue again. I smiled, and the foreman of the leprechauns—if that's what he was—saw me smile and became stiff and alert for a moment, as though suspecting that perhaps I actually could see him. Then he shrugged and turned away, clearly deeming such a thing impossible. I said, "Just a minute, friend, and I'll beg your pardon. It so happens I can see you." He whirled to face me again, staring open-mouthed. Then he said, "What? What's that, now?" "I can see you," I said. "Ohhh!" he said and put his palms to his cheekbones. "Saints be with us! He's a believer! Run everybody—run for your lives!" And they all began running, in as many directions as there were little souls. They began to scurry behind the trees and bushes, and a sloping embankment nearby. "No, wait!" I said. "Don't go away! I'll not be hurting you!" They continued to scurry. I knew what it was they feared. "I don't intend catching one of you!" I said. "Come back, you daft little creatures!" But the glade was silent, and they had all disappeared. They thought I wanted their crock of gold, of course. I'd be entitled to it if I could catch one and keep him. Or so the legends affirmed, though I've wondered often about the truth of them. But I was after no gold. I only wanted to hear the music of an Irish tongue. I was lonely here in America, even if I had latched on to a fine job of work for almost shamefully generous pay. You see, in a place as full of science as the nuclear propulsion center there is not much time for the old things. I very much wanted to talk to the little people. I walked over to the center of the glade where the curious shiny object was standing. It was as smooth as glass and shaped like a huge cigar. There were a pair of triangular fins down at the bottom, and stubby wings amidships. Of course it was a spaceship, or a miniature replica of one. I looked at it more closely. Everything seemed almost miraculously complete and workable. I shook my head in wonder, then stepped back from the spaceship and looked about the glade. I knew they were all hiding nearby, watching me apprehensively. I lifted my head to them. "Listen to me now, little people!" I called out. "My name's Houlihan of the Roscommon Houlihans. I am descended from King Niall himself—or so at least my father used to say! Come on out now, and pass the time o' day!" Then I waited, but they didn't answer. The little people always had been shy. Yet without reaching a decision in so many words I knew suddenly that I had to talk to them. I'd come to the glen to work out a knotty problem, and I was up against a blank wall. Simply because I was so lonely that my mind had become clogged. I knew that if I could just once hear the old tongue again, and talk about the old things, I might be able to think the problem through to a satisfactory conclusion. So I stepped back to the tiny spaceship, and this time I struck it a resounding blow with my fist. "Hear me now, little people! If you don't show yourselves and come out and talk to me, I'll wreck this spaceship from stem to stern!" I heard only the leaves rustling softly. "Do you understand? I'll give you until I count three to make an appearance! One!" The glade remained deathly silent. "Two!" I thought I heard a stirring somewhere, as if a small, brittle twig had snapped in the underbrush. " Three! " And with that the little people suddenly appeared. The leader—he seemed more wizened and bent than before—approached me slowly and warily as I stood there. The others all followed at a safe distance. I smiled to reassure them and then waved my arm in a friendly gesture of greeting. "Good morning," I said. "Good morning," the foreman said with some caution. "My name is Keech." "And mine's Houlihan, as I've told you. Are you convinced now that I have no intention of doing you any injury?" "Mr. Houlihan," said Keech, drawing a kind of peppered dignity up about himself, "in such matters I am never fully convinced. After living for many centuries I am all too acutely aware of the perversity of human nature." "Yes," I said. "Well, as you will quickly see, all I want to do is talk." I nodded as I spoke, and sat down cross-legged upon the grass. "Any Irishman wants to talk, Mr. Houlihan." "And often that's all he wants," I said. "Sit down with me now, and stop staring as if I were a snake returned to the Island." He shook his head and remained standing. "Have your say, Mr. Houlihan. And afterward we'll appreciate it if you'll go away and leave us to our work." "Well, now, your work," I said, and glanced at the spaceship. "That's exactly what's got me curious." The others had edged in a bit now and were standing in a circle, intently staring at me. I took out my pipe. "Why," I asked, "would a group of little people be building a spaceship here in America—out in this lonely place?" Keech stared back without much expression, and said, "I've been wondering how you guessed it was a spaceship. I was surprised enough when you told me you could see us but not overwhelmingly so. I've run into believers before who could see the little people. It happens every so often, though not as frequently as it did a century ago. But knowing a spaceship at first glance! Well, I must confess that does astonish me." "And why wouldn't I know a spaceship when I see one?" I said. "It just so happens I'm a doctor of science." "A doctor of science, now," said Keech. "Invited by the American government to work on the first moon rocket here at the nuclear propulsion center. Since it's no secret I can advise you of it." "A scientist, is it," said Keech. "Well, now, that's very interesting." "I'll make no apologies for it," I said. "Oh, there's no need for apology," said Keech. "Though in truth we prefer poets to scientists. But it has just now crossed my mind, Mr. Houlihan that you, being a scientist, might be of help to us." "How?" I asked. "Well, I might try starting at the beginning," he replied. "You might," I said. "A man usually does." Keech took out his own pipe—a clay dudeen—and looked hopeful. I gave him a pinch of tobacco from my pouch. "Well, now," he said, "first of all you're no doubt surprised to find us here in America." "I am surprised from time to time to find myself here," I said. "But continue." "We had to come here," said Keech, "to learn how to make a spaceship." "A spaceship, now," I said, unconsciously adopting some of the old manner. "Leprechauns are not really mechanically inclined," said Keech. "Their major passions are music and laughter and mischief, as anyone knows." "Myself included," I agreed. "Then why do you need a spaceship?" "Well, if I may use an old expression, we've had a feelin' lately that we're not long for this world. Or let me put it this way. We feel the world isn't long for itself." I scratched my cheek. "How would a man unravel a statement such as that?" "It's very simple. With all the super weapons you mortals have developed, there's the distinct possibility you might be blowin' us all up in the process of destroying yourselves." "There is that possibility," I said. "Well, then, as I say," said Keech, "the little people have decided to leave the planet in a spaceship. Which we're buildin' here and now. We've spied upon you and learned how to do it. Well—almost how to do it. We haven't learned yet how to control the power—" "Hold on, now," I said. "Leaving the planet, you say. And where would you be going?" "There's another committee working on that. 'Tis not our concern. I was inclined to suggest the constellation Orion, which sounds as though it has a good Irish name, but I was hooted down. Be that as it may, my own job was to go into your nuclear center, learn how to make the ship, and proceed with its construction. Naturally, we didn't understand all of your high-flyin' science, but some of our people are pretty clever at gettin' up replicas of things." "You mean you've been spying on us at the center all this time? Do you know, we often had the feeling we were being watched, but we thought it was by the Russians. There's one thing which puzzles me, though. If you've been constantly around us—and I'm still able to see the little people—why did I never see you before?" "It may be we never crossed your path. It may be you can only see us when you're thinkin' of us, and of course truly believin' in us. I don't know—'tis a thing of the mind, and not important at the moment. What's important is for us to get our first ship to workin' properly and then we'll be on our way." "You're determined to go." "Truly we are, Mr. Houlihan. Now—to business. Just during these last few minutes a certain matter has crossed my mind. That's why I'm wastin' all this time with you, sir. You say you are a scientist." "A nuclear engineer." "Well, then, it may be that you can help us—now that you know we're here." "Help you?" "The power control, Mr. Houlihan. As I understand it, 'tis necessary to know at any instant exactly how much thrust is bein' delivered through the little holes in back. And on paper it looks simple enough—the square of somethin' or other. I've got the figures jotted in a book when I need 'em. But when you get to doin' it it doesn't come out exactly as it does on paper." "You're referring to the necessity for a coefficient of discharge." "Whatever it might be named," said Keech, shrugging. "'Tis the one thing we lack. I suppose eventually you people will be gettin' around to it. But meanwhile we need it right now, if we're to make our ship move." "And you want me to help you with this?" "That is exactly what crossed my mind." I nodded and looked grave and kneaded my chin for a moment softly. "Well, now, Keech," I said finally, "why should I help you?" "Ha!" said Keech, grinning, but not with humor, "the avarice of humans! I knew it! Well, Mr. Houlihan, I'll give you reason enough. The pot o' gold, Mr. Houlihan!" "The one at the end of the rainbow?" "It's not at the end of the rainbow. That's a grandmother's tale. Nor is it actually in an earthen crock. But there's gold, all right, enough to make you rich for the rest of your life. And I'll make you a proposition." "Go ahead." "We'll not be needin' gold where we're goin'. It's yours if you show us how to make our ship work." "Well, now, that's quite an offer," I said. Keech had the goodness to be quiet while I sat and thought for a while. My pipe had gone out and I lit it again. I finally said, "Let's have a look at your ship's drive and see what we can see." "You accept the proposition then?" "Let's have a look," I said, and that was all. Well, we had a look, and then several looks, and before the morning was out we had half the spaceship apart, and were deep in argument about the whole project. It was a most fascinating session. I had often wished for a true working model at the center, but no allowance had been inserted in the budget for it. Keech brought me paper and pencil and I talked with the aid of diagrams, as engineers are wont to do. Although the pencils were small and I had to hold them between thumb and forefinger, as you would a needle, I was able to make many sensible observations and even a few innovations. I came back again the next day—and every day for the following two weeks. It rained several times, but Keech and his people made a canopy of boughs and leaves and I was comfortable enough. Every once in a while someone from the town or the center itself would pass by, and stop to watch me. But of course they wouldn't see the leprechauns or anything the leprechauns had made, not being believers. I would halt work, pass the time of day, and then, in subtle fashion, send the intruder on his way. Keech and the little people just stood by and grinned all the while. At the end of sixteen days I had the entire problem all but whipped. It is not difficult to understand why. The working model and the fact that the small people with their quick eyes and clever fingers could spot all sorts of minute shortcomings was a great help. And I was hearing the old tongue and talking of the old things every day, and truly that went far to take the clutter out of my mind. I was no longer so lonely that I couldn't think properly. On the sixteenth day I covered a piece of paper with tiny mathematical symbols and handed it to Keech. "Here is your equation," I said. "It will enable you to know your thrust at any given moment, under any circumstances, in or out of gravity, and under all conditions of friction and combustion." "Thank you, Mr. Houlihan," said Keech. All his people had gathered in a loose circle, as though attending a rite. They were all looking at me quietly. "Mr. Houlihan," said Keech, "you will not be forgotten by the leprechauns. If we ever meet again, upon another world perchance, you'll find our friendship always eager and ready." "Thank you," I said. "And now, Mr. Houlihan," said Keech, "I'll see that a quantity of gold is delivered to your rooms tonight, and so keep my part of the bargain." "I'll not be needing the gold," I said. Keech's eyebrows popped upward. "What's this now?" "I'll not be needing it," I repeated. "I don't feel it would be right to take it for a service of this sort." "Well," said Keech in surprise, and in some awe, too, "well, now, musha Lord help us! 'Tis the first time I ever heard such a speech from a mortal." He turned to his people. "We'll have three cheers now, do you hear, for Mr. Houlihan—friend of the little people as long as he shall live!" And they cheered. And little tears crept into the corners of some of their turned-up eyes. We shook hands, all of us, and I left. I walked through the park, and back to the nuclear propulsion center. It was another cool, green morning with the leaves making only soft noises as the breezes came along. It smelled exactly like a wood I had known in Roscommon. And I lit my pipe and smoked it slowly and chuckled to myself at how I had gotten the best of the little people. Surely it was not every mortal who could accomplish that. I had given them the wrong equation, of course. They would never get their spaceship to work now, and later, if they tried to spy out the right information I would take special measures to prevent it, for I had the advantage of being able to see them. As for our own rocket ship, it should be well on its way by next St. Patrick's Day. For I had indeed determined the true coefficient of discharge, which I never could have done so quickly without those sessions in the glade with Keech and his working model. It would go down in scientific literature now, I suppose, as Houlihan's Equation, and that was honor and glory enough for me. I could do without Keech's pot of gold, though it would have been pleasant to be truly rich for a change. There was no sense in cheating him out of the gold to boot, for leprechauns are most clever in matters of this sort and he would have had it back soon enough—or else made it a burden in some way. Indeed, I had done a piece of work greatly to my advantage, and also to the advantage of humankind, and when a man can do the first and include the second as a fortunate byproduct it is a most happy accident. For if I had shown the little people how to make a spaceship they would have left our world. And this world, as long as it lasts—what would it be in that event? I ask you now, wouldn't we be even more likely to blow ourselves to Kingdom Come without the little people here for us to believe in every now and then? Transcriber's Note: This etext was produced from Fantastic Universe September 1955. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed. Minor spelling and typographical errors have been corrected without note.
|
A. collaborating with the leprechauns, who speak his same language
|
Which best describes how Edith feels about Henry's return home?
A. She is uncertain about how the Henry in front of her is different from the one who left 11 months ago
B. She feels relieved that he made it back from his trip alive.
C. She is thankful that her family is now back together.
D. She is nervous about how the environment of Henry's trip might have changed him.
|
THE FIRST ONE By HERBERT D. KASTLE Illustrated by von Dongen [Transcriber's Note: This etext was produced from Analog July 1961. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] The first man to return from beyond the Great Frontier may be welcomed ... but will it be as a curiosity, rather than as a hero...? There was the usual welcoming crowd for a celebrity, and the usual speeches by the usual politicians who met him at the airport which had once been twenty miles outside of Croton, but which the growing city had since engulfed and placed well within its boundaries. But everything wasn't usual. The crowd was quiet, and the mayor didn't seem quite as at-ease as he'd been on his last big welcoming—for Corporal Berringer, one of the crew of the spaceship Washington , first to set Americans upon Mars. His Honor's handclasp was somewhat moist and cold. His Honor's eyes held a trace of remoteness. Still, he was the honored home-comer, the successful returnee, the hometown boy who had made good in a big way, and they took the triumphal tour up Main Street to the new square and the grandstand. There he sat between the mayor and a nervous young coed chosen as homecoming queen, and looked out at the police and fire department bands, the National Guard, the boy scouts and girl scouts, the Elks and Masons. Several of the churches in town had shown indecision as to how to instruct their parishioners to treat him. But they had all come around. The tremendous national interest, the fact that he was the First One, had made them come around. It was obvious by now that they would have to adjust as they'd adjusted to all the other firsts taking place in these—as the newspapers had dubbed the start of the Twenty-first Century—the Galloping Twenties. He was glad when the official greeting was over. He was a very tired man and he had come farther, traveled longer and over darker country, than any man who'd ever lived before. He wanted a meal at his own table, a kiss from his wife, a word from his son, and later to see some old friends and a relative or two. He didn't want to talk about the journey. He wanted to forget the immediacy, the urgency, the terror; then perhaps he would talk. Or would he? For he had very little to tell. He had traveled and he had returned and his voyage was very much like the voyages of the great mariners, from Columbus onward—long, dull periods of time passing, passing, and then the arrival. The house had changed. He saw that as soon as the official car let him off at 45 Roosevelt Street. The change was, he knew, for the better. They had put a porch in front. They had rehabilitated, spruced up, almost rebuilt the entire outside and grounds. But he was sorry. He had wanted it to be as before. The head of the American Legion and the chief of police, who had escorted him on this trip from the square, didn't ask to go in with him. He was glad. He'd had enough of strangers. Not that he was through with strangers. There were dozens of them up and down the street, standing beside parked cars, looking at him. But when he looked back at them, their eyes dropped, they turned away, they began moving off. He was still too much the First One to have his gaze met. He walked up what had once been a concrete path and was now an ornate flagstone path. He climbed the new porch and raised the ornamental knocker on the new door and heard the soft music sound within. He was surprised that he'd had to do this. He'd thought Edith would be watching at a window. And perhaps she had been watching ... but she hadn't opened the door. The door opened; he looked at her. It hadn't been too long and she hadn't changed at all. She was still the small, slender girl he'd loved in high school, the small, slender woman he'd married twelve years ago. Ralphie was with her. They held onto each other as if seeking mutual support, the thirty-three-year old woman and ten-year-old boy. They looked at him, and then both moved forward, still together. He said, "It's good to be home!" Edith nodded and, still holding to Ralphie with one hand, put the other arm around him. He kissed her—her neck, her cheek—and all the old jokes came to mind, the jokes of travel-weary, battle-weary men, the and- then -I'll-put-my-pack-aside jokes that spoke of terrible hunger. She was trembling, and even as her lips came up to touch his he felt the difference, and because of this difference he turned with urgency to Ralphie and picked him up and hugged him and said, because he could think of nothing else to say, "What a big fella, what a big fella." Ralphie stood in his arms as if his feet were still planted on the floor, and he didn't look at his father but somewhere beyond him. "I didn't grow much while you were gone, Dad, Mom says I don't eat enough." So he put him down and told himself that it would all change, that everything would loosen up just as his commanding officer, General Carlisle, had said it would early this morning before he left Washington. "Give it some time," Carlisle had said. "You need the time; they need the time. And for the love of heaven, don't be sensitive." Edith was leading him into the living room, her hand lying still in his, a cool, dead bird lying still in his. He sat down on the couch, she sat down beside him—but she had hesitated. He wasn't being sensitive; she had hesitated. His wife had hesitated before sitting down beside him. Carlisle had said his position was analogous to Columbus', to Vasco De Gama's, to Preshoff's when the Russian returned from the Moon—but more so. Carlisle had said lots of things, but even Carlisle who had worked with him all the way, who had engineered the entire fantastic journey—even Carlisle the Nobel prize winner, the multi-degreed genius in uniform, had not actually spoken to him as one man to another. The eyes. It always showed in their eyes. He looked across the room at Ralphie, standing in the doorway, a boy already tall, already widening in the shoulders, already large of feature. It was like looking into the mirror and seeing himself twenty-five years ago. But Ralphie's face was drawn, was worried in a way that few ten-year-old faces are. "How's it going in school?" he asked. "Gee, Dad, it's the second month of summer vacation." "Well, then, before summer vacation?" "Pretty good." Edith said, "He made top forum the six-month period before vacation, and he made top forum the six-month period you went away, Hank." He nodded, remembering that, remembering everything, remembering the warmth of her farewell, the warmth of Ralphie's farewell, their tears as he left for the experimental flight station in the Aleutians. They had feared for him, having read of the many launchings gone wrong even in continent-to-continent experimental flight. They had been right to worry. He had suffered much after that blow-up. But now they should be rejoicing, because he had survived and made the long journey. Ralphie suddenly said, "I got to go, Dad. I promised Walt and the others I'd pitch. It's Inter-Town Little League, you know. It's Harmon, you know. I got to keep my word." Without waiting for an answer, he waved his hand—it shook; a ten-year-old boy's hand that shook—and ran from the room and from the house. He and Edith sat beside each other, and he wanted badly to take her in his arms, and yet he didn't want to oppress her. He stood up. "I'm very tired. I'd like to lie down a while." Which wasn't true, because he'd been lying down all the months of the way back. She said, "Of course. How stupid of me, expecting you to sit around and make small talk and pick up just where you left off." He nodded. But that was exactly what he wanted to do—make small talk and pick up just where he'd left off. But they didn't expect it of him; they wouldn't let him; they felt he had changed too much. She led him upstairs and along the foyer past Ralphie's room and past the small guest room to their bedroom. This, too, had changed. It was newly painted and it had new furniture. He saw twin beds separated by an ornate little table with an ornate little lamp, and this looked more ominous a barrier to him than the twelve-foot concrete-and-barbed-wire fence around the experimental station. "Which one is mine," he asked, and tried to smile. She also tried to smile. "The one near the window. You always liked the fresh air, the sunshine in the morning. You always said it helped you to get up on time when you were stationed at the base outside of town. You always said it reminded you—being able to see the sky—that you were going to go up in it, and that you were going to come down from it to this bed again." "Not this bed," he murmured, and was a little sorry afterward. "No, not this bed," she said quickly. "Your lodge donated the bedroom set and I really didn't know—" She waved her hand, her face white. He was sure then that she had known, and that the beds and the barrier between them were her own choice, if only an unconscious choice. He went to the bed near the window, stripped off his Air Force blue jacket, began to take off his shirt, but then remembered that some arm scars still showed. He waited for her to leave the room. She said, "Well then, rest up, dear," and went out. He took off his shirt and saw himself in the mirror on the opposite wall; and then took off his under-shirt. The body scars were faint, the scars running in long lines, one dissecting his chest, the other slicing diagonally across his upper abdomen to disappear under his trousers. There were several more on his back, and one on his right thigh. They'd been treated properly and would soon disappear. But she had never seen them. Perhaps she never would. Perhaps pajamas and robes and dark rooms would keep them from her until they were gone. Which was not what he'd considered at all important on leaving Walter Reed Hospital early this morning; which was something he found distasteful, something he felt beneath them both. And, at the same time, he began to understand that there would be many things, previously beneath them both, which would have to be considered. She had changed; Ralphie had changed; all the people he knew had probably changed—because they thought he had changed. He was tired of thinking. He lay down and closed his eyes. He let himself taste bitterness, unhappiness, a loneliness he had never known before. But sometime later, as he was dozing off, a sense of reassurance began filtering into his mind. After all, he was still Henry Devers, the same man who had left home eleven months ago, with a love for family and friends which was, if anything, stronger than before. Once he could communicate this, the strangeness would disappear and the First One would again become good old Hank. It was little enough to ask for—a return to old values, old relationships, the normalcies of the backwash instead of the freneticisms of the lime-light. It would certainly be granted to him. He slept. Dinner was at seven p.m. His mother came; his Uncle Joe and Aunt Lucille came. Together with Edith, Ralphie and himself, they made six, and ate in the dining room at the big table. Before he'd become the First One, it would have been a noisy affair. His family had never been noted for a lack of ebullience, a lack of talkativeness, and Ralphie had always chosen mealtimes—especially with company present—to describe everything and anything that had happened to him during the day. And Edith herself had always chatted, especially with his mother, though they didn't agree about much. Still, it had been good-natured; the general tone of their lives had been good-natured. This wasn't good-natured. Exactly what it was he wasn't sure. "Stiff" was perhaps the word. They began with grapefruit, Edith and Mother serving quickly, efficiently from the kitchen, then sitting down at the table. He looked at Mother as he raised his first spoonful of chilled fruit, and said, "Younger than ever." It was nothing new; he'd said it many many times before, but his mother had always reacted with a bright smile and a quip something like, "Young for the Golden Age Center, you mean." This time she burst into tears. It shocked him. But what shocked him even more was the fact that no one looked up, commented, made any attempt to comfort her; no one indicated in any way that a woman was sobbing at the table. He was sitting directly across from Mother, and reached out and touched her left hand which lay limply beside the silverware. She didn't move it—she hadn't touched him once beyond that first, quick, strangely-cool embrace at the door—then a few seconds later she withdrew it and let it drop out of sight. So there he was, Henry Devers, at home with the family. So there he was, the hero returned, waiting to be treated as a human being. The grapefruit shells were cleaned away and the soup served. Uncle Joe began to talk. "The greatest little development of circular uniform houses you ever did see," he boomed in his powerful salesman's voice. "Still going like sixty. We'll sell out before—" At that point he looked at Hank, and Hank nodded encouragement, desperately interested in this normalcy, and Joe's voice died away. He looked down at his plate, mumbled, "Soup's getting cold," and began to eat. His hand shook a little; his ruddy face was not quite as ruddy as Hank remembered it. Aunt Lucille made a few quavering statements about the Ladies' Tuesday Garden Club, and Hank looked across the table to where she sat between Joe and Mother—his wife and son bracketed him, and yet he felt alone—and said, "I've missed fooling around with the lawn and the rose bushes. Here it is August and I haven't had my hand to a mower or trowel." Aunt Lucille smiled, if you could call it that—a pitiful twitching of the lips—and nodded. She threw her eyes in his direction, and past him, and then down to her plate. Mother, who was still sniffling, said, "I have a dismal headache. I'm going to lie down in the guest room a while." She touched his shoulder in passing—his affectionate, effusive mother who would kiss stray dogs and strange children, who had often irritated him with an excess of physical and verbal caresses—she barely touched his shoulder and fled. So now five of them sat at the table. The meat was served—thin, rare slices of beef, the pink blood-juice oozing warmly from the center. He cut into it and raised a forkful to his mouth, then glanced at Ralphie and said, "Looks fresh enough to have been killed in the back yard." Ralphie said, "Yeah, Dad." Aunt Lucille put down her knife and fork and murmured something to her husband. Joe cleared his throat and said Lucille was rapidly becoming a vegetarian and he guessed she was going into the living room for a while. "She'll be back for dessert, of course," he said, his laugh sounding forced. Hank looked at Edith; Edith was busy with her plate. Hank looked at Ralphie; Ralphie was busy with his plate. Hank looked at Joe; Joe was chewing, gazing out over their heads to the kitchen. Hank looked at Lucille; she was disappearing into the living room. He brought his fist down on the table. The settings jumped; a glass overturned, spilling water. He brought it down again and again. They were all standing now. He sat there and pounded the table with his big right fist—Henry Devers, who would never have thought of making such a scene before, but who was now so sick and tired of being treated as the First One, of being stood back from, looked at in awe of, felt in fear of, that he could have smashed more than a table. Edith said, "Hank!" He said, voice hoarse, "Shut up. Go away. Let me eat alone. I'm sick of the lot of you." Mother and Joe returned a few minutes later where he sat forcing food down his throat. Mother said, "Henry dear—" He didn't answer. She began to cry, and he was glad she left the house then. He had never said anything really bad to his mother. He was afraid this would have been the time. Joe merely cleared his throat and mumbled something about getting together again soon and "drop out and see the new development" and he, too, was gone. Lucille never did manage to speak to him. He finished his beef and waited. Soon Edith came in with the special dessert she'd been preparing half the day—a magnificent English trifle. She served him, and spooned out a portion for herself and Ralphie. She hesitated near his chair, and when he made no comment she called the boy. Then the three of them were sitting, facing the empty side of the table. They ate the trifle. Ralphie finished first and got up and said, "Hey, I promised—" "You promised the boys you'd play baseball or football or handball or something; anything to get away from your father." Ralphie's head dropped and he muttered, "Aw, no, Dad." Edith said, "He'll stay home, Hank. We'll spend an evening together—talking, watching TV, playing Monopoly." Ralphie said, "Gee, sure, Dad, if you want to." Hank stood up. "The question is not whether I want to. You both know I want to. The question is whether you want to." They answered together that of course they wanted to. But their eyes—his wife's and son's eyes—could not meet his, and so he said he was going to his room because he was, after all, very tired and would in all probability continue to be very tired for a long, long time and that they shouldn't count on him for normal social life. He fell asleep quickly, lying there in his clothes. But he didn't sleep long. Edith shook him and he opened his eyes to a lighted room. "Phil and Rhona are here." He blinked at her. She smiled, and it seemed her old smile. "They're so anxious to see you, Hank. I could barely keep Phil from coming up and waking you himself. They want to go out and do the town. Please, Hank, say you will." He sat up. "Phil," he muttered. "Phil and Rhona." They'd had wonderful times together, from grammar school on. Phil and Rhona, their oldest and closest friends. Perhaps this would begin his real homecoming. Do the town? They'd paint it and then tear it down! It didn't turn out that way. He was disappointed; but then again, he'd also expected it. This entire first day at home had conditioned him to expect nothing good. They went to the bowling alleys, and Phil sounded very much the way he always had—soft spoken and full of laughter and full of jokes. He patted Edith on the head the way he always had, and clapped Hank on the shoulder (but not the way he always had—so much more gently, almost remotely), and insisted they all drink more than was good for them as he always had. And for once, Hank was ready to go along on the drinking. For once, he matched Phil shot for shot, beer for beer. They didn't bowl very long. At ten o'clock they crossed the road to Manfred's Tavern, where Phil and the girls ordered sandwiches and coffee and Hank went right on drinking. Edith said something to him, but he merely smiled and waved his hand and gulped another ounce of nirvana. There was dancing to a juke box in Manfred's Tavern. He'd been there many times before, and he was sure several of the couples recognized him. But except for a few abortive glances in his direction, it was as if he were a stranger in a city halfway around the world. At midnight, he was still drinking. The others wanted to leave, but he said, "I haven't danced with my girl Rhona." His tongue was thick, his mind was blurred, and yet he could read the strange expression on her face—pretty Rhona, who'd always flirted with him, who'd made a ritual of flirting with him. Pretty Rhona, who now looked as if she were going to be sick. "So let's rock," he said and stood up. They were on the dance floor. He held her close, and hummed and chatted. And through the alcoholic haze saw she was a stiff-smiled, stiff-bodied, mechanical dancing doll. The number finished; they walked back to the booth. Phil said, "Beddy-bye time." Hank said, "First one dance with my loving wife." He and Edith danced. He didn't hold her close as he had Rhona. He waited for her to come close on her own, and she did, and yet she didn't. Because while she put herself against him, there was something in her face—no, in her eyes; it always showed in the eyes—that made him know she was trying to be the old Edith and not succeeding. This time when the music ended, he was ready to go home. They rode back to town along Route Nine, he and Edith in the rear of Phil's car, Rhona driving because Phil had drunk just a little too much, Phil singing and telling an occasional bad joke, and somehow not his old self. No one was his old self. No one would ever be his old self with the First One. They turned left, to take the short cut along Hallowed Hill Road, and Phil finished a story about a Martian and a Hollywood sex queen and looked at his wife and then past her at the long, cast-iron fence paralleling the road. "Hey," he said, pointing, "do you know why that's the most popular place on earth?" Rhona glanced to the left, and so did Hank and Edith. Rhona made a little sound, and Edith seemed to stop breathing, but Phil went on a while longer, not yet aware of his supposed faux pas . "You know why?" he repeated, turning to the back seat, the laughter rumbling up from his chest. "You know why, folks?" Rhona said, "Did you notice Carl Braken and his wife at—" Hank said, "No, Phil, why is it the most popular place on earth?" Phil said, "Because people are—" And then he caught himself and waved his hand and muttered, "I forgot the punch line." "Because people are dying to get in," Hank said, and looked through the window, past the iron fence, into the large cemetery at the fleeting tombstones. The car was filled with horrified silence when there should have been nothing but laughter, or irritation at a too-old joke. "Maybe you should let me out right here," Hank said. "I'm home—or that's what everyone seems to think. Maybe I should lie down in an open grave. Maybe that would satisfy people. Maybe that's the only way to act, like Dracula or another monster from the movies." Edith said, "Oh, Hank, don't, don't!" The car raced along the road, crossed a macadam highway, went four blocks and pulled to a stop. He didn't bother saying good night. He didn't wait for Edith. He just got out and walked up the flagstone path and entered the house. "Hank," Edith whispered from the guest room doorway, "I'm so sorry—" "There's nothing to be sorry about. It's just a matter of time. It'll all work out in time." "Yes," she said quickly, "that's it. I need a little time. We all need a little time. Because it's so strange, Hank. Because it's so frightening. I should have told you that the moment you walked in. I think I've hurt you terribly, we've all hurt you terribly, by trying to hide that we're frightened." "I'm going to stay in the guest room," he said, "for as long as necessary. For good if need be." "How could it be for good? How, Hank?" That question was perhaps the first firm basis for hope he'd had since returning. And there was something else; what Carlisle had told him, even as Carlisle himself had reacted as all men did. "There are others coming, Edith. Eight that I know of in the tanks right now. My superior, Captain Davidson, who died at the same moment I did—seven months ago next Wednesday—he's going to be next. He was smashed up worse than I was, so it took a little longer, but he's almost ready. And there'll be many more, Edith. The government is going to save all they possibly can from now on. Every time a young and healthy man loses his life by accident, by violence, and his body can be recovered, he'll go into the tanks and they'll start the regenerative brain and organ process—the process that made it all possible. So people have to get used to us. And the old stories, the old terrors, the ugly old superstitions have to die, because in time each place will have some of us; because in time it'll be an ordinary thing." Edith said, "Yes, and I'm so grateful that you're here, Hank. Please believe that. Please be patient with me and Ralphie and—" She paused. "There's one question." He knew what the question was. It had been the first asked him by everyone from the president of the United States on down. "I saw nothing," he said. "It was as if I slept those six and a half months—slept without dreaming." She came to him and touched his face with her lips, and he was satisfied. Later, half asleep, he heard a dog howling, and remembered stories of how they announced death and the presence of monsters. He shivered and pulled the covers closer to him and luxuriated in being safe in his own home. THE END
|
A. She is uncertain about how the Henry in front of her is different from the one who left 11 months ago
|
Mr. Williams’ medications changed between 2018 and March 2019 - how did they change when looking at March 2019?
Choose the correct answer from the following options:
A. Lenalidomide 5 mg nightly and Bisoprolol 2.5 mg were discontinued.
B. The patient started taking Lyrica 25 mg and Lenalidomide 5 mg nightly.
C. The patient started taking Zofran 8 mg as needed.
D. The patient started taking 500 mg of Novalgin.
E. Amlodipin 5 mg was paused.
|
### Patient Report 0
**Dear colleague, **
Herewith we report on Mr. John Williams, born 08/08/1956, inpatient from
10/03/2015 to 10/06/2015.
**Diagnosis:**
Multiple Myeloma IgG kappa.
**Staging and Initial Diagnosis:**
Date: 03/2015
Stage: IIA based on the Salmon and Durie scale, ISS II.
- CT whole body 03/11/2015: Osteolysis detected in the seventh
thoracic vertebra (T7); pathologic fracture observed in the first
lumbar vertebra (L1).
- Bone marrow infiltration: Initial histological evaluation showed
22%; cytomorphological assessment revealed 28%.
**Histological Findings:**
Date: 03/2015
**FISH (Fluorescence In Situ Hybridization) Results:** Detected an
additional signal for both CCND1 and CCND3. Presence of one trisomy or
tetrasomy 9. Additional signals observed for 5p15- and 5q31- as well as
19p13- and 19q13-. 46, XY with a detected ASxL1 mutation.
**Treatment Timeline:**
**01-02/15:** Administered 2 cycles of
Cyclophosphamide-Bortezomib-Dexamethasone (CyBorD). Resulted in stable
disease but caused prolonged pancytopenia.
**03/15 - 06/15:** Administered 3 cycles of a combination treatment
including Carfilzomib, Lenalidomide, and Dexamethasone.
**07/15:** Underwent stem cell mobilization using cyclophosphamide.
**07-08/15:** Experienced extended pancytopenia and regeneration. Bone
marrow puncture showed progressive disease with a significant increase
in plasma cell infiltration, reaching 92%.
**09/02/15:** Received the first dosage of daratumumab at 16mg/kg.
Subsequently developed thrombocytopenia. Treatment did not include
Revlimid.
**Histopathological report: **
Multiple myeloma, IgG kappa. The evaluation is for myelodysplastic
syndrome in the presence of tricytopenia and an ASXL1 mutation.
**Methods:** Hematoxylin and eosin (HE), periodic acid-Schiff (PAS),
iron, Giemsa, Gomori, chloroacetate esterase, step sections,
decalcification, and 1 block.
**Microscopic Examination:**
The sample is a 2 cm long bone marrow biopsy core that contains more
than ten medullary canals. The cellularity is around 20-30%, which is
considered normocellular for the patient\'s age. There is evidence of
bone marrow edema and heightened hemosiderosis. Recent stromal
hemorrhages are also observed. There is a relative increase in
erythropoiesis with a ratio of erythropoiesis to granulopoiesis being
approximately 2:1. Erythropoiesis is present in well-defined zones with
regular maturation. Only minimal nuclear rounding is observed.
Granulopoiesis matures into segmented granulocytes. PAS staining reveals
some morphologically normal megakaryocytes. Occasionally there are bare
nuclei and possible microforms. Scattered mature plasma cells are
observed with no signs of atypical proliferation. The argyrophilic
fibrous network is fine, and no fibrosis is detected.
**Preliminary Findings:**
The bone marrow biopsy is normocellular for the age with a relative
increase in erythropoiesis that shows only minimal cytological atypia.
Granulopoiesis is slightly reduced, while megakaryopoiesis is
normocellular with a few cells that are hypolobulated.There is bone
marrow edema and enhanced hemosiderosis. Scattered mature plasma cells
are also noted.
Based solely on histomorphologic observations, it is not enough to
confirm a diagnosis of myelodysplastic syndrome (MDS), which is the
suspected clinical diagnosis. For a more thorough evaluation of
potential atypicalities in the megakaryopoiesis (like
micromegakaryocytes), further immunohistochemical examination is
recommended. Assessing the blast content is also advised. There is no
evidence currently of manifest infiltrates from the previously diagnosed
multiple myeloma.
**Immunohistochemical Additional Findings (Dated 10/04/2015):**
**Immunohistochemistry Stains Used:** CD3, CD79a, CD34, CD117, MUM-1,
Kappa, lambda, CyclinD1, CD61.
Blast cells positive for CD34 and CD117 are below 5% of the total. CD3
stains scattered T lymphocytes, and CD79a identifies sporadic B
lymphocytes and some plasma cells. Plasma cells are also positive for
MUM-1 and exhibit polytypic expression of kappa and lambda light chains.
There is no co-expression with CyclinD1. CD61 highlights the previously
described megakaryocytes, and no micromegakaryocytes are observed.
**Final Report:**
The bone marrow biopsy is representative and normocellular for the
patient\'s age. There is a relative increase in erythropoiesis that
shows only minor cytological atypia. Granulopoiesis appears slightly
reduced, while megakaryopoiesis presents with a few hypolobulated cell
forms. Evidence of bone marrow edema and increased hemosiderosis is
noted, along with scattered mature plasma cells.
### Patient Report 1
**Dear colleague, **
We hereby report on Mr. Williams, John, born 08/08/1956, inpatient from
11/30/2015 to 12/28/2015.
**Oncological Diagnosis**:
Multiple myeloma IgG kappa.
Initial diagnosis 03/15: Stage IIA (Salmon and Durie), ISS II.
**Sites**:
Osteolysis in T7 vertebra, fracture in T1 vertebra.
Bone marrow: 22% histological, 28% cytomorphologic infiltration.
**Histology**:
Bone marrow biopsy 11/16: FISH: Additional signals for CCND1, CCND3;
Trisomy 3, 9; Additional signals on chromosomes 5 and 19. Chromosomal
analysis: 46, XY with ASxL1 mutation.
**Treatment**:
01-02/15: 2 cycles Cyclophosphamide-Bortezomib-Dexamethasone -\>
Stable disease, prolonged low blood counts.
03/15 - 06/15: 3 cycles Carfilzomib/Lenolidomide/Dexamethasone.
07/15: Stem cell mobilization with Cyclophosphamide.
07-08/15: Extended low blood count. Bone marrow biopsy: 92% plasma cell
infiltration.
09/02/15: Darzalex 16mg/kg initial dose, with platelet count drop. No
Lenalidomide.
09/04/15: 10 cycles of Darzalex, 1 cycle with Lenalidomide due to
renewed low platelet and white blood cell counts.
11-12/15: Conditioning chemo with Fludarabine/Treosulfan, then
allogeneic stem cell transplant from HLA-matched unrelated donor.
Immunosuppression with ATG, cyclosporine, Mycophenolate Mofetil.
**Complications**:
Mucositis, central line infection, gastrointestinal symptoms, urinary
infections with E. faecium and E.coli, JC virus bladder infection.
**Secondary Diagnoses**:
Dry eye syndrome, Type 2 diabetes managed with oral meds, Hypertension.
**Treatment Plan**:
Gradual reduction of immunosuppression based on graft vs. host disease
signs.
**Radiology**:
CT Whole Body: 12/01/15: Various areas of bone osteolysis. Degeneration
of spine.
CT Chest 12/02/15 and 12/03/15: Changes in lungs and some fluid
accumulation.
**Medication**:
**Medication** **Dosage** **Frequency**
------------------------------ ------------- ---------------
Mycophenolic Acid (Myfortic) 360 mg Twice Daily
Cyclosporine (Sandimmune) 200 mg Daily
Artificial Tears As directed 3x Daily
Candesartan (Atacand) 8 mg Daily
Tamsulosin (Flomax) 0.4 mg Daily
Pantoprazole (Protonix) 40 mg Daily
Amlodipine (Norvasc) 5 mg Twice Daily
Cotrimoxazole (Bactrim) 960 mg Mon/Wed/Fri
Valacyclovir (Valtrex) 500 mg Twice Daily
**Summary**:
Mr. Williams was admitted on 11/30/2015 for treatment related to his
Multiple Myeloma. He underwent conditioning chemotherapy,
immunosuppressive therapy, and stem cell transplantation. He experienced
complications, including infections and symptoms affecting multiple
systems. Close monitoring of blood pressure and glucose is recommended.
He was discharged on 12/28/2015 in good condition and will be followed
up in the outpatient clinic. If there are worsening symptoms, he should
visit the emergency department immediately.
**Dear Mr. Williams,**
We report on your outpatient treatment on 02/15/2016.
**Diagnoses:**
1. **Multiple Myeloma** IgG kappa, diagnosed 03/2015.
Stage IIA as per Salmon and Durie, stage II as per ISS.
Osteolysis at T7 vertebra, fracture at T1 vertebra.
Bone marrow infiltration: 22% histologically, 28% cytologically.
FISH: Indications of additional CCND1 and CCND3 signals; Trisomy 3,
additional signals at various chromosomes.
Chromosome analysis: 46, XY \[20\].
**Secondary diagnoses:**
Type 2 diabetes mellitus
Hypertension
Cataract (surgery 06/2018)
Nodular goiter
RSV pneumonia (03/2018)
**Summary:**
Mr. Williams presents in good general health to our bone marrow
transplant (BMT) outpatient clinic. There are no signs of infection or
chronic graft rejection. He has shown significant improvement in
resilience and does not have any complaints. Vital signs are stable.
Blood tests showed ongoing regeneration with normal light chains and
persistent positive immunofixation. There is no need for
myeloma-specific therapy at present, but close monitoring of the
paraprotein is required.
**Medication:**
**Medication** **Dosage** **Frequency**
----------------------------- ---------------------- -------------------------------------------------------
Tamsulosin (Flomax) 0.4 mg Daily in the morning
Candesartan (Atacand) 8 mg Twice Daily
Metformin (Glucophage) 1000 mg 0.5 tablet in the morning, 1.5 tablets in the evening
Pantoprazole (Protonix) 20 mg Daily in the morning
Vitamin D3 (various brands) 20,000 IU Once a week
Allopurinol (Zyloprim) 100 mg Daily in the morning
Insulin (various types) As per sliding scale As per sliding scale
With kind regards
### Patient Report 2
**Dear colleague, **
We are providing an update on our shared patient, Mr. John Williams, who
consulted with us on June 15, 2018.
**Consultation Summary:**
8. **Multiple Myeloma**
**Kidney biopsy scheduled for tomorrow.**
**Prostate cancer**
**Current Status:**
Acute renal failure accompanied by proteinuria due to the recent
diagnosis of multiple myeloma.
Multiple osteolytic lesions, including at the T4, T7, L1 vertebra and
the ribs.
**Diagnosis:**
Multiple myeloma.
Prostate cancer
**Clinical Presentation:**
Osteolytic lesion presenting as thoracic pain.
**Imaging Findings:**
Osteolytic lesion at T4 vertebra with involvement of the posterior edge.
**Planned Procedures:**
Restricted bed rest.
Whole spine MRI with STIR sequences, to be presented in the upcoming
tumor board meeting for deciding further course of action.
**Previous Diagnoses:**
May, 2018, Nephrology: Enlarged kidneys noted bilaterally.
January, 2018, Urology: Prostate cancer
December, 2015, Internal Medicine: Multiple myeloma without evidence of
complete remission.
**Previous Procedures:**
Transrectal biopsy of the prostate.
**Histology Report, Date: June 13, 2018:**
Suspected plasmacytoma with paraproteinemia.
WBC 6.47; Hb 10.8; Platelets 251,000.
Bone marrow biopsy: Cellularity approximated at 48%, indicating slightly
increased cellularity. Amidst reduced hematopoiesis, there is
proliferation of plasmacytoid cells with certain features.
**Preliminary Report:**
The bone marrow sample indicates possible infiltration due to plasma
cell myeloma. Additional tests will be conducted to confirm and further
elucidate this finding.
**Supplementary Findings:**
Immunohistochemical staining: CD138, Kappa, Lambda, CD20.
Microscopic findings confirm the presence of nodular infiltrates with
certain features.
**Final Report:**
Bone marrow sample indicates infiltration by a plasma cell myeloma with
kappa light chain restriction. Additionally, regular trilinear
hematopoiesis is significantly reduced.
### Patient Report 3
**Dear colleague, **
I wish to provide an update on our mutual patient, Mr. John Williams,
born 08/08/1956, who presented at our clinic at 08/20/2018.
**Diagnosis:**
Present condition: Multiple Myeloma IgG type, coded under ICD-10.
Stage: II B based on Durie and Salmon criteria; determined from Hb 9.1,
Creatinine 4.5 mg/dL.
**Histology:**
Bone marrow biopsy presents a strong indication of interstitial and
focal nodular invasion of the marrow space by plasma cell myeloma,
predominantly of high to intermediate maturity.
**Immunohistochemistry:**
The nodular infiltrates were found positive for CD138 with a kappa-light
chain restriction (infiltration rate at 62%).
Cytological findings align with high-grade bone marrow infiltration by
multiple myeloma.
**Tumor Localization:**
MRI of the entire spine conducted on 06/20/2018 reveals disseminated
bone lesions throughout the spine without any soft tissue involvement.
There is noted anterior vertebral body involvement at T4.
**Secondary Diagnoses:**
Cysts in the right kidney.
As of 01/2018, a diagnosis of Prostate cancer with a Gleason score of 8
and a PSA reading of 10.02.
Previous rib fracture, which may be associated with the multiple
myeloma.
Chronic renal failure, with ongoing dialysis treatment.
Documented mitral valve surgery in 2015.
History of Deep Vein Thrombosis in 1999.
**Prior Treatments:**
Initial diagnosis of multiple myeloma IgG kappa in 2015.
Prostate cancer was diagnosed in 01/2018 following spontaneous rib
fractures, Gleason score of 8.
A PSMA-PET-CT scan in 05/18 showed multiple bone lesions, notably
pronounced at Th4.
Tumor board review in 06/2018 concluded treatment strategies for
urological tumors, encompassing radiation therapy targeting Th4 and
antiandrogen therapy for the identified prostate cancer, using a GnRH
analog.
The progression of multiple myeloma required the commencement of
systemic treatment with Velcade and Dexamethasone.
**Study**: PSMA-PET-CT Scan
**Date of Study**: 05/2018
**Clinical Information**: Prostate cancer diagnosed in 01/2018 following
spontaneous rib fractures. Gleason score of 8.
**Technique**:
Whole body positron emission tomography/computed tomography (PET/CT) was
performed following the intravenous administration of PSMA-radiotracer.
Coronal, sagittal, and axial images were acquired and reviewed.
**Findings**:
Bone: Notably increased PSMA uptake is seen at the level of T4 vertebral
body consistent with metastatic involvement. The lesion has caused
cortical erosion and expansion with potential involvement of the
anterior spinal canal. Multiple rib lesions are identified,
corresponding with the clinical history of spontaneous rib fractures.
These lesions exhibit no increased PSMA uptake. No other foci of
increased PSMA uptake throughout the axial and appendicular skeleton.
**Prostate**:
12. The prostate gland demonstrates diffusely increased uptake, which is
consistent with primary prostate malignancy, especially given the
known clinical history.
**Thorax/Abdomen: **
13. No abnormal PSMA avid soft tissue masses or lymphadenopathies were
noted in the visualized fields. No pulmonary nodules or masses
suggestive of metastatic disease were identified. Liver, spleen,
kidneys, and adrenal glands appear unremarkable with no evidence of
metastatic lesions.
**Impression**:
Osseous metastasis from prostate cancer with involvement of the T4
vertebral body. No evidence of soft tissue, lymph node, or pulmonary
metastases in the visualized fields. Prostate gland showing evidence
consistent with primary malignancy.
**Current Radiation Therapy:**
**Indication:** Radiotherapy became a consideration due to a sizable
osteolytic lesion at T4, both for pain alleviation and stabilization.
Concurrent treatment of the aching ribs on the right side (7th-9th) was
also performed.
**Technique:** 6 MeV photons from a linear accelerator, administering a
cumulative dose of 30 Gy to thoracic vertebra 4 and 20 Gy to the ribs
with respective daily doses.
1. **Treatment Duration:**
Th4: 08/21/2018 to 08/27/2018
Rib area: 08/21/2018 to 08/27/2018
**Clinical Update:**
Throughout the therapy period, Mr. Williams remained admitted to our
Oncology ward for ongoing reduced dosage chemotherapy using Velcade. He
has reported a decline in pain sensations during this timeframe. The
overall health status appeared satisfactory, with no skin irritation
observed at the irradiated sites.
**Subsequent Actions:**
Guidance on skincare and potential adverse effects have been provided to
Mr. Williams. The intensity of the chemotherapy will soon be escalated.
A radio-oncological assessment has been scheduled in our outpatient
facility for 09/05/2018 at 12:00 PM. I kindly request the most recent
test results by this date.
**Note:** In compliance with the Radiation Protection Act, we shall
undertake regular evaluations and request updates on the patient\'s
condition. Mr. Williams has been apprised of the necessity for
consistent oncological check-ups.
Warm regards,
### Patient Report 4
**Dear colleague, **
We wish to update you on our mutual patient, Mr. John Williams.
**Diagnosis:**
Current multiple myeloma IgG type
**Tumor Localization:**
Based on a whole spine MRI dated June 20, 2018:
Multiple intraosseous lesions throughout the spine without soft tissue
involvement.
Known intrusion of the T4 cover plate.
**Secondary Diagnoses:**
Right kidney cysts
Diagnosed prostate carcinoma in January 2018, Gleason score 8, initial
PSA at 10.02.
History of a spontaneous rib fracture related to the multiple myeloma.
Chronic renal insufficiency; he remains on dialysis.
History of mitral valve reconstruction in 2015.
History of deep vein thrombosis in 1999.
**Treatment Overview:**
Diagnosed with multiple myeloma type kappa in 2015 with initially normal
renal function.
Diagnosed with prostate carcinoma in January 2018 due to spontaneous rib
fractures, Gleason score 8.
Treatment decisions in 2018 included radiation for vertebral lesions and
hormone therapy for prostate cancer using a GnRH analogue.
Systemic therapy with Velcade and Dexamethasone initiated due to
progressive myeloma.
Radiation therapy in August 2018 for vertebral and rib lesions.
**Summary:**
Mr. Williams had a radio-oncological follow-up on September 29, 2018.
His general health has improved. He remains on thrice-weekly dialysis.
Recent CT scans show extensive osteolysis of the spine with several
vertebral collapses. Currently, we see no urgent fracture risk or need
for additional radiation therapy. We have planned regular clinical
check-ups with Mr. Williams. His next follow-up is scheduled in three
months.
**Oncologic treatment: **
Daratumumab/lenalidomide/dexamethasone regimen:
Daratumumab 16mg/kg: Days 1, 8, 15, 22 for cycles 1 & 2 (every 28 days
for 8 weeks).
Days 1, 15 for cycles 3-6 (every 28 days for 16 weeks).
Day 1 for subsequent cycles (every 28 days).
Dexamethasone 20mg on Daratumumab days, with an additional 20mg the day
after (totaling 40mg/week).
Lenalidomide 5mg from day 1-21 (every 28 days).
Bondronate every 4 weeks (last administered on 12/13/2016).
Re-evaluation of hemodialysis and autologous peripheral blood stem cell
transplant (PBSCT) after 2 cycles of daratumumab.
**CT Spine scan (09/30/2018): **
**Technique**: Contrast-enhanced computed tomography (Omnipaque 240) of
the thoracic and lumbar spine was performed with axial slices, and
multiplanar reconstructions in sagittal and coronal orientations.
**Findings**:
**Thoracic Spine**:
Extensive osteolytic lesions are identified in multiple thoracic
vertebrae. Specifically, vertebral collapses are noted at T4, T7, T9,
T11. No significant bony destruction of pedicles, lamina and spinous
processes. No evidence of paravertebral or epidural soft tissue masses.
**Lumbar Spine**:
Prominent osteolytic changes are seen in L1 (with fracture) and L4
vertebral bodies. However, there is no significant vertebral collapse.
Preserved pedicles, lamina, and spinous Processes without significant
osteolysis. No evidence of abnormal masses or lymphadenopathy.
No significant central canal stenosis or neural foraminal narrowing. The
intervertebral discs are preserved without significant discopathies.
**Impression**:
Extensive osteolysis in multiple vertebral bodies, specifically in the
thoracic and lumbar spine, with vertebral collapses at levels T4, T7,
T9, and T11 as well as L1. Also, osteolytic changes in L4 of the lumbar
spine.
Currently, based on imaging, there does not appear to be an urgent
fracture risk, and no radiologic signs suggesting a need for imminent
radiation therapy. No soft tissue abnormalities identified in the
examined regions.
**Medication: **
**Medication** **Dosage** **Frequency**
---------------------------- ------------ ----------------------------------------
Fentanyl Patch (Duragesic) 25 μg Changed every 72 hours
Enoxaparin (Lovenox) 0.2 mL Nightly (dialysis dose)
Dexamethasone (Decadron) 8 mg In the morning (day after Daratumumab)
Pantoprazole (Protonix) 40 mg Daily in the morning
Cotrimoxazole (Bactrim) 480 mg Thrice weekly (Mon, Wed, Fri)
Valacyclovir (Valtrex) 500 mg Daily in the morning
Acetaminophen (Tylenol) 500 mg Orally, three times daily
Ibandronate (Boniva) 2 mg Every 4 weeks
Leuprorelin (Lupron Depot) 3.75 mg Monthly (4-week depot) subcutaneously
Pregabalin (Lyrica) 25 mg Twice a day
Amlodipine (Norvasc) 5 mg Daily in the morning
Bisoprolol (Zebeta) 5 mg Daily in the morning
Lenalidomide (Revlimid) 5 mg Nightly
Ondansetron (Zofran) 8 mg As needed, up to twice daily
### Patient Report 5
**Dear colleague, **
We are updating you on Mr. John Williams\' outpatient visit on December
13, 2018.
**Diagnosis:**
Febrile respiratory infection.
**Underlying Conditions:**
Multiple myeloma, kappa light chain, stage IIIB as classified by Salmon
and Durie.
Chronic kidney disease requiring hemodialysis.
Prostate cancer.
**Summary:**
Mr. Williams came to the emergency room with fever and dry cough during
his multiple myeloma treatment with Darzalex, Revlimid, and
Dexamethasone. His vital signs were recorded, and laboratory tests
showed signs of infection and confirmed chronic kidney disease. Chest
X-ray indicated possible inflammation. Given these findings, Mr.
Williams was admitted for antibiotic therapy. Further observations and
treatments were documented.
### Patient Report 6
**Dear colleague, **
This letter pertains to Mr. John Williams, who was hospitalized from
December 14 to 21st, 2018.
**Oncological Diagnosis:**
Multiple myeloma, kappa light chain, initially diagnosed in June 2018 as
stage IIIB per Durie and Salmon criteria.
**Treatment Details:**
He underwent various treatment regimens for multiple myeloma over the
course of the year. His current condition indicates an
influenza-positive pneumonia, likely with a bacterial superinfection. He
continues hemodialysis thrice a week.
**Secondary Diagnoses:**
Several renal complications were documented in June 2018.
**Plan of Care:**
Mr. Williams\' therapy plan was discussed in a tumor board meeting. He
remains on a regimen of Darzalex, Revlimid, and Dexamethasone.
**Summary:**
Mr. Williams came to the emergency room on December 13, 2018, with cough
and fever. Further details about his history can be found in previous
communications. On admission, he showed signs of a respiratory
infection, confirmed by a chest X-ray. He was treated with antibiotics,
which were later escalated. He also tested positive for influenza A and
was given Tamiflu. After a short in-patient stay, he has shown
improvement. He is scheduled to continue his therapy in our clinic on
December 22, 2018. In case of any complications, he has been advised to
return to our emergency room immediately.
For future consultations, please provide a referral slip for each new
quarter.
Warm regards
### Patient Report 7
**Dear colleague, **
We are writing to inform you about Mr. John Williams, who was an
inpatient in our clinic from March 1, 2019, to March 3, 2019.
Oncological diagnosis:
Mr. Williams was diagnosed with Multiple Myeloma light chain kappa. He
received his follow-up diagnosis in June 2018, which was at stage IIIB
per the Durie and Salmon staging system.
Treatment:
In June 2018, he was given VelDex due to impaired renal function.
Subsequently, he received Carfilzomib (15mg/m2 on days 1-2, 8-9, 15-16),
Lenalidomide (5 mg, on days 1-21), and Dexamethasone (40mg, on days 1,
8, 15-16, 22). In addition, he was treated with Pomalidomide (4mg on
days 1-21), Doxorubicin (9mg/m2 on days 1, 4), and Dexamethasone (40mg,
on days 1, 8, 15, 22). He underwent radiation therapy to T4 of the rib
thorax in August. Between August to October 2018, he had three cycles of
Pomalidomide, Doxorubicin, and Dexamethasone, after which the disease
progressed. From November 2018 to February 2019, he had four cycles of
Daratumumab, Lenalidomide, and Dexamethasone.
**Outcome:**
The response to the treatment was very good partial remission (VGPR).
**Present Treatment:**
He underwent mobilization chemotherapy with cyclophosphamide, with a
dosage adjusted due to his requirement for dialysis (1500mg/m^2^ on day
1 and 1000mg/m^2^ on day 2). He received dialysis on March 2 in our
nephrology department.
**Secondary diagnoses:**
In March 2018, he developed renal insufficiency requiring thrice-weekly
dialysis. In January 2018, he was diagnosed with prostate carcinoma and
was treated with an androgen blockade using Enantone.
**Future Therapy Plan:**
The tumor board\'s decision from March 3, 2019 was to continue with
Daratumumab, Revlimid, and Dexamethasone due to the good response. He
will undergo stem cell mobilization and high-dose therapy with
autologous stem cell transplant. Monitoring is scheduled for March 14,
2019, followed by dialysis at our dialysis center on Mondays,
Wednesdays, and Fridays.
**Medications:**
His current medications include:
**Medication** **Dosage** **Frequency**
------------------------------ ------------------ ---------------------------------------------------
Fentanyl Patch (Duragesic) 25 μg Changed every 72 hours
Enoxaparin (Lovenox) 0.2 mL For dialysis
Dexamethasone (Decadron) 8 mg On March 4 and 5
Pantoprazole (Protonix) 40 mg
Cotrimoxazole (Bactrim) 480 mg Thrice weekly on Mondays, Wednesdays, and Fridays
Valacyclovir (Valtrex) 500 mg
Ibandronate (Boniva) 2 mg Every four weeks
Leuprorelin (Lupron Depot) 3.75 mg Every four weeks
Pregabalin (Lyrica) 25 mg
Amlodipine (Norvasc) Currently paused Currently paused
Bisoprolol (Zebeta) 2.5 mg
Filgrastim (Neupogen/Granix) 48 million IU
**Summary:**
Mr. Williams was admitted on March 1, 2019, for mobilization
chemotherapy with cyclophosphamide. Please refer to our previous letters
for a detailed history. His last treatment was with daratumumab,
Revlimid, and dexamethasone. Fortunately, this treatment showed a very
good response. He is dialyzed three times a week at our clinic due to
chronic renal insufficiency. He was discharged on March 3, 2019, and we
request the administration of filgrastim as per the medication plan
starting March 6, 2019. CD34+ monitoring is scheduled for March 14,
2019. Depending on the CD34+ count, stem cell collection may need to be
scheduled on a dialysis-free day. We have coordinated with our
colleagues at the dialysis center for the collection via the atrial
catheter. A follow-up for blood count and Ibandronate administration has
been scheduled for March 10, 2017. If his condition deteriorates or if
he shows signs of infection, bleeding, or any other complications, he
should immediately be brought to our emergency department. Please
remember to bring a referral form during your initial visit each
quarter.
Therapy recommendation based on Transthoracic echocardiography findings:
Mr. Williams has a normally sized left ventricle with standard global
function. There\'s no evidence of any regional wall motion
abnormalities. The right ventricle is also of normal size with standard
function. The left atrium is not dilated. There\'s marked concentric
left ventricular hypertrophy. His aortic valve shows insufficiency of I°
(PHT 520 ms), while the mitral and tricuspid valves appear normal. There
is no significant pericardial effusion. Overall, he has a standard left
ventricular function with no significant valvular diseases or pulmonary
hypertension.
**Surgery Report:**
Diagnosis: Terminal renal failure.
Procedure: Creation of a right upper arm brachialis-basilica fistula
with the anterior movement of the right basilic vein.
**Report:**
Mr. Williams required dialysis due to terminal renal insufficiency. For
this purpose, an arteriovenous (AV) fistula was created as a dialysis
access. Previously, dialysis was performed using a right atrial
catheter. After mapping, only the basilic vein on the right arm seemed
suitable. Hence, a brachialis-basilica fistula was created with anterior
transposition of the basilica vein. A partial mobilization of the
basilica vein was performed. Afterward, a brachialis-basilica
anastomosis was carried out. The operation was uncomplicated.
Your collaboration has been instrumental in managing this patient
effectively. If you have any further queries or require additional
details, please do not hesitate to contact our office.
**Medication:**
**Medication** **Dosage** **Frequency**
------------------------------- ------------------ ------------------------------------
Fentanyl Patch (Duragesic) 25 μg Change every 72 hours
Enoxaparin (Lovenox) 0.2 mL Nightly (dialysis dose)
Dexamethasone (Decadron) 8 mg Morning on 03/05 & 03/06
Pantoprazole (Protonix) 40 mg Morning
Cotrimoxazole (Bactrim Forte) 480 mg Morning 3x weekly on Mon, Wed, Fri
Valacyclovir (Valtrex) 500 mg Half tablet in the morning
Ibandronate (Boniva) 2 mg Every 4 weeks
Leuprorelin (Lupron Depot) 3.75 mg Monthly subcutaneous (Morning)
Pregabalin (Lyrica) 25 mg Morning and Evening
Amlodipine (Norvasc) Currently paused Currently paused
Bisoprolol (Zebeta) 2.5 mg Morning and Evening
Filgrastim (Neupogen/Granix) 48 million IU Morning and Evening
Best regards,
### Patient Report 8
**Dear colleague, **
I am writing to provide you with a detailed report on Mr. John Williams,
who was admitted to our facility from May 8, 2020, to May 28, 2020.
**Diagnoses:**
History of acute mitral valve endocarditis in March 2020.
Subsequent re-operation entailing mitral valve replacement using a
Bioprosthesis (29 mm) coupled with the resection of all infected tissue
from the mitral valve\'s supporting apparatus on March 24, 2020.
The origin remains uncertain, but potential associations include Demers
catheter infection and port catheter infection (confirmed presence of
Staphylococcus epidermidis).
Surgical removal was conducted on March 21, 2020, with no findings at
the catheter tips.
14. Antibiotic regimen included:
Meropenem from April 2, 2020, to April 23, 2020.
Linezolid 600 mg from April 3, 2020, to April 19, 2020.
Daptomycin from April 3, 2020, to May 27, 2020.
Fosfomycin from April 19, 2020, to May 28, 2020.
History of mitral valve reconstruction via minithoracotomy in 2015.
Right-side vision loss due to septic-embolic central retinal artery
occlusion.
Left hemispheric ischemia in the caput nuclei caudati/lenticular nuclei
on April 5, 2020, possibly embolic in origin from mitral valve
endocarditis.
History of brainstem transient ischemic attack (TIA) on March 11, 2020,
potentially embolic in relation to mitral valve endocarditis.
Jugular vein thrombosis.
20. Hematological/oncological diagnoses comprise:
Multiple myeloma with lambda light chains, stage IIIB according to
the Salmon and Durie criteria, first diagnosed in 2015. This was
accompanied by multiple osteolysis occurrences, history of radiation
to Th4 and rib thorax, and treatment with Daratumumab. Current
treatment has been paused due to remission.
A prostate carcinoma diagnosis in January 2018
**Other medical conditions include:**
-Chronic kidney failure necessitating dialysis since 2018, history of a
Demer catheter with explantation on March 2020, and angioplasty on the
right V. basilica and V. brachialis due to stenosis-related shunt
dysfunction.
-History of brainstem TIA in April 2019.
-Sensations of tingling paresthesias in both lower legs.
-History of bilateral deep vein thrombosis.
-Frequent calf muscle cramps.
**Medical History Overview:**
Mr. Williams\'s latest admission on May 8, 2020, was to assess remission
status and determine if continuation of treatment for his known multiple
myeloma was necessary. Previously, until March 2020 he was under a
Daratumumab monotherapy (as he could not tolerate Revlimid), which
showed stable disease progression. Prior to this, he was treated at our
local hospital for mitral valve endocarditis which had a complex
trajectory. At the time of admission, Mr. Williams felt generally weak
but was otherwise in stable condition. Upon discontinuation of the
fentanyl patch, his back pain increased. He exhibited no fevers and had
no known allergies. His appetite was low, and he reported no nausea.
Since his heart surgery, he has experienced numbness in his left heel
and toes. His residual urine output was about 190 mL per day, and he was
undergoing regular dialysis.
**Physical Examination:**
The patient was alert, responsive, and fully oriented. The examination
of the head, neck, and lungs was unremarkable. Cardiac auscultation
revealed clear and rhythmic heart sounds without any abnormal findings.
There was a non-irritated sternotomy scar. Examination of his back
revealed decubitus ulcers. Abdominal examination showed a soft,
non-tender abdomen with normal bowel sounds. Extremity examination
revealed minor edema.
**Diagnostic Imaging and Tests:**
A series of diagnostic tests, including sonography, whole body CT scan,
ophthalmological exams, and histology were conducted. The results are
detailed within this report. In summary, the findings indicate:
-Limited abnormalities in the heart\'s echocardiography, with potential
mitral valve issues to monitor.
-Bone scans revealed extensive osteopenia and other abnormalities
related to his known multiple myeloma, but no evidence of new
osteolysis.
-Eye examinations confirmed the previously noted vision issues,
potentially stemming from the mitral valve endocarditis, but provided no
clear solutions.
-Histological evaluation of bone marrow samples indicates largely
regular hematopoiesis but confirms infiltration from the known multiple
myeloma.
**Summary and Recommendations:**
Mr. John Williams is a 63-year-old male with a complex medical history
involving multiple organ systems. His most recent admission was in
relation to his multiple myeloma, for which he has been in remission and
will be monitored closely. His mitral valve endocarditis from earlier
this year has been resolved and treated appropriately. Due to the
multiple comorbidities, it is crucial for any treating facility or
physician to be fully aware of his history to provide optimal care.
Continual monitoring of his cardiovascular and renal systems is
essential. The importance of maintaining strict adherence to his
dialysis regimen and potential antibiotic prophylaxis is emphasized.
Given his weakened general condition and chronic pain, palliative care
might also be a suitable approach to consider, focusing on enhancing his
quality of life and addressing his pain management needs.
Please refer to the attached files for further details and a complete
breakdown of tests and findings. I trust this report will help guide the
appropriate medical care for Mr. John Williams.
Sincerely,
**Medication:**
**Medication** **Dosage** **Frequency**
----------------------------------------- -------------------- -----------------------------------------------------------------
Clopidogrel (Plavix) 75 mg Morning
Enoxaparin (Lovenox) 0.2 mL s.c. Evening, only on days when not receiving dialysis
Dronabinol (Marinol) Drops 3 drops Morning and Evening
Leuprorelin (Lupron Depot) Monthly depot Every 4 weeks via subcutaneous injection
Fentanyl Transdermal System 12 μg/hour Changed every 3 days
Pantoprazole (Protonix) 40 mg Morning
Sevelamer (Renagel) 800 mg Morning
Multivitamin One tablet Morning
Torsemide (Torem) 200 mg Morning
Vitamin D3 20,000 IU Once weekly
Sodium bicarbonate (Bicanorm) One tablet Morning
Calcitriol (Rocaltrol) 0.25 μg Morning
Valacyclovir (Valtrex) 500 mg half-tablet Morning
Trimethoprim/Sulfamethoxazole (Bactrim) 480 mg Morning on Mondays, Wednesdays, and Fridays
Dexamethasone (Decadron) 4 mg Morning on day 1 and day 2 following daratumumab administration
### Patient Report 9
**Dear colleague, **
I am writing to provide an update on the medical condition and treatment
of Mr. John Williams, who has been undergoing inpatient treatment in our
facility since September 30, 2021.
**Diagnoses**:
**Present**: Acute impairment of the visual field.
**Oncological Diagnosis**:
1. Diagnosis of Multiple Myeloma with kappa light chains, staged at
IIIB as per the Salmon and Durie criteria
Observable multiple osteolyses.
History of radiation to the T4 and thoracic rib.
Starting from 2018, he required dialysis due to renal insufficiency,
scheduled on Mondays, Wednesdays, and Fridays in our local clinic.
2018: Treatment involved Bortezomib and Dexamethasone, but he was
refractory to this combination. The regimen of Carfilzomib,
Lenalidomide, and Dexamethasone was also found to be ineffective.
Radiation was administered to the T4 (totaling 30 Gy) and the
thoracic rib (totaling 20 Gy) in August 2018.
Between August and October 2018: Mr. Williams underwent three cycles
of Pomalidomide, Doxorubicin, and Dexamethasone, but the disease
showed progression.
November 2018 to February 2019: He received four treatments of
Daratumumab, Lenalidomide, and Dexamethasone, which led to a very
good partial response (VGPR).
In March 2019, he underwent stem cell mobilization due to RSV
pneumonia complications and then started on Daratumumab monotherapy
(VGPR was last noted in May 2018).
He continued with Daratumumab treatment until November 2019, after
which there was a pause until March 2020 due to remission (VGPR) and
a diagnosis of endocarditis.
A whole body CT scan conducted in March 2020 did not show any new
osteolyses.
By May 2020, there was an increase in LK values, prompting the
resumption of Daratumumab, which led to a decrease in free light
chains.
As of June 2020, there was a noted increase in light chain kappa
values to 102 mg/L.
In July 2020, therapy was escalated to include Daratumumab, Revlimid
(5 mg), and Dexamethasone.
By September 2020, a further increase in light chains was observed,
prompting a planned switch to Elotuzumab, Pomalidomide, and
Dexamethasone.
**For his heart condition:**
Acute mitral valve endocarditis was diagnosed in March 2020. He
underwent a re-operation for mitral valve replacement with a
bioprosthesis (29 mm). This procedure, performed in March, 2020,
involved the resection of all infected tissue from the mitral valve\'s
holding apparatus. The cause is presumed to be associated with a Demers
catheter infection or possibly related to a port catheter infection
(Staphylococcus epidermidis was found). The catheter was surgically
removed in March 2020. He was on a series of antibiotics, including
Meropenem, Linezolid, Daptomycin, and Fosfomycin.
**Other pertinent medical events include:**
A history of radiation treatment using a minithoracotomy technique for
mitral valve reconstruction in 2015.
Right eye amaurosis due to septic-embolic central retinal artery
occlusion.
Left hemispheric ischemia diagnosed in April 2020, possibly due to
emboli from the mitral valve endocarditis.
A transient ischemic attack (TIA) in the brainstem observed on in March
2020, which could be related to emboli from the mitral valve
endocarditis.
Jugular vein thrombosis.
Prostate cancer diagnosed in 2018.
Chronic renal failure necessitating dialysis since 2018.
Previous procedures include Demers catheter placement (removed on March
2020) and angioplasty on the right basilic vein and brachial vein due to
stenosis causing shunt dysfunction.
History of transient ischemic attacks.
Bilateral tingling paresthesias in the lower legs, history of deep vein
thrombosis, recurrent calf cramps, and hypothyroidism.
Please let me know if you require any further information on Mr.
Williams. I am confident that this detailed account will assist you in
understanding his medical history and ensuring optimal care.
**Therapy: **
Therapy schedule: Daratumumab s.c. 1800mg abs. weekly in week 1-8,
2-weekly in week 9-24, every 4 weeks from week 25. Continuation of
Bondronat. Regular monitoring and optimal adjustment of cardiovascular
risk factors.
Medication:
Plavix (Clopidogrel) 75 mg; once daily in the morning
Lovenox (Enoxaparin) 0.2 ml subcutaneously; once daily in the evening on
non-dialysis days
Marinol (Dronabinol) drops; four drops in the morning and four drops in
the evening
Duragesic (Fentanyl transdermal patch) 12 μg/hour; change every 3 days
Protonix (Pantoprazole) 40 mg; dosing: Once daily in the morning and
once daily in the evening for 2 weeks, then once daily in the morning
Renvela 800 mg; dosing: Once daily in the morning
Torem 200 mg; once daily in the morning
Vitamin D3 20,000 IU; once weekly
Calcijex (Calcitriol) 0.25 mcg; once daily in the morning
Valtrex (Valacyclovir) 500 mg; dosing: Half a tablet (250 mg) once daily
in the morning
Bactrim (Cotrimoxazole or trimethoprim/sulfamethoxazole) 480 mg, once
daily
Warm regards,
**Clinical Update, 11/12/2022**
Mr. John Williams, a 66-year-old male with a known history of multiple
myeloma and associated complications, presented again to our facility
with worsening symptoms over the past three weeks.
**Symptoms**:
Persistent fatigue
Shortness of breath on minimal exertion
Bilateral pitting edema in the lower extremities up to the mid-calf
**Preliminary Findings**:
**Physical Examination**:
1. Jugular venous distention
Decreased breath sounds bilaterally with mild basilar crackles
S3 gallop on cardiac auscultation
**Chest X-ray**:
4. Cardiomegaly with an enlarged cardiac silhouette. Mild pulmonary
edema evident.
**Echocardiogram**:
5. Reduced left ventricular ejection fraction (LVEF) of 35% (normal \>
55%)
Mild mitral regurgitation
**Lab Results**:
7. B-type natriuretic peptide (BNP): 890 pg/mL (Normal: \<100 pg/mL)
Serum Sodium: 130 mEq/L (Normal: 135-145 mEq/L)
Serum Potassium: 5.8 mEq/L (Normal: 3.5-5.1 mEq/L)
Blood Urea Nitrogen (BUN): 38 mg/dL (Normal: 7-20 mg/dL)
Creatinine: 2.1 mg/dL (Normal: 0.8-1.3 mg/dL)
GFR: 35 mL/min (Reduced)
**Diagnosis**:
Congestive Heart Failure (CHF) with reduced ejection fraction
Renal insufficiency
Multiple Myeloma (primary diagnosis 2015)
Prostate cancer
**Treatment Administered**:
Intravenous furosemide was administered to relieve fluid overload,
resulting in a significant reduction in edema and improvement in
breathlessness over the subsequent 48 hours. Lisinopril was initiated
cautiously to manage CHF and to potentially provide renal protection.
Metoprolol was started at a low dose, with close monitoring of blood
pressure and heart rate. Potassium levels were closely monitored given
initial hyperkalemia; diet and medications were adjusted accordingly.
Dietary consult emphasized a low-sodium, moderate protein, and
potassium-restricted diet. Close monitoring of fluid balance
(input-output) was maintained throughout the stay.
**Progress**:
Mr. Williams showed consistent improvement over his two-week admission.
Serial echocardiograms indicated a slight improvement in LVEF to 39%.
The edema receded notably, and his shortness of breath on exertion
reduced significantly. Labs before discharge showed:
Serum Sodium: 134 mEq/L
Serum Potassium: 4.9 mEq/L
BUN: 32 mg/dL
Creatinine: 1.9 mg/dL
BNP: 550 pg/mL
**Discharge Recommendations**:
Outpatient cardiology follow-up in two weeks and then monthly to monitor
LVEF and adjust medications. Nephrology consultation to keep an eye on
renal function, given his increased susceptibility to kidney damage.
Continue with dietary restrictions and modifications as advised.
Commence an outpatient cardiac rehabilitation program for supervised
exercise and lifestyle modifications. Weekly blood tests for the first
month to monitor electrolytes and kidney function.
Mr. Williams remains at risk due to multiple comorbidities. It is
essential to address each condition holistically while ensuring no
single treatment exacerbates another condition. A collaborative and
vigilant approach is imperative for his ongoing health management.
Warm regards,
--------------------------- ---------------- ---------------------
**Parameter** **Value** **Reference Range**
**Blood Count**
White Blood Cells (WBC) 5.8 x 10^9^/L 4-11 x 10^9^/L
Red Blood Cells (RBC) 3.9 x 10^12^/L 4.5-5.5 x 10^12^/L
Hemoglobin (Hb) 9.8 g/dL 13-18 g/dL for men
Platelets (Plt) 150 x 10^9^/L 150-450 x 10^9^/L
**Biochemistry**
Creatinine 2.8 mg/dL 0.6-1.3 mg/dL
Blood Urea Nitrogen (BUN) 40 mg/dL 7-20 mg/dL
Glucose 98 mg/dL 70-100 mg/dL
**Electrolytes**
Sodium (Na) 137 mEq/L 135-145 mEq/L
Potassium (K) 5.1 mEq/L 3.5-5.0 mEq/L
Calcium 8.6 mg/dL 8.5-10.5 mg/dL
Phosphate 4.5 mg/dL 2.5-4.5 mg/dL
**Oncologic Markers**
Free light chain kappa 692 mg/L 3.3-19.4 mg/L
Free light chain lambda 12 mg/L 5.7-26.3 mg/L
**Other Values**
LDL cholesterol 80 mg/dL \<100 mg/dL
HbA1c 6.2% \<5.7%
--------------------------- ---------------- ---------------------
|
Amlodipin 5 mg was paused.
|
What is significant about the riot?
A. There are so few people involved, but because of the laws against interreacting with other specializations it's a huge issue.
B. It was so easily pulled off. It didn't take a lot of effort for it to be successful.
C. It's making nation wide news.
D. There are a lot of prisoners involved, and they needed to call upon a lot of departments to address it.
|
My Lady Greensleeves By FREDERIK POHL Illustrated by GAUGHAN [Transcriber's Note: This etext was produced from Galaxy Science Fiction February 1957. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] This guard smelled trouble and it could be counted on to come—for a nose for trouble was one of the many talents bred here! I His name was Liam O'Leary and there was something stinking in his nostrils. It was the smell of trouble. He hadn't found what the trouble was yet, but he would. That was his business. He was a captain of guards in Estates-General Correctional Institution—better known to its inmates as the Jug—and if he hadn't been able to detect the scent of trouble brewing a cell-block away, he would never have survived to reach his captaincy. And her name, he saw, was Sue-Ann Bradley, Detainee No. WFA-656R. He frowned at the rap sheet, trying to figure out what got a girl like her into a place like this. And, what was more important, why she couldn't adjust herself to it, now that she was in. He demanded: "Why wouldn't you mop out your cell?" The girl lifted her head angrily and took a step forward. The block guard, Sodaro, growled warningly: "Watch it, auntie!" O'Leary shook his head. "Let her talk, Sodaro." It said in the Civil Service Guide to Prison Administration : "Detainees will be permitted to speak in their own behalf in disciplinary proceedings." And O'Leary was a man who lived by the book. She burst out: "I never got a chance! That old witch Mathias never told me I was supposed to mop up. She banged on the door and said, 'Slush up, sister!' And then, ten minutes later, she called the guards and told them I refused to mop." The block guard guffawed. "Wipe talk—that's what she was telling you to do. Cap'n, you know what's funny about this? This Bradley is—" "Shut up, Sodaro." Captain O'leary put down his pencil and looked at the girl. She was attractive and young—not beyond hope, surely. Maybe she had got off to a wrong start, but the question was, would putting her in the disciplinary block help straighten her out? He rubbed his ear and looked past her at the line of prisoners on the rap detail, waiting for him to judge their cases. He said patiently: "Bradley, the rules are you have to mop out your cell. If you didn't understand what Mathias was talking about, you should have asked her. Now I'm warning you, the next time—" "Hey, Cap'n, wait!" Sodaro was looking alarmed. "This isn't a first offense. Look at the rap sheet. Yesterday she pulled the same thing in the mess hall." He shook his head reprovingly at the prisoner. "The block guard had to break up a fight between her and another wench, and she claimed the same business—said she didn't understand when the other one asked her to move along." He added virtuously: "The guard warned her then that next time she'd get the Greensleeves for sure." Inmate Bradley seemed to be on the verge of tears. She said tautly: "I don't care. I don't care!" O'Leary stopped her. "That's enough! Three days in Block O!" It was the only thing to do—for her own sake as much as for his. He had managed, by strength of will, not to hear that she had omitted to say "sir" every time she spoke to him, but he couldn't keep it up forever and he certainly couldn't overlook hysteria. And hysteria was clearly the next step for her. All the same, he stared after her as she left. He handed the rap sheet to Sodaro and said absently: "Too bad a kid like her has to be here. What's she in for?" "You didn't know, Cap'n?" Sodaro leered. "She's in for conspiracy to violate the Categoried Class laws. Don't waste your time with her, Cap'n. She's a figger-lover!" Captain O'Leary took a long drink of water from the fountain marked "Civil Service." But it didn't wash the taste out of his mouth, the smell from his nose. What got into a girl to get her mixed up with that kind of dirty business? He checked out of the cell blocks and walked across the yard, wondering about her. She'd had every advantage—decent Civil Service parents, a good education, everything a girl could wish for. If anything, she had had a better environment than O'Leary himself, and look what she had made of it. The direction of evolution is toward specialization and Man is no exception, but with the difference that his is the one species that creates its own environment in which to specialize. From the moment that clans formed, specialization began—the hunters using the weapons made by the flint-chippers, the food cooked in clay pots made by the ceramists, over fire made by the shaman who guarded the sacred flame. Civilization merely increased the extent of specialization. From the born mechanic and the man with the gift of gab, society evolved to the point of smaller contact and less communication between the specializations, until now they could understand each other on only the most basic physical necessities—and not even always then. But this was desirable, for the more specialists, the higher the degree of civilization. The ultimate should be the complete segregation of each specialization—social and genetic measures to make them breed true, because the unspecialized man is an uncivilized man, or at any rate he does not advance civilization. And letting the specializations mix would produce genetic undesirables: clerk-laborer or Professional-GI misfits, for example, being only half specialized, would be good at no specialization. And the basis of this specialization society was: "The aptitude groups are the true races of mankind." Putting it into law was only the legal enforcement of a demonstrable fact. "Evening, Cap'n." A bleary old inmate orderly stood up straight and touched his cap as O'Leary passed by. "Evening." O'Leary noted, with the part of his mind that always noted those things, that the orderly had been leaning on his broom until he'd noticed the captain coming by. Of course, there wasn't much to sweep—the spray machines and sweeperdozers had been over the cobblestones of the yard twice already that day. But it was an inmate's job to keep busy. And it was a guard captain's job to notice when they didn't. There wasn't anything wrong with that job, he told himself. It was a perfectly good civil-service position—better than post-office clerk, not as good as Congressman, but a job you could be proud to hold. He was proud of it. It was right that he should be proud of it. He was civil-service born and bred, and naturally he was proud and content to do a good, clean civil-service job. If he had happened to be born a fig—a clerk , he corrected himself—if he had happened to be born a clerk, why, he would have been proud of that, too. There wasn't anything wrong with being a clerk—or a mechanic or a soldier, or even a laborer, for that matter. Good laborers were the salt of the Earth! They weren't smart, maybe, but they had a—well, a sort of natural, relaxed joy of living. O'Leary was a broad-minded man and many times he had thought almost with a touch of envy how comfortable it must be to be a wipe—a laborer . No responsibilities. No worries. Just an easy, slow routine of work and loaf, work and loaf. Of course, he wouldn't really want that kind of life, because he was Civil Service and not the kind to try to cross over class barriers that weren't meant to be— "Evening, Cap'n." He nodded to the mechanic inmate who was, theoretically, in charge of maintaining the prison's car pool, just inside the gate. "Evening, Conan," he said. Conan, now—he was a big buck greaser and he would be there for the next hour, languidly poking a piece of fluff out of the air filter on the prison jeep. Lazy, sure. Undependable, certainly. But he kept the cars going—and, O'Leary thought approvingly, when his sentence was up in another year or so, he would go back to his life with his status restored, a mechanic on the outside as he had been inside, and he certainly would never risk coming back to the Jug by trying to pass as Civil Service or anything else. He knew his place. So why didn't this girl, this Sue-Ann Bradley, know hers? II Every prison has its Greensleeves—sometimes they are called by different names. Old Marquette called it "the canary;" Louisiana State called it "the red hats;" elsewhere it was called "the hole," "the snake pit," "the Klondike." When you're in it, you don't much care what it is called; it is a place for punishment. And punishment is what you get. Block O in Estates-General Correctional Institution was the disciplinary block, and because of the green straitjackets its inhabitants wore, it was called the Greensleeves. It was a community of its own, an enclave within the larger city-state that was the Jug. And like any other community, it had its leading citizens ... two of them. Their names were Sauer and Flock. Sue-Ann Bradley heard them before she reached the Greensleeves. She was in a detachment of three unfortunates like herself, convoyed by an irritable guard, climbing the steel steps toward Block O from the floor below, when she heard the yelling. "Owoo-o-o," screamed Sauer from one end of the cell block and "Yow-w-w!" shrieked Flock at the other. The inside deck guard of Block O looked nervously at the outside deck guard. The outside guard looked impassively back—after all, he was on the outside. The inside guard muttered: "Wipe rats! They're getting on my nerves." The outside guard shrugged. "Detail, halt !" The two guards turned to see what was coming in as the three new candidates for the Greensleeves slumped to a stop at the head of the stairs. "Here they are," Sodaro told them. "Take good care of 'em, will you? Especially the lady—she's going to like it here, because there's plenty of wipes and greasers and figgers to keep her company." He laughed coarsely and abandoned his charges to the Block O guards. The outside guard said sourly: "A woman, for God's sake. Now O'Leary knows I hate it when there's a woman in here. It gets the others all riled up." "Let them in," the inside guard told him. "The others are riled up already." Sue-Ann Bradley looked carefully at the floor and paid them no attention. The outside guard pulled the switch that turned on the tanglefoot electronic fields that swamped the floor of the block corridor and of each individual cell. While the fields were on, you could ignore the prisoners—they simply could not move fast enough, against the electronic drag of the field, to do any harm. But it was a rule that, even in Block O, you didn't leave the tangler fields on all the time—only when the cell doors had to be opened or a prisoner's restraining garment removed. Sue-Ann walked bravely forward through the opened gate—and fell flat on her face. It was her first experience of a tanglefoot field. It was like walking through molasses. The guard guffawed and lifted her up by one shoulder. "Take it easy, auntie. Come on, get in your cell." He steered her in the right direction and pointed to a greensleeved straitjacket on the cell cot. "Put that on. Being as you're a lady, we won't tie it up, but the rules say you got to wear it and the rules—Hey. She's crying!" He shook his head, marveling. It was the first time he had ever seen a prisoner cry in the Greensleeves. However, he was wrong. Sue-Ann's shoulders were shaking, but not from tears. Sue-Ann Bradley had got a good look at Sauer and at Flock as she passed them by and she was fighting off an almost uncontrollable urge to retch. Sauer and Flock were what are called prison wolves. They were laborers—"wipes," for short—or, at any rate, they had been once. They had spent so much time in prisons that it was sometimes hard even for them to remember what they really were, outside. Sauer was a big, grinning redhead with eyes like a water moccasin. Flock was a lithe five-footer with the build of a water moccasin—and the sad, stupid eyes of a calf. Sauer stopped yelling for a moment. "Hey, Flock!" "What do you want, Sauer?" called Flock from his own cell. "We got a lady with us! Maybe we ought to cut out this yelling so as not to disturb the lady!" He screeched with howling, maniacal laughter. "Anyway, if we don't cut this out, they'll get us in trouble, Flock!" "Oh, you think so?" shrieked Flock. "Jeez, I wish you hadn't said that, Sauer. You got me scared! I'm so scared, I'm gonna have to yell!" The howling started all over again. The inside guard finished putting the new prisoners away and turned off the tangler field once more. He licked his lips. "Say, you want to take a turn in here for a while?" "Uh-uh." The outside guard shook his head. "You're yellow," the inside guard said moodily. "Ah, I don't know why I don't quit this lousy job. Hey, you! Pipe down or I'll come in and beat your head off!" "Ee-ee-ee!" screamed Sauer in a shrill falsetto. "I'm scared!" Then he grinned at the guard, all but his water-moccasin eyes. "Don't you know you can't hurt a wipe by hitting him on the head, Boss?" "Shut up !" yelled the inside guard. Sue-Ann Bradley's weeping now was genuine. She simply could not help it. The crazy yowling of the hard-timers, Sauer and Flock, was getting under her skin. They weren't even—even human , she told herself miserably, trying to weep silently so as not to give the guards the satisfaction of hearing her—they were animals! Resentment and anger, she could understand. She told herself doggedly that resentment and anger were natural and right. They were perfectly normal expressions of the freedom-loving citizen's rebellion against the vile and stifling system of Categoried Classes. It was good that Sauer and Flock still had enough spirit to struggle against the vicious system— But did they have to scream so? The senseless yelling was driving her crazy. She abandoned herself to weeping and she didn't even care who heard her any more. Senseless! It never occurred to Sue-Ann Bradley that it might not be senseless, because noise hides noise. But then she hadn't been a prisoner very long. III "I smell trouble," said O'Leary to the warden. "Trouble? Trouble?" Warden Schluckebier clutched his throat and his little round eyes looked terrified—as perhaps they should have. Warden Godfrey Schluckebier was the almighty Caesar of ten thousand inmates in the Jug, but privately he was a fussy old man trying to hold onto the last decent job he would have in his life. "Trouble? What trouble?" O'Leary shrugged. "Different things. You know Lafon, from Block A? This afternoon, he was playing ball with the laundry orderlies in the yard." The warden, faintly relieved, faintly annoyed, scolded: "O'Leary, what did you want to worry me for? There's nothing wrong with playing ball in the yard. That's what recreation periods are for." "You don't see what I mean, Warden. Lafon was a professional on the outside—an architect. Those laundry cons were laborers. Pros and wipes don't mix; it isn't natural. And there are other things." O'Leary hesitated, frowning. How could you explain to the warden that it didn't smell right? "For instance—Well, there's Aunt Mathias in the women's block. She's a pretty good old girl—that's why she's the block orderly. She's a lifer, she's got no place to go, she gets along with the other women. But today she put a woman named Bradley on report. Why? Because she told Bradley to mop up in wipe talk and Bradley didn't understand. Now Mathias wouldn't—" The warden raised his hand. "Please, O'Leary, don't bother me about that kind of stuff." He sighed heavily and rubbed his eyes. He poured himself a cup of steaming black coffee from a brewpot, reached in a desk drawer for something, hesitated, glanced at O'Leary, then dropped a pale blue tablet into the cup. He drank it down eagerly, ignoring the scalding heat. He leaned back, looking suddenly happier and much more assured. "O'Leary, you're a guard captain, right? And I'm your warden. You have your job, keeping the inmates in line, and I have mine. Now your job is just as important as my job," he said piously. " Everybody's job is just as important as everybody else's, right? But we have to stick to our own jobs. We don't want to try to pass ." O'Leary snapped erect, abruptly angry. Pass! What the devil way was that for the warden to talk to him? "Excuse the expression, O'Leary," the warden said anxiously. "I mean, after all, 'Specialization is the goal of civilization,' right?" He was a great man for platitudes, was Warden Schluckebier. " You know you don't want to worry about my end of running the prison. And I don't want to worry about yours . You see?" And he folded his hands and smiled like a civil-service Buddha. O'Leary choked back his temper. "Warden, I'm telling you that there's trouble coming up. I smell the signs." "Handle it, then!" snapped the warden, irritated at last. "But suppose it's too big to handle. Suppose—" "It isn't," the warden said positively. "Don't borrow trouble with all your supposing, O'Leary." He sipped the remains of his coffee, made a wry face, poured a fresh cup and, with an elaborate show of not noticing what he was doing, dropped three of the pale blue tablets into it this time. He sat beaming into space, waiting for the jolt to take effect. "Well, then," he said at last. "You just remember what I've told you tonight, O'Leary, and we'll get along fine. 'Specialization is the—' Oh, curse the thing." His phone was ringing. The warden picked it up irritably. That was the trouble with those pale blue tablets, thought O'Leary; they gave you a lift, but they put you on edge. "Hello," barked the warden, not even glancing at the viewscreen. "What the devil do you want? Don't you know I'm—What? You did what ? You're going to WHAT?" He looked at the viewscreen at last with a look of pure horror. Whatever he saw on it, it did not reassure him. His eyes opened like clamshells in a steamer. "O'Leary," he said faintly, "my mistake." And he hung up—more or less by accident; the handset dropped from his fingers. The person on the other end of the phone was calling from Cell Block O. Five minutes before, he hadn't been anywhere near the phone and it didn't look as if his chances of ever getting near it were very good. Because five minutes before, he was in his cell, with the rest of the hard-timers of the Greensleeves. His name was Flock. He was still yelling. Sue-Ann Bradley, in the cell across from him, thought that maybe, after all, the man was really in pain. Maybe the crazy screams were screams of agony, because certainly his face was the face of an agonized man. The outside guard bellowed: "Okay, okay. Take ten!" Sue-Ann froze, waiting to see what would happen. What actually did happen was that the guard reached up and closed the switch that actuated the tangler fields on the floors of the cells. The prison rules were humanitarian, even for the dregs that inhabited the Greensleeves. Ten minutes out of every two hours, even the worst case had to be allowed to take his hands out of the restraining garment. "Rest period" it was called—in the rule book. The inmates had a less lovely term for it. At the guard's yell, the inmates jumped to their feet. Bradley was a little slow getting off the edge of the steel-slat bed—nobody had warned her that the eddy currents in the tangler fields had a way of making metal smoke-hot. She gasped but didn't cry out. Score one more painful lesson in her new language course. She rubbed the backs of her thighs gingerly—and slowly, slowly, for the eddy currents did not permit you to move fast. It was like pushing against rubber; the faster you tried to move, the greater the resistance. The guard peered genially into her cell. "You're okay, auntie." She proudly ignored him as he slogged deliberately away on his rounds. He didn't have to untie her and practically stand over her while she attended to various personal matters, as he did with the male prisoners. It was not much to be grateful for, but Sue-Ann Bradley was grateful. At least she didn't have to live quite like a fig—like an underprivileged clerk, she told herself, conscience-stricken. Across the hall, the guard was saying irritably: "What the hell's the matter with you?" He opened the door of the cell with an asbestos-handled key held in a canvas glove. Flock was in that cell and he was doubled over. The guard looked at him doubtfully. It could be a trick, maybe. Couldn't it? But he could see Flock's face and the agony in it was real enough. And Flock was gasping, through real tears: "Cramps. I—I—" "Ah, you wipes always got a pain in the gut." The guard lumbered around Flock to the draw-strings at the back of the jacket. Funny smell in here, he told himself—not for the first time. And imagine, some people didn't believe that wipes had a smell of their own! But this time, he realized cloudily, it was a rather unusual smell. Something burning. Almost like meat scorching. It wasn't pleasant. He finished untying Flock and turned away; let the stinking wipe take care of his own troubles. He only had ten minutes to get all the way around Block O and the inmates complained like crazy if he didn't make sure they all got the most possible free time. He was pretty good at snowshoeing through the tangler field. He was a little vain about it, even; at times he had been known to boast of his ability to make the rounds in two minutes, every time. Every time but this. For Flock moaned behind him, oddly close. The guard turned, but not quickly enough. There was Flock—astonishingly, he was half out of his jacket; his arms hadn't been in the sleeves at all! And in one of the hands, incredibly, there was something that glinted and smoked. "All right," croaked Flock, tears trickling out of eyes nearly shut with pain. But it wasn't the tears that held the guard; it was the shining, smoking thing, now poised at his throat. A shiv! It looked as though it had been made out of a bed-spring, ripped loose from its frame God knows how, hidden inside the greensleeved jacket God knows how—filed, filed to sharpness over endless hours. No wonder Flock moaned—the eddy currents in the shiv were slowly cooking his hand; and the blister against his abdomen, where the shiv had been hidden during other rest periods, felt like raw acid. "All right," whispered Flock, "just walk out the door and you won't get hurt. Unless the other screw makes trouble, you won't get hurt, so tell him not to, you hear?" He was nearly fainting with the pain. But he hadn't let go. He didn't let go. And he didn't stop. IV It was Flock on the phone to the warden—Flock with his eyes still streaming tears, Flock with Sauer standing right behind him, menacing the two bound deck guards. Sauer shoved Flock out of the way. "Hey, Warden!" he said, and the voice was a cheerful bray, though the serpent eyes were cold and hating. "Warden, you got to get a medic in here. My boy Flock, he hurt himself real bad and he needs a doctor." He gestured playfully at the guards with the shiv. "I tell you, Warden. I got this knife and I got your guards here. Enough said? So get a medic in here quick, you hear?" And he snapped the connection. O'Leary said: "Warden, I told you I smelled trouble!" The warden lifted his head, glared, started feebly to speak, hesitated, and picked up the long-distance phone. He said sadly to the prison operator: "Get me the governor—fast." Riot! The word spread out from the prison on seven-league boots. It snatched the city governor out of a friendly game of Seniority with his manager and their wives—and just when he was holding the Porkbarrel Joker concealed in the hole. It broke up the Base Championship Scramble Finals at Hap Arnold Field to the south, as half the contestants had to scramble in earnest to a Red Alert that was real. It reached to police precinct houses and TV newsrooms and highway checkpoints, and from there it filtered into the homes and lives of the nineteen million persons that lived within a few dozen miles of the Jug. Riot. And yet fewer than half a dozen men were involved. A handful of men, and the enormous bulk of the city-state quivered in every limb and class. In its ten million homes, in its hundreds of thousands of public places, the city-state's people shook under the impact of the news from the prison. For the news touched them where their fears lay. Riot! And not merely a street brawl among roistering wipes, or a bar-room fight of greasers relaxing from a hard day at the plant. The riot was down among the corrupt sludge that underlay the state itself. Wipes brawled with wipes and no one cared; but in the Jug, all classes were cast together. Forty miles to the south, Hap Arnold Field was a blaze of light. The airmen tumbled out of their quarters and dayrooms at the screech of the alert siren, and behind them their wives and children stretched and yawned and worried. An alert! The older kids fussed and complained and their mothers shut them up. No, there wasn't any alert scheduled for tonight; no, they didn't know where Daddy was going; no, the kids couldn't get up yet—it was the middle of the night. And as soon as they had the kids back in bed, most of the mothers struggled into their own airwac uniforms and headed for the briefing area to hear. They caught the words from a distance—not quite correctly. "Riot!" gasped an aircraftswoman first-class, mother of three. "The wipes! I told Charlie they'd get out of hand and—Alys, we aren't safe. You know how they are about GI women! I'm going right home and get a club and stand right by the door and—" "Club!" snapped Alys, radarscope-sergeant, with two children querulously awake in her nursery at home. "What in God's name is the use of a club? You can't hurt a wipe by hitting him on the head. You'd better come along to Supply with me and draw a gun—you'll need it before this night is over." But the airmen themselves heard the briefing loud and clear over the scramble-call speakers, and they knew it was not merely a matter of trouble in the wipe quarters. The Jug! The governor himself had called them out; they were to fly interdicting missions at such-and-such levels on such-and-such flight circuits around the prison. The rockets took off on fountains of fire; and the jets took off with a whistling roar; and last of all, the helicopters took off ... and they were the ones who might actually accomplish something. They took up their picket posts on the prison perimeter, a pilot and two bombardiers in each 'copter, stone-faced, staring grimly alert at the prison below. They were ready for the breakout. But there wasn't any breakout. The rockets went home for fuel. The jets went home for fuel. The helicopters hung on—still ready, still waiting. The rockets came back and roared harmlessly about, and went away again. They stayed away. The helicopter men never faltered and never relaxed. The prison below them was washed with light—from the guard posts on the walls, from the cell blocks themselves, from the mobile lights of the guard squadrons surrounding the walls. North of the prison, on the long, flat, damp developments of reclaimed land, the matchbox row houses of the clerical neighborhoods showed lights in every window as the figgers stood ready to repel invasion from their undesired neighbors to the east, the wipes. In the crowded tenements of the laborers' quarters, the wipes shouted from window to window; and there were crowds in the bright streets. "The whole bloody thing's going to blow up!" a helicopter bombardier yelled bitterly to his pilot, above the flutter and roar of the whirling blades. "Look at the mobs in Greaserville! The first breakout from the Jug's going to start a fight like you never saw and we'll be right in the middle of it!" He was partly right. He would be right in the middle of it—for every man, woman and child in the city-state would be right in the middle of it. There was no place anywhere that would be spared. No mixing. That was the prescription that kept the city-state alive. There's no harm in a family fight—and aren't all mechanics a family, aren't all laborers a clan, aren't all clerks and office workers related by closer ties than blood or skin? But the declassed cons of the Jug were the dregs of every class; and once they spread, the neat compartmentation of society was pierced. The breakout would mean riot on a bigger scale than any prison had ever known. But he was also partly wrong. Because the breakout wasn't seeming to come.
|
A. There are so few people involved, but because of the laws against interreacting with other specializations it's a huge issue.
|
How do they combine the two proposed neural network models?
|
### Introduction
Grammatical error correction (GEC) is a challenging task due to the variability of the type of errors and the syntactic and semantic dependencies of the errors on the surrounding context. Most of the grammatical error correction systems use classification and rule-based approaches for correcting specific error types. However, these systems use several linguistic cues as features. The standard linguistic analysis tools like part-of-speech (POS) taggers and parsers are often trained on well-formed text and perform poorly on ungrammatical text. This introduces further errors and limits the performance of rule-based and classification approaches to GEC. As a consequence, the phrase-based statistical machine translation (SMT) approach to GEC has gained popularity because of its ability to learn text transformations from erroneous text to correct text from error-corrected parallel corpora without any additional linguistic information. They are also not limited to specific error types. Currently, many state-of-the-art GEC systems are based on SMT or use SMT components for error correction BIBREF0 , BIBREF1 , BIBREF2 . In this paper, grammatical error correction includes correcting errors of all types, including word choice errors and collocation errors which constitute a large class of learners' errors. We model our GEC system based on the phrase-based SMT approach. However, traditional phrase-based SMT systems treat words and phrases as discrete entities. We take advantage of continuous space representation by adding two neural network components that have been shown to improve SMT systems BIBREF3 , BIBREF4 . These neural networks are able to capture non-linear relationships between source and target sentences and can encode contextual information more effectively. Our experiments show that the addition of these two neural networks leads to significant improvements over a strong baseline and outperforms the current state of the art. ### Related Work
In the past decade, there has been increasing attention on grammatical error correction in English, mainly due to the growing number of English as Second Language (ESL) learners around the world. The popularity of this problem in natural language processing research grew further through Helping Our Own (HOO) and the CoNLL shared tasks BIBREF5 , BIBREF6 , BIBREF7 , BIBREF8 . Most published work in GEC aimed at building specific classifiers for different error types and then use them to build hybrid systems BIBREF9 , BIBREF10 . One of the first approaches of using SMT for GEC focused on correction of countability errors of mass nouns (e.g., many informations INLINEFORM0 much information) BIBREF11 . They had to use an artificially constructed parallel corpus for training their SMT system. Later, the availability of large-scale error corrected data BIBREF12 further improved SMT-based GEC systems. Recently, continuous space representations of words and phrases have been incorporated into SMT systems via neural networks. Specifically, addition of monolingual neural network language models BIBREF13 , BIBREF14 , neural network joint models (NNJM) BIBREF4 , and neural network global lexicon models (NNGLM) BIBREF3 have been shown to be useful for SMT. Neural networks have been previously used for GEC as a language model feature in the classification approach BIBREF15 and as a classifier for article error correction BIBREF16 . Recently, a neural machine translation approach has been proposed for GEC BIBREF17 . This method uses a recurrent neural network to perform sequence-to-sequence mapping from erroneous to well-formed sentences. Additionally, it relies on a post-processing step based on statistical word-based translation models to replace out-of-vocabulary words. In this paper, we investigate the effectiveness of two neural network models, NNGLM and NNJM, in SMT-based GEC. To the best of our knowledge, there is no prior work that uses these two neural network models for SMT-based GEC. ### A Machine Translation Framework for Grammatical Error Correction
In this paper, the task of grammatical error correction is formulated as a translation task from the language of `bad' English to the language of `good' English. That is, the source sentence is written by a second language learner and potentially contains grammatical errors, whereas the target sentence is the corrected fluent sentence. We use a phrase-based machine translation framework BIBREF18 for translation, which employs a log-linear model to find the best translation INLINEFORM0 given a source sentence INLINEFORM1 . The best translation is selected according to the following equation: INLINEFORM2 where INLINEFORM0 is the number of features, INLINEFORM1 and INLINEFORM2 are the INLINEFORM3 th feature function and feature weight, respectively. We make use of the standard features used in phrase-based translation without any reordering, leading to monotone translations. The features can be broadly categorized as translation model and language model features. The translation model in the phrase-based machine translation framework is trained using parallel data, i.e., sentence-aligned erroneous source text and corrected target text. The translation model is responsible for finding the best transformation of the source sentence to produce the corrected sentence. On the other hand, the language model is trained on well-formed English text and this ensures the fluency of the corrected text. To find the optimal feature weights ( INLINEFORM4 ), we use minimum error rate training (MERT), maximizing the INLINEFORM5 measure on the development set BIBREF2 . The INLINEFORM6 measure BIBREF19 , which weights precision twice as much as recall, is the evaluation metric widely used for GEC and was the official evaluation metric adopted in the CoNLL 2014 shared task BIBREF8 . Additionally, we augment the feature set by adding two neural network translation models, namely a neural network global lexicon model BIBREF3 and a neural network joint model BIBREF4 . These models are described in detail in Sections SECREF4 and SECREF5 . ### Neural Network Global Lexicon Model
A global lexicon model is used to predict the presence of words in the corrected output. The model estimates the overall probability of a target hypothesis (i.e., a candidate corrected sentence) given the source sentence, by making use of the probability computed for each word in the hypothesis. The individual word probabilities can be computed by training density estimation models such as maximum entropy BIBREF20 or probabilistic neural networks BIBREF3 . Following BIBREF3 , we formulate our global lexicon model using a feed-forward neural network. The model and the training algorithm are described below. ### Model
The probability of a target hypothesis is computed using the following equation: DISPLAYFORM0 where INLINEFORM0 and INLINEFORM1 are the source sentence and the target hypothesis respectively, and INLINEFORM2 denotes the number of words in the target hypothesis. INLINEFORM3 is the probability of the target word INLINEFORM4 given the source sentence INLINEFORM5 . INLINEFORM6 is the output of the neural network. The architecture of the neural network is shown in Figure FIGREF3 . INLINEFORM7 is calculated by: where INLINEFORM0 is the hidden layer output, and INLINEFORM1 and INLINEFORM2 are the output layer weights and biases respectively. INLINEFORM3 is the element-wise sigmoid function which scales the output to INLINEFORM4 . INLINEFORM0 is computed by the following equation: INLINEFORM1 where INLINEFORM0 is the activation function, and INLINEFORM1 and INLINEFORM2 are the hidden layer weights and biases applied on a binary bag-of-words representation of the input sentence denoted by INLINEFORM3 . The size of INLINEFORM4 is equal to the size of the source vocabulary INLINEFORM5 and each element indicates the presence or absence (denoted by 1 or 0 respectively) of a given source word. The probability of the target hypothesis INLINEFORM0 given the source sentence INLINEFORM1 is estimated by the following equation: DISPLAYFORM0 where INLINEFORM0 is the number of words in the target sentence, INLINEFORM1 is the INLINEFORM2 th target word, and INLINEFORM3 is the context (history) for the target word INLINEFORM4 . The context INLINEFORM5 consists of a set of INLINEFORM6 source words represented by INLINEFORM7 and INLINEFORM8 words preceding INLINEFORM9 from the target sentence represented by INLINEFORM10 . The context words from the source side are the words in the window of size INLINEFORM11 surrounding the source word INLINEFORM12 that is aligned to the target word INLINEFORM13 . The output of the neural network INLINEFORM14 is the output of the final softmax layer which is given by the following equation: DISPLAYFORM0 where INLINEFORM0 is the output of the neural network before applying softmax and INLINEFORM1 is given by following equation: INLINEFORM2 The output of the neural network before softmax is computed by applying output layer weights INLINEFORM0 and biases INLINEFORM1 to the hidden layer output INLINEFORM2 . INLINEFORM3 INLINEFORM0 is computed by applying weights INLINEFORM1 and biases INLINEFORM2 on the hidden layer input INLINEFORM3 and using a non-linear activation function INLINEFORM4 : INLINEFORM5 The input to the hidden layer ( INLINEFORM0 ) is a concatenated vector of context word embeddings: INLINEFORM1 where INLINEFORM0 and INLINEFORM1 are the one-hot representations of the source word INLINEFORM2 and the target word INLINEFORM3 , respectively. Similarly, INLINEFORM4 and INLINEFORM5 are the word embeddings matrices for the source words and the target words. As we use log probabilities instead of raw probabilities in our GEC system, Equation EQREF11 can be rewritten as the following: DISPLAYFORM0 Finally, since the network is trained by Noise Contrastive Estimation (NCE) (described in Section SECREF14 ), it becomes self-normalized. This means that INLINEFORM0 will be approximately 1 and hence the raw output of the neural network INLINEFORM1 can be directly used as the log probabilities during decoding. ### Training
The model is trained using mini-batch gradient descent with back-propagation. We use binary cross entropy (Equation EQREF5 ) as the cost function: DISPLAYFORM0 where INLINEFORM0 refers to the binary bag-of-words representation of the reference target sentence, and INLINEFORM1 is the target vocabulary. Each mini-batch is composed of a fixed number of sentence pairs INLINEFORM2 . The training algorithm repeatedly minimizes the cost function calculated for a given mini-batch by updating the parameters according to the gradients. To avoid the costly softmax layer and thereby speed up both training and decoding, we use Noise Contrastive Estimation (NCE) following BIBREF14 . During training, the negative log likelihood cost function is modified to a probabilistic binary classifier, which learns to discriminate between the actual target word and INLINEFORM0 random words (noisy samples) per training instance selected from a noise distribution INLINEFORM1 . The two classes are INLINEFORM2 indicating that the word is the target word and INLINEFORM3 indicating that the word is a noisy sample. The conditional probabilities for INLINEFORM4 and INLINEFORM5 given a target word and context is given by: INLINEFORM6 INLINEFORM7 where, INLINEFORM0 is the model probability given in Equation EQREF12 . The negative log likelihood cost function is replaced by the following function. INLINEFORM1 where INLINEFORM0 refers to the INLINEFORM1 th noise sample for the target word INLINEFORM2 . INLINEFORM3 is required for the computation of the neural network output, INLINEFORM4 . However, setting the term INLINEFORM5 to 1 during training forces the output of the neural network to be self-normalized. Hence, Equation EQREF13 reduces to: DISPLAYFORM0 Using Equation EQREF15 avoids the expensive softmax computation in the final layer and consequently speeds up decoding. ### Rescaling
Since the prior probability of observing a particular word in a sentence is usually a small number, the probabilistic output of NNGLM can be biased towards zero. This bias can hurt the performance of our system and therefore, we try to alleviate this problem by rescaling the output after training NNGLM. Our solution is to map the output probabilities to a new probability space by fitting a logistic function on the output. Formally, we use Equation EQREF7 as the mapping function: DISPLAYFORM0 where INLINEFORM0 is the rescaled probability and INLINEFORM1 and INLINEFORM2 are the parameters. For each sentence pair INLINEFORM3 in the development set, we collect training instances of the form INLINEFORM4 for every word INLINEFORM5 in the target vocabulary, where INLINEFORM6 and INLINEFORM7 . The value of INLINEFORM8 is set according to the presence ( INLINEFORM9 ) or absence ( INLINEFORM10 ) of the word INLINEFORM11 in the target sentence INLINEFORM12 . We use weighted cross entropy loss function with INLINEFORM13 -regularization to train INLINEFORM14 and INLINEFORM15 on the development set: INLINEFORM16 Here, INLINEFORM0 is the number of training samples, INLINEFORM1 is the probability of INLINEFORM2 computed by INLINEFORM3 , and INLINEFORM4 and INLINEFORM5 are the weights assigned to the two classes INLINEFORM6 and INLINEFORM7 , respectively. In order to balance the two classes, we weight each class inversely proportional to class frequencies in the training data (Equation EQREF8 ) to put more weight on the less frequent class: DISPLAYFORM0 In Equation EQREF8 , INLINEFORM0 and INLINEFORM1 are the number of samples in each class. After training the rescaling model, we use INLINEFORM2 and INLINEFORM3 to calculate INLINEFORM4 according to Equation EQREF7 . Finally, we use INLINEFORM5 instead of INLINEFORM6 in Equation EQREF2 . ### Neural Network Joint Model
Joint models in translation augment the context information in language models with words from the source sentence. A neural network joint model (NNJM) BIBREF4 uses a neural network to model the word probabilities given a context composed of source and target words. NNJM can scale up to large order of n-grams and still perform well because of its ability to capture semantic information through continuous space representations of words and to learn non-linear relationship between source and target words. Unlike the global lexicon model, NNJM uses a fixed window from the source side and take sequence information of words into consideration in order to estimate the probability of the target word. The model and the training method are described below. ### Experiments
We describe our experimental setup including the description of the data we used, the configuration of our baseline system and the neural network components, and the evaluation method in Section SECREF16 , followed by the results and discussion in Section SECREF23 ### Setup
We use the popular phrase-based machine translation toolkit Moses as our baseline SMT system. NUCLE BIBREF21 , which is the official training data for the CoNLL 2013 and 2014 shared tasks, is used as the parallel text for training. Additionally, we obtain parallel corpora from Lang-8 Corpus of Learner English v1.0 BIBREF12 , which consists of texts written by ESL (English as Second Language) learners on the language learning platform Lang-8. We use the test data for the CoNLL 2013 shared task as our development data. The statistics of the training and development data are given in Table TABREF19 . Source side refers to the original text written by the ESL learners and target side refers to the corresponding corrected text hand-corrected by humans. The source side and the target side are sentence-aligned and tokenized. We train the translation model for our SMT system using a concatenation of NUCLE and Lang-8 v1.0 parallel data. The training data is cleaned up by removing sentence pairs in which either the source or the target sentence is empty, or is too long (greater than 80 tokens), or violate a 9:1 sentence ratio limit. The translation model uses the default features in Moses which include the forward and inverse phrase translation probabilities, forward and inverse lexical weights, word penalty, and phrase penalty. We compute the phrase alignments using standard tools in Moses. We use two language model features: a 5-gram language model trained using the target side of NUCLE used for training the translation model and a 5-gram language model trained using English Wikipedia ( INLINEFORM0 1.78 billion tokens). Both language models are estimated with KenLM using modified Kneser-Ney smoothing. We use MERT for tuning the feature weights by optimizing the INLINEFORM1 measure (which weights precision twice as much as recall). This system constitutes our baseline system in Table TABREF24 . Our baseline system uses exactly the same training data as BIBREF0 for training the translation model and the language model. The difference between our baseline system and the SMT components of BIBREF0 is that we tune with INLINEFORM2 instead of BLEU and we use the standard Moses configuration without the Levenshtein distance feature. On top of our baseline system described above, we incorporate the two neural network components, neural network global lexicon model (NNGLM) and neural network joint model (NNJM) as features. Both NNGLM and NNJM are trained using the parallel data used to train the translation model of our baseline system. We implement NNGLM using the Theano library in Python in order to make use of parallelization with GPUs, thus speeding up training significantly. We use a source and target vocabulary of 10,000 most frequent words on both sides. We use a single hidden layer neural network with 2,000 hidden nodes. We use INLINEFORM0 as the activation function for the hidden layer. We optimize the model weights by stochastic gradient descent using a mini-batch size of 100 and a learning rate of 10. We train the model for 45 epochs. The logistic regression function for rescaling is trained using the probabilities obtained from this model on the development set. To speed up tuning and decoding, we pre-compute the probabilities of target words using the source side sentences of the development and the test sets, respectively. We implement a feature function in Moses to compute the probability of a target hypothesis given the source sentence using the pre-computed probabilities. To train NNJM, we use the publicly available implementation, Neural Probabilistic Language Model (NPLM) BIBREF14 . The latest version of Moses can incorporate NNJM trained using NPLM as a feature while decoding. Similar to NNGLM, we use the parallel text used for training the translation model in order to train NNJM. We use a source context window size of 5 and a target context window size of 4. We select a source context vocabulary of 16,000 most frequent words from the source side. The target context vocabulary and output vocabulary is set to the 32,000 most frequent words. We use a single hidden layer to speed up training and decoding with an input embedding dimension of 192 and 512 hidden layer nodes. We use rectified linear units (ReLU) as the activation function. We train NNJM with noise contrastive estimation with 100 noise samples per training instance, which are obtained from a unigram distribution. The neural network is trained for 30 epochs using stochastic gradient descent optimization with a mini-batch size of 128 and learning rate of 0.1. We conduct experiments by incorporating NNGLM and NNJM both independently and jointly into our baseline system. The results of our experiments are described in Section SECREF23 . The evaluation is performed similar to the CoNLL 2014 shared task setting using the the official test data of the CoNLL 2014 shared task with annotations from two annotators (without considering alternative annotations suggested by the participating teams). The test dataset consists of 1,312 error-annotated sentences with 30,144 tokens on the source side. We make use of the official scorer for the shared task, M INLINEFORM0 Scorer v3.2 BIBREF19 , for evaluation. We perform statistical significance test using one-tailed sign test with bootstrap resampling on 100 samples. ### Results and Discussion
Table TABREF24 presents the results of our experiments with neural network global lexicon model (NNGLM) and neural network joint model (NNJM). We see that the addition of both NNGLM and NNJM to our baseline individually improves INLINEFORM0 measure on the CoNLL 2014 test set by 0.43 and 0.80, respectively. Although both improvements over the baseline are statistically significant (with INLINEFORM1 ), we observe that the improvement of NNGLM is slightly lower than that of NNJM. NNGLM encodes the entire lexical information from the source sentence without word ordering information. Hence, it focuses mostly on the choice of words appearing in the output. Many of the words in the source context may not be necessary for ensuring the quality of corrected output. On the other hand, NNJM looks at a smaller window of words in the source side. NNJM can act as a language model and can ensure a fluent translation output compared to NNGLM. We also found rescaling to be important for NNGLM because of imbalanced training data. While the most frequent words in the data, `I' and to', appear in 43% and 27% of the training sentences, respectively, most words occur in very few sentences only. For example, the word `set' appears in 0.15% of the sentences and the word `enterprise' appears in 0.003% of the sentences. By incorporating both components together, we obtain an improvement of 1.17 in terms of INLINEFORM0 measure. This indicates that both components are beneficial and complement each other to improve the performance of the baseline system. While NNGLM looks at the entire source sentence and ensures the appropriate choice of words to appear in the output sentence, NNJM encourages the system to choose appropriate corrections that give a fluent output. We compare our system to the top 3 systems in the CoNLL 2014 shared task and to the best published results BIBREF17 , BIBREF0 on the test data of the CoNLL 2014 shared task. The results are summarized in Table TABREF26 . Our final system including both neural network models outperforms the best system BIBREF17 by 1.85 in F INLINEFORM0 measure. It should be noted that this is despite the fact that the system proposed in BIBREF17 uses much larger training data than our system. We qualitatively analyze the output of our neural network-enhanced systems against the outputs produced by our baseline system. We have included some examples in Table TABREF25 and the corresponding outputs of the baseline system and the reference sentences. The selected examples show that NNGLM and NNJM choose appropriate words by making use of the surrounding context effectively. Note that our neural networks, which rely on fixed source and target vocabulary, map the rare words and misspelled words to the UNK token. Therefore, phrases with the UNK token may get a higher probability than they actually should due to the large number of UNK tokens seen during training. This leads to fewer spelling error corrections compared to the baseline system which does not employ these neural networks. Consider the following example from the test data: ... numerous profit-driven companies realize the hugh (huge) human traffic on such social media sites .... The spelling error hugh INLINEFORM0 huge is corrected by the baseline system, but not by our final system with the neural networks. This is because the misspelled word hugh is not in the neural network vocabulary and so it is mapped to the UNK token. The sentence with the UNK token gets a higher score and hence the system chooses this output over the correct one. From our experiments and analysis, we see that NNGLM and NNJM capture contextual information better than regular translation models and language models. This is because they make use of larger source sentence contexts and continuous space representation of words. This enables them to make better predictions compared to traditional translation models and language models. We also observed that our system has an edge over the baseline for correction of word choice and collocation errors. ### Conclusion
Our experiments show that using the two neural network translation models improves the performance of a phrase-based SMT approach to GEC. To the best of our knowledge, this is the first work that uses these two neural network models for SMT-based GEC. The ability of neural networks to model words and phrases in continuous space and capture non-linear relationships enables them to generalize better and make more accurate grammatical error correction. We have achieved state-of-the-art results on the CoNLL 2014 shared task test dataset. This has been done without using any additional training data compared to the best performing systems evaluated on the same dataset. ### Acknowledgments
This research is supported by Singapore Ministry of Education Academic Research Fund Tier 2 grant MOE2013-T2-1-150. Figure 1: A single hidden layer neural network global lexicon model Figure 2: A single hidden layer neural network joint model Table 1: Statistics of training and development data Table 2: Results of our experiments with NNGLM and NNJM on the CoNLL 2014 test set (* indicates statistical significance with p < 0.01) Table 3: Examples from the outputs of the systems compared against our baseline system. ‘Source’ is the erroneous input sentence, ‘Baseline’ and ‘System’ are the outputs of our baseline and our neural networks-enhanced system, respectively. ‘Reference’ is the corrected sentence in which the corrections are made by a human annotator. Table 4: Our system compared against competitive grammatical error correction systems. CAMB, CUUI, and AMU are Team IDs in the CoNLL 2014 shared task.
|
ncorporating NNGLM and NNJM both independently and jointly into, baseline system
|
What would have likely happened if Thig had allowed the crew to return information to Ortha that Earth was habitable?
A. He would have had to forget all about Ellen and continue life on Ortha as before.
B. The Orthans would have made the voyage to Earth and lived in harmony with the people of Earth.
C. Earth would have been blown away by Orthans and no longer be habitable.
D. The people of Earth would have been wiped out and Ortha would take over.
|
QUEST OF THIG By BASIL WELLS Thig of Ortha was the vanguard of the conquering "HORDE." He had blasted across trackless space to subdue a defenseless world—only to meet on Earth emotions that were more deadly than weapons. [Transcriber's Note: This etext was produced from Planet Stories Fall 1942. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Thig carefully smoothed the dark sand and seaweed of the lonely beach over the metal lid of the flexible ringed tunnel that linked the grubby ship from another planet with the upper air. He looked out across the heaving waters of the Sound toward Connecticut. He stared appraisingly around at the luxuriant green growth of foliage further inland; and started toward the little stretch of trees and brush, walking carefully because of the lesser gravitation. Thig was shorter than the average Earthman—although on Ortha he was well above the average in height—but his body was thick and powerfully muscled. His skull was well-shaped and large; his features were regular, perhaps a trifle oversize, and his hair and eyes were a curiously matching blend of reddish brown. Oddest of all, he wore no garments, other than the necessary belt and straps to support his rod-like weapon of white metal and his pouches for food and specimens. The Orthan entered the narrow strip of trees and crossed to the little-used highway on the other side. Here he patiently sat down to wait for an Earthman or an Earthwoman to pass. His task now was to bring a native, intact if possible, back to the carefully buried space cruiser where his two fellows and himself would drain the creature's mentality of all its knowledge. In this way they could learn whether a planet was suited for colonization by later swarms of Orthans. Already they had charted over a hundred celestial bodies but of them all only three had proven worthy of consideration. This latest planet, however, 72-P-3 on the chart, appeared to be an ideal world in every respect. Sunlight, plenty of water and a dense atmospheric envelope made of 72-P-3 a paradise among planets. The explorer from another world crouched into the concealment of a leafy shrub. A creature was approaching. Its squat body was covered with baggy strips of bluish cloth and it carried a jointed rod of metal and wood in its paw. It walked upright as did the men of Ortha. Thig's cold eyes opened a trifle wider as he stared into the thing's stupid face. It was as though he was looking into a bit of polished metal at the reflection of himself! The Earthman was opposite now and he must waste no more precious time. The mighty muscles of the Orthan sent him hurtling across the intervening space in two prodigious bounds, and his hands clamped across the mouth and neck of the stranger.... Lewis Terry was going fishing. For a week the typewriter mill that had ground out a thousand assorted yarns of the untamed West and the frigid desolation of the Northwoods had been silent. Lewis wondered if he was going stale. He had sat every day for eight hours in front of that shiny-buttoned bane of the typist, but there were no results. Feebly he had punched a key two days ago and a $ sign had appeared. He hadn't dared touch the machine since. For Mr. Terry, that hard-hitting writer of two-gun action, had never been further west of Long Island than Elizabeth, and he had promised his wife, Ellen, that he would take the three children and herself on a trailer tour of the West that very summer. Since that promise, he could not write a word. Visions of whooping red-skinned Apaches and be-chapped outlaws raiding his little trailer home kept rolling up out of his subconscious. Yet he had to write at least three novelets and a fistful of short stories in the next two weeks to finance the great adventure—or the trip was off. So Lewis left the weathered old cottage in the early dawn and headed for his tubby old boat at the landing in an attempt to work out a salable yarn.... "Hey!" he shouted as a naked man sprang out of the bushes beside the road. "What's the trouble?" Then he had no time for further speech, the massive arms of the stranger had wound around him and two hamlike hands shut off his speech and his wind. He fought futilely against trained muscles. The hand clamping his throat relaxed for a moment and hacked along the side of his head. Blackness flooded the brain of Lewis, and he knew no more. "There it is," announced Thig, dropping the limp body of the captured Earthman to the metal deck-plates. "It is a male of the species that must have built the cities we saw as we landed." "He resembles Thig," announced Kam. "But for the strange covering he wears he might be Thig." "Thig will be this creature!" announced Torp. "With a psychic relay we will transfer the Earthman's memories and meager store of knowledge to the brain of Thig! He can then go out and scout this world without arousing suspicion. While he is gone, I will take Kam and explore the two inner planets." "You are the commander," said Thig. "But I wish this beast did not wear these clumsy sheathing upon his body. On Ortha we do not hamper the use of our limbs so." "Do not question the word of your commander," growled Torp, swelling out his thick chest menacingly. "It is for the good of our people that you disguise yourself as an Earthman." "For the good of the Horde," Thig intoned almost piously as he lifted Terry's body and headed for the laboratory. Service for the Horde was all that the men of Ortha knew. Carefully cultured and brought to life in the laboratories of their Horde, they knew neither father nor mother. Affection and love were entirely lacking in their early training and later life. They were trained antlike from childhood that only the growth and power of the Horde were of any moment. Men and women alike toiled and died like unfeeling robots of flesh and bone for the Horde. The Horde was their religion, their love-life, their everything! So it was that the bodies of the Earthman and the Orthan were strapped on two parallel tables of chill metal and the twin helmets, linked to one another by the intricacies of the psychic relay, put upon their heads. For ten hours or more the droning hum of the relay sucked Terry's brain dry of knowledge. The shock upon the nervous system of the Earthman proved too violent and his heart faltered after a time and stopped completely. Twice, with subtle drugs they restored pseudo-life to his body and kept the electrical impulses throbbing from his tortured brain, but after the third suspension of life Thig removed his helmet. "There is nothing more to learn," he informed his impassive comrades. "Now, let us get on with the plastic surgery that is required. My new body must return to its barbaric household before undue attention is aroused. And when I return I will take along some of the gleaming baubles we found on the red planet—these people value them highly." An hour later, his scars and altered cartilage already healed and painless, Thig again scraped sand over the entrance to the space ship and set out along the moonlit beach toward the nearest path running inland to his home. Memory was laying the country bare about him, Terry's own childhood memories of this particular section of Long Island. Here was the place where Jake and Ted had helped him dig for the buried treasure that old 'Notch-ear' Beggs had told them so exactly about. Remembrance of that episode gave Thig an idea about the little lump of jewels in his pocket. He had found them in a chest along the beach! He was coming up on the porch now and at the sound of his foot on the sagging boards the screen door burst open and three little Earth-creatures were hugging at his legs. An odd sensation, that his acquired memories labeled as pleasure, sent a warm glow upward from around his heart. Then he saw the slender red-haired shape of a woman, the mate of the dead man he knew, and confusion struck his well-trained brain. Men had no mates on Ortha, sex had been overthrown with all the other primitive impulses of barbarism; so he was incapable of understanding the emotions that swept through his acquired memory. Unsteadily he took her in his arms and felt her warm lips pressed, trembling, against his own. That same hot wave of pulsing blood choked achingly up into his throat. "Lew, dear," Ellen was asking, "where have you been all day? I called up at the landing but you were not there. I wanted to let you know that Saddlebag Publications sent a check for $50 for "Reversed Revolvers" and three other editors asked for shorts soon." "Shoulda got a hundred bucks for that yarn," grunted Thig, and gasped. For the moment he had been Lewis Terry and not Thig! So thoroughly had he acquired the knowledge of Terry that he found himself unconsciously adopting the thinking and mannerism of the other. All the better this way, he realized—more natural. "Sorry I was late," he said, digging into his pocket for the glittering baubles, "but I was poking around on the beach where we used to hunt treasure and I found an old chest. Inside it I found nothing but a handful of these." He flashed the jewels in front of Ellen's startled eyes and she clung, unbelieving, to his arm. "Why, Lew," she gasped, "they're worth a fortune! We can buy that new trailer now and have a rebuilt motor in the car. We can go west right away.... Hollywood, the Grand Canyon, cowboys!" "Uh huh," agreed the pseudo Lewis, memories of the ferocious savages and gunmen of his stories rendering him acutely unhappy. Sincerely he hoped that the west had reformed. "I saved some kraut and weiners," Ellen said. "Get washed up while I'm warming them up. Kids ate all the bread so I had to borrow some from the Eskoes. Want coffee, too?" "Mmmmmm," came from the depths of the chipped white wash-basin. "Home again," whispered Ellen as she stood beside Thig twelve weeks later and gazed tearfully at the weathered little gray house. She knelt beside the front stoop and reached for the key hidden beneath it. "The west was wonderful; tremendous, vast and beautiful," she went on as they climbed the steps, "but nowhere was there any place as beautiful as our own little strip of sky and water." Thig sank into a dusty old swing that hung on creaking chains from the exposed rafters of the porch roof. He looked down at the dusty gray car and the bulbous silvery bulk of the trailer that had been their living quarters for almost three months. Strange thoughts were afloat in the chaos of his cool Orthan brain. Tonight or tomorrow night at the latest he must contact his two fellows and report that Earth was a planetary paradise. No other world, including Ortha, was so well-favored and rich. An expeditionary force to wipe the grotesque civilizations of Earth out of existence would, of course, be necessary before the first units of new Hordes could be landed. And there Thig balked. Why must they destroy these people, imperfect though their civilization might be, to make room for the Hordes? Thig tried to tell himself that it was the transmitted thoughts of the dead Earthman that made him feel so, but he was not too sure. For three months he had lived with people who loved, hated, wept and sacrificed for reasons that he had never known existed. He had learned the heady glory of thinking for himself and making his own decisions. He had experienced the primitive joy of matching his wits and tongue against the wits of other unpredictable human beings. There was no abrupt division of men and women into definite classes of endeavor. A laborer thought the same thoughts that a governor might think. Uncertainty added zest to every day's life. The Orthan had come to question the sole devotion of the individual to the Horde to the exclusion of all other interests. What, he wondered, would one new world—or a hundred—populated by the Hordes add to the progress of humanity? For a hundred thousand years the Orthan civilization had remained static, its energies directed into certain well-defined channels. They were mindless bees maintaining their vast mechanical hives. There was that moment on the brink of the Grand Canyon when Ellen had caught his arm breathlessly at all the beauty spread away there beneath them. There were mornings in the desert when the sun painted in lurid red the peaks above the harsh black-and-whites of the sagebrush and cactus slopes. There was the little boy, his body burning with fever, who nestled trustingly against his tense man's body and slept—the son of Ellen and the man he had destroyed. Thig groaned. He was a weakling to let sentimentality so get the better of his judgment. He would go now to the space ship and urge them to blast off for Ortha. He sprang off the porch and strode away down the road toward the beach. The children ran to him; wanted to go along. He sent them away harshly but they smiled and waved their brown little hands. Ellen came to the door and called after him. "Hurry home, dear," she said. "I'll have a bite ready in about an hour." He dared not say anything, for his voice would have broken and she would have known something was wrong. She was a very wise sort of person when something was troubling him. He waved his stubby paw of a hand to show that he had heard, and blindly hurried toward the Sound. Oddly enough, as he hurried away along the narrow path through the autumn woods, his mind busied itself with a new epic of the west that lived no longer. He mentally titled it: "Rustlers' Riot" and blocked in the outlines of his plot. One section of his brain was that of the careless author of gunslinging yarns, a section that seemed to be sapping the life from his own brain. He knew that the story would never be written, but he toyed with the idea. So far had Thig the emotionless, robot-being from Ortha drifted from the unquestioning worship of the Horde! "You have done well," announced Torp when Thig had completed his report on the resources and temperatures of various sections of Terra. "We now have located three worlds fit for colonization and so we will return to Ortha at once. "I will recommend the conquest of this planet, 72-P-3 at once and the complete destruction of all biped life upon it. The mental aberrations of the barbaric natives might lead to endless complications if they were permitted to exist outside our ordered way of life. I imagine that three circuits of the planet about its primary should prove sufficient for the purposes of complete liquidation." "But why," asked Thig slowly, "could we not disarm all the natives and exile them on one of the less desirable continents, Antarctica for example or Siberia? They are primitive humans even as our race was once a race of primitives. It is not our duty to help to attain our own degree of knowledge and comfort?" "Only the good of the Horde matters!" shouted Torp angrily. "Shall a race of feeble-witted beasts, such as these Earthmen, stand in the way of a superior race? We want their world, and so we will take it. The Law of the Horde states that all the universe is ours for the taking." "Let us get back to Ortha at once, then," gritted out Thig savagely. "Never again do I wish to set foot upon the soil of this mad planet. There are forces at work upon Earth that we of Ortha have long forgotten." "Check the blood of Thig for disease, Kam," ordered Torp shortly. "His words are highly irrational. Some form of fever perhaps native to this world. While you examine him I will blast off for Ortha." Thig followed Kam into the tiny laboratory and found a seat beside the squat scientist's desk. His eyes roamed over the familiar instruments and gauges, each in its own precise position in the cases along the walls. His gaze lingered longest on the stubby black ugliness of a decomposition blaster in its rack close to the deck. A blast of the invisible radiations from that weapon's hot throat and flesh or vegetable fiber rotted into flaky ashes. The ship trembled beneath their feet; it tore free from the feeble clutch of the sand about it, and they were rocketing skyward. Thig's broad fingers bit deep into the unyielding metal of his chair. Suddenly he knew that he must go back to Earth, back to Ellen and the children of the man he had helped destroy. He loved Ellen, and nothing must stand between them! The Hordes of Ortha must find some other world, an empty world—this planet was not for them. "Turn back!" he cried wildly. "I must go back to Earth. There is a woman there, helpless and alone, who needs me! The Horde does not need this planet." Kam eyed him coldly and lifted a shining hypodermic syringe from its case. He approached Thig warily, aware that disease often made a maniac of the finest members of the Horde. "No human being is more important than the Horde," he stated baldly. "This woman of whom you speak is merely one unit of the millions we must eliminate for the good of the Horde." Then it was that Thig went berserk. His fists slashed into the thick jaw of the scientist and his fingers ripped at the hard cords overlying the Orthan's vital throat tubes. His fingers and thumb gouged deep into Kam's startled throat and choked off any cry for assistance before it could be uttered. Kam's hand swept down to the holster swung from his intricate harness and dragged his blaster from it. Thig's other hand clamped over his and for long moments they swayed there, locked together in silent deadly struggle. The fate of a world hung in the balance as Kam's other hand fought against that lone arm of Thig. The scales swung in favor of Kam. Slowly the flaring snout of his weapon tilted upward until it reached the level of Thig's waist. Thig suddenly released his grip and dragged his enemy toward him. A sudden reversal of pressure on Kam's gun hand sent the weapon swivelling about full upon its owner's thick torso. Thig's fingers pressed down upon Kam's button finger, down upon the stud set into the grip of the decomposition blaster, and Kam's muscles turned to water. He shrieked. Before Thig's eyes half of his comrade's body sloughed away into foul corruption that swiftly gave way to hardened blobs of dessicated matter. Horror for what he had done—that he had slain one of his own Horde—made his limbs move woodenly. All of his thoughts were dulled for the moment. Painfully slow, he turned his body around toward the control blister, turned around on leaden feet, to look full into the narrowed icy eyes of his commander. He saw the heavy barrel of the blaster slashing down against his skull but he could not swing a fraction of an inch out of the way. His body seemed paralyzed. This was the end, he thought as he waited stupidly for the blow to fall, the end for Ellen and the kids and all the struggling races of Earth. He would never write another cowboy yarn—they would all be dead anyhow soon. Then a thunderclap exploded against his head and he dropped endlessly toward the deck. Blows rained against his skull. He wondered if Torp would ever cease to hammer at him and turn the deadly ray of the weapon upon him. Blood throbbed and pounded with every blow.... Bam, Bam, Bam, the blood pounded in his ears. Like repeated blows of a hammer they shook his booming head. No longer was Torp above him. He was in the corner of the laboratory, a crumpled blood-smeared heap of bruised flesh and bone. He was unfettered and the blood was caked upon his skull and in his matted hair. Torp must have thought he had killed him with those savage blows upon the head. Even Torp, thought Thig ruefully, gave way to the primitive rage of his ancestors at times; but to that very bit of unconscious atavism he now owed his life. A cool-headed robot of an Orthan would have efficiently used the blaster to destroy any possibility of remaining life in his unconscious body. Thig rolled slowly over so that his eye found the door into the control room. Torp would be coming back again to dispose of their bodies through the refuse lock. Already the body of Kam was gone. He wondered why he had been left until last. Perhaps Torp wished to take cultures of his blood and tissues to determine whether a disease was responsible for his sudden madness. The cases of fragile instruments were just above his head. Association of memories brought him the flash of the heavy blaster in its rack beneath them. His hand went up and felt the welcome hardness of the weapon. He tugged it free. In a moment he was on his knees crawling across the plates of the deck toward the door. Halfway across the floor he collapsed on his face, the metal of the gun making a harsh clang. He heard the feet of Torp scuffle out of silence and a choked cry in the man's throat squalled out into a senseless whinny. Thig raised himself up on a quivering elbow and slid the black length of the blaster in front of him. His eyes sought the doorway and stared full into the glaring vacant orbs of his commander. Torp leaned there watching him, his breath gurgling brokenly through his deep-bitten lips. The clawing marks of nails, fingernails, furrowed his face and chest. He was a madman! The deadly attack of Thig; his own violent avenging of Kam's death, and now the apparent return of the man he had killed come to life had all served to jolt his rigidly trained brain from its accustomed groove. The shock had been too much for the established thought-processes of the Orthan. So Thig shot him where he stood, mercifully, before that vacant mad stare set him, too, to gibbering and shrieking. Then he stepped over the skeleton-thing that had been Torp, using the new strength that victory had given him to drive him along. He had saved a world's civilization from extinction! The thought sobered him; yet, somehow, he was pleased that he had done so. After all, it had been the Earthwoman and the children he had been thinking of while he battled Kam, a selfish desire to protect them all. He went to the desk where Torp had been writing in the ship's log and read the last few nervously scrawled lines: Planet 72-P-3 unfit for colonization. Some pernicious disease that strikes at the brain centers and causes violent insanity is existent there. Thig, just returned from a survey of the planet, went mad and destroyed Kam. In turn I was forced to slay him. But it is not ended. Already I feel the insidious virus of.... And there his writing ended abruptly. Thig nodded. That would do it. He set the automatic pilot for the planet Ortha. Unless a rogue asteroid or a comet crossed the ship's path she would return safely to Ortha with that mute warning of danger on 72-P-3. The body of Torp would help to confirm his final message. Then Thig crossed the cabin to the auxiliary life boat there, one of a half-dozen space ships in miniature nested within the great ship's hull, and cut free from the mother vessel. He flipped the drive lever, felt the thrumming of the rockets driving him from the parent ship. The sensation of free flight against his new body was strangely exhilerating and heady. It was the newest of the emotions he had experienced on Earth since that day, so many months before, when he had felt the warmness of Ellen's lips tight against his. Thig flipped the drive lever, felt the thrumming of the rockets driving him from the parent ship. He swung about to the port, watched the flaming drive-rockets of the great exploratory ship hurl it toward far-away Ortha, and there was no regret in his mind that he was not returning to the planet of his first existence. He thought of the dull greys and blacks of his planet, of the monotonous routine of existence that had once been his—and his heart thrilled to the memories of the starry nights and perfect exciting days he had spent on his three month trip over Earth. He made a brief salute to the existence he had known, turned with a tiny sigh, and his fingers made brief adjustments in the controls. The rocket-thrum deepened, and the thin whistle of tenuous air clutching the ship echoed through the hull-plates. He thought of many things in those few moments. He watched the roundness of Earth flatten out, then take on the cup-like illusion that all planets had for an incoming ship. He reduced the drive of his rockets to a mere whisper, striving to control the impatience that crowded his mind. He shivered suddenly, remembering his utter callousness the first time he had sent a space ship whipping down toward the hills and valleys below. And there was a sickness within him when he fully realized that, despite his acquired memory and traits, he was an alien from outer space. He fingered the tiny scars that had completely obliterated the slight differences in his appearance from an Earthman's, and his fingers trembled a bit, as he bent and stared through the vision port. He said a brief prayer in his heart to a God whose presence he now felt very deeply. There were tears in the depths of his eyes, then, and memories were hot, bitter pains. Earth was not far below him. As he let gravity suck him earthward, he heaved a gasp of relief. He was no longer Thig, a creature of a Horde's creation, but Lewis Terry, writer of lurid gun-smoking tales of the West. He must remember that always. He had destroyed the real Terry and now, for the rest of his life, he must make up to the dead man's family. The knowledge that Ellen's love was not really meant for him would be a knife twisting in his heart but for her sake he must endure it. Her dreams and happiness must never be shattered. The bulge of Earth was flattening out now and he could see the outlines of Long Island in the growing twilight. A new plot was growing in the brain of Lewis Terry, a yarn about a cowboy suddenly transported to another world. He smiled ironically. He had seen those other worlds. Perhaps some day he would write about them.... He was Lewis Terry! He must remember that!
|
D. The people of Earth would have been wiped out and Ortha would take over.
|
How do they model a city description using embeddings?
|
### Introduction
Literary critics form interpretations of meaning in works of literature. Building computational models that can help form and test these interpretations is a fundamental goal of digital humanities research BIBREF0 . Within natural language processing, most previous work that engages with literature relies on “distant reading” BIBREF1 , which involves discovering high-level patterns from large collections of stories BIBREF2 , BIBREF3 . We depart from this trend by showing that computational techniques can also engage with literary criticism at a closer distance: concretely, we use recent advances in text representation learning to test a single literary theory about the novel Invisible Cities by Italo Calvino. Framed as a dialogue between the traveler Marco Polo and the emperor Kublai Khan, Invisible Cities consists of 55 prose poems, each of which describes an imaginary city. Calvino categorizes these cities into eleven thematic groups that deal with human emotions (e.g., desires, memories), general objects (eyes, sky, signs), and unusual properties (continuous, hidden, thin). Many critics argue that Calvino's labels are not meaningful, while others believe that there is a distinct thematic separation between the groups, including the author himself BIBREF4 . The unique structure of this novel — each city's description is short and self-contained (Figure FIGREF1 ) — allows us to computationally examine this debate. As the book is too small to train any models, we leverage recent advances in large-scale language model-based representations BIBREF5 , BIBREF6 to compute a representation of each city. We feed these representations into a clustering algorithm that produces exactly eleven clusters of five cities each and evaluate them against both Calvino's original labels and crowdsourced human judgments. While the overall correlation with Calvino's labels is low, both computers and humans can reliably identify some thematic groups associated with concrete objects. While prior work has computationally analyzed a single book BIBREF7 , our work goes beyond simple word frequency or n-gram counts by leveraging the power of pretrained language models to engage with literary criticism. Admittedly, our approach and evaluations are specific to Invisible Cities, but we believe that similar analyses of more conventionally-structured novels could become possible as text representation methods improve. We also highlight two challenges of applying computational methods to literary criticisms: (1) text representation methods are imperfect, especially when given writing as complex as Calvino's; and (2) evaluation is difficult because there is no consensus among literary critics on a single “correct” interpretation. ### Literary analyses of Invisible Cities
Before describing our method and results, we first review critical opinions on both sides of whether Calvino's thematic groups meaningfully characterize his city descriptions. ### A Computational Analysis
We focus on measuring to what extent computers can recover Calvino's thematic groupings when given just raw text of the city descriptions. At a high level, our approach (Figure FIGREF4 ) involves (1) computing a vector representation for every city and (2) performing unsupervised clustering of these representations. The rest of this section describes both of these steps in more detail. ### Embedding city descriptions
While each of the city descriptions is relatively short, Calvino's writing is filled with rare words, complex syntactic structures, and figurative language. Capturing the essential components of each city in a single vector is thus not as simple as it is with more standard forms of text. Nevertheless, we hope that representations from language models trained over billions of words of text can extract some meaningful semantics from these descriptions. We experiment with three different pretrained representations: ELMo BIBREF5 , BERT BIBREF6 , and GloVe BIBREF18 . To produce a single city embedding, we compute the TF-IDF weighted element-wise mean of the token-level representations. For all pretrained methods, we additionally reduce the dimensionality of the city embeddings to 40 using PCA for increased compatibility with our clustering algorithm. ### Clustering city representations
Given 55 city representations, how do we group them into eleven clusters of five cities each? Initially, we experimented with a graph-based community detection algorithm that maximizes cluster modularity BIBREF20 , but we found no simple way to constrain this method to produce a specific number of equally-sized clusters. The brute force approach of enumerating all possible cluster assignments is intractable given the large search space ( INLINEFORM0 possible assignments). We devise a simple clustering algorithm to approximate this process. First, we initialize with random cluster assignments and define “cluster strength” to be the relative difference between “intra-group” Euclidean distance and “inter-group” Euclidean distance. Then, we iteratively propose random exchanges of memberships, only accepting these proposals when the cluster strength increases, until convergence. To evaluate the quality of the computationally-derived clusters against those of Calvino, we measure cluster purity BIBREF21 : given a set of predicted clusters INLINEFORM1 and ground-truth clusters INLINEFORM2 that both partition a set of INLINEFORM3 data points, INLINEFORM4 ### Evaluating clustering assignments
While the results from the above section allow us to compare our three computational methods against each other, we additionally collect human judgments to further ground our results. In this section, we first describe our human experiment before quantitatively analyzing our results. ### Quantitative comparison
We compare clusters computed on different representations using community purity; additionally, we compare these computational methods to humans by their accuracy on the odd-one-out task. City representations computed using language model-based representation (ELMo and BERT) achieve significantly higher purity than a clustering induced from random representations, indicating that there is at least some meaningful coherence to Calvino's thematic groups (first row of Table TABREF11 ). ELMo representations yield the highest purity among the three methods, which is surprising as BERT is a bigger model trained on data from books (among other domains). Both ELMo and BERT outperform GloVe, which intuitively makes sense because the latter do not model the order or structure of the words in each description. While the purity of our methods is higher than that of a random clustering, it is still far below 1. To provide additional context to these results, we now switch to our “odd-one-out” task and compare directly to human performance. For each triplet of cities, we identify the intruder as the city with the maximum Euclidean distance from the other two. Interestingly, crowd workers achieve only slightly higher accuracy than ELMo city representations; their interannotator agreement is also low, which indicates that close reading to analyze literary coherence between multiple texts is a difficult task, even for human annotators. Overall, results from both computational and human approaches suggests that the author-assigned labels are not entirely arbitrary, as we can reliably recover some of the thematic groups. ### Examining the learned clusters
Our quantitative results suggest that while vector-based city representations capture some thematic similarities, there is much room for improvement. In this section, we first investigate whether the learned clusters provide evidence for any arguments put forth by literary critics on the novel. Then, we explore possible reasons that the learned clusters deviate from Calvino's. ### Related work
Most previous work within the NLP community applies distant reading BIBREF1 to large collections of books, focusing on modeling different aspects of narratives such as plots and event sequences BIBREF22 , BIBREF23 , BIBREF24 , BIBREF25 , characters BIBREF2 , BIBREF26 , BIBREF27 , BIBREF28 , and narrative similarity BIBREF3 . In the same vein, researchers in computational literary analysis have combined statistical techniques and linguistics theories to perform quantitative analysis on large narrative texts BIBREF29 , BIBREF30 , BIBREF31 , BIBREF32 , BIBREF33 , but these attempts largely rely on techniques such as word counting, topic modeling, and naive Bayes classifiers and are therefore not able to capture the meaning of sentences or paragraphs BIBREF34 . While these works discover general patterns from multiple literary works, we are the first to use cutting-edge NLP techniques to engage with specific literary criticism about a single narrative. There has been other computational work that focuses on just a single book or a small number of books, much of it focused on network analysis: BIBREF35 extract character social networks from Alice in Wonderland, while BIBREF36 recover social networks from 19th century British novels. BIBREF37 disentangles multiple narrative threads within the novel Infinite Jest, while BIBREF7 provides several automated statistical methods for close reading and test them on the award-winning novel Cloud Atlas (2004). Compared to this work, we push further on modeling the content of the narrative by leveraging pretrained language models. ### Conclusion
Our work takes a first step towards computationally engaging with literary criticism on a single book using state-of-the-art text representation methods. While we demonstrate that NLP techniques can be used to support literary analyses and obtain new insights, they also have clear limitations (e.g., in understanding abstract themes). As text representation methods become more powerful, we hope that (1) computational tools will become useful for analyzing novels with more conventional structures, and (2) literary criticism will be used as a testbed for evaluating representations. ### Acknowledgement
We thank the anonymous reviewers for their insightful comments. Additionally, we thank Nader Akoury, Garrett Bernstein, Chenghao Lv, Ari Kobren, Kalpesh Krishna, Saumya Lal, Tu Vu, Zhichao Yang, Mengxue Zhang and the UMass NLP group for suggestions that improved the paper's clarity, coverage of related work, and analysis experiments. Figure 1: Calvino labels the thematically-similar cities in the top row as cities & the dead. However, although the bottom two cities share a theme of desire, he assigns them to different groups. Figure 2: We first embed each city by averaging token representations derived from a pretrained model such as ELMo. Then, we feed the city embeddings to a clustering algorithm and analyze the learned clusters. Table 1: Results from cluster purity and accuracy on the “odd-one-out” task suggests that Calvino’s thematic groups are not completely arbitrary.
|
We experiment with three different pretrained representations: ELMo BIBREF5 , BERT BIBREF6 , and GloVe BIBREF18 . To produce a single city embedding, we compute the TF-IDF weighted element-wise mean of the token-level representations. For all pretrained methods, we additionally reduce the dimensionality of the city embeddings to 40 using PCA for increased compatibility with our clustering algorithm.
|
Which isn't true?
A. Stardust Charlie was proud of Ben
B. Mickey is jealous of Ben's future job
C. Laura was hoping to settle down with Ben
D. Ben wants to travel to other planets
|
Spacemen Die at Home By EDWARD W. LUDWIG Illustrated by THORNE [Transcriber's Note: This etext was produced from Galaxy Science Fiction October 1951. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] One man's retreat is another's prison ... and it takes a heap of flying to make a hulk a home! Forty days of heaven and forty nights of hell. That's the way it's been, Laura. But how can I make you understand? How can I tell you what it's like to be young and a man and to dream of reaching the stars? And yet, at the same time, to be filled with a terrible, gnawing fear—a fear locked in my mind during the day and bursting out like an evil jack-in-the-box at night. I must tell you, Laura. Perhaps if I start at the beginning, the very beginning.... It was the Big Day. All the examinations, the physicals and psychos, were over. The Academy, with its great halls and classrooms and laboratories, lay hollow and silent, an exhausted thing at sleep after spawning its first-born. For it was June in this year of 1995, and we were the graduating class of the U. S. Academy of Interplanetary Flight. The first graduating class, Laura. That's why it was so important, because we were the first . We sat on a little platform, twenty-five of us. Below us was a beach of faces, most of them strange, shining like pebbles in the warm New Mexican sunlight. They were the faces of mothers and fathers and grandparents and kid brothers and sisters—the people who a short time ago had been only scrawled names on letters from home or words spoken wistfully at Christmas. They were the memory-people who, to me, had never really existed. But today they had become real, and they were here and looking at us with pride in their eyes. A voice was speaking, deep, sure, resonant. "... these boys have worked hard for six years, and now they're going to do a lot of big things. They're going to bring us the metals and minerals that we desperately need. They're going to find new land for our colonists, good rich land that will bear food and be a home for our children. And perhaps most important of all, they'll make other men think of the stars and look up at them and feel humility—for mankind needs humility." The speaker was Robert Chandler, who'd brought the first rocket down on Mars just five years ago, who'd established the first colony there, and who had just returned from his second hop to Venus. Instead of listening to his words, I was staring at his broad shoulders and his dark, crew-cut hair and his white uniform which was silk-smooth and skin-tight. I was worshiping him and hating him at the same time, for I was thinking: He's already reached Mars and Venus. Let him leave Jupiter and the others alone! Let us be the first to land somewhere! Let us be the first! Mickey Cameron, sitting next to me, dug an elbow into my ribs. "I don't see 'em, Ben," he whispered. "Where do you suppose they are?" I blinked. "Who?" "My folks." That was something I didn't have to worry about. My parents had died in a strato-jet crash when I was four, so I hadn't needed many of those "You are cordially invited" cards. Just one, which I'd sent to Charlie Taggart. Stardust Charlie, we called him, although I never knew why. He was a veteran of Everson's first trip to the Moon nearly twenty-five years ago, and he was still at it. He was Chief Jetman now on the Lunar Lady , a commercial ore ship on a shuttle between Luna City and White Sands. I remembered how, as a kid, I'd pestered him in the Long Island Spaceport, tagging after him like a puppy, and how he'd grown to like me until he became father, mother, and buddy all in one to me. And I remembered, too, how his recommendation had finally made me a cadet. My gaze wandered over the faces, but I couldn't find Charlie's. It wasn't surprising. The Lunar Lady was in White Sands now, but liberties, as Charlie said, were as scarce as water on Mars. It doesn't matter , I told myself. Then Mickey stiffened. "I see 'em, Ben! There in the fifth row!" Usually Mickey was the same whether in a furnace-hot engine room or a garden party, smiling, accepting whatever the world offered. But now a tenseness and an excitement had gripped even him. I was grateful that he was beside me; we'd been a good team during those final months at the Academy and I knew we'd be a good team in space. The Universe was mighty big, but with two of us to face it together, it would be only half as big. And then it seemed that all the proud faces were looking at us as if we were gods. A shiver went through my body. Though it was daytime, I saw the stars in my mind's vision, the great shining balls of silver, each like a voice crying out and pleading to be explored, to be touched by the sons of Earth. They expect a lot from us. They expect us to make a new kind of civilization and a better place out of Earth. They expect all this and a hell of a lot more. They think there's nothing we can't do. I felt very small and very humble. I was scared. Damned scared. At last it was over, and the proud faces descended upon us in a huge, babbling wave. Then I saw him. Good old Stardust Charlie. His wizened little body was shuffling down an aisle, his eyes shining like a child's. He'd been sandwiched, evidently, in one of the rear rows. But he wasn't the Charlie I'd seen a year ago. He'd become gaunt and old, and he walked with an unnatural stiffness. He looked so old that it was hard to believe he'd once been young. He scratched his mop of steel-gray hair and grinned. "You made it, boy," he chortled, "and by Jupiter, we'll celebrate tonight. Yes, siree, I got twenty-four hours, and we'll celebrate as good spacemen should!" Then Mickey strode up to us. He was his normal, boyish self again, walking lightly, his blond, curly-haired skull swaying as if in rhythm with some silent melody. And you, Laura, were with him. "Meet the Brat," he said. "My sister Laura." I stared almost rudely. You were like a doll lost in the immensity of your fluffy pink dress. Your hair was long and transformed into a golden froth where sunlight touched it. But your eyes were the eyes of a woman, glowing like dark stars and reflecting a softness, a gentleness that I'd never seen in eyes before. "I'm happy to meet you, Ben," you said. "I've heard of no one else for the past year." A tide of heat crept up from my collar. I stuttered through an introduction of Charlie. You and Mickey looked strangely at Charlie, and I realized that old Stardust was not a cadet's notion of the ideal spaceman. Charlie scorned the skin-tight uniforms of the government service and wore a shiny black suit that was a relic of Everson's early-day Moon Patrol. His tie was clumsily knotted, and a button on his coat was missing. And the left side of his face was streaked with dark scar tissue, the result of an atomic blowup on one of the old Moon ships. I was so accustomed to the scars, I was seldom aware of them; but others, I knew, would find them ugly. You were kind. You shook hands and said, softly: "It's a privilege to meet you, Charlie. Just think—one of Everson's men, one of the first to reach the Moon!" Charlie gulped helplessly, and Mickey said: "Still going to spend the weekend with us, aren't you, Ben?" I shook my head. "Charlie has only twenty-four hours liberty. We're planning to see the town tonight." "Why don't you both come with us?" you asked. "Our folks have their own plane, so it would be no problem. And we've got a big guest room. Charlie, wouldn't you like a home-cooked meal before going back to the Moon?" Charlie's answer was obscured by a sudden burst of coughing. I knew that he'd infinitely prefer to spend his liberty sampling Martian fizzes and Plutonian zombies. But this night seemed too sacred for Charlie's kind of celebration. "We'd really like to come," I said. On our way to the 'copter parking field, Dean Dawson passed us. He was a tall, willowy man, spectacled, looking the way an academy professor should look. "Ben," he called, "don't forget that offer. Remember you've got two months to decide." "No, thanks," I answered. "Better not count on me." A moment later Mickey said, frowning, "What was he talking about, Ben? Did he make you an offer?" I laughed. "He offered me a job here at the Academy teaching astrogation. What a life that would be! Imagine standing in a classroom for forty years when I've got the chance to—" I hesitated, and you supplied the right words: "When you've got the chance to be the first to reach a new planet. That's what most of you want, isn't it? That's what Mickey used to want." I looked at you as if you were Everson himself, because you seemed to understand the hunger that could lie in a man's heart. Then your last words came back and jabbed me: "That's what Mickey used to want." " Used to want?" I asked. "What do you mean?" You bit your lip, not answering. "What did she mean, Mickey?" Mickey looked down at his feet. "I didn't want to tell you yet, Ben. We've been together a long time, planning to be on a rocket. But—" "Yes?" "Well, what does it add up to? You become a spaceman and wear a pretty uniform. You wade through the sands of Mars and the dust of Venus. If you're lucky, you're good for five, maybe ten years. Then one thing or another gets you. They don't insure rocketmen, you know." My stomach was full of churning, biting ice. "What are you trying to say, Mickey?" "I've thought about it a long time. They want me for Cargo Supervisor of White Sands Port." He raised his hand to stop me. "I know. It's not so exciting. I'll just live a lot longer. I'm sorry, Ben." I couldn't answer. It was as if someone had whacked the back of my knees with the blast of a jet. "It doesn't change anything, Ben—right now, I mean. We can still have a good weekend." Charlie was muttering under his breath, smoldering like a bomb about to reach critical mass. I shook my head dazedly at him as we got to the 'copter. "Sure," I said to Mickey, "we can still have a good weekend." I liked your folks, Laura. There was no star-hunger in them, of course. They were simple and solid and settled, like green growing things, deep-rooted, belonging to Earth. They were content with a home that was cool on this warm summer night, with a 'copter and a tri-dimensional video, and a handsome automatic home that needed no servants or housework. Stardust Charlie was as comfortable as a Martian sand-monkey in a shower, but he tried courageously to be himself. At the dinner table he stared glassily at nothing and grated, "Only hit Mars once, but I'll never forget the kid who called himself a medic. Skipper started coughing, kept it up for three days. Whoopin' cough, the medic says, not knowin' the air had chemicals that turned to acid in your lungs. I'd never been to Mars before, but I knew better'n that. Hell, I says, that ain't whoopin' cough, that's lung-rot." That was when your father said he wasn't so hungry after all. Afterward, you and I walked onto the terrace, into the moonlit night, to watch for crimson-tailed continental rockets that occasionally streaked up from White Sands. We gazed for a few seconds up into the dark sky, and then you said: "Charlie is funny, isn't he? He's nice and I'm glad he's here, but he's sort of funny." "He's an old-time spaceman. You didn't need much education in those days, just a lot of brawn and a quick mind. It took guts to be a spaceman then." "But he wasn't always a spaceman. Didn't he ever have a family?" I smiled and shook my head. "If he had, he never mentioned it. Charlie doesn't like to be sentimental, at least not on the outside. As far as I know, his life began when he took off for the Moon with Everson." You stared at me strangely, almost in a sacred kind of way. I knew suddenly that you liked me, and my heart began to beat faster. There was silence. You were lovely, your soft hair like strands of gold, and there were flecks of silver in your dark eyes. Somehow I was afraid. I had the feeling that I shouldn't have come here. You kept looking at me until I had to ask: "What are you thinking, Laura?" You laughed, but it was a sad, fearful laugh. "No, I shouldn't be thinking it. You'd hate me if I told you, and I wouldn't want that." "I could never hate you." "It—it's about the stars," you said very softly. "I understand why you want to go to them. Mickey and I used to dream about them when we were kids. Of course I was a girl, so it was just a game to me. But once I dreamed of going to England. Oh, it was going to be so wonderful. I lived for months, just thinking about it. "One summer we went. I had fun. I saw the old buildings and castles, and the spaceports and the Channel Tube. But after it was over, I realized England wasn't so different from America. Places seem exciting before you get to them, and afterward they're not really." I frowned. "And you mean it might be the same with the stars? You think maybe I haven't grown up yet?" Anxiety darkened your features. "No, it'd be good to be a spaceman, to see the strange places and make history. But is it worth it? Is it worth the things you'd have to give up?" I didn't understand at first, and I wanted to ask, "Give up what ?" Then I looked at you and the promise in your eyes, and I knew. All through the years I'd been walking down a single, narrow path. Government boarding school, the Academy, my eyes always upward and on the stars. Now I'd stumbled into a cross-roads, beholding a strange new path that I'd never noticed before. You can go into space , I thought, and try to do as much living in ten years as normal men do in fifty. You can be like Everson, who died in a Moon crash at the age of 36, or like a thousand others who lie buried in Martian sand and Venusian dust. Or, if you're lucky, like Charlie—a kind of human meteor streaking through space, eternally alone, never finding a home. Or there's the other path. To stay on this little prison of an Earth in cool, comfortable houses. To be one of the solid, rooted people with a wife and kids. To be one of the people who live long enough to grow old, who awake to the song of birds instead of rocket grumblings, who fill their lungs with the clean rich air of Earth instead of poisonous dust. "I'm sorry," you said. "I didn't mean to make you sad, Ben." "It's all right," I said, clenching my fists. "You made sense—a lot of sense." The next morning Charlie said good-bye in our room. He rubbed his scarred face nervously as he cleared his throat with a series of thin, tight coughs. Then he pointed to a brown, faded tin box lying on the bed. "I'm leavin' that for you. It's full of old stuff, souvenirs mostly. Thought maybe you'd like to have 'em." I scowled, not understanding. "Why, Charlie? What for?" He shrugged as if afraid he might be accused of sentimentality. "Oh, it's just that I've been dodgin' meteors now for twenty-five years. That's a long time, boy. Ain't one spaceman in a thousand that lucky. Some of these days, I won't be so lucky." I tried to laugh. "You're good for another twenty-five years, Charlie." He shook his head stiffly, staring at nothing. "Maybe. Anyway, I'm gonna get off the Shuttle this time, make one more trip to Mars. Tell you what. There's a little stone cafe on Mars, the Space Rat , just off Chandler Field on the Grand Canal. When you get to Mars, take a look inside. I'll probably be there." He coughed again, a deep, rasping cough that filled his eyes with tears. "Not used to this Earth air," he muttered. "What I need's some Martian climate." Suddenly that cough frightened me. It didn't seem normal. I wondered, too, about his stiff movements and glassy stare. It was as if he were drugged. I shook the thought away. If Charlie was sick, he wouldn't talk about going to Mars. The medics wouldn't let him go even as far as Luna. We watched him leave, you and Mickey and I. "When will you be back?" you asked. Charlie's hard face contorted itself into a gargoylish grin. "Maybe a couple of months, maybe a couple of years. You know spacemen." Then he waved and strode away, a strange, gray, withered gnome of a man. I wanted him to say something, to tell me the secret that would kill the doubt worming through my brain. But he rounded a corner, still grinning and waving, and then he was gone. That afternoon Mickey showed me his room. It was more like a boy's room than a spaceman's. In it were all the little things that kids treasure—pennants, models of Everson's two ships, a tennis trophy, books, a home-made video. I began to realize how important a room like this could be to a boy. I could imagine, too, the happiness that parents felt as they watched their children grow to adulthood. I'd missed something. My folks were shadow-people, my impressions of them drawn half from ancient photos, half from imagination. For me, it had been a cold, automatic kind of life, the life of dormitories and routines and rules. I'd been so blinded by the brilliancy of my dreams, I hadn't realized I was different. My folks were killed in a rocket crash. If it weren't for rockets, I'd have lived the kind of life a kid should live. Mickey noticed my frown. "What's the matter, Ben? Still sore? I feel like a heel, but I'm just not like you and Charlie, I guess. I—" "No, I understand, Mickey. I'm not sore, really." "Listen, then. You haven't accepted any offer yet, have you?" "No. I got a couple of possibilities. Could get a berth on the Odyssey , the new ship being finished at Los Angeles. They want me, too, for the Moon Patrol, but that's old stuff, not much better than teaching. I want to be in deep space." "Well, how about staying with us till you decide? Might as well enjoy Earth life while you can. Okay?" I felt like running from the house, to forget that it existed. I wanted someone to tell me one of the old stories about space, a tale of courage that would put fuel on dying dreams. But I wanted, also, to be with you, Laura, to see your smile and the flecks of silver in your eyes and the way your nose turned upward ever so slightly when you laughed. You see, I loved you already, almost as much as I loved the stars. And I said, slowly, my voice sounding unfamiliar and far away, "Sure, I'll stay, Mickey. Sure." Forty days of joy, forty nights of fear and indecision. We did all the little things, like watching the rockets land at White Sands and flying down to the Gulf to swim in cool waters. You tried, unsuccessfully, to teach me to dance, and we talked about Everson and Charlie and the Moon and the stars. You felt you had to give the stars all the beauty and promise of a child's dream, because you knew that was what I wanted. One morning I thought, Why must I make a choice? Why can't I have both you and the stars? Would that be asking too much? All day the thought lay in my mind like fire. That evening I asked you to marry me. I said it very simply: "Laura, I want you to be my wife." You looked up at Venus, and you were silent for a long while, your face flushed. Then you murmured, "I—I want to marry you, Ben, but are you asking me to marry a spaceman or a teacher?" "Can't a spaceman marry, too?" "Yes, a spaceman can marry, but what would it be like? Don't you see, Ben? You'd be like Charlie. Gone for maybe two months, maybe two years. Then you'd have a twenty-four hour liberty—and I'd have what?" Somehow I'd expected words like these, but still they hurt. "I wouldn't have to be a spaceman forever. I could try it for a couple of years, then teach." "Would you, Ben? Would you be satisfied with just seeing Mars? Wouldn't you want to go on to Jupiter and Saturn and Uranus and on and on?" Your voice was choked, and even in the semi-darkness I saw tears glittering in your eyes. "Do you think I'd dare have children, Ben? Mickey told me what happened on the Cyclops . There was a leak in the atomic engines. The ship was flooded with radiation—just for a second. It didn't seem serious. The men had no burns. But a year later the captain had a child. And it was—" "I know, Laura. Don't say it." You had to finish. "It was a monster." That night I lay awake, the fears and doubts too frantic to let me sleep. You've got to decide now , I told myself. You can't stay here. You've got to make a choice. The teaching job was still open. The spot on the Odyssey was still open—and the big ship, it was rumored, was equipped to make it all the way to Pluto. You can take Dean Dawson's job and stay with Laura and have kids and a home and live to see what happens in this world sixty years from now. Or you can see what's on the other side of the mountain. You can be a line in a history book. I cursed. I knew what Charlie would say. He'd say, "Get the hell out of there, boy. Don't let a fool woman make a sucker out of you. Get out there on the Odyssey where you belong. We got a date on Mars, remember? At the Space Rat , just off Chandler Field on the Grand Canal." That's what he'd say. And yet I wanted you, Laura. I wanted to be with you, always. "Oh God," I moaned, "what shall I do?" Next morning the door chimes pealed, and you went to the door and brought back the audiogram. It was addressed to me; I wondered who could be sending me a message. I pressed the stud on the little gray cylinder, and a rasping, automatic voice droned: "Luna City, Luna, July 27, 1995. Regret to inform you of death of Charles Taggart, Chief Jetman...." Then there was a Latin name which was more polite than the word "lung-rot" and the metallic phrase, "This message brought to you by courtesy of United Nations Earth-Luna Communication Corps." I stood staring at the cylinder. Charles Taggart was dead. Charles Taggart was Charlie. Stardust Charlie. My heart thudded crazily against my chest. It couldn't be! Not Charlie! The audiogram had lied! I pressed the stud again. "... regret to inform you of death of Charles ..." I hurled the cylinder at the wall. It thudded, fell, rolled. The broken voice droned on. You ran to it, shut it off. "I'm sorry, Ben, so terribly—" Without answering, I walked into my room. I knew it was true now. I remembered Charlie's coughing, his gaunt features, his drugged gaze. The metallic words had told the truth. I sat for a long time on my bed, crying inside, but staring dry-eyed at Charlie's faded tin box. Then, finally, I fingered his meager possessions—a few wrinkled photos, some letters, a small black statue of a forgotten Martian god, a gold service medal from the Moon Patrol. This was what remained of Charlie after twenty-five years in space. It was a bitter bargain. A statue instead of a wife, yellowed letters instead of children, a medal instead of a home. It'd be a great future , I thought. You'd dream of sitting in a dingy stone dive on the Grand Canal with sand-wasps buzzing around smoky, stinking candles. A bottle of luchu juice and a couple of Martian girls with dirty feet for company. And a sudden cough that would be the first sign of lung-rot. To hell with it! I walked into your living room and called Dean Dawson on the visiphone. I accepted that job teaching. And now, Laura, it's nearly midnight. You're in your room, sleeping, and the house is silent. It's hard to tell you, to make you understand, and that is why I am writing this. I looked through Charlie's box again, more carefully this time, reading the old letters and studying the photographs. I believe now that Charlie sensed my indecision, that he left these things so that they could tell me what he could not express in words. And among the things, Laura, I found a ring. A wedding ring. In that past he never talked about, there was a woman—his wife. Charlie was young once, his eyes full of dreams, and he faced the same decision that I am facing. Two paths were before him, but he tried to travel both. He later learned what we already know—that there can be no compromise. And you know, too, which path he finally chose. Do you know why he had to drug himself to watch me graduate? So he could look at me, knowing that I would see the worlds he could never live to see. Charlie didn't leave just a few trinkets behind him. He left himself, Laura, for he showed me that a boy's dream can also be a man's dream. He made his last trip to Luna when he knew he was going to die. Heaven knows how he escaped a checkup. Maybe the captain understood and was kind—but that doesn't matter now. Do you know why he wanted to reach Mars? Do you know why he didn't want to die in the clean, cool air of Earth? It was because he wanted to die nearer home. His home, Laura, was the Universe, where the ship was his house, the crew his father, mother, brothers, the planets his children. You say that the beauty of the other side of the mountain vanishes after you reach it. But how can one ever be sure until the journey is made? Could I or Charlie or the thousand before us bear to look upon a star and think, I might have gone there; I could have been the first ? We said, too, that the life of a spaceman is lonely. Yet how could one be lonely when men like Charlie roam the spaceways? Charlie wanted me to himself that night after graduation. He wanted us to celebrate as spacemen should, for he knew that this would be his last night on Earth. It might have seemed an ugly kind of celebration to you, but he wanted it with all his heart, and we robbed him of it. Because of these things, Laura, I will be gone in the morning. Explain the best you can to Mickey and to your parents and Dean Dawson. Right now I've got a date that I'm going to keep—at a dingy stone cafe on Mars, the Space Rat , just off Chandler Field on the Grand Canal. Stardust Charlie will be there; he'll go with me in memory to whatever part of the Galaxy I may live to reach. And so will you, Laura. I have two wedding rings with me—his wife's ring and yours.
|
B. Mickey is jealous of Ben's future job
|
Why didn't Julia pick up her suitcase with the other passengers?
A. Julia was detained by customs before she could get to the baggage claim.
B. Julia went to call her sister before collecting her suitcase.
C. Julia was told that her suitcase didn't make the flight when they were mid-air.
D. Julia didn't want to be near the suitcase when the bomb went off.
|
Nuts to wild talents! Mine was no satisfaction, never earned me a penny—and now it had me fighting for my life in ... THE LITTLE RED BAG By JERRY SOHL [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, January 1960. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] About an hour out of San Francisco on the flight to Los Angeles, I made the discovery. I had finished reading the Chronicle , folded and put it beside me, turned and looked out the window, expecting to see the San Joaquin Valley but finding only a sea of clouds instead. So I returned my attention to the inside of the plane, to the overstuffed gray-haired woman asleep beside me, to the backs of heads in seats before me, across the aisle to other heads, and down to the blonde. I had seen her in the concourse and at the gate, a shapely thing. Now she had crossed her legs and I was privileged to view a trim ankle and calf, and her profile as she stared moodily across the aisle and out a window where there was nothing to see. I slid my eyes past her to others. A crossword-puzzle worker, a togetherness-type-magazine reader. Inventory completed, I went back to looking at the clouds, knowing I should be thinking about the printing order I was going to Los Angeles for, and not wanting to. So I started going through the purse of the woman next to me. Perhaps that sounds bad. It wasn't. I'd been doing it for years and nobody ever complained. It started when I was a kid, this business of being able to explore the insides of things like purses and sealed boxes and locked drawers and—well, human beings. But human beings aren't worth the trouble. It's like swimming through spaghetti. And I've got to stay away from electric wires. They hurt. Now don't ask me how they hurt. Maybe you think it's fun. For the most part, it really isn't. I always knew what was in Christmas presents before I unwrapped them, and therefore Christmas was always spoiled for me as a kid. I can't feel the color of anything, just its consistency. An apple senses about the same as a potato, except for the core and the stem. I can't even tell if there's writing on a piece of paper. So you see it isn't much. Just the feel of shapes, the hardnesses and softnesses. But I've learned to become pretty good at guessing. Like this woman next to me. She had a short, cylindrical metal object in her purse with waxlike stuff inside it—a lipstick. A round, hard object with dust inside—a compact. Handkerchief, chewing gum, a small book, probably an address book, money in a change purse—a few bills and coins. Not much else. I was a little disappointed. I've run across a gun or two in my time. But I never say anything. I learned the wisdom of keeping my mouth shut in the fourth grade when Miss Winters, a stern, white-haired disciplinarian, ordered me to eat my sack lunch in the classroom with her instead of outside with some of the other kids. This was the punishment for some minor infraction. Lunchtime was nearly over and we'd both finished eating; she said she'd be gone for a few moments and that I was to erase the blackboard during her absence, which I dutifully did. Class had hardly resumed when she started looking around the desk for her favorite mechanical pencil, asking if any of us had seen it, and looking straight at me. I didn't want her to think I had taken it while she was out of the room, so I probed the contents of her purse, which she always kept in the upper right drawer of her desk. "It's in your purse," I blurted out. I was sent home with a stinging note. Since then I've kept quiet. At one time I assumed everybody was able to sense. I've known better for years. Still, I wonder how many other people are as close-mouthed about their special gift as I am about mine. I used to think that some day I'd make a lot of money out of it, but how? I can't read thoughts. I can't even be sure what some of the things I sense in probing really are. But I've learned to move things. Ever so little. A piece of paper. A feather. Once I stopped one of those little glass-enclosed light or heat-powered devices with vanes you see now and then in a jeweler's window. And I can stop clocks. Take this morning, for example. I had set my alarm for five-thirty because I had to catch the seven o'clock plane at San Francisco International Airport. This being earlier than I usually get up, it seems all I did during the night was feel my way past the escapement and balance wheel to see where the notch for the alarm was. The last time I did it there was just the merest fraction of an inch between the pawl and the notch. So I sighed and moved to the balance wheel and its delicate ribbon of spiraling steel. I hung onto the wheel, exerting influence to decrease the restoring torque. The wheel slowed down until there was no more ticking. It took quite a bit of effort, as it always does, but I did it, as I usually do. I can't stand the alarm. When I first learned to do this, I thought I had it made. I even went to Las Vegas to try my hand, so to speak, with the ratchets and pawls and cams and springs on the slot machines. But there's nothing delicate about a slot machine, and the spring tensions are too strong. I dropped quite a lot of nickels before I finally gave up. So I'm stuck with a talent I've found little real use for. Except that it amuses me. Sometimes. Not like this time on the plane. The woman beside me stirred, sat up suddenly and looked across me out the window. "Where are we?" she asked in a surprised voice. I told her we were probably a little north of Bakersfield. She said, "Oh," glanced at her wristwatch and sank back again. Soon the stewardesses would bring coffee and doughnuts around, so I contented myself with looking at the clouds and trying to think about Amos Magaffey, who was purchasing agent for a Los Angeles amusement chain, and how I was going to convince him our printing prices were maybe a little higher but the quality and service were better. My mind wandered below where I was sitting, idly moving from one piece of luggage to another, looking for my beat-up suitcase. I went through slips and slippers, lingerie and laundry, a jig saw puzzle and a ukulele. I never did find my suitcase because I found the bomb first. The bomb was in a small bag—a woman's bag judging by the soft, flimsy things you'd never find in a man's—and I didn't know it was a bomb right away. I thought it was just a clock, one of those small, quiet alarms. I was going to pass it by and go on, but what held me was that something was taped to it. By the feel, I knew it must be electrician's tape. Interested and curious, I explored the clock more closely, found two wires. One went to a battery and the other to hard round cylinders taped together. The hairs stood up at the base of my neck when I suddenly realized what it was. The clock's balance wheel was rocking merrily. Quickly I went up past the train of gears to the alarm wheel. If this was anything like my own alarm clock, this one had something like ten minutes to go. It was forty minutes to Burbank and Lockheed Air Terminal. My mind was churning when I turned from the window to look around at the unconcerned passengers, the woman at my side asleep again. I thought: Which one of these.... No, none of them would know it was there. I glanced out the window again; clouds were still in the way. We'd be leaving the valley for the mountain range north of Los Angeles soon, if we hadn't left it already. No place to land the plane there. But of course that had been the plan! My heart was beating in jackhammer rhythm; my mouth was dry and my mind was numb. Tell somebody about the bomb before it's too late! No, they'd think I put it there. Besides, what good would it do? There would be panic and they'd never get the plane down in time—if they believed me. "Sir." My head jerked around. The stewardess stood in the aisle, smiling, extending a tray to me, a brown plastic tray bearing a small paper cup of tomato juice, a cup of coffee, a cellophane-wrapped doughnut, paper spoon, sugar and dehydrated cream envelopes, and a napkin. I goggled at her, managed to croak, "No, thanks." She gave me an odd look and moved along. My seatmate had accepted hers and was tearing at the cellophane. I couldn't bear to watch her. I closed my eyes, forced my mind back to the luggage compartment, spent a frantic moment before I found the bag again. I had to stop that balance wheel, just as I stopped my alarm clock every morning. I tried to close everything off—the throb of engines, the rush of air, the woman sipping coffee noisily beside me—and I went into the clock and surrounded the seesawing wheel. When it went forward, I pulled it back; when it went back, I pulled it forward. I struggled with it, and it was like trying to work with greasy hands, and I was afraid I wasn't going to be able to stop it. Then, little by little, it started to slow its beat. But I could not afford to relax. I pushed and pulled and didn't dare release my hold until it came to a dead stop. "Anything the matter?" My eyelids flew open and I looked into the eyes of the woman next to me. There was sugar from the doughnut around her mouth and she was still chewing. "No," I said, letting out my breath. "I'm all right." "You were moaning, it sounded like. And you kept moving your head back and forth." "Must have been dreaming," I said as I rang for the stewardess. When she came I told her I'd take some of that coffee now. No, nothing else, just coffee. I didn't tell her how much I needed it. I sat there clammy with sweat until she returned. Coffee never tasted so good. All right, so I had stopped the bomb's timer. My mind raced ahead to the landing. When they unloaded the luggage, the balance wheel would start again. I wouldn't be able to stay with it, keeping it still. I considered telling the authorities as soon as we landed, or maybe calling in ahead, but wouldn't that just bring suspicion, questions. Maybe I could convince them I could stop a clock—but not before the bomb exploded. And then what? My secret would be out and my life would be changed. I'd be a man not to be trusted, a prying man, a man literally with gimlet eyes. Mountain crags jutted through the clouds. We were in the range north of the city. Here and there were clear spots and I could see roads below, but there were also clouds far above us. It was very beautiful, but it was also very bumpy, and we started to slip and slide. To my horror I found that the balance wheel was rocking again. Closing my eyes and gritting my teeth, I forced my senses to the wheel, tugging and pulling and shoving and pushing until it finally stopped. A jab in the shoulder. I jumped, startled. "Your cup," my seat partner said, pointing. I looked down at the coffee cup I had crushed in my hands. Then I looked up into the eyes of the stewardess. I handed it to her. She took it without a word and went away. "Were you really asleep that time?" "Not really," I said. I was tempted to tell the woman I was subject to fits, but I didn't. It was only a few minutes to landing, but they became the longest minutes of my life as time after time I stopped the rocking wheel when the plane dipped and bumped to a landing. Leaving the apron with the other passengers, I tried to walk as unconcernedly as they through the exit gate. I would have liked walking through the terminal and out the entrance and away, but I could not. I had my suitcase to get, for one thing. The damned bomb was the other. So I strolled out into the concourse again to look at the plane and watch the baggagemen at work, transferring the luggage to two airfield carts. They weren't as careful as I would have been. It was impossible to tell from this distance just which bag contained the bomb; I could hardly identify my own scarred suitcase. The assortment of bags—a strange conglomeration of sizes and colors—was packed in some places six deep, and it rolled toward the gate where I was standing. I didn't know whether to stay or run, imagining the balance wheel now happily rocking again. The load went past me down a ramp to the front of the air terminal where the luggage was unloaded and placed in a long rack. I went with it. There was a flurry of ticket matching, hands grabbing for suitcases, and a general exodus on the part of my fellow passengers, too fast to determine who had got the one with the bomb. Now all that was left was the attendant and I had two bags—my own battered veteran of years, and a fine new red overnight case, small enough to be the one. I lit a cigarette, reached out. Inside were a woman's things and—a clock. The escapement was clicking vigorously. I didn't moan this time. I just closed my eyes, stretched toward and grabbed the balance wheel I was getting to know like my own. I entered into a union with it so strong that after I had reduced it to immobility, it was like waking when I opened my eyes. The baggage claim attendant was staring at me. For only a moment I stared back. Then I quickly reached for my baggage check and presented it to him. His hand hovered over the handle of the little red bag and I was ready to yell at him. But then, matching numbers on the tags with his eyes, his hand grasped the handle of my own suitcase and pushed it toward me. "Thanks," I said, taking it. I glanced ever so casually toward the remaining bag. "One left over, eh?" "Yeah." He was so bored I was tempted to tell him what was in it. But he was eying me with a "well-why-don't-you-get-along?" look. I said, "What happens if nobody claims it?" "Take it inside. Why?" He was getting too curious. "Oh, I just wondered, that's all." I stepped on my cigarette and walked toward the air terminal entrance and put my suitcase on the stone steps there. A redcap came hurrying over. "Cab?" I shook my head. "Just waiting." Just waiting for somebody to pick up a bomb. I lit another cigarette and glanced now and then toward the baggage claim area. The red bag was still there. All sorts of theories ran through my head as to why it should still be there, and none satisfied me. I should not have been there, that much I knew; I should be with a man named Amos Magaffey on Sixth Street at ten o'clock, discussing something very mundane, the matter of a printing order. But what could I do? If I left the airport, the attendant would eventually take the bag inside and there would be an explosion, and I wouldn't be able to live with myself. No. I had to stay to keep the balance wheel stationary until—until what? A man in tan gabardine, wearing a police cap and badge, walked out of the entrance to stand on the stone steps beside me while he put on a pair of dark glasses. A member of the airport police detail. I could tell him. I could take him down to the little red bag and explain the whole thing. Then it would be his baby and I would be off on my own business. But he moved on down the steps, nodded at the redcap, and started across the street to the parking area. I could have called to him, "Hey, officer, let me tell you about a bomb in a little red bag." But I didn't. I didn't because I caught a movement at the baggage claim counter out of the side of my eye. The attendant had picked up the bag and was walking with it up the ramp to the rear of the air terminal. Picking up my own suitcase, I went inside in time to see him enter through a side door and deposit the bag on the scales at the airline desk and say something to the clerk. The clerk nodded and moved the bag to the rear room. I could visualize the balance wheel once again rocking like crazy. How many minutes—or seconds—were left? I was sweating when I moved to the counter, and it wasn't because of the sunshine I'd been soaking in. I had to get as close to the bag as I could if I was going to stop the clock again. "Can I help you?" the clerk asked. "No. I'm waiting for someone." I turned my back to him, put down my suitcase, leaned against the counter and reached out for the wheel. I found I could reach the device, but it was far away. When I tried to dampen it, the wheel escaped my grasp. "Do you have my suitcase?" I blinked my eyes open and looked around. The blonde in the plane stood there looking very fresh and bright and unconcerned. In her right hand she had a green baggage claim check. The clerk took it, nodded, and in a moment brought out the overnight case and set it on the scales. The girl thanked him, picked it up, glanced at me indifferently, and then started for the entrance with it. "Just a moment," I found myself saying, grabbing my bag and hurrying after her. At her side and a little ahead of her, I said, "Listen to me." She looked annoyed and increased her stride toward the door. "It's a matter of life or death," I said. I wanted to wrest the bag from her and hurl it out through the doorway into the street, but I restrained myself. She stopped and stared. I noticed a short, fat man in a rumpled suitcoat and unpressed pants staring, too. Ignoring him, I said, "Please put the bag down. Over there." I indicated a spot beside a telephone booth where it would be out of the way. She didn't move. She just said, "Why?" "For God's sake!" I took the case. She offered no resistance. I put her bag and mine next to the booth. When I turned around she was standing there looking at me as if I had gone out of my mind. Her eyes were blue and brown-flecked, very pretty eyes, and my thought at the moment was, I'm glad the bomb didn't go off; these eyes wouldn't be looking at me or anything else right now if it had. "I've got to talk to you. It's very important." The girl said, "Why?" I was beginning to think it was the only word she knew. At the same time I was wondering why anyone would want to kill someone so lovely. "I'll explain in a moment. Please stand right here while I make a telephone call." I moved toward the phone booth, paused and said, "And don't ask me why." She gave me a speculative look. I must not have seemed a complete idiot because she said, "All right, but—" I didn't listen for the rest. I went into the booth, closed the door, pretended to drop a coin and dial a number. But all the time I was in there, I was reaching out through the glass for the clock. At this range it wasn't difficult to stop the balance wheel. Just the same, when I came out I was wringing wet. "Now will you please tell me what this is all about?" she said stiffly. "Gladly. Let me buy you a cup of coffee and I'll explain." She glanced at the bags. I told her they'd be all right. We followed the short, fat man into the coffee shop. Over coffee I explained it all to her, how I had this extrasensory ability, how she was the first person I had ever revealed it to, and how I had discovered what was in her overnight bag. During the telling, her untouched coffee grew a skin, her face grew pale, her eyes grew less curious and more troubled. There were tears there when I finished. I asked her who put the bomb in her bag. "Joe did," she said in a toneless voice, not looking at me any more but staring vacantly across the room. "Joe put it there." Behind her eyes she was reliving some recent scene. "Who is Joe?" "My husband." I thought she was going to really bawl, but she got control again. "This trip was his idea, my coming down here to visit my sister." Her smile was bleak. "I see now why he wanted to put in those books. I'd finished packing and was in the bathroom. He said he'd put in some books we'd both finished reading—for my sister. That's when he must have put the—put it in there." I said gently, "Why would he want to do a thing like that?" "I don't know." She shook her head. "I just don't know." And she was close to bawling again. Then she recovered and said, "I'm not sure I want to know." I admired her for saying it. Joe must have been crazy. "It's all right now?" she asked. I nodded. "As long as we don't move it." I told her I didn't know how much more time there was, that I'd been thinking it over and that the only way out seemed to be to tell the airport policeman. After I explained it to her, the girl—she said her name was Julia Claremont—agreed to tell him she thought there was a bomb in her bag, that she had noticed a ticking and had become worried because she knew she hadn't packed a clock. It wasn't good, but it would have to do. "We've got to get it deactivated," I said, watching the fat man pay for his coffee and leave. "The sooner the better." I finished my coffee in one gulp and went to pay the bill with her. I asked her why she didn't claim the bag at the same time the other people had. She said she had called her sister and the phone was busy for a long while. "She was supposed to meet me, and when she wasn't here, I got worried. She said she isn't feeling well and asked me to take a cab." She smiled a little. It was a bright, cheery thing. I had the feeling it was all for me. "That's where I was going when you caught up with me." It had become a very nice day. But the bottom dropped out of it again when we reached the lobby. The two bags weren't there. I ran to the entrance and nearly collided with the redcap. "See anybody go out of here with a little red bag and an old battered suitcase?" "Bag? Suitcase?" he mumbled. Then he became excited. "Why, a man just stepped out of here—" He turned to look down the street. "That's him." The dumpy man I'd seen was walking off; Julia's bag in his right hand, mine in his left. He seemed in no hurry. "Hey!" I shouted, starting toward him. The man turned, took one look at me, and started to run. He came abreast an old gray, mud-spattered coupe, ran around, opened the door and threw both bags into the rear seat as he got in. The car was a hundred feet away and gathering speed by the time I reached where it had been parked. I watched it for a moment, then walked back to the entranceway where Julia was standing with the redcap, who said, "That man steal them suitcases?" "That he did," I said. Just then the airport policeman started across the street from the parking lot. Redcap said, "Better tell him about it." The policeman was sympathetic and concerned. He said, "We'd better get over to the office." But we never left the spot because an explosion some blocks distant shattered the air. Julia's hand grasped my arm. Hard. "Jets," the redcap said, eying the sky. "I don't know," the policeman said. "Didn't sound much like a jet to me." We stood there. I could visualize the wreckage of an old gray coupe in the middle of a street, but I couldn't visualize the driver. That was all right. I didn't want to see him. I didn't know what Julia was thinking. She said, "About those bags," and looked at me. The officer said, "Yes, miss?" "I—I don't care about mine. I didn't have much of anything in it." "I feel the same way," I said. "Would it be all right if we didn't bother to report it?" "Well," the policeman said, "I can't make you report it." "I'd rather not then," Julia said. She turned to me. "I'd like some air. Can't we walk a little?" "Sure," I said. We started down the street, her arm in mine, as the air began to fill with the distant sounds of sirens.
|
B. Julia went to call her sister before collecting her suitcase.
|
How did Doggo feel about their plan?
A. Hesitant for it to happen so soon
B. Reluctant at first but then confident
C. Worried for the queen
D. He trusted Myles, so he knew it would work
|
THE RADIO PLANET Ralph Milne Farley I “It’s too bad that Myles Cabot can’t see this!” I exclaimed, as my eye fell on the following item: SIGNALS FROM MARS FAIL TO REACH HARVARD Cambridge, Massachusetts, Wednesday. The Harvard College Radio Station has for several weeks been in receipt of fragmentary signals of extraordinarily long wave-length, Professor Hammond announced yesterday. So far as it has been possible to test the direction of the source of these waves, it appears that the direction has a twenty-four hour cycle, thus indicating that the origin of these waves is some point outside the earth. The university authorities will express no opinion as to whether or not these messages come from Mars. Myles, alone of all the radio engineers of my acquaintance, was competent to surmount these difficulties, and thus enable the Cambridge savants to receive with clearness the message from another planet. 6 Twelve months ago he would have been available, for he was then quietly visiting at my farm, after five earth-years spent on the planet Venus, where, by the aid of radio, he had led the Cupians to victory over their oppressors, a human-brained race of gigantic black ants. He had driven the last ant from the face of continental Poros, and had won and wed the Princess Lilla, who had borne him a son to occupy the throne of Cupia. While at my farm Cabot had rigged up a huge radio set and a matter-transmitting apparatus, with which he had (presumably) shot himself back to Poros on the night of the big October storm which had wrecked his installation. I showed the newspaper item to Mrs. Farley, and lamented on Cabot’s absence. Her response opened up an entirely new line of thought. Said she: “Doesn’t the very fact that Mr. Cabot isn’t here suggest to you that this may be a message, not from Mars, but from him? Or perhaps from the Princess Lilla, inquiring about him in case he has failed in his attempted return?” That had never occurred to me! How stupid! “What had I better do about it, if anything?” I asked. “Drop Professor Hammond a line?” But Mrs. Farley was afraid that I would be taken for a crank. That evening, when I was over in town, the clerk in the drug store waylaid me to say that there had been a long-distance phone call for me, and would I please call a certain Cambridge number. So, after waiting an interminable time in the stuffy booth with my hands full of dimes, nickels, and quarters, I finally got my party. “Mr. Farley?” “Speaking.” “This is Professor Kellogg, O. D. Kellogg,” the voice replied. 7 It was my friend of the Harvard math faculty, the man who had analyzed the measurements of the streamline projectile in which Myles Cabot had shot to earth the account of the first part of his adventures on Venus. Some further adventures Myles had told me in person during his stay on my farm. “Professor Hammond thinks that he is getting Mars on the air,” the voice continued. “Yes,” I replied. “I judged as much from what I read in this morning’s paper. But what do you think?” Kellogg’s reply gave my sluggish mind the second jolt which it had received that day. “Well,” he said, “in view of the fact that I am one of the few people among your readers who take your radio stories seriously, I think that Hammond is getting Venus. Can you run up here and help me try and convince him?” And so it was that I took the early boat next morning for Boston, and had lunch with the two professors. As a result of our conference, a small committee of engineers returned with me to Edgartown that evening for the purpose of trying to repair the wrecked radio set which Myles Cabot had left on my farm. They utterly failed to comprehend the matter-transmitting apparatus, and so—after the fallen tower had been reerected and the rubbish cleared away—they had devoted their attention to the restoration of the conversational part of the set. To make a long story short, we finally restored it, with the aid of some old blue prints of Cabot’s which Mrs. Farley, like Swiss Family Robinson’s wife, produced from somewhere. I was the first to try the earphones, and was rewarded by a faint “bzt-bzt” like the song of a north woods blackfly. In conventional radioese, I repeated the sounds to the Harvard group: “Dah-dit-dah-dit dah-dah-dit-dah. Dah-dit-dah-dit dah-dah-dit-dah. Dah-dit-dah-dit dah-dah-dit-dah. Dah-dit-dit dit. Dah-dit-dah-dit dit-dah dah-dit dit dit dah-dah-dah dah. Dah-dit-dah-dit dit-dah dah-dit-dit-dit dah-dah-dah dah. Dah-dit-dah-dit dit-dah dah-dit-dit-dit-dah dah-dah-dah.” 8 A look of incredulity spread over their faces. Again came the same message, and again I repeated it. “You’re spoofing us!” one of them shouted. “Give me the earphones.” And he snatched them from my head. Adjusting them on his own head, he spelled out to us, “C-Q C-Q C-Q D-E C-A-B-O-T C-A-B-O-T C-A-B-O-T—” Seizing the big leaf-switch, he threw it over. The motor-generator began to hum. Grasping the key, the Harvard engineer ticked off into space: “Cabot Cabot Cabot D-E—” “Has this station a call letter?” he hurriedly asked me. “Yes,” I answered quickly, “One-X-X-B.” “One-X-X-B,” he continued the ticking “K.” Interplanetary communication was an established fact at last! And not with Mars after all these years of scientific speculations. But what meant more to me was that I was again in touch with my classmate Myles Standish Cabot, the radio man. The next day a party of prominent scientists, accompanied by a telegrapher and two stenographers, arrived at my farm. During the weeks that followed there was recorded Myles’s own account of the amazing adventures on the planet Venus (or Poros, as its own inhabitants call it,) which befell him upon his return there after his brief visit to the earth. I have edited those notes into the following coherent story. II TOO MUCH STATIC Myles Cabot had returned to the earth to study the latest developments of modern terrestrial science for the benefit of the Cupian nation. He was the regent of Cupia during the minority of his baby son, King Kew the Thirteenth. The loyal Prince Toron occupied the throne in his absence. The last of the ant-men and their ally, the renegade Cupian Prince Yuri, had presumably perished in an attempt to escape by flying through the steam-clouds which completely hem in continental Poros. What lay beyond the boiling seas no man knew. 9 During his stay on my farm, Cabot had built the matter-transmitting apparatus, with which he had shot himself off into space on that October night on which he had received the message from the skies: “S O S, Lilla.” A thunderstorm had been brewing all that evening, and just as Myles had placed himself between the coordinate axes of his machine and had gathered up the strings which ran from his control levers to within the apparatus, there had come a blinding flash. Lightning had struck his aerial. How long his unconsciousness lasted he knew not. He was some time in regaining his senses. But when he had finally and fully recovered, he found himself lying on a sandy beach beside a calm and placid lake beneath a silver sky. He fell to wondering, vaguely and pleasantly, where he was and how he had got here. Suddenly, however, his ears were jarred by a familiar sound. At once his senses cleared, and he listened intently to the distant purring of a motor. Yes, there could be no mistake; an airplane was approaching. Now he could see it, a speck in the sky, far down the beach. Nearer and nearer it came. Myles sprang to his feet. To his intense surprise, he found that the effort threw him quite a distance into the air. Instantly the idea flashed through his mind: “I must be on Mars! Or some other strange planet.” This idea was vaguely reminiscent of something. But while he was trying to catch this vaguely elusive train of thought, his attention was diverted by the fact that, for some unaccountable reason, his belt buckle and most of the buttons which had held his clothes together were missing, so that his clothing came to pieces as he rose, and that he had to shed it rapidly in order to avoid impeding his movements. He wondered at the cause of this. 10 But his speculations were cut short by the alighting of the plane a hundred yards down the beach. What was his horror when out of it clambered, not men but ants! Ants, six-footed, and six feet high. Huge ants, four of them, running toward him over the glistening sands. Gone was all his languor, as he seized a piece of driftwood and prepared to defend himself. As he stood thus expectant, Myles realized that his present position and condition, the surrounding scenery, and the advance of the ant-men were exactly, item for item, like the opening events of his first arrival on the planet Poros. He even recognized one of the ant-men as old Doggo, who had befriended him on his previous visit. Could it be that all his adventures in Cupia had been naught but a dream; a recurring dream, in fact? Were his dear wife Lilla and his little son Kew merely figments of his imagination? Horrible thought! And then events began to differ from those of the past; for the three other Formians halted, and Doggo advanced alone. By the agitation of the beast’s antennae the earth man could see that it was talking to him. But Myles no longer possessed the wonderful electrical headset which he had contrived and built during his previous visit to that planet, so as to talk with Cupians and Formians, both of which races are earless and converse by means of radiations from their antennae. So he picked up two sticks from the beach, and held them projecting from his forehead; then threw them to the ground with a grimace of disgust and pointed to his ears. Doggo understood, and scratched with his paw in Cupian shorthand on the silver sands the message: “Myles Cabot, you are our prisoner.” “What, again?” scratched Myles, then made a sign of submission. 11 He dreaded the paralyzing bite which Formians usually administer to their victims, and which he had twice experienced in the past; but, fortunately, it was not now forthcoming. The other three ants kept away from him as Doggo led him to the beached airplane, and soon they were scudding along beneath silver skies, northward as it later turned out. Far below them were silver-green fields and tangled tropical woods, interspersed with rivulets and little ponds. This was Cupia, his Cupia. He was home once more, back again upon the planet which held all that was dear to him in two worlds. His heart glowed with the warmth of homecoming. What mattered it that he was now a prisoner, in the hands (or, rather, claws) of his old enemies, the Formians? He had been their prisoner before, and had escaped. Once more he could escape, and rescue the Princess Lilla. Poor girl! How eager he was to reach her side, and save her from that peril, whatever it was, which had caused her to flash that “S O S” a hundred million miles across the solar system from Poros to the earth. He wondered what could have happened in Cupia since his departure, only a few sangths ago. How was it that the ant-men had survived their airplane journey across the boiling seas? What had led them to return? Or perhaps these ants were a group who had hidden somewhere and thus had escaped the general extermination of their race. In either event, how had they been able to reconquer Cupia? And where was their former leader, Yuri, the renegade Cupian prince? These and a hundred other similar questions flooded in upon the earth-man, as the Formian airship carried him, a captive, through the skies. He gazed again at the scene below, and now noted one difference from the accustomed Porovian landscape, for nowhere ran the smooth concrete roads which bear the swift two-wheeled kerkools of the Cupians to all parts of their continent. What uninhabited portion of Cupia could this be, over which they were now passing? 12 Turning to Doggo, Myles extended his left palm, and made a motion as though writing on it with the thumb and forefinger of his right hand. But the ant-man waved a negative with one of his forepaws. It was evident that there were no writing materials aboard the ship. Myles would have to wait until they reached their landing place; for doubtless they would soon hover down in some city or town, though just which one he could not guess, as the country below was wholly unfamiliar. Finally a small settlement loomed ahead. It was of the familiar style of toy-building-block architecture affected by the ant-men, and, from its appearance, was very new. On its outskirts further building operations were actively in progress. Apparently a few survivors of the accursed race of Formians were consolidating their position and attempting to build up a new empire in some out-of-the-way portion of the continent. As the earth-man was turning these thoughts over in his mind the plane softly settled down upon one of the flat roofs, and its occupants disembarked. Three of the ants advanced menacingly toward Myles, but Doggo held them off. Then all of the party descended down one of the ramps to the lower levels of the building. Narrow slitlike window openings gave onto courtyards, where fountains played and masses of blue and yellow flowers bloomed, amid gray-branched lichens with red and purple twig-knobs. It was in just such a garden, through just such a window, that he had first looked upon the lovely blue-eyed, golden-haired Lilla, Crown Princess of Cupia. The earth-man sighed. Where was his beloved wife now? That she needed his help was certain. He must therefore get busy. So once again he made motions of writing on the palm of his left hand with the thumb and forefinger of his right; and this time the sign language produced results, for Doggo halted the procession and led Cabot into a room. 13 It was a plain bare room, devoid of any furniture except a small table, for ant-men have no use for chairs and couches. The sky outside was already beginning to pinken with the unseen sun. With a sweep of his paw, Doggo indicated that this was to be Cabot’s quarters. Then, with another wave, he pointed to the table, where lay a pad of paper and stylus, not a pencil-like stylus as employed by the Cupians, but rather one equipped with straps for attaching it to the claw of a Formian. Even so, it was better than nothing. The earth-man seized it eagerly, but before he could begin writing an ant entered bearing a Cupian toga, short-sleeved and bordered with Grecian wave designs in blue. Myles put on this garment, and then quickly filled a sheet with questions: “How is my princess and my son, the baby king? Whence come all you Formians, whose race I thought had been exterminated? What part of Cupia is this? What is this city? Where is Prince Yuri? And what do you intend to do with me this time?” Then he passed the paper and stylus over to his old friend Doggo. They were alone together at last. The ant-man’s reply consumed sheet after sheet of paper; but, owning to the rapidity of Porovian shorthand, did not take so very much more time than speaking would have required. As he completed each sheet he passed it over to Myles, who read as follows: “As to your princess and your son, I know not, for this is not Cupia. Do you remember how, when your victorious army and air navy swept to the southern extremity of what had been Formia, a few of our survivors rose in planes from the ruins of our last stronghold and braved the dangers of the steam clouds which overhang the boiling seas? Our leader was Prince Yuri, erstwhile contender for the throne of Cupia, splendid even in defeat. “It was his brain that conceived our daring plan of escape. If there were other lands beyond the boiling seas, the lands which tradition taught were the origin of the Cupian race, then there we might prosper and raise up a new empire. At the worst we should merely meet death in another form, rather than at your hands. So we essayed. 14 “Your planes followed us, but turned back as we neared the area of terrific heat. Soon the vapor closed over us, blotting our enemies and our native land from view.” For page after page Doggo, the ant-man, related the harrowing details of that perilous flight across the boiling seas, ending with the words: “Here we are, and here are you, in Yuriana, capitol of New Formia. But how is it that you, Myles Cabot, have arrived here on this continent in exactly the same manner and condition in which I discovered you in old Formia eight years ago?” When Myles reached the end of reading this narrative, he in turn took the pad and stylus and related how he had gone to the planet Minos (which we call the Earth) to learn the latest discoveries and inventions there, and how his calculations for his return to Poros had been upset by some static conditions just as he had been about to transmit himself back. Oh, if only he had landed by chance upon the same beach as on his first journey through the skies! Wisely he refrained from mentioning the “S O S” message from Lilla. But his recollection of her predicament spurred him to be anxious about her rescue. His immediate problem was to learn what the ant-men planned for him; so the concluding words which he wrote upon the pad were: “And, now that you have me in your power, what shall you do with me?” “Old friend,” Doggo wrote in reply, “that depends entirely upon Yuri, our king, whose toga you now have on.” III YURI OR FORMIS? The earth-man grimaced, but then smiled. Perhaps, his succeeding to the toga of King Yuri might prove to be an omen. 15 “So Yuri is king of the ants?” he asked. “Yes,” his captor replied, “for Queen Formis did not survive the trip across the boiling seas.” “Then what of your empire?” Myles inquired. “No queen. No eggs. How can your race continue? For you Formians are like the ants on my own planet Minos.” Doggo’s reply astounded him. “Do you remember back at Wautoosa, I told you that some of us lesser Formians had occasionally laid eggs? So now behold before you Doggo, Admiral of the Formian Air Navy, and mother of a new Queen Formis.” This was truly a surprise! All along Cabot had always regarded the Formians as mannish. And rightly so, for they performed in their own country the duties assigned to men among the Cupians. Furthermore, all Formians, save only the reigning Formis herself, were called by the Porovian pronoun, which corresponds to “he” in English. When Myles had somewhat recovered from his astonishment, he warmly congratulated his friend by patting him on the side of the head, as is the Porovian custom. “Doggo,” he wrote, “this ought to constitute you a person of some importance among the Formians.” “It ought to,” the ant-man replied, “but as a matter of fact, it merely intensifies Yuri’s mistrust and hatred of me. Now that I am mother of the queen, he fears that I may turn against him and establish Formis in his place as the head of an empire of the Formians, by the Formians, and for the Formians exclusively.” “Why don’t you?” Myles wrote. It seemed to him to be a bully good idea, and incidentally a solution of his own difficulties. But Doggo wrote in horror, “It would be treason!” Then tore up all the correspondence. It is difficult to inculcate the thought of independence in the mind of one reared in an autocracy. The earth-man, however, persisted. “How many of the council can you count on, if the interests of Yuri should clash with those of Formis?” 16 “Only one—myself.” And again Doggo tore up the correspondence. Myles tactfully changed the subject. “Where is the arch-fiend now?” he asked. “We know not,” the Formian wrote in reply. “Six days ago he left us in his airship and flew westward. When he failed to return, we sent out scout planes to search for him, and we have been hunting ever since. When we sighted you on the beach this morning we thought that you might be our lost leader, and that is why we landed and approached you.” At about this point the conversation was interrupted by a worker ant who brought food: roast alta and green aphid milk. With what relish did the earth-man plunge into the feast, his first taste of Porovian delicacies in many months. During the meal conversation lagged, owing to the difficulty of writing and eating at the same time. But now Myles Cabot seized his pad and stylus and wrote: “Have you ever known me to fail in any undertaking on the planet Poros?” “No,” the ant-man wrote in reply. “Have you ever known me to be untrue to a principle, a cause, or a friend?” “No,” Doggo replied. “Then,” Myles wrote, “let us make your daughter queen in fact as well as in name.” “It is treason,” Doggo wrote in reply, but this time he did not tear up the correspondence. “Treason?” Myles asked. If he had spoken the word, he would have spoken it with scorn and derision. “Treason? Is it treason to support your own queen? What has become of the national pride of the once great Formians? Look! I pledge myself to the cause of Formis, rightful Queen of Formia. Formis, daughter of Doggo! What say you?” This time, as he tore up the correspondence, Doggo signified an affirmative. And thus there resulted further correspondence. 17 “Doggo,” Myles wrote, “can you get to the antenna of the queen?” The ant-man indicated that he could. “If she has inherited any of your character,” Myles continued, “she will assert herself, if given half a chance.” So the Pitmanesque conversation continued. Long since had the pink light of Porovian evening faded from the western sky. The ceiling vapor-lamps were lit. The night showed velvet-black through the slit-like windows. And still the two old friends wrote on, Myles Standish Cabot, the Bostonian, and Doggo, No. 334-2-18, the only really humanlike ant-man whom Myles had ever known among the once dominant race of Poros. Finally, as the dials indicated midnight, the two conspirators ceased their labors. All was arranged for the coup d’ etat . They tore into shreds every scrap of used paper, leaving extant merely the ant-man’s concluding words: “Meanwhile you are my prisoner.” Doggo then rang a soundless bell, which was answered by a worker ant, whom he inaudibly directed to bring sufficient draperies to form a bed for the earth-man. These brought, the two friends patted each other a fond good night, and the tired earth-man lay down for the first sleep which he had had in over forty earth hours. It hardly seemed possible! Night before last he had slept peacefully on a conventional feather-bed in a little New England farmhouse. Then had come the S O S message from the skies; and here he was now, millions of miles away through space retiring on matted silver felting on the concrete floor of a Porovian ant-house. Such are the mutations of fortune! With these thoughts the returned wanderer lapsed into a deep and dreamless sleep. When he awakened in the morning there was a guard posted at the door. 18 Doggo did not show up until nearly noon, when he rattled in, bristling with excitement. Seizing the pad he wrote: “A stormy session of the Council of Twelve! We are all agreed that you must be indicted for high crimes and misdemeanors. But the great question is as to just what we can charge you with.” “Sorry I can’t assist you,” the earth-man wrote. “How would it be if I were to slap your daughter’s face, or something? Or why not try me for general cussedness?” “That is just what we finally decided to do,” the ant-man wrote in reply. “We shall try you on general principles, and let the proper accusation develop from the evidence. “At some stage of the proceedings it will inevitably occur to some member of the council to suggest that you be charged with treason to Yuri, whereupon two members of the council, whom I have won over to the cause of my daughter, will raise the objection that Yuri is not our king. This will be the signal for the proclaiming of Queen Formis. If you will waive counsel the trial can take place to-morrow.” “I will waive anything,” Myles replied, “counsel, immunity, extradition, anything in order to speed up my return to Cupia, where Lilla awaits in some dire extremity.” “All right,” Doggo wrote, and the conference was at an end. The morrow would decide the ascendancy of Myles Cabot or the Prince Yuri over the new continent. IV THE COUP D’ETAT The next morning Myles Cabot was led under guard to the council chamber of the dread thirteen: Formis and her twelve advisers. The accused was placed in a wicker cage, from which he surveyed his surroundings as the proceedings opened. 19 On a raised platform stood the ant queen, surmounted by a scarlet canopy, which set off the perfect proportions of her jet-black body. On each side of her stood six refined and intelligent ant-men, her councillors. One of the twelve was Doggo. Messenger ants hurried hither and thither. First the accusation was read, Myles being furnished with a written copy. The witnesses were then called. They were veterans who had served in the wars in which Cabot had twice freed Cupia from the domination of its Formian oppressors. They spoke with bitterness of the downfall of their beloved Formia. Their testimony was brief. Then the accused was asked if he wished to say anything in his own behalf. Myles rose, then shrugged his shoulders, sat down again, and wrote: “I fully realize the futility of making an argument through the antennae of another.” Whereupon the queen and the council went into executive session. Their remarks were not intended for the eyes of the prisoner, but he soon observed that some kind of a dispute was on between Doggo, supported by two councillors named Emu and Fum on one side, and a councillor named Barth on the other. As this dispute reached its height, a messenger ant rushed in and held up one paw. Cabot’s interpreter, not deeming this a part of the executive session, obligingly translated the following into writing: The messenger: “Yuri lives and reigns over Cupia. It is his command that Cabot die.” Barth: “It is the radio. Know then, O Queen, and ye, members of the council, that when we fled across the boiling seas under the gallant leadership of Prince Yuri, the man with the heart of a Formian, he brought with him one of those powerful radio sets invented by the beast who is our prisoner here to-day. “Supporters of Yuri still remained among the Cupians, and he has been in constant communication with these ever since shortly after our arrival here. From them he learned of the return of Myles Cabot to the planet Minos. 20 “Then Yuri disappeared. Those of us who were closest to him suspected that he had gone back across the boiling seas to claim as his own the throne of Cupia. But we hesitated to announce this until we were sure, for we feared that some of our own people would regard his departure as desertion. Yet who can blame him for returning to his father-land and to the throne which is his by rights?” To which the messenger added: “And he offers to give us back our own old country, if we too will return across the boiling seas again.” “It is a lie!” Doggo shouted. “Yuri, usurper of the thrones of two continents. Bah!” shouted Emu. “Yuri, our rightful leader,” shouted Barth. “Give us a queen of our own race,” shouted Fum. “Release the prisoner,” shouted the Queen. And that is all that Myles learned of the conversation, for his interpreter at this juncture stopped writing and obeyed the queen. The earth-man was free! With one bound he gained the throne, where fighting was already in progress between the two factions. Barth and Doggo were rolling over and over on the floor in a death grapple, while the ant-queen had backed to the rear of the stage, closely guarded by Emu and Fum. Seizing one of the pikes which supported the scarlet canopy, Myles wrenched it loose and drove it into the thorax of Barth. In another instant the earth-man and Doggo stood beside the queen. Ant-men now came pouring into the chamber through all the entrances, taking sides as they entered and sized up the situation. If it had still been in vogue among the Formians to be known by numbers rather than names, and to have these identifying numbers painted on the backs of their abdomens followed by the numbers of those whom they had defeated in the duels so common among them, then many a Formian would have “got the number” of many another, that day.
|
B. Reluctant at first but then confident
|
Which terms describe how the reviewers compare Brad Pitt's performance to Hilary Swank's, respectively?
A. Irritating / Courageous
B. Facetious / Naive
C. Disjointed / Measured
D. Conceited / Captivating
|
Boys Do Bleed Fight Club is silly stuff, sensationalism that mistakes itself for satire, but it's also a brash and transporting piece of moviemaking, like Raging Bull on acid. The film opens with--literally--a surge of adrenalin, which travels through the bloodstream and into the brain of its protagonist, Jack (Edward Norton), who's viewed, as the camera pulls out of his insides, with a gun stuck in his mouth. How'd he get into this pickle? He's going to tell you, breezily, and the director, David Fincher, is going to illustrate his narrative--violently. Fincher ( Seven , 1995; The Game , 1997) is out to bombard you with so much feverish imagery that you have no choice but to succumb to the movie's reeling, punch-drunk worldview. By the end, you might feel as if you, too, have a mouthful of blood. Not to mention a hole in your head. Fight Club careers from one resonant satirical idea to the next without quite deciding whether its characters are full of crap or are Gen X prophets. It always gives you a rush, though. At first, it goofs on the absurd feminization of an absurdly macho culture. An increasingly desperate insomniac, Jack finds relief (and release) only at meetings for the terminally ill. At a testicular cancer group, he's enfolded in the ample arms of Bob (the singer Meat Loaf Aday), a former bodybuilder who ruined his health with steroids and now has "bitch tits." Jack and Bob subscribe to a new form of male bonding: They cling to each other and sob. But Jack's idyll is rudely disrupted by--wouldn't you know it?--a woman. A dark-eyed, sepulchral head case named Marla Singer (Helena Bonham Carter) begins showing up at all the same disparate meetings for essentially the same voyeuristic ends, and the presence of this "tourist" makes it impossible for Jack to emote. Jack finds another outlet, though. On a plane, he meets Tyler Durden (Brad Pitt), a cryptic hipster with a penchant for subversive acts both large (he makes high-priced soaps from liposuctioned human fat) and small (he splices frames from porn flicks into kiddie movies). When Jack's apartment mysteriously explodes--along with his carefully chosen IKEA furniture--he moves into Tyler's squalid warehouse and helps to found a new religion: Fight Club, in which young males gather after hours in the basement of a nightclub to pound one another (and be pounded) to a bloody pulp. That last parenthesis isn't so parenthetical. In some ways, it's the longing to be beaten into oblivion that's the strongest. "Self-improvement," explains Tyler, "is masturbation"; self-destruction is the new way. Tyler's manifesto calls for an end to consumerism ("Things you own end up owning you"), and since society is going down ("Martha Stewart is polishing brass on the Titanic "), the only creative outlet left is annihilation. "It's only after we've lost everything that we're free to do anything," he says. Fincher and his screenwriter, Jim Uhls, seem to think they've broken new ground in Fight Club , that their metaphor for our discontents hits harder than anyone else's. Certainly it produces more bloody splatter. But 20 years ago, the same impulse was called punk and, as Greil Marcus documents in Lipstick Traces , it was other things before that. Yes, the mixture of Johnny Rotten, Jake La Motta, and Jesus is unique; and the Faludi-esque emasculation themes are more explicit. But there's something deeply movie-ish about the whole conceit, as if the novelist and director were weaned on Martin Scorsese pictures and never stopped dreaming of recapturing that first masochistic rush. The novel, the first by Chuck Palahniuk (the surname sounds like Eskimo for "palooka"--which somehow fits), walks a line between the straight and ironic--it isn't always clear if its glib sociological pronouncements are meant to be taken straight or as the ravings of a delusional mama's boy. But onscreen, when Pitt announces to the assembled fighters that they are the "middle children of history" with "no purpose and no place"--emasculated on one hand by the lack of a unifying crisis (a world war or depression) and on the other by lack of material wealth as promised by television--he seems meant to be intoning gospel. "We are a generation of men raised by women," Tyler announces, and adds, "If our fathers bail, what does that tell you about God?" (I give up: What?) F ight Club could use a few different perspectives: a woman's, obviously, but also an African-American's--someone who'd have a different take on the "healing" properties of violence. It's also unclear just what has emasculated Jack: Is it that he's a materialist or that the materials themselves (i.e., IKEA's lacquered particle boards) don't measure up to his fantasies of opulence? Is he motivated by spiritual hunger or envy? Tyler's subsequent idea of confining his group's mayhem to franchise coffee bars and corporate-subsidized art is a witty one--it's like a parody of neo-Nazism as re-enacted by yuppies. It might have been a howl if performed by, say, the troupe of artsy German nihilists in Joel and Ethan Coen's The Big Lebowski (1998). Somehow Brad Pitt doesn't have the same piquancy. Actually, Pitt isn't as terrible as usual: He's playing not a character but a conceit, and he can bask in his movie-idol arrogance, which seems to be the most authentic emotion he has. But the film belongs to Norton. As a ferocious skinhead in last year's American History X , Norton was taut and ropy, his long torso curled into a sneer; here, he's skinny and wilting, a quivering pansy. Even when he fights he doesn't transform--he's a raging wimp. The performance is marvelous, and it makes poetic sense in light of the movie's climactic twist. But that twist will annoy more people than it will delight, if only because it shifts the drama from the realm of the sociological to that of the psychoanalytic. The finale, scored with the Pixies' great "Where Is My Mind?" comes off facetiously--as if Fincher is throwing the movie away. Until then, however, he has done a fabulous job of keeping it spinning. The most thrilling thing about Fight Club isn't what it says but how Uhls and Fincher pull you into its narrator's head and simulate his adrenalin rushes. A veteran of rock videos, Fincher is one of those filmmakers who helps make the case that MTV--along with digital editing--has transformed cinema for better as well as worse. The syntax has become more intricate. Voice-over narration, once considered uncinematic, is back in style, along with novelistic asides, digressions, fantasies, and flashbacks. To make a point, you can jazzily interject anything--even, as in Three Kings , a shot of a bullet slicing through internal organs. Films like Fight Club might not gel, but they have a breathless, free-associational quality that points to new possibilities in storytelling. Or maybe old possibilities: The language of movies hasn't seemed this unfettered since the pre-sound days of Sergei Eisenstein and Abel Gance. An actress named Hilary Swank gives one of the most rapturous performances I've ever seen as the cross-dressing Brandon Teena (a k a Teena Brandon) in Kimberly Peirce's stark and astonishingly beautiful debut feature, Boys Don't Cry . The movie opens with Teena being shorn of her hated female tresses and becoming "Brandon," who swaggers around in tight jeans and leather jackets. The joy is in watching the actor transform, and I don't just mean Swank: I mean Teena Brandon playing Brandon Teena--the role she has been longing for her whole life. In a redneck Nebraska bar, Brandon throws back a shot of whiskey and the gesture--a macho cliché--becomes an act of self-discovery. Every gesture does. "You're gonna have a shiner in the morning," someone tells Brandon after a barroom brawl, and he takes the news with a glee that's almost mystical: "I am????? Oh, shit!!!" he cries, grinning. That might be my favorite moment in the picture, because Swank's ecstatic expression carries us through the next hour, as Brandon acts out his urban-cowboy fantasies--"surfing" from the bumper of a pickup truck, rolling in the mud, and straddling a barstool with one hand on a brewski and the other on the shoulder of a gorgeous babe. That the people with whom Brandon feels most at home would kill him if they knew his true gender is the movie's most tragic irony--and the one that lifts it out of the realm of gay-martyr hagiography and into something more complex and irreducible: a meditation on the irrelevance of gender. Peirce's triumph is to make these scenes at once exuberant (occasionally hilarious) and foreboding, so that all the seeds of Brandon's killing are right there on the screen. John (Peter Sarsgaard), one of his future rapists and murderers, calls him "little buddy" and seems almost attracted to him; Sarsgaard's performance is a finely chiseled study of how unresolved emotion can suddenly resolve itself into violence. Though harrowing, the second half of Boys Don't Cry isn't as great as the first. The early scenes evoke elation and dread simultaneously, the later ones just dread; and the last half-hour is unrelieved torture. What keeps the movie tantalizing is Chloë Sevigny's Lana, who might or might not know that Brandon is a girl but who's entranced by him anyway. With her lank hair, hooded eyes, and air of sleepy sensuality, Sevigny--maybe even more than Swank--embodies the mystery of sex that's at the core of Boys Don't Cry . Everything she does is deliberate, ironic, slightly unreadable--and unyielding. She's could be saying, "I'm in this world but not of it. ... You'd never dream what's underneath." I n brief: If a friend tells you you'll love Happy Texas , rethink the friendship. This clunky mistaken-identity comedy about escaped cons who impersonate gay pageant directors doesn't even make sense on its own low farcical terms; it's mostly one lame homo joke after another. The only bright spot is Steve Zahn, who could be the offspring of Michael J. Fox and Crispin Glover if they'd mated on the set of Back to the Future (1985). It's hard to make a serious case for Lawrence Kasdan's Mumford , which has apparently flopped but which you can still catch at second- and third-tier theaters. It looks peculiar--a Norman Rockwell painting with noir shadows. And its tale of a small town healed by a depressive (Loren Dean) posing as a psychologist is full of doddering misconceptions about psychotherapy. I almost don't know why I loved it, but the relaxed pacing and the witty turns by Martin Short, Ted Danson, David Paymer, and Mary McDonnell surely helped. I can't decide if the weirdly affectless Dean is inspired or inept, but my indecision suggests why he works in the role. There's no doubt, however, about his even more depressive love object, Hope Davis, who posseses the cinema's most expressive honking-nasal voice and who slumps through the movie like the world's most lyrical anti-ballerina. Even her puffy cheeks are eloquent: They made me think of Mumford as the home of the psychological mumps.
|
D. Conceited / Captivating
|
What is the crew’s mission?
A. To conduct tests about life in space
B. To experiment with suspension and memory
C. To return to Earth as quickly as possible
D. To explore possible planets to support life
|
CAPTAIN CHAOS By D. ALLEN MORRISSEY Science equipped David Corbin with borrowed time; sent him winging out in a state of suspension to future centuries ... to a dark blue world whose only defense was to seal tight the prying minds of foolish interlopers. [Transcriber's Note: This etext was produced from Planet Stories November 1952. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] I heard the voice as I opened my eyes. I was lying down, still not aware of where I was, waiting for the voice. "Your name is David Corbin. Do you understand?" I looked in the direction of the sound. Above my feet a bulkhead loomed. There were round dials set in a row above a speaker. Over the mesh-covered speaker, two knobs glowed red. I ran the words over in my sluggish mind, thinking about an answer. The muscles in my throat tightened up in reflex as I tried to bring some unity into the jumble of thoughts and ideas that kept forming. One word formed out of the rush of anxiety. "No." I shouted a protest against the strangeness of the room. I looked to the right, my eyes following the curving ceiling that started at the cot. The curve met another straight bulkhead on the left. I was in a small room, gray in color, like dull metal. Overhead a bright light burned into my vision. I wondered where in the universe I was. "Your name is David Corbin. If you understand, press button A on your right." I stared at the speaker in the wall. The mesh-covered hole and the two lights looked like a caricature of a face, set in a panel of dials. I twisted my head to look for the button. I pushed away from the close wall but I couldn't move. I reached down to the tightness that held my body, found the wide strap that held me and fumbled with the buckle. I threw it off and pushed myself up from the hard cot. I heard myself yell in surprise as I floated up towards the light overhead. I was weightless. How do you describe being weightless when you are born into a world bound by gravity. I twisted and shut my eyes in terror. There was no sensation of place, no feeling of up or down, no direction. My back bumped against the ceiling and I opened my eyes to stare at the cot and floor. I was concentrating too hard on remembering to be frightened for long. I pushed away from the warm metal and the floor moved up to meet me. "If you understand, press button A on your right." What should I understand? That I was floating in a room that had a curved wall ... that nothing was right in this hostile room? When I reached the cot I held it and drew myself down. I glanced at the planes of the room, trying to place it with other rooms I could see in my mind. Gray walls with a crazy curved ceiling ... a door to my left that appeared to be air tight. I stared at my familiar hands. I rubbed them across my face, feeling the solidity of flesh and bone, afraid to think too hard about myself. "My name ... my name is...." "Your name is David Corbin." I stared at the speaker. How long did this go on? The name meant nothing to me, but I thought about it, watching the relentless lights that shone below the dials. I stood up slowly and looked at myself. I was naked except for heavy shorts, and there was no clue to my name in the pockets. The room was warm and the air I had been breathing was good but it seemed wrong to be dressed like this. I didn't know why. I thought about insanity, and the room seemed to fit my thoughts. When the voice repeated the message again I had to act. Walking was like treading water that couldn't be seen or felt. I floated against the door, twisting the handle in fear that it wouldn't turn. The handle clanged as I pushed it down and I stared at the opposite wall of a narrow gray passageway. I pushed out into it and grasped the metal rail that ran along the wall. I reasoned it was there to propel yourself through the passageway in this weightless atmosphere. It was effortless to move. I turned on my side like a swimmer and went hand over hand, shooting down the corridor. I braced against forward motion and stopped against a door at the end. Behind me I could see the opened door I had left, and the thought of that questioning voice made me want to move. I swung the door open, catching a glimpse of a room crowded with equipment and.... I will always remember the scream of terror, the paralyzing fright of what I saw through the portholes in the wall of the room. I saw the blackest night, pierced by brilliance that blinded me. There was no depth to the searing brightness of countless stars. They seemed to press against the glass, blobs of fire against a black curtain burning into my eyes and brain. It was space. I looked out at deep space, star systems in clusters. I shut my eyes. When I looked again I knew where I was. Why the little room had been shaped like quarter round. Why I drifted weightlessly. Why I was.... David Corbin. I knew more of the puzzle. Something was wrong. After the first shock of looking out, I accepted the fact that I was in a space ship, yet I couldn't read the maps that were fastened to a table, nor understand the function or design of the compact machinery. WHY, Why, Why? The thought kept pounding at me. I was afraid to touch anything in the room. I pressed against the clear window, wondering if the stars were familiar. I had a brief vivid picture of a night sky on Earth. This was not the same sky. Back in the room where I had awakened, I touched the panel with the glowing eyes. It had asked me if I understood. Now it must tell me why I didn't. It had to help me, that flat metallic voice that repeated the same words. It must tell me.... "Your name is David Corbin. If you understand, press button A on your right." I pressed the button by the cot. The red lights blinked out as I stood in patient attention, trying to outguess the voice. I recalled a phrase ... some words about precaution. Precaution against forgetting. It was crazy, but I trusted the panel. It was the only thing I saw that could help me, guard me against another shock like seeing outside of the clear portholes. "It is assumed the experiment is a success," the voice said. What experiment? "You have been removed from suspension. Assume manual control of this ship." Control of a ship? Going where? "Do not begin operations until the others are removed from suspension." What others? Tell me what to do. "Rely on instructions for factoring when you check the coordinates. Your maximum deviation from schedule cannot exceed two degrees. Adopt emergency procedures as you see fit. Good luck." The voice snapped off and I laughed hysterically. None of it had made sense, and I cursed whatever madness had put me here. "Tell me what to do," I shouted wildly. I hammered the hard metal until the pain in my hands made me stop. "I can't remember what to do." I held my bruised hands to my mouth, and I knew that was all the message there was. In blind panic I pushed away from the panel. Something tripped me and I fell back in a graceless arc. I pushed away from the floor, barely feeling the pain in my leg, and went into the hall. Pain burned along my leg but I couldn't stop. In the first panic of waking up in strangeness I had missed the other doors in the passage. The first swung back to reveal a deep closet holding five bulky suits. The second room was like my own. A dark haired, deep chested man lay on the cot. His muscular body was secured by a wide belt. He was as still as death, motionless without warmth or breath as I hovered over him. I couldn't remember his face. The next room held another man. He was young and wiry, like an athlete cast in marble, dark haired and big jawed. A glassy eye stared up when I rolled back his eyelid. The eyelid remained open until I closed it and went on. Another room ... another man ... another stranger. This man was tall and raw boned, light of skin and hair, as dead as the others. A flat, illogical voice had instructed me to revive these men. I shivered in spite of the warmth of the room, studying the black box that squatted on a shelf by his head. My hand shook when I touched the metal. I dared not try to operate anything. Revive the others ... instructions without knowledge were useless to me. I stopped looking into the doors in the passageway and went back to the room with the portholes. Everything lay in readiness, fastened down star charts, instruments, glittering equipment. There was no feeling of disorder or use in the room. It waited for human hands to make it operate. Not mine. Not now. I went past the room into another, where the curves were more sharp. I could visualize the tapering hull leading to the nose of the ship. This room was filled with equipment that formed a room out of the bordered area I stood in. I sat in the deep chair facing the panel of dials and instruments, in easy reach. I ran my hands over the dials, the rows of smooth colored buttons, wondering. The ports on the side were shielded and I stared out at static energy, hung motionless in a world of searing light. There was no distortion, no movement outside and I glanced back at the dials. What speeds were they recording? What speeds and perhaps, what distance? It was useless to translate the markings. They stood for anything I might guess, and something kept pricking my mind, telling me I had no time to guess. I thought of time again. I was supposed to act according to ... plan. Did that mean ... in time ... in time. I went back down the passageway. The fourth small room was the same. Except for the woman. She lay on a cot, young and beautiful, even in the death-like immobility I had come to accept. Her beauty was graceful lines of face and her figure—smooth tapering legs, soft curves that were carved out of flesh colored stone. Yet not stone. I held her small hand, then put it back on the cot. Her attire was brief like the rest of us, shorts and a man's shirt. Golden hair curled up around her lovely face. I wondered if she would ever smile or move that graceful head. I rolled back her eyelid and looked at a deep blue eye that stared back in glassy surprise. Four people in all, depending on a blind helpless fool who didn't know their names or the reason for that dependence. I sat beside her on the cot until I could stand it no longer. Searching the ship made me forget my fear. I hoped I would find some answers. I went from the nose to the last bulkhead in a frenzy of floating motion, looking behind each door until I went as far as I could. There were two levels to the ship. They both ended in the lead shield that was set where the swell of the curve was biggest. It meant the engine or engines took up half the ship, cut off from the forward half by the instrument studded shield. I retraced my steps and took a rough estimate of size. The ship, as I called it, was at least four hundred feet long, fifty feet in diameter on the inside. The silence was a force in itself, pressing down from the metal walls, driving me back to the comforting smallness of the room where I had been reborn. I laughed bitterly, thinking about the aptness of that. I had literally been reborn in this room, equipped with half ideas, and no point to start from, no premise to seek. I sensed the place to start from was back in the room. I searched it carefully. Minutes later I realized the apparatus by the cot was different. It was the same type of black box, but out from it was a metal arm, bent in a funny angle. At the tip of the arm, a needle gleamed dully and I rubbed the deep gash on my leg. I bent the arm back until the angle looked right. It was then I realized the needle came to a spot where it could have hit my neck when I lay down. My shout of excitement rang out in the room, as I pictured the action of the extended arm. I lost my sudden elation in the cabin where the girl lay. The box behind her head was completely closed, and it didn't yield to the pressure I applied. It had a cover, but no other opening where an arm could extend. I ran my fingers over the unbroken surface, prying over the thin crack at the base helplessly. If some sort of antidote was to be administered manually I was lost. I had no knowledge of what to inject or where to look for it. The chamber of the needle that had awakened me was empty. That meant a measured amount. In the laboratory on the lower level I went over the rows of cans and tubes fastened to the shelves. There were earths and minerals, seeds and chemicals, testing equipment in compact drawers, but nothing marked for me. I wondered if I was an engineer or a pilot, or perhaps a doctor sent along to safeguard the others. Complete amnesia would have been terrible enough but this half knowledge, part awareness and association with the ship was a frightening force that seemed ready to break out of me. I went back to the cabin where the powerful man lay. I had to risk failure with one of them. I didn't want it to be the girl. I fought down the thought that he might be the key man, remembering the voice that had given the message. It was up to me, and soon. The metal in the box would have withstood a bullet. It couldn't be pried apart, and I searched again and again for a release mechanism. I found it. I swung the massive cover off and set it down. The equipment waited for the touch of a button and it went into operation. I stepped back as the tubes glowed to life and the arm swung down with the gleaming needle. The needle went into the corded neck of the man. The fluid chamber drained under pressure and the arm moved back. I stood by the man for long minutes. Finally it came. He stirred restlessly, closing his hands into fists. The deep chest rose and fell unevenly as he breathed. Finally the eyes opened and he looked at me. I watched him adjust to the room. It was in his eyes, wide at first, moving about the confines of the room back to me. "It looks like we made it," he said. "Yes." He unfastened the belt and sat up. I pushed him back as he floated up finding little humor in the comic expression on his face. "No gravity," he grunted and sat back. "You get used to it fast," I answered. I thought of what to say as he watched me. "How do you feel?" He shrugged at the question. "Fine, I guess. Funny, I can't remember." He saw it in my face, making him stop. "I can't remember dropping off to sleep," he finished. I held his hard arm. "What else? How much do you remember?" "I'm all right," he answered. "There aren't supposed to be any effects from this." "Who is in charge of this ship?" I asked. He tensed suddenly. "You are, sir. Why?" I moved away from the cot. "Listen, I can't remember. I don't know your name or anything about this ship." "What do you mean? What can't you remember?" he asked. He stood up slowly, edging around towards the door. I didn't want to fight him. I wanted him to understand. "Look, I'm in trouble. Nothing fits, except my name." "You don't know me?" "No." "Are you serious?" "Yes, yes. I don't know why but it's happened." He let his breath out in a whistle. "For God's sake. Any bump on your head?" "I feel all right physically. I just can't place enough." "The others. What about the others?" he blurted. "I don't know. You're the first besides myself. I don't know how I stumbled on the way to revive you." He shook his head, watching me like I was a freak. "Let's check the rest right away." "Yes. I've got to know if they are like me. I'm afraid to think they might be." "Maybe it's temporary. We can figure something out." II The second man, the dark haired one, opened his eyes and recognized us. He asked questions in rapid fire excitement. The third man, the tall Viking, was all right until he moved. The weightless sensation made him violently sick. We put him back on the cot, securing him again with the belt, but the sight of us floating made him shake. He was retching without results when we drifted out. I followed him to the girl's quarters. "What about her. Why is she here?" I asked my companion. He lifted the cover from the apparatus. "She's the chemist in the crew." "A girl?" "Dr. Thiesen is an expert, trained for this," he said. I looked at her. She looked anything but like a chemist. "There must be men who could have been sent. I've been wondering why a girl." "I don't know why, Captain. You tried to stop her before. Age and experience were all that mattered to the brass." "It's a bad thing to do." "I suppose. The mission stated one chemist." "What is the mission of this ship?" I asked. He held up his hand. "We'd better wait, sir. Everything was supposed to be all right on this end. First you, then Carl, sick to his stomach." "Okay. I'll hold the questions until we see about her." We were out of luck with the girl. She woke up and she was frightened. We questioned her and she was coherent but she couldn't remember. I tried to smile as I sat on the cot, wondering what she was thinking. "How do you feel?" I asked. Her face was a mask of wide-eyed fear as she shook her head. "Can you remember?" "I don't know." Blue eyes stared at me in fear. Her voice was low. "Do you know my name?" The question frightened her. "Should I? I feel so strange. Give me a minute to think." I let her sit up slowly. "Do you know your name?" She tightened up in my arms. "Yes. It's...." She looked at us for help, frightened by the lack of clothing we wore, by the bleak room. Her eyes circled the room. "I'm afraid," she cried. I held her and she shook uncontrollably. "What's happened to me?" she asked. The dark haired man came into the room, silent and watchful. My companion motioned to him. "Get Carl and meet us in Control." The man looked at me and I nodded. "We'll be there in a moment. I'm afraid we've got trouble." He nodded and pushed away from us. The girl screamed and covered her face with her hands. I turned to the other man. "What's your name?" "Croft. John Croft." "John, what are your duties if any?" "Automatic control. I helped to install it." "Can you run this ship? How about the other two?" He hit his hands together. "You fly it, sir. Can't you think?" "I'm trying. I know the ship is familiar, but I've looked it over. Maybe I'm trying too hard." "You flew her from earth until we went into suspension," he said. "I can't remember when," I said. I held the trembling girl against me, shaking my head. He glanced at the girl. "If the calculations are right it was more than a hundred years ago." We assembled in the control room for a council. We were all a little better for being together. John Croft named the others for me. I searched each face without recognition. The blond man was Carl Herrick, a metallurgist. His lean face was white from his spell but he was better. Paul Sample was a biologist, John said. He was lithe and restless, with dark eyes that studied the rest of us. I looked at the girl. She was staring out of the ports, her hands pressed against the transparent break in the smooth wall. Karen Thiesen was a chemist, now frightened and trying to remember. I wasn't in much better condition. "Look, if it comes too fast for me, for any of us, we'll stop. John, you can lead off." "You ask the questions," he said. I indicated the ship. "Where in creation are we going?" "We set out from Earth for a single star in the direction of the center of our Galaxy." "From Earth? How could we?" "Let's move slowly, sir," he said. "We're moving fast. I don't know if you can picture it, but we're going about one hundred thousand miles an hour." "Through space?" "Yes." "What direction?" Paul cut in. "It's a G type star, like our own sun in mass and luminosity. We hope to find a planetary system capable of supporting life." "I can't grasp it. How can we go very far in a lifetime?" "It can be done in two lifetimes," John said quietly. "You said I had flown this ship. You meant before this suspension." "Yes. That's why we can cross space to a near star." "How long ago was it?" "It was set at about a hundred years, sir. Doesn't that fit at all?" "I can't believe it's possible." Carl caught my eye. "Captain, we save this time without aging at all. It puts us near a calculated destination." "We've lost our lifetime." It was Karen. She had been crying silently while we talked. "Don't think about it," Paul said. "We can still pull this out all right if you don't lose your nerve." "What are we to do?" she asked. John answered for me. "First we've got to find out where we are. I know this ship but I can't fly it." "Can I?" I asked. We set up a temporary plan of action. Paul took Karen to the laboratory in an effort to help her remember her job. Carl went back to divide the rations. I was to study the charts and manuals. It was better than doing nothing, and I went into the navigation room and sat down. Earth was an infinitesimal point somewhere behind us on the galactic plane, and no one else was trained to navigate. The ship thundered to life as I sat there. The blast roared once ... twice, then settled into a muted crescendo of sound that hummed through the walls. I went into the control room and watched John at the panel. "I wish I knew what you were doing," I said savagely. "Give it time." "We can't spare any, can we?" I asked. "I wish we knew. What about her—Dr. Thiesen?" "She's in the lab. I don't think that will do much good. She's got to be shocked out of a mental state like that." "I guess you're right," he said slowly. "She's trained to administer the suspension on the return trip." I let my breath out slowly. "I didn't think about that." "We couldn't even get part way back in a lifetime," he said. "How old are you, John?" "Twenty-eight." "What about me?" "Thirty." He stared at the panel in thought for a minutes. "What about shock treatment? It sounds risky." "I know. It's the only thing I could think of. Why didn't everyone react the same?" "That had me wondering for a while. I don't know. Anyway how could you go about making her remember?" "Throw a crisis, some situation at her, I guess." He shrugged, letting his sure hands rest on the panel of dials. I headed back towards the lab. If I could help her I might help myself. I was past the rooms when the horn blasted through the corridor. I turned automatically with the sound, pushing against the rail, towards the control room. Deep in my mind I could see danger, and without questioning why I knew I had to be at Control when the sound knifed through the stillness. John was shouting as I thrust my way into the room. "Turn the ship. There's something dead ahead." I had a glimpse of his contorted face as I dove at the control board. My hands hit buttons, thumbed a switch and then a sudden force threw me to the right. I slammed into the panel on the right, as the pressure of the change dimmed my vision. Reflex made me look up at the radar control screen. It wasn't operating. John let go of the padded chair, grinning weakly. I was busy for a few seconds, feeding compensation into the gyros. Relief flooded through me like warm liquid. I hung on the intercom for support, drawing air into my heaving lungs. "What—made you—think of that," I asked weakly. "Shock treatment." "I must have acted on instinct." "You did. Even for a sick man that was pretty fast," he laughed. "I can think again, John. I know who I am," I shouted. I threw my arms around his massive shoulders. "You did it." "You gave me the idea, Mister, talking about Dr. Thiesen." "It worked. I'm okay," I said in giddy relief. "I don't have to tell you I was scared as hell. I wish you could have seen your face, the look in your eyes when I woke up." "I wouldn't want to wake up like that again." "You're all right now?" he asked. I grinned and nodded an answer. I saw John as he was at the base, big and competent, sweating in the blazing sun. I thought about the rest of the crew too. "We're heading right for a star...." "It's been dead ahead for hours," he grunted. I leaned over and threw the intercom to open. "This is control. Listen ... everyone. I'm over it. Disregard the warning siren ... we were testing the ship." The lab light blinked on as Paul cut in. "What was it ... hey, you said you're all right." "John did it. He hit the alarm figuring I would react. Listen, Paul. Is any one hurt?" "No. Carl is here too. His stomach flopped again but he's okay. What about food. We're supposed to be checked before we eat." "We'll have to go ahead without it. Any change?" "No, I put her to bed. Shall I bring food?" I glanced at John. He rubbed his stomach. "Yes," I answered. "Bring it when you can. I've got to find out where we are." We had to get off course before we ran into the yellow-white star that had been picked for us. Food was set down by me, grew cold and was carried away and I was still rechecking the figures. We were on a line ten degrees above the galactic plane. The parallactic baseline from Earth to the single star could be in error several degrees, or we could be right on the calculated position of the star. The radar confirmed my findings ... and my worst fears. When we set it for direction and distance, the screen glowed to life and recorded the star dead ahead. In all the distant star clusters, only this G type star was thought to have a planetary system like our own. We were out on a gamble to find a planet capable of supporting life. The idea had intrigued scientists before I had first looked up at the night sky. When I was sure the electronically recorded course was accurate for time, I checked direction and speed from the readings and plotted our position. If I was right we were much closer than we wanted to be. The bright pips on the screen gave us the distance and size of the star while we fed the figures into the calculator for our rate of approach. Spectroscopic tests were run on the sun and checked against the figures that had been calculated on Earth. We analyzed temperature, magnetic fields, radial motion, density and luminosity, checking against the standards the scientists had constructed. It was a G type star like our own. It had more density and temperature and suitable planets or not, we had to change course in a hurry. Carl analyzed the findings while we came to a decision. Somewhere along an orbit that might be two hundred miles across, our hypothetical planet circled this star. That distance was selected when the planets in Earth's solar system had proved to be barren. If the observations on this star were correct, we could expect to find a planet in a state of fertility ... if it existed ... if it were suitable for colonization ... if we could find it.
|
D. To explore possible planets to support life
|
What might lead the reader to think that Ashlew is trying to draw Kolin into a trap?
A. The way in which he offers to talk to the powerful force about Kolin's history
B. The holes strewn across Ashlew's back.
C. The fact that Ashlew assumed Kolin had been to Earth.
D. The fact that anyone would think a tree would be a good being to change into.
|
By H. B. Fyfe THE TALKATIVE TREE Dang vines! Beats all how some plants have no manners—but what do you expect, when they used to be men! All things considered—the obscure star, the undetermined damage to the stellar drive and the way the small planet's murky atmosphere defied precision scanners—the pilot made a reasonably good landing. Despite sour feelings for the space service of Haurtoz, steward Peter Kolin had to admit that casualties might have been far worse. Chief Steward Slichow led his little command, less two third-class ration keepers thought to have been trapped in the lower hold, to a point two hundred meters from the steaming hull of the Peace State . He lined them up as if on parade. Kolin made himself inconspicuous. "Since the crew will be on emergency watches repairing the damage," announced the Chief in clipped, aggressive tones, "I have volunteered my section for preliminary scouting, as is suitable. It may be useful to discover temporary sources in this area of natural foods." Volunteered HIS section! thought Kolin rebelliously. Like the Supreme Director of Haurtoz! Being conscripted into this idiotic space fleet that never fights is bad enough without a tin god on jets like Slichow! Prudently, he did not express this resentment overtly. His well-schooled features revealed no trace of the idea—or of any other idea. The Planetary State of Haurtoz had been organized some fifteen light-years from old Earth, but many of the home world's less kindly techniques had been employed. Lack of complete loyalty to the state was likely to result in a siege of treatment that left the subject suitably "re-personalized." Kolin had heard of instances wherein mere unenthusiastic posture had betrayed intentions to harbor treasonable thoughts. "You will scout in five details of three persons each," Chief Slichow said. "Every hour, each detail will send one person in to report, and he will be replaced by one of the five I shall keep here to issue rations." Kolin permitted himself to wonder when anyone might get some rest, but assumed a mildly willing look. (Too eager an attitude could arouse suspicion of disguising an improper viewpoint.) The maintenance of a proper viewpoint was a necessity if the Planetary State were to survive the hostile plots of Earth and the latter's decadent colonies. That, at least, was the official line. Kolin found himself in a group with Jak Ammet, a third cook, and Eva Yrtok, powdered foods storekeeper. Since the crew would be eating packaged rations during repairs, Yrtok could be spared to command a scout detail. Each scout was issued a rocket pistol and a plastic water tube. Chief Slichow emphasized that the keepers of rations could hardly, in an emergency, give even the appearance of favoring themselves in regard to food. They would go without. Kolin maintained a standard expression as the Chief's sharp stare measured them. Yrtok, a dark, lean-faced girl, led the way with a quiet monosyllable. She carried the small radio they would be permitted to use for messages of utmost urgency. Ammet followed, and Kolin brought up the rear. To reach their assigned sector, they had to climb a forbidding ridge of rock within half a kilometer. Only a sparse creeper grew along their way, its elongated leaves shimmering with bronze-green reflections against a stony surface; but when they topped the ridge a thick forest was in sight. Yrtok and Ammet paused momentarily before descending. Kolin shared their sense of isolation. They would be out of sight of authority and responsible for their own actions. It was a strange sensation. They marched down into the valley at a brisk pace, becoming more aware of the clouds and atmospheric haze. Distant objects seemed blurred by the mist, taking on a somber, brooding grayness. For all Kolin could tell, he and the others were isolated in a world bounded by the rocky ridge behind them and a semi-circle of damp trees and bushes several hundred meters away. He suspected that the hills rising mistily ahead were part of a continuous slope, but could not be sure. Yrtok led the way along the most nearly level ground. Low creepers became more plentiful, interspersed with scrubby thickets of tangled, spike-armored bushes. Occasionally, small flying things flickered among the foliage. Once, a shrub puffed out an enormous cloud of tiny spores. "Be a job to find anything edible here," grunted Ammet, and Kolin agreed. Finally, after a longer hike than he had anticipated, they approached the edge of the deceptively distant forest. Yrtok paused to examine some purple berries glistening dangerously on a low shrub. Kolin regarded the trees with misgiving. "Looks as tough to get through as a tropical jungle," he remarked. "I think the stuff puts out shoots that grow back into the ground to root as they spread," said the woman. "Maybe we can find a way through." In two or three minutes, they reached the abrupt border of the odd-looking trees. Except for one thick trunked giant, all of them were about the same height. They craned their necks to estimate the altitude of the monster, but the top was hidden by the wide spread of branches. The depths behind it looked dark and impenetrable. "We'd better explore along the edge," decided Yrtok. "Ammet, now is the time to go back and tell the Chief which way we're— Ammet! " Kolin looked over his shoulder. Fifty meters away, Ammet sat beside the bush with the purple berries, utterly relaxed. "He must have tasted some!" exclaimed Kolin. "I'll see how he is." He ran back to the cook and shook him by the shoulder. Ammet's head lolled loosely to one side. His rather heavy features were vacant, lending him a doped appearance. Kolin straightened up and beckoned to Yrtok. For some reason, he had trouble attracting her attention. Then he noticed that she was kneeling. "Hope she didn't eat some stupid thing too!" he grumbled, trotting back. As he reached her, whatever Yrtok was examining came to life and scooted into the underbrush with a flash of greenish fur. All Kolin saw was that it had several legs too many. He pulled Yrtok to her feet. She pawed at him weakly, eyes as vacant as Ammet's. When he let go in sudden horror, she folded gently to the ground. She lay comfortably on her side, twitching one hand as if to brush something away. When she began to smile dreamily, Kolin backed away. The corners of his mouth felt oddly stiff; they had involuntarily drawn back to expose his clenched teeth. He glanced warily about, but nothing appeared to threaten him. "It's time to end this scout," he told himself. "It's dangerous. One good look and I'm jetting off! What I need is an easy tree to climb." He considered the massive giant. Soaring thirty or forty meters into the thin fog and dwarfing other growth, it seemed the most promising choice. At first, Kolin saw no way, but then the network of vines clinging to the rugged trunk suggested a route. He tried his weight gingerly, then began to climb. "I should have brought Yrtok's radio," he muttered. "Oh, well, I can take it when I come down, if she hasn't snapped out of her spell by then. Funny … I wonder if that green thing bit her." Footholds were plentiful among the interlaced lianas. Kolin progressed rapidly. When he reached the first thick limbs, twice head height, he felt safer. Later, at what he hoped was the halfway mark, he hooked one knee over a branch and paused to wipe sweat from his eyes. Peering down, he discovered the ground to be obscured by foliage. "I should have checked from down there to see how open the top is," he mused. "I wonder how the view will be from up there?" "Depends on what you're looking for, Sonny!" something remarked in a soughing wheeze. Kolin, slipping, grabbed desperately for the branch. His fingers clutched a handful of twigs and leaves, which just barely supported him until he regained a grip with the other hand. The branch quivered resentfully under him. "Careful, there!" whooshed the eerie voice. "It took me all summer to grow those!" Kolin could feel the skin crawling along his backbone. "Who are you?" he gasped. The answering sigh of laughter gave him a distinct chill despite its suggestion of amiability. "Name's Johnny Ashlew. Kinda thought you'd start with what I am. Didn't figure you'd ever seen a man grown into a tree before." Kolin looked about, seeing little but leaves and fog. "I have to climb down," he told himself in a reasonable tone. "It's bad enough that the other two passed out without me going space happy too." "What's your hurry?" demanded the voice. "I can talk to you just as easy all the way down, you know. Airholes in my bark—I'm not like an Earth tree." Kolin examined the bark of the crotch in which he sat. It did seem to have assorted holes and hollows in its rough surface. "I never saw an Earth tree," he admitted. "We came from Haurtoz." "Where's that? Oh, never mind—some little planet. I don't bother with them all, since I came here and found out I could be anything I wanted." "What do you mean, anything you wanted?" asked Kolin, testing the firmness of a vertical vine. "Just what I said," continued the voice, sounding closer in his ear as his cheek brushed the ridged bark of the tree trunk. "And, if I do have to remind you, it would be nicer if you said 'Mr. Ashlew,' considering my age." "Your age? How old—?" "Can't really count it in Earth years any more. Lost track. I always figured bein' a tree was a nice, peaceful life; and when I remembered how long some of them live, that settled it. Sonny, this world ain't all it looks like." "It isn't, Mr. Ashlew?" asked Kolin, twisting about in an effort to see what the higher branches might hide. "Nope. Most everything here is run by the Life—that is, by the thing that first grew big enough to do some thinking, and set its roots down all over until it had control. That's the outskirts of it down below." "The other trees? That jungle?" "It's more'n a jungle, Sonny. When I landed here, along with the others from the Arcturan Spark , the planet looked pretty empty to me, just like it must have to—Watch it, there, Boy! If I didn't twist that branch over in time, you'd be bouncing off my roots right now!" "Th-thanks!" grunted Kolin, hanging on grimly. "Doggone vine!" commented the windy whisper. " He ain't one of my crowd. Landed years later in a ship from some star towards the center of the galaxy. You should have seen his looks before the Life got in touch with his mind and set up a mental field to help him change form. He looks twice as good as a vine!" "He's very handy," agreed Kolin politely. He groped for a foothold. "Well … matter of fact, I can't get through to him much, even with the Life's mental field helping. Guess he started living with a different way of thinking. It burns me. I thought of being a tree, and then he came along to take advantage of it!" Kolin braced himself securely to stretch tiring muscles. "Maybe I'd better stay a while," he muttered. "I don't know where I am." "You're about fifty feet up," the sighing voice informed him. "You ought to let me tell you how the Life helps you change form. You don't have to be a tree." "No?" " Uh -uh! Some of the boys that landed with me wanted to get around and see things. Lots changed to animals or birds. One even stayed a man—on the outside anyway. Most of them have to change as the bodies wear out, which I don't, and some made bad mistakes tryin' to be things they saw on other planets." "I wouldn't want to do that, Mr. Ashlew." "There's just one thing. The Life don't like taking chances on word about this place gettin' around. It sorta believes in peace and quiet. You might not get back to your ship in any form that could tell tales." "Listen!" Kolin blurted out. "I wasn't so much enjoying being what I was that getting back matters to me!" "Don't like your home planet, whatever the name was?" "Haurtoz. It's a rotten place. A Planetary State! You have to think and even look the way that's standard thirty hours a day, asleep or awake. You get scared to sleep for fear you might dream treason and they'd find out somehow." "Whooeee! Heard about them places. Must be tough just to live." Suddenly, Kolin found himself telling the tree about life on Haurtoz, and of the officially announced threats to the Planetary State's planned expansion. He dwelt upon the desperation of having no place to hide in case of trouble with the authorities. A multiple system of such worlds was agonizing to imagine. Somehow, the oddity of talking to a tree wore off. Kolin heard opinions spouting out which he had prudently kept bottled up for years. The more he talked and stormed and complained, the more relaxed he felt. "If there was ever a fellow ready for this planet," decided the tree named Ashlew, "you're it, Sonny! Hang on there while I signal the Life by root!" Kolin sensed a lack of direct attention. The rustle about him was natural, caused by an ordinary breeze. He noticed his hands shaking. "Don't know what got into me, talking that way to a tree," he muttered. "If Yrtok snapped out of it and heard, I'm as good as re-personalized right now." As he brooded upon the sorry choice of arousing a search by hiding where he was or going back to bluff things out, the tree spoke. "Maybe you're all set, Sonny. The Life has been thinkin' of learning about other worlds. If you can think of a safe form to jet off in, you might make yourself a deal. How'd you like to stay here?" "I don't know," said Kolin. "The penalty for desertion—" "Whoosh! Who'd find you? You could be a bird, a tree, even a cloud." Silenced but doubting, Kolin permitted himself to try the dream on for size. He considered what form might most easily escape the notice of search parties and still be tough enough to live a long time without renewal. Another factor slipped into his musings: mere hope of escape was unsatisfying after the outburst that had defined his fuming hatred for Haurtoz. I'd better watch myself! he thought. Don't drop diamonds to grab at stars! "What I wish I could do is not just get away but get even for the way they make us live … the whole damn set-up. They could just as easy make peace with the Earth colonies. You know why they don't?" "Why?" wheezed Ashlew. "They're scared that without talk of war, and scouting for Earth fleets that never come, people would have time to think about the way they have to live and who's running things in the Planetary State. Then the gravy train would get blown up—and I mean blown up!" The tree was silent for a moment. Kolin felt the branches stir meditatively. Then Ashlew offered a suggestion. "I could tell the Life your side of it," he hissed. "Once in with us, you can always make thinking connections, no matter how far away. Maybe you could make a deal to kill two birds with one stone, as they used to say on Earth…." Chief Steward Slichow paced up and down beside the ration crate turned up to serve him as a field desk. He scowled in turn, impartially, at his watch and at the weary stewards of his headquarters detail. The latter stumbled about, stacking and distributing small packets of emergency rations. The line of crewmen released temporarily from repair work was transient as to individuals but immutable as to length. Slichow muttered something profane about disregard of orders as he glared at the rocky ridges surrounding the landing place. He was so intent upon planning greetings with which to favor the tardy scouting parties that he failed to notice the loose cloud drifting over the ridge. It was tenuous, almost a haze. Close examination would have revealed it to be made up of myriads of tiny spores. They resembled those cast forth by one of the bushes Kolin's party had passed. Along the edges, the haze faded raggedly into thin air, but the units evidently formed a cohesive body. They drifted together, approaching the men as if taking intelligent advantage of the breeze. One of Chief Slichow's staggering flunkies, stealing a few seconds of relaxation on the pretext of dumping an armful of light plastic packing, wandered into the haze. He froze. After a few heartbeats, he dropped the trash and stared at ship and men as if he had never seen either. A hail from his master moved him. "Coming, Chief!" he called but, returning at a moderate pace, he murmured, "My name is Frazer. I'm a second assistant steward. I'll think as Unit One." Throughout the cloud of spores, the mind formerly known as Peter Kolin congratulated itself upon its choice of form. Nearer to the original shape of the Life than Ashlew got , he thought. He paused to consider the state of the tree named Ashlew, half immortal but rooted to one spot, unable to float on a breeze or through space itself on the pressure of light. Especially, it was unable to insinuate any part of itself into the control center of another form of life, as a second spore was taking charge of the body of Chief Slichow at that very instant. There are not enough men , thought Kolin. Some of me must drift through the airlock. In space, I can spread through the air system to the command group. Repairs to the Peace State and the return to Haurtoz passed like weeks to some of the crew but like brief moments in infinity to other units. At last, the ship parted the air above Headquarters City and landed. The unit known as Captain Theodor Kessel hesitated before descending the ramp. He surveyed the field, the city and the waiting team of inspecting officers. "Could hardly be better, could it?" he chuckled to the companion unit called Security Officer Tarth. "Hardly, sir. All ready for the liberation of Haurtoz." "Reformation of the Planetary State," mused the captain, smiling dreamily as he grasped the handrail. "And then—formation of the Planetary Mind!" END Transcriber's Note: This e-text was produced from Worlds of If January 1962 . Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.
|
A. The way in which he offers to talk to the powerful force about Kolin's history
|
Who does Extrone trust the most?
A. Ri
B. Mia
C. businessmen
D. Lin
|
HUNT the HUNTER BY KRIS NEVILLE Illustrated by ELIZABETH MacINTYRE [Transcriber's Note: This etext was produced from Galaxy Science Fiction June 1951. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Of course using live bait is the best way to lure dangerous alien animals ... unless it turns out that you are the bait! "We're somewhat to the south, I think," Ri said, bending over the crude field map. "That ridge," he pointed, "on our left, is right here." He drew a finger down the map. "It was over here," he moved the finger, "over the ridge, north of here, that we sighted them." Extrone asked, "Is there a pass?" Ri looked up, studying the terrain. He moved his shoulders. "I don't know, but maybe they range this far. Maybe they're on this side of the ridge, too." Delicately, Extrone raised a hand to his beard. "I'd hate to lose a day crossing the ridge," he said. "Yes, sir," Ri said. Suddenly he threw back his head. "Listen!" "Eh?" Extrone said. "Hear it? That cough? I think that's one, from over there. Right up ahead of us." Extrone raised his eyebrows. This time, the coughing roar was more distant, but distinct. "It is!" Ri said. "It's a farn beast, all right!" Extrone smiled, almost pointed teeth showing through the beard. "I'm glad we won't have to cross the ridge." Ri wiped his forehead on the back of his sleeve. "Yes, sir." "We'll pitch camp right here, then," Extrone said. "We'll go after it tomorrow." He looked at the sky. "Have the bearers hurry." "Yes, sir." Ri moved away, his pulse gradually slowing. "You, there!" he called. "Pitch camp, here!" He crossed to Mia, who, along with him, had been pressed into Extrone's party as guides. Once more, Ri addressed the bearers, "Be quick, now!" And to Mia, "God almighty, he was getting mad." He ran a hand under his collar. "It's a good thing that farn beast sounded off when it did. I'd hate to think of making him climb that ridge." Mia glanced nervously over his shoulder. "It's that damned pilot's fault for setting us down on this side. I told him it was the other side. I told him so." Ri shrugged hopelessly. Mia said, "I don't think he even saw a blast area over here. I think he wanted to get us in trouble." "There shouldn't be one. There shouldn't be a blast area on this side of the ridge, too." "That's what I mean. The pilot don't like businessmen. He had it in for us." Ri cleared his throat nervously. "Maybe you're right." "It's the Hunting Club he don't like." "I wish to God I'd never heard of a farn beast," Ri said. "At least, then, I wouldn't be one of his guides. Why didn't he hire somebody else?" Mia looked at his companion. He spat. "What hurts most, he pays us for it. I could buy half this planet, and he makes me his guide—at less than I pay my secretary." "Well, anyway, we won't have to cross that ridge." "Hey, you!" Extrone called. The two of them turned immediately. "You two scout ahead," Extrone said. "See if you can pick up some tracks." "Yes, sir," Ri said, and instantly the two of them readjusted their shoulder straps and started off. Shortly they were inside of the scrub forest, safe from sight. "Let's wait here," Mia said. "No, we better go on. He may have sent a spy in." They pushed on, being careful to blaze the trees, because they were not professional guides. "We don't want to get too near," Ri said after toiling through the forest for many minutes. "Without guns, we don't want to get near enough for the farn beast to charge us." They stopped. The forest was dense, the vines clinging. "He'll want the bearers to hack a path for him," Mia said. "But we go it alone. Damn him." Ri twisted his mouth into a sour frown. He wiped at his forehead. "Hot. By God, it's hot. I didn't think it was this hot, the first time we were here." Mia said, "The first time, we weren't guides. We didn't notice it so much then." They fought a few yards more into the forest. Then it ended. Or, rather, there was a wide gap. Before them lay a blast area, unmistakable. The grass was beginning to grow again, but the tree stumps were roasted from the rocket breath. "This isn't ours!" Ri said. "This looks like it was made nearly a year ago!" Mia's eyes narrowed. "The military from Xnile?" "No," Ri said. "They don't have any rockets this small. And I don't think there's another cargo rocket on this planet outside of the one we leased from the Club. Except the one he brought." "The ones who discovered the farn beasts in the first place?" Mia asked. "You think it's their blast?" "So?" Ri said. "But who are they?" It was Mia's turn to shrug. "Whoever they were, they couldn't have been hunters. They'd have kept the secret better." "We didn't do so damned well." "We didn't have a chance," Mia objected. "Everybody and his brother had heard the rumor that farn beasts were somewhere around here. It wasn't our fault Extrone found out." "I wish we hadn't shot our guide, then. I wish he was here instead of us." Mia shook perspiration out of his eyes. "We should have shot our pilot, too. That was our mistake. The pilot must have been the one who told Extrone we'd hunted this area." "I didn't think a Club pilot would do that." "After Extrone said he'd hunt farn beasts, even if it meant going to the alien system? Listen, you don't know.... Wait a minute." There was perspiration on Ri's upper lip. " I didn't tell Extrone, if that's what you're thinking," Mia said. Ri's mouth twisted. "I didn't say you did." "Listen," Mia said in a hoarse whisper. "I just thought. Listen. To hell with how he found out. Here's the point. Maybe he'll shoot us, too, when the hunt's over." Ri licked his lips. "No. He wouldn't do that. We're not—not just anybody. He couldn't kill us like that. Not even him . And besides, why would he want to do that? It wouldn't do any good to shoot us. Too many people already know about the farn beasts. You said that yourself." Mia said, "I hope you're right." They stood side by side, studying the blast area in silence. Finally, Mia said, "We better be getting back." "What'll we tell him?" "That we saw tracks. What else can we tell him?" They turned back along their trail, stumbling over vines. "It gets hotter at sunset," Ri said nervously. "The breeze dies down." "It's screwy. I didn't think farn beasts had this wide a range. There must be a lot of them, to be on both sides of the ridge like this." "There may be a pass," Mia said, pushing a vine away. Ri wrinkled his brow, panting. "I guess that's it. If there were a lot of them, we'd have heard something before we did. But even so, it's damned funny, when you think about it." Mia looked up at the darkening sky. "We better hurry," he said. When it came over the hastily established camp, the rocket was low, obviously looking for a landing site. It was a military craft, from the outpost on the near moon, and forward, near the nose, there was the blazoned emblem of the Ninth Fleet. The rocket roared directly over Extrone's tent, turned slowly, spouting fuel expensively, and settled into the scrub forest, turning the vegetation beneath it sere by its blasts. Extrone sat on an upholstered stool before his tent and spat disgustedly and combed his beard with his blunt fingers. Shortly, from the direction of the rocket, a group of four high-ranking officers came out of the forest, heading toward him. They were spruce, the officers, with military discipline holding their waists in and knees almost stiff. "What in hell do you want?" Extrone asked. They stopped a respectful distance away. "Sir...." one began. "Haven't I told you gentlemen that rockets frighten the game?" Extrone demanded, ominously not raising his voice. "Sir," the lead officer said, "it's another alien ship. It was sighted a few hours ago, off this very planet, sir." Extrone's face looked much too innocent. "How did it get there, gentlemen? Why wasn't it destroyed?" "We lost it again, sir. Temporarily, sir." "So?" Extrone mocked. "We thought you ought to return to a safer planet, sir. Until we could locate and destroy it." Extrone stared at them for a space. Then, indifferently, he turned away, in the direction of a resting bearer. "You!" he said. "Hey! Bring me a drink!" He faced the officers again. He smiled maliciously. "I'm staying here." The lead officer licked his firm lower lip. "But, sir...." Extrone toyed with his beard. "About a year ago, gentlemen, there was an alien ship around here then, wasn't there? And you destroyed it, didn't you?" "Yes, sir. When we located it, sir." "You'll destroy this one, too," Extrone said. "We have a tight patrol, sir. It can't slip through. But it might try a long range bombardment, sir." Extrone said, "To begin with, they probably don't even know I'm here. And they probably couldn't hit this area if they did know. And you can't afford to let them get a shot at me, anyway." "That's why we'd like you to return to an inner planet, sir." Extrone plucked at his right ear lobe, half closing his eyes. "You'll lose a fleet before you'll dare let anything happen to me, gentlemen. I'm quite safe here, I think." The bearer brought Extrone his drink. "Get off," Extrone said quietly to the four officers. Again they turned reluctantly. This time, he did not call them back. Instead, with amusement, he watched until they disappeared into the tangle of forest. Dusk was falling. The takeoff blast of the rocket illuminated the area, casting weird shadows on the gently swaying grasses; there was a hot breath of dry air and the rocket dwindled toward the stars. Extrone stood up lazily, stretching. He tossed the empty glass away, listened for it to shatter. He reached out, parted the heavy flap to his tent. "Sir?" Ri said, hurrying toward him in the gathering darkness. "Eh?" Extrone said, turning, startled. "Oh, you. Well?" "We ... located signs of the farn beast, sir. To the east." Extrone nodded. After a moment he said, "You killed one, I believe, on your trip?" Ri shifted. "Yes, sir." Extrone held back the flap of the tent. "Won't you come in?" he asked without any politeness whatever. Ri obeyed the order. The inside of the tent was luxurious. The bed was of bulky feathers, costly of transport space, the sleep curtains of silken gauze. The floor, heavy, portable tile blocks, not the hollow kind, were neatly and smoothly inset into the ground. Hanging from the center, to the left of the slender, hand-carved center pole, was a chain of crystals. They tinkled lightly when Extrone dropped the flap. The light was electric from a portable dynamo. Extrone flipped it on. He crossed to the bed, sat down. "You were, I believe, the first ever to kill a farn beast?" he said. "I.... No, sir. There must have been previous hunters, sir." Extrone narrowed his eyes. "I see by your eyes that you are envious—that is the word, isn't it?—of my tent." Ri looked away from his face. "Perhaps I'm envious of your reputation as a hunter. You see, I have never killed a farn beast. In fact, I haven't seen a farn beast." Ri glanced nervously around the tent, his sharp eyes avoiding Extrone's glittering ones. "Few people have seen them, sir." "Oh?" Extrone questioned mildly. "I wouldn't say that. I understand that the aliens hunt them quite extensively ... on some of their planets." "I meant in our system, sir." "Of course you did," Extrone said, lazily tracing the crease of his sleeve with his forefinger. "I imagine these are the only farn beasts in our system." Ri waited uneasily, not answering. "Yes," Extrone said, "I imagine they are. It would have been a shame if you had killed the last one. Don't you think so?" Ri's hands worried the sides of his outer garment. "Yes, sir. It would have been." Extrone pursed his lips. "It wouldn't have been very considerate of you to—But, still, you gained valuable experience. I'm glad you agreed to come along as my guide." "It was an honor, sir." Extrone's lip twisted in wry amusement. "If I had waited until it was safe for me to hunt on an alien planet, I would not have been able to find such an illustrious guide." "... I'm flattered, sir." "Of course," Extrone said. "But you should have spoken to me about it, when you discovered the farn beast in our own system." "I realize that, sir. That is, I had intended at the first opportunity, sir...." "Of course," Extrone said dryly. "Like all of my subjects," he waved his hand in a broad gesture, "the highest as well as the lowest slave, know me and love me. I know your intentions were the best." Ri squirmed, his face pale. "We do indeed love you, sir." Extrone bent forward. " Know me and love me." "Yes, sir. Know you and love you, sir," Ri said. "Get out!" Extrone said. "It's frightening," Ri said, "to be that close to him." Mia nodded. The two of them, beneath the leaf-swollen branches of the gnarled tree, were seated on their sleeping bags. The moon was clear and cold and bright in a cloudless sky; a small moon, smooth-surfaced, except for a central mountain ridge that bisected it into almost twin hemispheres. "To think of him. As flesh and blood. Not like the—well; that—what we've read about." Mia glanced suspiciously around him at the shadows. "You begin to understand a lot of things, after seeing him." Ri picked nervously at the cover of his sleeping bag. "It makes you think," Mia added. He twitched. "I'm afraid. I'm afraid he'll.... Listen, we'll talk. When we get back to civilization. You, me, the bearers. About him. He can't let that happen. He'll kill us first." Ri looked up at the moon, shivering. "No. We have friends. We have influence. He couldn't just like that—" "He could say it was an accident." "No," Ri said stubbornly. "He can say anything," Mia insisted. "He can make people believe anything. Whatever he says. There's no way to check on it." "It's getting cold," Ri said. "Listen," Mia pleaded. "No," Ri said. "Even if we tried to tell them, they wouldn't listen. Everybody would know we were lying. Everything they've come to believe would tell them we were lying. Everything they've read, every picture they've seen. They wouldn't believe us. He knows that." "Listen," Mia repeated intently. "This is important. Right now he couldn't afford to let us talk. Not right now. Because the Army is not against him. Some officers were here, just before we came back. A bearer overheard them talking. They don't want to overthrow him!" Ri's teeth, suddenly, were chattering. "That's another lie," Mia continued. "That he protects the people from the Army. That's a lie. I don't believe they were ever plotting against him. Not even at first. I think they helped him, don't you see?" Ri whined nervously. "It's like this," Mia said. "I see it like this. The Army put him in power when the people were in rebellion against military rule." Ri swallowed. "We couldn't make the people believe that." "No?" Mia challenged. "Couldn't we? Not today, but what about tomorrow? You'll see. Because I think the Army is getting ready to invade the alien system!" "The people won't support them," Ri answered woodenly. " Think. If he tells them to, they will. They trust him." Ri looked around at the shadows. "That explains a lot of things," Mia said. "I think the Army's been preparing for this for a long time. From the first, maybe. That's why Extrone cut off our trade with the aliens. Partly to keep them from learning that he was getting ready to invade them, but more to keep them from exposing him to the people. The aliens wouldn't be fooled like we were, so easy." "No!" Ri snapped. "It was to keep the natural economic balance." "You know that's not right." Ri lay down on his bed roll. "Don't talk about it. It's not good to talk like this. I don't even want to listen." "When the invasion starts, he'll have to command all their loyalties. To keep them from revolt again. They'd be ready to believe us, then. He'll have a hard enough time without people running around trying to tell the truth." "You're wrong. He's not like that. I know you're wrong." Mia smiled twistedly. "How many has he already killed? How can we even guess?" Ri swallowed sickly. "Remember our guide? To keep our hunting territory a secret?" Ri shuddered. "That's different. Don't you see? This is not at all like that." With morning came birds' songs, came dew, came breakfast smells. The air was sweet with cooking and it was nostalgic, childhoodlike, uncontaminated. And Extrone stepped out of the tent, fully dressed, surly, letting the flap slap loudly behind him. He stretched hungrily and stared around the camp, his eyes still vacant-mean with sleep. "Breakfast!" he shouted, and two bearers came running with a folding table and chair. Behind them, a third bearer, carrying a tray of various foods; and yet behind him, a fourth, with a steaming pitcher and a drinking mug. Extrone ate hugely, with none of the delicacy sometimes affected in his conversational gestures. When he had finished, he washed his mouth with water and spat on the ground. "Lin!" he said. His personal bearer came loping toward him. "Have you read that manual I gave you?" Lin nodded. "Yes." Extrone pushed the table away. He smacked his lips wetly. "Very ludicrous, Lin. Have you noticed that I have two businessmen for guides? It occurred to me when I got up. They would have spat on me, twenty years ago, damn them." Lin waited. "Now I can spit on them, which pleases me." "The farn beasts are dangerous, sir," Lin said. "Eh? Oh, yes. Those. What did the manual say about them?" "I believe they're carnivorous, sir." "An alien manual. That's ludicrous, too. That we have the only information on our newly discovered fauna from an alien manual—and, of course, two businessmen." "They have very long, sharp fangs, and, when enraged, are capable of tearing a man—" "An alien?" Extrone corrected. "There's not enough difference between us to matter, sir. Of tearing an alien to pieces, sir." Extrone laughed harshly. "It's 'sir' whenever you contradict me?" Lin's face remained impassive. "I guess it seems that way. Sir." "Damned few people would dare go as far as you do," Extrone said. "But you're afraid of me, too, in your own way, aren't you?" Lin shrugged. "Maybe." "I can see you are. Even my wives are. I wonder if anyone can know how wonderful it feels to have people all afraid of you." "The farn beasts, according to the manual...." "You are very insistent on one subject." "... It's the only thing I know anything about. The farn beast, as I was saying, sir, is the particular enemy of men. Or if you like, of aliens. Sir." "All right," Extrone said, annoyed. "I'll be careful." In the distance, a farn beast coughed. Instantly alert, Extrone said, "Get the bearers! Have some of them cut a path through that damn thicket! And tell those two businessmen to get the hell over here!" Lin smiled, his eyes suddenly afire with the excitement of the hunt. Four hours later, they were well into the scrub forest. Extrone walked leisurely, well back of the cutters, who hacked away, methodically, at the vines and branches which might impede his forward progress. Their sharp, awkward knives snickered rhythmically to the rasp of their heavy breathing. Occasionally, Extrone halted, motioned for his water carrier, and drank deeply of the icy water to allay the heat of the forest, a heat made oppressive by the press of foliage against the outside air. Ranging out, on both sides of the central body, the two businessmen fought independently against the wild growth, each scouting the flanks for farn beasts, and ahead, beyond the cutters, Lin flittered among the tree trunks, sometimes far, sometimes near. Extrone carried the only weapon, slung easily over his shoulder, a powerful blast rifle, capable of piercing medium armor in sustained fire. To his rear, the water carrier was trailed by a man bearing a folding stool, and behind him, a man carrying the heavy, high-powered two-way communication set. Once Extrone unslung his blast rifle and triggered a burst at a tiny, arboreal mammal, which, upon the impact, shattered asunder, to Extrone's satisfied chuckle, in a burst of blood and fur. When the sun stood high and heat exhaustion made the near-naked bearers slump, Extrone permitted a rest. While waiting for the march to resume, he sat on the stool with his back against an ancient tree and patted, reflectively, the blast rifle, lying across his legs. "For you, sir," the communications man said, interrupting his reverie. "Damn," Extrone muttered. His face twisted in anger. "It better be important." He took the head-set and mike and nodded to the bearer. The bearer twiddled the dials. "Extrone. Eh?... Oh, you got their ship. Well, why in hell bother me?... All right, so they found out I was here. You got them, didn't you?" "Blasted them right out of space," the voice crackled excitedly. "Right in the middle of a radio broadcast, sir." "I don't want to listen to your gabbling when I'm hunting!" Extrone tore off the head-set and handed it to the bearer. "If they call back, find out what they want, first. I don't want to be bothered unless it's important." "Yes, sir." Extrone squinted up at the sun; his eyes crinkled under the glare, and perspiration stood in little droplets on the back of his hands. Lin, returning to the column, threaded his way among reclining bearers. He stopped before Extrone and tossed his hair out of his eyes. "I located a spoor," he said, suppressed eagerness in his voice. "About a quarter ahead. It looks fresh." Extrone's eyes lit with passion. Lin's face was red with heat and grimy with sweat. "There were two, I think." "Two?" Extrone grinned, petting the rifle. "You and I better go forward and look at the spoor." Lin said, "We ought to take protection, if you're going, too." Extrone laughed. "This is enough." He gestured with the rifle and stood up. "I wish you had let me bring a gun along, sir," Lin said. "One is enough in my camp." The two of them went forward, alone, into the forest. Extrone moved agilely through the tangle, following Lin closely. When they came to the tracks, heavily pressed into drying mud around a small watering hole, Extrone nodded his head in satisfaction. "This way," Lin said, pointing, and once more the two of them started off. They went a good distance through the forest, Extrone becoming more alert with each additional foot. Finally, Lin stopped him with a restraining hand. "They may be quite a way ahead. Hadn't we ought to bring up the column?" The farn beast, somewhere beyond a ragged clump of bushes, coughed. Extrone clenched the blast rifle convulsively. The farn beast coughed again, more distant this time. "They're moving away," Lin said. "Damn!" Extrone said. "It's a good thing the wind's right, or they'd be coming back, and fast, too." "Eh?" Extrone said. "They charge on scent, sight, or sound. I understand they will track down a man for as long as a day." "Wait," Extrone said, combing his beard. "Wait a minute." "Yes?" "Look," Extrone said. "If that's the case, why do we bother tracking them? Why not make them come to us?" "They're too unpredictable. It wouldn't be safe. I'd rather have surprise on our side." "You don't seem to see what I mean," Extrone said. " We won't be the—ah—the bait." "Oh?" "Let's get back to the column." "Extrone wants to see you," Lin said. Ri twisted at the grass shoot, broke it off, worried and unhappy. "What's he want to see me for?" "I don't know," Lin said curtly. Ri got to his feet. One of his hands reached out, plucked nervously at Lin's bare forearm. "Look," he whispered. "You know him. I have—a little money. If you were able to ... if he wants," Ri gulped, "to do anything to me—I'd pay you, if you could...." "You better come along," Lin said, turning. Ri rubbed his hands along his thighs; he sighed, a tiny sound, ineffectual. He followed Lin beyond an outcropping of shale to where Extrone was seated, petting his rifle. Extrone nodded genially. "The farn beast hunter, eh?" "Yes, sir." Extrone drummed his fingers on the stock of the blast rifle. "Tell me what they look like," he said suddenly. "Well, sir, they're ... uh...." "Pretty frightening?" "No, sir.... Well, in a way, sir." "But you weren't afraid of them, were you?" "No, sir. No, because...." Extrone was smiling innocently. "Good. I want you to do something for me." "I ... I...." Ri glanced nervously at Lin out of the tail of his eye. Lin's face was impassive. "Of course you will," Extrone said genially. "Get me a rope, Lin. A good, long, strong rope." "What are you going to do?" Ri asked, terrified. "Why, I'm going to tie the rope around your waist and stake you out as bait." "No!" "Oh, come now. When the farn beast hears you scream—you can scream, by the way?" Ri swallowed. "We could find a way to make you." There was perspiration trickling down Ri's forehead, a single drop, creeping toward his nose. "You'll be safe," Extrone said, studying his face with amusement. "I'll shoot the animal before it reaches you." Ri gulped for air. "But ... if there should be more than one?" Extrone shrugged. "I—Look, sir. Listen to me." Ri's lips were bloodless and his hands were trembling. "It's not me you want to do this to. It's Mia, sir. He killed a farn beast before I did, sir. And last night—last night, he—" "He what?" Extrone demanded, leaning forward intently. Ri breathed with a gurgling sound. "He said he ought to kill you, sir. That's what he said. I heard him, sir. He said he ought to kill you. He's the one you ought to use for bait. Then if there was an accident, sir, it wouldn't matter, because he said he ought to kill you. I wouldn't...." Extrone said, "Which one is he?" "That one. Right over there." "The one with his back to me?" "Yes, sir. That's him. That's him, sir." Extrone aimed carefully and fired, full charge, then lowered the rifle and said, "Here comes Lin with the rope, I see." Ri was greenish. "You ... you...." Extrone turned to Lin. "Tie one end around his waist." "Wait," Ri begged, fighting off the rope with his hands. "You don't want to use me, sir. Not after I told you.... Please, sir. If anything should happen to me.... Please, sir. Don't do it." "Tie it," Extrone ordered. "No, sir. Please. Oh, please don't, sir." "Tie it," Extrone said inexorably. Lin bent with the rope; his face was colorless. They were at the watering hole—Extrone, Lin, two bearers, and Ri. Since the hole was drying, the left, partially exposed bank was steep toward the muddy water. Upon it was green, new grass, tender-tuffed, half mashed in places by heavy animal treads. It was there that they staked him out, tying the free end of the rope tightly around the base of a scaling tree. "You will scream," Extrone instructed. With his rifle, he pointed across the water hole. "The farn beast will come from this direction, I imagine." Ri was almost slobbering in fear. "Let me hear you scream," Extrone said. Ri moaned weakly. "You'll have to do better than that." Extrone inclined his head toward a bearer, who used something Ri couldn't see. Ri screamed. "See that you keep it up that way," Extrone said. "That's the way I want you to sound." He turned toward Lin. "We can climb this tree, I think." Slowly, aided by the bearers, the two men climbed the tree, bark peeling away from under their rough boots. Ri watched them hopelessly. Once at the crotch, Extrone settled down, holding the rifle at alert. Lin moved to the left, out on the main branch, rested in a smaller crotch. Looking down, Extrone said, "Scream!" Then, to Lin, "You feel the excitement? It's always in the air like this at a hunt." "I feel it," Lin said. Extrone chuckled. "You were with me on Meizque?" "Yes." "That was something, that time." He ran his hand along the stock of the weapon. The sun headed west, veiling itself with trees; a large insect circled Extrone's head. He slapped at it, angry. The forest was quiet, underlined by an occasional piping call, something like a whistle. Ri's screams were shrill, echoing away, shiveringly. Lin sat quiet, hunched. Extrone's eyes narrowed, and he began to pet the gun stock with quick, jerky movements. Lin licked his lips, keeping his eyes on Extrone's face. The sun seemed stuck in the sky, and the heat squeezed against them, sucking at their breath like a vacuum. The insect went away. Still, endless, hopeless, monotonous, Ri screamed. A farn beast coughed, far in the matted forest. Extrone laughed nervously. "He must have heard." "We're lucky to rouse one so fast," Lin said. Extrone dug his boot cleats into the tree, braced himself. "I like this. There's more excitement in waiting like this than in anything I know." Lin nodded. "The waiting, itself, is a lot. The suspense. It's not only the killing that matters." "It's not only the killing," Lin echoed. "You understand?" Extrone said. "How it is to wait, knowing in just a minute something is going to come out of the forest, and you're going to kill it?" "I know," Lin said. "But it's not only the killing. It's the waiting, too." The farn beast coughed again; nearer. "It's a different one," Lin said. "How do you know?" "Hear the lower pitch, the more of a roar?" "Hey!" Extrone shouted. "You, down there. There are two coming. Now let's hear you really scream!" Ri, below, whimpered childishly and began to retreat toward the tether tree, his eyes wide. "There's a lot of satisfaction in fooling them, too," Extrone said. "Making them come to your bait, where you can get at them." He opened his right hand. "Choose your ground, set your trap. Bait it." He snapped his hand into a fist, held the fist up before his eyes, imprisoning the idea. "Spring the trap when the quarry is inside. Clever. That makes the waiting more interesting. Waiting to see if they really will come to your bait." Lin shifted, staring toward the forest. "I've always liked to hunt," Extrone said. "More than anything else, I think." Lin spat toward the ground. "People should hunt because they have to. For food. For safety." "No," Extrone argued. "People should hunt for the love of hunting." "Killing?" "Hunting," Extrone repeated harshly. The farn beast coughed. Another answered. They were very near, and there was a noise of crackling underbrush. "He's good bait," Extrone said. "He's fat enough and he knows how to scream good." Ri had stopped screaming; he was huddled against the tree, fearfully eying the forest across from the watering hole. Extrone began to tremble with excitement. "Here they come!" The forest sprang apart. Extrone bent forward, the gun still across his lap. The farn beast, its tiny eyes red with hate, stepped out on the bank, swinging its head wildly, its nostrils flaring in anger. It coughed. Its mate appeared beside it. Their tails thrashed against the scrubs behind them, rattling leaves. "Shoot!" Lin hissed. "For God's sake, shoot!" "Wait," Extrone said. "Let's see what they do." He had not moved the rifle. He was tense, bent forward, his eyes slitted, his breath beginning to sound like an asthmatic pump. The lead farn beast sighted Ri. It lowered its head. "Look!" Extrone cried excitedly. "Here it comes!" Ri began to scream again. Still Extrone did not lift his blast rifle. He was laughing. Lin waited, frozen, his eyes staring at the farn beast in fascination. The farn beast plunged into the water, which was shallow, and, throwing a sheet of it to either side, headed across toward Ri. "Watch! Watch!" Extrone cried gleefully. And then the aliens sprang their trap.
|
D. Lin
|
Was the gas incident deadly?
A. Yes, there were bodies scattered all over the ship.
B. No, exposed crewmen were left nearly comatose.
C. Yes, and only gas masks could help prevent death from the gas exposure.
D. No, because Androka made sure to expose the crewmen to a nondeadly gas.
|
SILENCE IS—DEADLY By Bertrand L. Shurtleff Radio is an absolute necessity in modern organization—and particularly in modern naval organization. If you could silence all radio—silence of that sort would be deadly! [Transcriber's Note: This etext was produced from Astounding Science-Fiction April 1942. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] The hurried rat-a-tat of knuckles hammered on the cabin door. Commander Bob Curtis roused himself from his doze, got up from his chair, stretched himself to his full, lanky height and yawned. That would be Nelson, his navigating officer. Nelson always knocked that way—like a man in an external state of jitters over nothing at all. Curtis didn't hurry. It pleased him to let Nelson wait. He moved slowly to the door, paused there, and flung a backward glance at the man in the cabin with him—Zukor Androka, the elderly Czech scientist, a guest of the United States navy, here aboard the cruiser Comerford . The wizened face of the older man was molded in intent lines of concentration, as his bushy gray head bent over his drawing board. Curtis got a glimpse of the design on which he was working, and his lips relaxed in a faint smile. Androka had arrived on board the Comerford the day before she sailed from Norfolk. With him came a boatload of scientific apparatus and equipment, including a number of things that looked like oxygen tanks, which were now stored in the forward hold. Androka had watched over his treasures with the jealous care of a mother hen, and spent hours daily in the room in the superstructure that had been assigned as his laboratory. Sometimes, Curtis thought old Androka was a bit wacky—a scientist whose mind had been turned by the horror that had come to his country under the domination of the Nazi gestapo . At other times, the man seemed a genius. Perhaps that was the answer—a mad genius! Curtis opened the door and looked out. Rain whipped against his face like a stinging wet lash. Overhead, the sky was a storm-racked mass of clouds, broken in one spot by a tiny patch of starlit blue. His eyes rested inquiringly on the face of the man who stood before him. It was Nelson, his shaggy blond brows drawn scowlingly down over his pale eyes; his thin face a mass of tense lines; his big hands fumbling at the neck of his slicker. Rain was coursing down his white cheeks, streaking them with glistening furrows. The fellow was a headache to Curtis. He was overfriendly with a black-browed bos'n's mate named Joe Bradford—the worst trouble maker on board. But there was no question of his ability. He was a good navigating officer—dependable, accurate, conscientious. Nevertheless, his taut face, restless, searching eyes, and eternally nervous manner got Curtis' goat. "Come in, Nelson!" he said. Nelson shouldered his way inside, and stood there in his dripping oilskins, blinking his eyes against the yellow light. Curtis closed the door and nodded toward the bent form of Zukor Androka, with a quizzical grin. "Old Czech-and-Double-Czech is working hard on his latest invention to pull Hitler's teeth and re-establish the Czech Republic!" Nelson had no answering smile, although there had been a great deal of good-natured joking aboard the Comerford ever since the navy department had sent the scientist on board the cruiser to carry on his experiments. "I'm worried, sir!" Nelson said. "I'm not sure about my dead reckoning. This storm—" Curtis threw his arm around Nelson's dripping shoulders. "Forget it! Don't let a little error get you down!" "But this storm, sir!" Nelson avoided Curtis' friendly eyes and slipped out from under his arm. "It's got me worried. Quartering wind of undetermined force, variable and gusty. There's a chop to the sea—as if from unestimated currents among the islets. No chance to check by observation, and now there is a chance—look at me!" He held out his hands. They were shaking as if he had the chills. "You say there is a chance?" Curtis asked. "Stars out?" "As if by providence, sir, there's a clear patch. I'm wondering—" His voice trailed off, but his eyes swung toward the gleaming sextant on the rack. Commander Curtis shrugged good-naturedly and reached for the instrument. "Not that I've lost confidence in you, Nels, but just because you asked for it!" Curtis donned his slicker and went outside, sextant in hand. In a few minutes he returned and handed Nelson a sheet of paper with figures underlined heavily. "Here's what I make it," the commander told his navigating officer. "Bet you're not off appreciably." Nelson stared at the computations with shaking head. Then he mutely held up his own. Curtis stared, frowned, grabbed his own sheet again. "Any time I'm that far off old Figure-'em Nelson's estimate, I'm checking back," he declared, frowning at the two papers and hastily rechecking his own figures. "Call up to the bridge to stop her," he told Nelson. "We can't afford to move in these waters with such a possibility of error!" Nelson complied, and the throbbing drive of the engines lessened at once. Nelson said: "I've been wondering, sir, if it wouldn't be advisable to try getting a radio cross-bearing. With all these rocks and islets—" "Radio?" repeated the little Czech, thrusting his face between the other two, in his independent fashion that ignored ship's discipline. "You're using your radio?" He broke into a knowing chuckle, his keen old eyes twinkling behind their thick lenses. "Go ahead and try it. See how much you can get! It will be no more than Hitler can get when Zukor Androka decrees silence over the German airways! Try it! Try it, I say!" Bob Curtis stared at him, as if questioning his sanity. Then he hastened to the radio room, with Nelson at his heels, and the Czech trotting along behind. The door burst open as they neared it. A frightened operator came out, still wearing his earphones, and stood staring upward incredulously at the aërial. "Get us a radio cross-bearing for location at once," Curtis said sharply, for the operator seemed in a daze. "Bearing, sir?" The man brought his eyes down with difficulty, as if still dissatisfied. "I'm sorry, sir, but the outfit's dead. Went out on me about five minutes ago. I was taking the weather report when the set conked. I was trying to see if something's wrong." The Czech inventor giggled. Curtis gave him another curious look and thrust himself into the radio room. "Try again!" he told the operator. "See what you can get!" The radio man leaped to his seat and tried frantically. Again and again, he sent off a request for a cross-bearing from shore stations that had recently been established to insure safety to naval vessels, but there was no answer on any of the bands—not even the blare of a high-powered commercial program in the higher reach, nor the chatter of ships or amateurs on the shorter. "Dead!" Androka muttered, with a bitter laugh. "Yet not dead, gentlemen! The set is uninjured. The waves are what have been upset. I have shattered them around your ship, just as I can eventually shatter them all over Central Europe! For the next two hours, no radio messages can enter or leave my zone of radio silence—of refracted radio waves, set up by my little station on one of the neighboring islets!" There was a long pause, while commander and navigator stared at him. Curtis was the first to speak. "Your secrecy might well cost the United States navy one of its best light cruisers—and us our lives!" he said angrily. "We need that check by radio at once! If you're not talking nonsense, call off your dogs till we learn just where we are!" Androka held out his palms helplessly. "I can do nothing. I have given orders to my assistant that he must keep two hours of radio silence! I can get no message to him, for our radio is dead!" As if to mock him, the ship's radio began to answer: "Station 297 calling U. S. Cruiser Comerford . Station 297 calling U. S. Cruiser Comerford —" "U. S. Cruiser Comerford calling Station 297!" the operator intoned, winking at the two officers over Androka's discomfiture, and asked for the bearings. The answer came back: "Bearings north east by a quarter east, U. S. Cruiser Comerford !" Curtis sighed with relief. He saw that Nelson was staring fiercely at the radio operator, as the man went on calling: "U. S. Cruiser Comerford calling Station 364. U. S. Cruiser Comerford calling Station 364—" Then the instrument rasped again: "Station 364 calling U. S. Cruiser Comerford . Bearings north west by three west. Bearings north west by three west, U. S. Cruiser Comerford from Cay 364." Commander and navigator had both scribbled verifications of the numbers. Ignoring the gibbering Androka, who was wailing his disappointment that messages had penetrated his veil of silence, they raced for the chart room. Quickly the parallels stepped off the bearing from the designated points. Light intersecting lines proclaimed a check on their position. Curtis frowned and shook his head. Slowly he forced a reluctant grin as he stuck out his hand. "Shake, Nels," he said. "It's my turn to eat crow. You and the radio must be right. Continue as you were!" "I'm relieved, sir, just the same," Nelson admitted, "to have the radio bearings. We'd have piled up sure if you'd been right." They went on through the night. The starlit gap in the clouds had closed. The sky was again a blanket of darkness pouring sheets of rain at them. Nelson went back to the bridge, and Androka returned to the commander's cabin. Curtis lingered in the wireless room with the radio operator. "It's a funny thing," the latter said, still dialing and grousing, "how I got that cross-bearing through and can't get another squeak out of her. I'm wondering if that old goat really has done something to the ether. The set seems O. K." He lingered over the apparatus, checking and rechecking. Tubes lighted; wires were alive to the touch and set him to shaking his head at the tingle they sent through his inquiring fingers. Curtis left him at it, and went to rejoin Androka in the cabin. He found the little inventor pacing up and down, shaking his fists in the air; pausing every now and then to run his bony fingers through his tangled mop of gray hair, or to claw nervously at his beard. "You have seen a miracle, commander!" he shouted at Curtis. " My miracle! My invention has shattered the ether waves hereabouts hopelessly." "Seems to me," Curtis said dryly, "this invention can harm your friends as much as your enemies." The scientist drew himself up to his full height—which was only a little over five feet. His voice grew shrill. "Wait! Just wait! There are other inventions to supplement this one. Put them together, and they will defeat the Nazi hordes which have ravaged my country!" Curtis was a little shocked by the hatred that gleamed in Androka's eyes, under their bushy brows. There was something of the wild animal in the man's expression, as his lips drew back from his yellowed teeth. "Those tanks you have below," Curtis said, "have they some connection with this radio silence?" A far-away look came into Androka's eyes. He did not seem to hear the question. He lowered his voice: "My daughter is still in Prague. So are my sister and her husband, and their two daughters. If the gestapo knew what I am doing, all of them would be better dead. You understand—better dead?" Curtis said: "I understand." "And if the Nazi agents in America knew of the islet from which my zone of silence is projected—" Androka paused, his head tilted to one side, as if he were listening to something— On deck, there was shouting and commotion. Curtis rushed out, pulling on his slicker as he went. The shout from the watch forward had been picked up, and was being relayed all over the ship. The words struck on Curtis' ears with a note of impending tragedy. "Breakers ahead!" He was beside Navigating Officer Nelson on the bridge, and saw the helmsman climbing the rapidly spinning wheel like a monkey as he put it hard aport. Then the ship struck. Everything movable shot ahead until it brought up at the end of a swing or smacked against something solid. Curtis felt Nelson's hand grip his shoulder, as he put his lips close to his ear and shouted: "You must have been right, sir, and the radio bearings and my reckoning wrong. We've hit that reef a terrific smack. I'm afraid we're gored!" "Get out the collision mat!" Curtis ordered. "We ought to be able to keep her up!" And then he became aware of a deadly stillness. A vast wall of silence enveloped the entire cruiser. Looking over the side, he could no longer see the waves that a few minutes before had beaten savagely against the ship. The Comerford was shrouded in a huge pall of yellowish-gray mist, and more of it was coming up from below—from ventilators and hatchways and skylights—as if the whole ship were flooded with some evil vapor. Somehow, Curtis' mind flashed to the stories he'd heard of the forts of the Maginot Line, and of other forts in Holland and Belgium that had fallen before the early Nazi blitzkrieg, when their defenders found themselves struck numb and helpless by a gas that had been flooded into the inner compartments of their strongholds. There were those who said it was the work of sappers who had tunneled under the foundations, while others laid the induction of the gas to Fifth Column traitors. There were a hundred more or less plausible explanations— The vapor clouds that enveloped the Comerford were becoming thicker. All about the deck lay the forms of unconscious seamen, suddenly stricken helpless. And then Curtis saw other forms flitting about the deck—forms that looked like creatures from another world, but he recognized them for what they were—men wearing gas masks. Nelson was nowhere in sight. The steersman lay in a limp heap beside the swinging wheel. Then a gas-masked figure appeared through the shroud of mist and steadied it, so that the cruiser would not be completely at the mercy of the wind and the waves. Curtis heard the anchor let down, as if by invisible hands, the chain screaming and flailing its clanking way through the hawse hole. Then he was completely walled in by the yellowish-gray mist. He felt his senses swimming. Voices droned all around him in mumbling confusion—guttural voices that ebbed and flowed in a tide of excited talk. He caught a word of English now and then, mixed in with a flood of Teuton phonetics. Two words, in particular, registered clearly on his mind. One was " Carethusia "; the other was "convoy." But gradually his eardrums began to throb, as if someone were pounding on them from the inside. He couldn't get his breath; a cloud seemed to be mounting within him until it swept over his brain— He felt something strike the side of his head, and realized that he had fallen in a heap on the bridge. And after that, he wasn't conscious of anything— The rain had abated to a foggy drizzle. The wash of the surf swung the Comerford in a lazy, rolling motion, as she lay with her bow nosing into the sandbar at the entrance of the inlet. From her bridge, Navigating Officer Nelson watched the gas-masked figures moving about the decks, descending companionways—like goblins from an ancient fairy tale or a modern horror story. Nelson looked like a goblin himself, with his face covered by a respirator. At his side, stood his fellow conspirator Bos'n's Mate Joe Bradford, also wearing a gas mask. Nelson spoke in a low tone, his lips close to Bradford's ear. "It worked, Joe!" "Yeah!" Bradford agreed. "It worked—fine!" The limp bodies of the Comerford's crew were being carried to the lowered accommodation ladder and transferred into waiting lifeboats. Nelson swore under his breath. "Reckon it'll take a couple of hours before the ship's rid of that damn gas!" Bradford shook his head in disagreement. "The old geezer claims he's got a neutralizing chemical in one of them tanks of his that'll clear everything up inside half an hour." "I'd rather get along without Androka, if we could!" Nelson muttered. "He's nothing but a crackpot!" "It was a crackpot who invented the gas we used to break up the Maginot Line," Bradford reminded him. "It saved a lot of lives for the Fuehrer —lives that'd have been lost if the forts had to be taken by our storm troopers!" Nelson grunted and turned away. A short, thick-set figure in the uniform of a German naval commander had ascended the accommodation ladder and was mounting to the bridge. He, too, was equipped with a respirator. He came up to Nelson, saluted, and held out his hand, introducing himself as Herr Kommander Brandt. He began to speak in German, but Nelson stopped him. "I don't speak any German," he explained. "I was born and educated in the United States—of German parents, who had been ruined in the First World War. My mother committed suicide when she learned that we were penniless. My father—" He paused and cleared his throat. " Ja! Your father?" the German officer prompted, dropping into accented English. "Your father?" "My father dedicated me to a career of revenge—to wipe out his wrongs," Nelson continued. "If America hadn't gone into the First World War, he wouldn't have lost his business; my mother would still be living. When he joined the Nazi party, the way became clear to use me—to educate me in a military prep school, then send me to Annapolis, for a career in the United States navy—and no one suspected me. No one—" "Sometimes," Bradford put in, "I think Curtis suspected you." "Maybe Curtis'll find out his suspicions were justified," Nelson said bitterly. "But it won't do Curtis any good—a commander who's lost his ship." He turned to Brandt. "You have plenty of men to work the Comerford ?" Brandt nodded his square head. "We have a full crew—two hundred men—officers, seamen, mechanics, radio men, technical experts, all German naval reservists living in the United States, who've been sent here secretly, a few at a time, during the past six weeks!" The three—Brandt, Nelson and Bradford—stood on the bridge and talked, while the efficient stretcher-bearers worked industriously to remove the limp bodies of the Comerford's unconscious crew and row them ashore. And when that task was completed, lifeboats began to come alongside with strange-looking radio equipment, and more gas tanks like those Androka had brought aboard the Comerford with him, and dynamos and batteries that looked like something out of a scientific nightmare. And bustling all over the place, barking excited commands in German, pushing and pulling and pointing to emphasize his directions, was the strange figure of Professor Zukor Androka! "The professor's in his glory!" Nelson remarked to Kommander Brandt. "Funny thing about him," Bradford put in, "is that his inventions work. That zone of silence cut us off completely." Kommander Brandt nodded. "Goodt! But you got your message giving your bearings—the wrong ones?" "Yes," Nelson said. "That came through all right. And won't Curtis have a time explaining it!" "Hereafter," Brandt said solemnly, "the zone of silence vill be projected from the Comerford ; and ve have another invention of Androka's vich vill be even more useful vhen ve come to cut the Carethusia out of her convoy." "The Carethusia ?" Nelson asked, in a puzzled tone. Brandt said: "She's a freighter in a convoy out of St. Johns—twelve thousand tons. The orders are to take her; not sink her." "What's the idea?" "Her cargo," Brandt explained. "It iss more precious than rubies. It includes a large shipment of boarts." "Boarts?" Nelson repeated. "What are they?" "Boarts," Brandt told him, "are industrial diamonds—black, imperfectly crystallized stones, but far more valuable to us than flawless diamonds from Tiffany's on Fift' Avenue. They are needed for making machine tools. They come from northern Brazil—and our supply is low." "I should think we could get a shipment of these boarts direct from Brazil—through the blockade," Nelson said, "without taking the risk of capturing a United States navy cruiser." "There are other things Germany needs desperately on board the Carethusia ," Brandt explained. "Vanadium and nickel and hundreds of barrels of lard oil for machine-tool lubrication. Our agents have been watching the convoys closely for weeks for just such a cargo as the Carethusia is taking over." "Can we trust Androka?" Nelson asked, with a sudden note of suspicion in his voice. "Yes," Brandt assured him. "Of all men—we can trust Androka!" "But he's a Czech," Nelson argued. "The gestapo takes care of Czechs and Poles and Frenchmen and other foreigners whom it chooses as its agents," Brandt pointed out. "Androka has a daughter and other relations in Prague. He knows that if anything misfires, if there is the slightest suspicion of treachery on his part, his daughter and the others will suffer. Androka's loyalty is assured!" Nelson turned to watch the forward fighting top of the Comerford . The masked German seamen were installing some sort of apparatus up there—a strange-looking object that looked something like an old-fashioned trench mortar, and which connected with cables to the room that served as Androka's laboratory and workshop. Another crew was installing radio apparatus in the mizzentop turret. Descending a companionway to see what was going on below, Nelson found that portholes were being opened, and men were spraying chemical around to rid the below-decks atmosphere of the lethal gas that had overcome the Comerford's American crew. Returning to the bridge, he found that the tide in the inlet had risen considerably, and that the cruiser was riding more easily at her anchor. Then, at Brandt's orders, the anchor was hauled in, and lifeboats and a motor launch were used as tugs to work the vessel entirely free of the sand bar. This was accomplished without difficulty. Brandt came over to where Nelson was standing on the bridge and held out his hand. "Congratulations, Herr Kommander Nelson!" he said. "Ve have stolen one of the United States navy's newest and fastest cruisers!" He made a gesture as if raising a beer stein to drink a toast. " Prosit! " he added. " Prosit! " Nelson repeated, and the two grinned at each other. Stars were twinkling in a patch of black-blue sky, and broken mountains of gray cloud were skudding before the east wind. Commander Bob Curtis found himself lying in wet sand, on a beach, somewhere, with the rain—now a light, driving mist—beating on his face. He was chilled; his limbs were stiff and numb. His nose and throat felt parched inside, as if a wave of searing heat had scorched them. According to his last calculations, the Comerford had been cruising off the Maine coast. This probably was one of the islets of that region, or it might be the mainland. It was hard work getting to his feet, and when he did manage to stand, he could only plant his heels in the sand and sway to and fro for fully a minute, like a child learning to walk. All around him in the nearly total darkness, he could make out the dim forms of men sprawled on the beach; and of other men moving about, exploring. He heard the murmur of voices and saw the glow of lighted cigarettes. A man with a flashlight was approaching him. Its white glare shone for a moment in Curtis' face, and the familiar voice of Ensign Jack Dillon spoke: "Commander Curtis! Are you O. K., sir?" "I think so!" Curtis' heart warmed at the eager expression in Dillon's face; at the heartfelt concern in his friendly brown eyes. The young ensign was red-headed, impetuous, thoroughly genuine in his emotions. "How about yourself, Jack?" Curtis added. "A bit of a headache from the gas, but that's all. Any orders, sir?" Curtis thought for a moment. "Muster the crew, as best you can. We'll try to make a roll call. Is there any sign of the ship?" There was a solemn note in Dillon's voice. "No, sir. She's been worked off the sandbar and put to sea!" The words struck Curtis with the numbing shock of a blow on some nerve center. For the first time, he realized fully the tragedy that had swept down on him. He had lost his ship—one of the United States navy's fastest and newest small light cruisers—under circumstances which smelled strongly of treachery and sabotage. As he thought back, he realized that he might have prevented the loss, if he had been more alert, more suspicious. For it was clear to him now that the Comerford had been deliberately steered to this place; that the men who had seized her had been waiting here for that very purpose. The pieces of the picture fitted together like a jigsaw puzzle—Androka's zone of silence; the bearings given by radio; Navigating Officer Nelson's queer conduct. They were all part of a carefully laid plan! All the suspicious circumstances surrounding Nelson came flooding into Curtis' mind. He had never liked the man; never trusted him. Nelson always acted as if he had some secret, something to hide. Curtis recalled that Nelson and Androka had long conversations together—conversations which they would end abruptly when anyone else came within earshot. And Nelson had always been chummy with the worst trouble maker in the crew—Bos'n's Mate Bradford. Curtis went around, finding the officers, issuing orders. There were still some unconscious men to be revived. In a sheltered cove among the rocks, an exploring group had found enough dry driftwood to make a fire— In another hour, the skies had cleared, and white moonlight flooded the scene with a ghostly radiance. The men of the Comerford had all regained consciousness and were drying out in front of the big driftwood bonfires in the cove. Curtis ordered a beacon kept burning on a high promontory. Then he got the men lined up, according to their respective classifications, for a check-up on the missing. When this was completed, it was found that the Comerford's entire complement of two hundred and twenty men were present—except Navigating Officer Nelson, and Bos'n's Mate Bradford! And Zukor Androka was also missing! With the coming of dawn, a little exploration revealed that the Comerford's crew was marooned on an islet, about a square mile in area; that they had been put ashore without food or extra clothing or equipment of any kind, and that no boats had been left for them. One searching party reported finding the remains of what had been a radio station on a high promontory on the north shore of the islet. Another had found the remains of tents and log cabins, recently demolished, in a small, timbered hollow—a well-hidden spot invisible from the air, unless one were flying very low; a place where two hundred or more men could have camped. There was a good water supply—a small creek fed by springs—but nothing in the way of food. Evidently food was a precious commodity which the recent inhabitants of the islet couldn't afford to leave behind. Curtis was studying the wreckage of the wireless station, wondering if this might have been the source of Androka's zone of silence, when Ensign Jack Dillon came up to him. "There's a coast-guard cutter heading for the island, sir," he announced.
|
B. No, exposed crewmen were left nearly comatose.
|
What is result of their Principal Component Analysis?
|
### Introduction
A number of works have explored integrating the visual modality for Neural Machine Translation (NMT) models, though, there has been relatively modest gains or no gains at all by incorporating the visual modality in the translation pipeline BIBREF0. In particular, BIBREF1 leverage multi-task learning, BIBREF2 use visual adaptive training, while BIBREF3, BIBREF4, BIBREF5 use a number of fusion techniques to incorporate features obtained from the visual modality. Regarding the seemingly low utility of visual modality in machine translation, BIBREF6 hypothesize that the highly relevant visual properties are often not represented by linguistic models because they are too obvious to be explicitly mentioned in text (e.g., birds have wings, violins are brown). Similarly, BIBREF7 argue that perceptual information is already sufficiently encoded in textual cues. However, recently BIBREF0 have demonstrated that neural models are capable of leveraging the visual modality for translations, and posit that it is the nature of the Multi30k dataset (the only multimodal machine translation dataset at the time) which is inhibiting gains from the visual modality to emerge, due to the presence of short, simple and repetitive sentences, which renders the source text as sufficient context for translation. In this work, we further investigate this hypothesis on a large-scale multimodal machine translation (MMT) dataset, named How2 BIBREF2, which has 1.57 times longer sentences, in terms of the mean sentence length, when compared to Multi30k . To this end, we restrict ourselves to the Sequence-to-Sequence (Seq2Seq) framework and propose three simple but novel fusion techniques to ensure the utilization of visual context during different stages (Input Context Encoding, Attention and Supervision) of the Sequence-to-Sequence transduction pipeline. We then evaluate and analyze the results for further insights, with the goal of testing the utility of visual modality for NMT under full source-side linguistic context. ### Proposed Fusion Techniques
In this section, we describe three additions to the Seq2Seq model to ensure that the visual context is utilized at different stages, namely when computing context during each step of the decoder, during attention as well as when computing the supervision signal in the Sequence-to-Sequence pipeline. This is done to encourage the Seq2Seq NMT model to make use of the visual features under full linguistic context. In each case, we assume that the visual features are fine-tuned using a visual encoder, which is trained jointly alongside the Seq2Seq model. ### Proposed Fusion Techniques ::: Step-Wise Decoder Fusion
Our first proposed technique is the step-wise decoder fusion of visual features during every prediction step i.e. we concatenate the visual encoding as context at each step of the decoding process. This differs from the usual practice of passing the visual feature only at the beginning of the decoding process BIBREF5. ### Proposed Fusion Techniques ::: Multimodal Attention Modulation
Similar to general attention BIBREF8, wherein a variable-length alignment vector $a_{th}(s)$, whose size equals the number of time steps on the source side, is derived by comparing the current target hidden state $h_{t}$ with each source hidden state $\overline{h_{s}}$; we consider a variant wherein the visual encoding $v_{t}$ is used to calculate an attention distribution $a_{tv}(s)$ over the source encodings as well. Then, the true attention distribution $a_{t}(s)$ is computed as an interpolation between the visual and text based attention scores. The score function is a content based scoring mechanism as usual. This formulation differs from BIBREF3 in that we use both the natural language as well as the visual modality to compute attention over the source sentence, rather than having attention over images. Since attention is computed over the same source embeddings (arising from a single encoder) using two different modalities, our approach also differs from BIBREF4, which focuses on combining the attention scores of multiple source encoders. ### Proposed Fusion Techniques ::: Visual-Semantic (VS) Regularizer
In terms of leveraging the visual modality for supervision, BIBREF1 use multi-task learning to learn grounded representations through image representation prediction. However, to our knowledge, visual-semantic supervision hasn't been much explored for multimodal translation in terms of loss functions. Our proposed technique is the inclusion of visual-semantic supervision to the machine translation model. Recently, BIBREF9 proposed an optimal transport based loss function which computes the distance between the word embeddings of the predicted sentence and the target sentence and uses it as a regularizer $L_{\text{ot}}^{\text{tgt}}$. The purpose of this term is to provide the model with sequence level supervision. We leverage this idea by including a Cosine distance term, $L_{\text{cosine}}^{\text{visual}}$, between the visual encoding (which is at the sentence level) and the target/predicted sentence embeddings (computed as the average of the target/predicted word embeddings). The purpose of this distance term is to provide sequence level supervision by aligning the visual and text embeddings. In practice, as in BIBREF9, we introduce a hyperparameter in the loss function: where $\gamma $ is a hyper-parameter balancing the effect of loss components (a separate hyperparameter than in Section 2.2). ### Results and Analysis
Throughout our experiments, we use the 300 hours subset of How2 dataset BIBREF10, which contains 300 hours of videos, sentence-level time alignments to the ground-truth English subtitles, and Portuguese translations of English subtitles. The How2 dataset has 2048 dimensional pre-trained ResNeXt embeddings BIBREF11 available for each of the video clips aligned to the sentences. Further, our baseline model is the canonical Seq2Seq model BIBREF12 consisting of bidirectional LSTM as encoder and decoder, general attention BIBREF8 and length normalization BIBREF13. In all cases, we use the embedding size of 300 and the hidden size of 512. Whenever the visual modality is used, we encode each of the visual features to 300 dimensional vectors through an encoder (consisting of a Linear layer followed by Batch Normalization and ReLU non-linearity) which is also trained end-to-end with the Seq2Seq model. Further, to integrate sequence level supervision as in BIBREF9, we utilize the Geomloss library , which provides a batched implementation of the Sinkhorn algorithm for the Optimal Transport computation. For all the translation experiments, we preprocess the data by lowercasing and removing the punctuations BIBREF2, and construct vocabulary at word level. Adam optimizer with a learning rate of 0.001 and a learning rate decay of 0.5 is used to throughout to train our models. ### Results and Analysis ::: Experimental Results
The performances of the models are summarized in Table TABREF9, along with the gains in BLEU points. From Table TABREF9, we can make a few observations: The visual modality leads to modest gains in BLEU scores. The proposed VS regularizer leads to slightly higher gain when compared to Decoder-Fusion and Attention modulation techniques for the En-Pt language pair. Further, the gains from incorporating the visual modality are less for Multimodal Attention and VS Regularization in the case of the reversed language pair of Pt-En (Table TABREF10), even though the visual modality is common to both the languages. This can possibly be attributed to the How2 dataset creation process wherein first the videos were aligned with English sentences and then the Portuguese translations were created, implying a reduction in correspondence with the visual modality due to errors introduced in the translation process. ### Results and Analysis ::: Discussion
To analyze the reasons for modest gains, despite incorporating multiple techniques to effectively leverage the visual modality for machine translation, we inspect the dataset as well as the proposed mechanisms. ### Results and Analysis ::: Discussion ::: PCA of Visual Features
We first investigate and compare the visual feature quality of the How2 dataset with respect to that of the Multi30k dataset . To analyze the discriminativeness of the visual features for both of these datasets, we leverage an analysis mechanism used in BIBREF14 in the context of analyzing word embedding discriminativeness. We analyze the variance of the visual features corresponding to each sentence in the training set. Since the visual features semantically represent the sentence as well, we could analyze how well the features are able to discriminate between the sentences and consequently between the individual words, as a measure of their utility for NMT. Figure FIGREF14 (Top) shows the variance explained by the Top 100 principal components, obtained by applying PCA on the How2 and Multi30k training set visual features. The original feature dimensions are 2048 in both the cases. It is clear from the Figure FIGREF14 that most of the energy of the visual feature space resides in a low-dimensional subspace BIBREF14. In other words, there exist a few directions in the embedding space which disproportionately explain the variance. These "common" directions affect all of the embeddings in the same way, rendering them less discriminative. Figure FIGREF14 also shows the cumulative variance explained by Top 10, 20, 50 and 100 principal components respectively. It is clear that the visual features in the case of How2 dataset are much more dominated by the "common" dimensions, when compared to the Multi30k dataset. Further, this analysis is still at the sentence level, i.e. the visual features are much less discriminative among individual sentences, further aggravating the problem at the token level. This suggests that the existing visual features aren't sufficient enough to expect benefits from the visual modality in NMT, since they won't provide discriminativeness among the vocabulary elements at the token level during prediction. Further, this also indicates that under subword vocabulary such as BPE BIBREF15 or Sentence-Piece BIBREF16, the utility of such visual embeddings will only aggravate. ### Results and Analysis ::: Discussion ::: Comparison of Attention Components
In this section, we analyze the visual and text based attention mechanisms. We find that the visual attention is very sparse, in that just one source encoding is attended to (the maximum visual attention over source encodings, across the test set, has mean 0.99 and standard deviation 0.015), thereby limiting the use of modulation. Thus, in practice, we find that a small weight ($\gamma =0.1$) is necessary to prevent degradation due to this sparse visual attention component. Figure FIGREF18 & FIGREF19 shows the comparison of visual and text based attention for two sentences, one long source sentence of length 21 and one short source sentence of length 7. In both cases, we find that the visual component of the attention hasn't learnt any variation over the source encodings, again suggesting that the visual embeddings do not lend themselves to enhancing token-level discriminativess during prediction. We find this to be consistent across sentences of different lengths. ### Conclusions and Future Work
To conclude, we investigated the utility of visual modality for NMT, under full linguistic context on a new large-scale MMT dataset named How2. Our results on the How2 dataset confirm the general consensus that the visual modality does not lead to any significant gains for NMT, however, unlike BIBREF0 we attribute the relatively modest gains to the limited discriminativeness offered by the existing visual features, rather than the length of the sentences in the dataset. We validate this hypothesis quantitatively through a PCA based analysis of the visual features as well as qualitatively by analyzing attention components. We hope that our work would lead to more useful techniques and better visual features for MMT. An immediate future direction to explore would be to construct more discriminative features for utilizing the visual modality in NMT. Table 2: BLEU Score Comparison of the proposed methods Figure 1: Top: Variance Explained by the Top 100 Components. Bottom: Cumulative Variance Explained by the Top Components. Table 1: BLEU Score Comparison of the proposed methods Figure 2: Left: Text Based Attention (Horizontal Direction Represents the Source Sentence) Right: Visual Attention for a 21 word Source Sentence (Labels omitted to avoid cluttering). Figure 3: Left: Text Based Attention (Horizontal Direction Represents the Source Sentence) Right: Visual Attention for a 7 word Source Sentence.
|
existing visual features aren't sufficient enough to expect benefits from the visual modality in NMT
|
What does Simon think about the possibility of time travel?
A. He thinks it's possible, but finds it ridiculous that Oktoberfest would be the place to find it.
B. He hopes that it's real, and spends a lot of time thinking about how to avoid a paradox.
C. He knows that it's real, but thinks that its secret will be kept in the future.
D. He thinks it's incredibly stupid and not worth considering.
|
UNBORN TOMORROW BY MACK REYNOLDS Unfortunately , there was only one thing he could bring back from the wonderful future ... and though he didn't want to ... nevertheless he did.... Illustrated by Freas Betty looked up from her magazine. She said mildly, "You're late." "Don't yell at me, I feel awful," Simon told her. He sat down at his desk, passed his tongue over his teeth in distaste, groaned, fumbled in a drawer for the aspirin bottle. He looked over at Betty and said, almost as though reciting, "What I need is a vacation." "What," Betty said, "are you going to use for money?" "Providence," Simon told her whilst fiddling with the aspirin bottle, "will provide." "Hm-m-m. But before providing vacations it'd be nice if Providence turned up a missing jewel deal, say. Something where you could deduce that actually the ruby ring had gone down the drain and was caught in the elbow. Something that would net about fifty dollars." Simon said, mournful of tone, "Fifty dollars? Why not make it five hundred?" "I'm not selfish," Betty said. "All I want is enough to pay me this week's salary." "Money," Simon said. "When you took this job you said it was the romance that appealed to you." "Hm-m-m. I didn't know most sleuthing amounted to snooping around department stores to check on the clerks knocking down." Simon said, enigmatically, "Now it comes." There was a knock. Betty bounced up with Olympic agility and had the door swinging wide before the knocking was quite completed. He was old, little and had bug eyes behind pince-nez glasses. His suit was cut in the style of yesteryear but when a suit costs two or three hundred dollars you still retain caste whatever the styling. Simon said unenthusiastically, "Good morning, Mr. Oyster." He indicated the client's chair. "Sit down, sir." The client fussed himself with Betty's assistance into the seat, bug-eyed Simon, said finally, "You know my name, that's pretty good. Never saw you before in my life. Stop fussing with me, young lady. Your ad in the phone book says you'll investigate anything." "Anything," Simon said. "Only one exception." "Excellent. Do you believe in time travel?" Simon said nothing. Across the room, where she had resumed her seat, Betty cleared her throat. When Simon continued to say nothing she ventured, "Time travel is impossible." "Why?" "Why?" "Yes, why?" Betty looked to her boss for assistance. None was forthcoming. There ought to be some very quick, positive, definite answer. She said, "Well, for one thing, paradox. Suppose you had a time machine and traveled back a hundred years or so and killed your own great-grandfather. Then how could you ever be born?" "Confound it if I know," the little fellow growled. "How?" Simon said, "Let's get to the point, what you wanted to see me about." "I want to hire you to hunt me up some time travelers," the old boy said. Betty was too far in now to maintain her proper role of silent secretary. "Time travelers," she said, not very intelligently. The potential client sat more erect, obviously with intent to hold the floor for a time. He removed the pince-nez glasses and pointed them at Betty. He said, "Have you read much science fiction, Miss?" "Some," Betty admitted. "Then you'll realize that there are a dozen explanations of the paradoxes of time travel. Every writer in the field worth his salt has explained them away. But to get on. It's my contention that within a century or so man will have solved the problems of immortality and eternal youth, and it's also my suspicion that he will eventually be able to travel in time. So convinced am I of these possibilities that I am willing to gamble a portion of my fortune to investigate the presence in our era of such time travelers." Simon seemed incapable of carrying the ball this morning, so Betty said, "But ... Mr. Oyster, if the future has developed time travel why don't we ever meet such travelers?" Simon put in a word. "The usual explanation, Betty, is that they can't afford to allow the space-time continuum track to be altered. If, say, a time traveler returned to a period of twenty-five years ago and shot Hitler, then all subsequent history would be changed. In that case, the time traveler himself might never be born. They have to tread mighty carefully." Mr. Oyster was pleased. "I didn't expect you to be so well informed on the subject, young man." Simon shrugged and fumbled again with the aspirin bottle. Mr. Oyster went on. "I've been considering the matter for some time and—" Simon held up a hand. "There's no use prolonging this. As I understand it, you're an elderly gentleman with a considerable fortune and you realize that thus far nobody has succeeded in taking it with him." Mr. Oyster returned his glasses to their perch, bug-eyed Simon, but then nodded. Simon said, "You want to hire me to find a time traveler and in some manner or other—any manner will do—exhort from him the secret of eternal life and youth, which you figure the future will have discovered. You're willing to pony up a part of this fortune of yours, if I can deliver a bona fide time traveler." "Right!" Betty had been looking from one to the other. Now she said, plaintively, "But where are you going to find one of these characters—especially if they're interested in keeping hid?" The old boy was the center again. "I told you I'd been considering it for some time. The Oktoberfest , that's where they'd be!" He seemed elated. Betty and Simon waited. "The Oktoberfest ," he repeated. "The greatest festival the world has ever seen, the carnival, feria , fiesta to beat them all. Every year it's held in Munich. Makes the New Orleans Mardi gras look like a quilting party." He began to swing into the spirit of his description. "It originally started in celebration of the wedding of some local prince a century and a half ago and the Bavarians had such a bang-up time they've been holding it every year since. The Munich breweries do up a special beer, Marzenbräu they call it, and each brewery opens a tremendous tent on the fair grounds which will hold five thousand customers apiece. Millions of liters of beer are put away, hundreds of thousands of barbecued chickens, a small herd of oxen are roasted whole over spits, millions of pair of weisswurst , a very special sausage, millions upon millions of pretzels—" "All right," Simon said. "We'll accept it. The Oktoberfest is one whale of a wingding." "Well," the old boy pursued, into his subject now, "that's where they'd be, places like the Oktoberfest . For one thing, a time traveler wouldn't be conspicuous. At a festival like this somebody with a strange accent, or who didn't know exactly how to wear his clothes correctly, or was off the ordinary in any of a dozen other ways, wouldn't be noticed. You could be a four-armed space traveler from Mars, and you still wouldn't be conspicuous at the Oktoberfest . People would figure they had D.T.'s." "But why would a time traveler want to go to a—" Betty began. "Why not! What better opportunity to study a people than when they are in their cups? If you could go back a few thousand years, the things you would wish to see would be a Roman Triumph, perhaps the Rites of Dionysus, or one of Alexander's orgies. You wouldn't want to wander up and down the streets of, say, Athens while nothing was going on, particularly when you might be revealed as a suspicious character not being able to speak the language, not knowing how to wear the clothes and not familiar with the city's layout." He took a deep breath. "No ma'am, you'd have to stick to some great event, both for the sake of actual interest and for protection against being unmasked." The old boy wound it up. "Well, that's the story. What are your rates? The Oktoberfest starts on Friday and continues for sixteen days. You can take the plane to Munich, spend a week there and—" Simon was shaking his head. "Not interested." As soon as Betty had got her jaw back into place, she glared unbelievingly at him. Mr. Oyster was taken aback himself. "See here, young man, I realize this isn't an ordinary assignment, however, as I said, I am willing to risk a considerable portion of my fortune—" "Sorry," Simon said. "Can't be done." "A hundred dollars a day plus expenses," Mr. Oyster said quietly. "I like the fact that you already seem to have some interest and knowledge of the matter. I liked the way you knew my name when I walked in the door; my picture doesn't appear often in the papers." "No go," Simon said, a sad quality in his voice. "A fifty thousand dollar bonus if you bring me a time traveler." "Out of the question," Simon said. "But why ?" Betty wailed. "Just for laughs," Simon told the two of them sourly, "suppose I tell you a funny story. It goes like this:" I got a thousand dollars from Mr. Oyster (Simon began) in the way of an advance, and leaving him with Betty who was making out a receipt, I hustled back to the apartment and packed a bag. Hell, I'd wanted a vacation anyway, this was a natural. On the way to Idlewild I stopped off at the Germany Information Offices for some tourist literature. It takes roughly three and a half hours to get to Gander from Idlewild. I spent the time planning the fun I was going to have. It takes roughly seven and a half hours from Gander to Shannon and I spent that time dreaming up material I could put into my reports to Mr. Oyster. I was going to have to give him some kind of report for his money. Time travel yet! What a laugh! Between Shannon and Munich a faint suspicion began to simmer in my mind. These statistics I read on the Oktoberfest in the Munich tourist pamphlets. Five million people attended annually. Where did five million people come from to attend an overgrown festival in comparatively remote Southern Germany? The tourist season is over before September 21st, first day of the gigantic beer bust. Nor could the Germans account for any such number. Munich itself has a population of less than a million, counting children. And those millions of gallons of beer, the hundreds of thousands of chickens, the herds of oxen. Who ponied up all the money for such expenditures? How could the average German, with his twenty-five dollars a week salary? In Munich there was no hotel space available. I went to the Bahnhof where they have a hotel service and applied. They put my name down, pocketed the husky bribe, showed me where I could check my bag, told me they'd do what they could, and to report back in a few hours. I had another suspicious twinge. If five million people attended this beer bout, how were they accommodated? The Theresienwiese , the fair ground, was only a few blocks away. I was stiff from the plane ride so I walked. There are seven major brewers in the Munich area, each of them represented by one of the circuslike tents that Mr. Oyster mentioned. Each tent contained benches and tables for about five thousand persons and from six to ten thousands pack themselves in, competing for room. In the center is a tremendous bandstand, the musicians all lederhosen clad, the music as Bavarian as any to be found in a Bavarian beer hall. Hundreds of peasant garbed fräuleins darted about the tables with quart sized earthenware mugs, platters of chicken, sausage, kraut and pretzels. I found a place finally at a table which had space for twenty-odd beer bibbers. Odd is right. As weird an assortment of Germans and foreign tourists as could have been dreamed up, ranging from a seventy- or eighty-year-old couple in Bavarian costume, to the bald-headed drunk across the table from me. A desperate waitress bearing six mugs of beer in each hand scurried past. They call them masses , by the way, not mugs. The bald-headed character and I both held up a finger and she slid two of the masses over to us and then hustled on. "Down the hatch," the other said, holding up his mass in toast. "To the ladies," I told him. Before sipping, I said, "You know, the tourist pamphlets say this stuff is eighteen per cent. That's nonsense. No beer is that strong." I took a long pull. He looked at me, waiting. I came up. "Mistaken," I admitted. A mass or two apiece later he looked carefully at the name engraved on his earthenware mug. "Löwenbräu," he said. He took a small notebook from his pocket and a pencil, noted down the word and returned the things. "That's a queer looking pencil you have there," I told him. "German?" "Venusian," he said. "Oops, sorry. Shouldn't have said that." I had never heard of the brand so I skipped it. "Next is the Hofbräu," he said. "Next what?" Baldy's conversation didn't seem to hang together very well. "My pilgrimage," he told me. "All my life I've been wanting to go back to an Oktoberfest and sample every one of the seven brands of the best beer the world has ever known. I'm only as far as Löwenbräu. I'm afraid I'll never make it." I finished my mass . "I'll help you," I told him. "Very noble endeavor. Name is Simon." "Arth," he said. "How could you help?" "I'm still fresh—comparatively. I'll navigate you around. There are seven beer tents. How many have you got through, so far?" "Two, counting this one," Arth said. I looked at him. "It's going to be a chore," I said. "You've already got a nice edge on." Outside, as we made our way to the next tent, the fair looked like every big State-Fair ever seen, except it was bigger. Games, souvenir stands, sausage stands, rides, side shows, and people, people, people. The Hofbräu tent was as overflowing as the last but we managed to find two seats. The band was blaring, and five thousand half-swacked voices were roaring accompaniment. In Muenchen steht ein Hofbräuhaus! Eins, Zwei, G'sufa! At the G'sufa everybody upped with the mugs and drank each other's health. "This is what I call a real beer bust," I said approvingly. Arth was waving to a waitress. As in the Löwenbräu tent, a full quart was the smallest amount obtainable. A beer later I said, "I don't know if you'll make it or not, Arth." "Make what?" "All seven tents." "Oh." A waitress was on her way by, mugs foaming over their rims. I gestured to her for refills. "Where are you from, Arth?" I asked him, in the way of making conversation. "2183." "2183 where?" He looked at me, closing one eye to focus better. "Oh," he said. "Well, 2183 South Street, ah, New Albuquerque." "New Albuquerque? Where's that?" Arth thought about it. Took another long pull at the beer. "Right across the way from old Albuquerque," he said finally. "Maybe we ought to be getting on to the Pschorrbräu tent." "Maybe we ought to eat something first," I said. "I'm beginning to feel this. We could get some of that barbecued ox." Arth closed his eyes in pain. "Vegetarian," he said. "Couldn't possibly eat meat. Barbarous. Ugh." "Well, we need some nourishment," I said. "There's supposed to be considerable nourishment in beer." That made sense. I yelled, " Fräulein! Zwei neu bier! " Somewhere along in here the fog rolled in. When it rolled out again, I found myself closing one eye the better to read the lettering on my earthenware mug. It read Augustinerbräu. Somehow we'd evidently navigated from one tent to another. Arth was saying, "Where's your hotel?" That seemed like a good question. I thought about it for a while. Finally I said, "Haven't got one. Town's jam packed. Left my bag at the Bahnhof. I don't think we'll ever make it, Arth. How many we got to go?" "Lost track," Arth said. "You can come home with me." We drank to that and the fog rolled in again. When the fog rolled out, it was daylight. Bright, glaring, awful daylight. I was sprawled, complete with clothes, on one of twin beds. On the other bed, also completely clothed, was Arth. That sun was too much. I stumbled up from the bed, staggered to the window and fumbled around for a blind or curtain. There was none. Behind me a voice said in horror, "Who ... how ... oh, Wodo , where'd you come from?" I got a quick impression, looking out the window, that the Germans were certainly the most modern, futuristic people in the world. But I couldn't stand the light. "Where's the shade," I moaned. Arth did something and the window went opaque. "That's quite a gadget," I groaned. "If I didn't feel so lousy, I'd appreciate it." Arth was sitting on the edge of the bed holding his bald head in his hands. "I remember now," he sorrowed. "You didn't have a hotel. What a stupidity. I'll be phased. Phased all the way down." "You haven't got a handful of aspirin, have you?" I asked him. "Just a minute," Arth said, staggering erect and heading for what undoubtedly was a bathroom. "Stay where you are. Don't move. Don't touch anything." "All right," I told him plaintively. "I'm clean. I won't mess up the place. All I've got is a hangover, not lice." Arth was gone. He came back in two or three minutes, box of pills in hand. "Here, take one of these." I took the pill, followed it with a glass of water. And went out like a light. Arth was shaking my arm. "Want another mass ?" The band was blaring, and five thousand half-swacked voices were roaring accompaniment. In Muenchen steht ein Hofbräuhaus! Eins, Zwei, G'sufa! At the G'sufa everybody upped with their king-size mugs and drank each other's health. My head was killing me. "This is where I came in, or something," I groaned. Arth said, "That was last night." He looked at me over the rim of his beer mug. Something, somewhere, was wrong. But I didn't care. I finished my mass and then remembered. "I've got to get my bag. Oh, my head. Where did we spend last night?" Arth said, and his voice sounded cautious, "At my hotel, don't you remember?" "Not very well," I admitted. "I feel lousy. I must have dimmed out. I've got to go to the Bahnhof and get my luggage." Arth didn't put up an argument on that. We said good-by and I could feel him watching after me as I pushed through the tables on the way out. At the Bahnhof they could do me no good. There were no hotel rooms available in Munich. The head was getting worse by the minute. The fact that they'd somehow managed to lose my bag didn't help. I worked on that project for at least a couple of hours. Not only wasn't the bag at the luggage checking station, but the attendant there evidently couldn't make heads nor tails of the check receipt. He didn't speak English and my high school German was inadequate, especially accompanied by a blockbusting hangover. I didn't get anywhere tearing my hair and complaining from one end of the Bahnhof to the other. I drew a blank on the bag. And the head was getting worse by the minute. I was bleeding to death through the eyes and instead of butterflies I had bats in my stomach. Believe me, nobody should drink a gallon or more of Marzenbräu. I decided the hell with it. I took a cab to the airport, presented my return ticket, told them I wanted to leave on the first obtainable plane to New York. I'd spent two days at the Oktoberfest , and I'd had it. I got more guff there. Something was wrong with the ticket, wrong date or some such. But they fixed that up. I never was clear on what was fouled up, some clerk's error, evidently. The trip back was as uninteresting as the one over. As the hangover began to wear off—a little—I was almost sorry I hadn't been able to stay. If I'd only been able to get a room I would have stayed, I told myself. From Idlewild, I came directly to the office rather than going to my apartment. I figured I might as well check in with Betty. I opened the door and there I found Mr. Oyster sitting in the chair he had been occupying four—or was it five—days before when I'd left. I'd lost track of the time. I said to him, "Glad you're here, sir. I can report. Ah, what was it you came for? Impatient to hear if I'd had any results?" My mind was spinning like a whirling dervish in a revolving door. I'd spent a wad of his money and had nothing I could think of to show for it; nothing but the last stages of a grand-daddy hangover. "Came for?" Mr. Oyster snorted. "I'm merely waiting for your girl to make out my receipt. I thought you had already left." "You'll miss your plane," Betty said. There was suddenly a double dip of ice cream in my stomach. I walked over to my desk and looked down at the calendar. Mr. Oyster was saying something to the effect that if I didn't leave today, it would have to be tomorrow, that he hadn't ponied up that thousand dollars advance for anything less than immediate service. Stuffing his receipt in his wallet, he fussed his way out the door. I said to Betty hopefully, "I suppose you haven't changed this calendar since I left." Betty said, "What's the matter with you? You look funny. How did your clothes get so mussed? You tore the top sheet off that calendar yourself, not half an hour ago, just before this marble-missing client came in." She added, irrelevantly, "Time travelers yet." I tried just once more. "Uh, when did you first see this Mr. Oyster?" "Never saw him before in my life," she said. "Not until he came in this morning." "This morning," I said weakly. While Betty stared at me as though it was me that needed candling by a head shrinker preparatory to being sent off to a pressure cooker, I fished in my pocket for my wallet, counted the contents and winced at the pathetic remains of the thousand. I said pleadingly, "Betty, listen, how long ago did I go out that door—on the way to the airport?" "You've been acting sick all morning. You went out that door about ten minutes ago, were gone about three minutes, and then came back." "See here," Mr. Oyster said (interrupting Simon's story), "did you say this was supposed to be amusing, young man? I don't find it so. In fact, I believe I am being ridiculed." Simon shrugged, put one hand to his forehead and said, "That's only the first chapter. There are two more." "I'm not interested in more," Mr. Oyster said. "I suppose your point was to show me how ridiculous the whole idea actually is. Very well, you've done it. Confound it. However, I suppose your time, even when spent in this manner, has some value. Here is fifty dollars. And good day, sir!" He slammed the door after him as he left. Simon winced at the noise, took the aspirin bottle from its drawer, took two, washed them down with water from the desk carafe. Betty looked at him admiringly. Came to her feet, crossed over and took up the fifty dollars. "Week's wages," she said. "I suppose that's one way of taking care of a crackpot. But I'm surprised you didn't take his money and enjoy that vacation you've been yearning about." "I did," Simon groaned. "Three times." Betty stared at him. "You mean—" Simon nodded, miserably. She said, "But Simon . Fifty thousand dollars bonus. If that story was true, you should have gone back again to Munich. If there was one time traveler, there might have been—" "I keep telling you," Simon said bitterly, "I went back there three times. There were hundreds of them. Probably thousands." He took a deep breath. "Listen, we're just going to have to forget about it. They're not going to stand for the space-time continuum track being altered. If something comes up that looks like it might result in the track being changed, they set you right back at the beginning and let things start—for you—all over again. They just can't allow anything to come back from the future and change the past." "You mean," Betty was suddenly furious at him, "you've given up! Why this is the biggest thing— Why the fifty thousand dollars is nothing. The future! Just think!" Simon said wearily, "There's just one thing you can bring back with you from the future, a hangover compounded of a gallon or so of Marzenbräu. What's more you can pile one on top of the other, and another on top of that!" He shuddered. "If you think I'm going to take another crack at this merry-go-round and pile a fourth hangover on the three I'm already nursing, all at once, you can think again." THE END Transcriber's Note: This etext was produced from Astounding Science Fiction June 1959. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed. Minor spelling and typographical errors have been corrected without note.
|
C. He knows that it's real, but thinks that its secret will be kept in the future.
|
By explaining neural activity in the brain, what does the author of the article imply?
A. If humans want to avoid the major illnesses like dementia and Alzheimers, they can do so by sharing more content as they grow older
B. If humans do not use their neurons, they will lose them (and their potential) forever
C. If humans can quickly acclimate to a Sharist ideology, there is a better chance that they can survive global threats
D. If humans are not constantly sharing, they will deteriorate and become unproductive
|
Sharism: A Mind Revolution With the People of the World Wide Web communicating more fully and freely in Social Media while rallying a Web 2.0 content boom, the inner dynamics of such a creative explosion must be studied more closely. What motivates those who join this movement and what future will they create? A key fact is that a superabundance of community respect and social capital are being accumulated by those who share. The key motivator of Social Media and the core spirit of Web 2.0 is a mind switch called Sharism. Sharism suggests a re-orientation of personal values. We see it in User Generated Content. It is the pledge of Creative Commons. It is in the plans of future-oriented cultural initiatives. Sharism is also a mental practice that anyone can try, a social-psychological attitude to transform a wide and isolated world into a super-smart Social Brain. The Neuron Doctrine Sharism is encoded in the Human Genome. Although eclipsed by the many pragmatisms of daily life, the theory of Sharism finds basis in neuroscience and its study of the working model of the human brain. Although we can’t entirely say how the brain works as a whole, we do have a model of the functional mechanism of the nervous system and its neurons. A neuron is not a simple organic cell, but a very powerful, electrically excitable biological processor. Groups of neurons form vastly interconnected networks, which, by changing the strength of the synapses between cells, can process information, and learn. A neuron, by sharing chemical signals with its neighbors, can be integrated into more meaningful patterns that keep the neuron active and alive. Moreover, such a simple logic can be iterated and amplified, since all neurons work on a similar principle of connecting and sharing. Originally, the brain is quite open. A neural network exists to share activity and information, and I believe this model of the brain should inspire ideas and decisions about human networks. Thus, our brain supports sharing in its very system-nature. This has profound implications for the creative process. Whenever you have an intention to create, you will find it easier to generate more creative ideas if you keep the sharing process firmly in mind. The idea-forming-process is not linear, but more like an avalanche of amplifications along the thinking path. It moves with the momentum of a creative snowball. If your internal cognitive system encourages sharing, you can engineer a feedback loop of happiness, which will help you generate even more ideas in return. It’s a kind of butterfly- effect, as the small creative energy you spend will eventually return to make you, and the world, more creative. However, daily decisions for most adults are quite low in creative productivity, if only because they’ve switched off their sharing paths. People generally like to share what they create, but in a culture that tells them to be protective of their ideas, people start to believe in the danger of sharing. Then Sharism will be degraded in their mind and not encouraged in their society. But if we can encourage someone to share, her sharing paths will stay open. Sharism will be kept in her mind as a memory and an instinct. If in the future she faces a creative choice, her choice will be, “Share.” These mind-switches are too subtle to be felt. But since the brain, and society, is a connected system, the accumulation of these micro-attitudes, from neuron to neuron and person to person, can result in observable behavior. It is easy to tell if a person, a group, a company, a nation is oriented toward Sharism or not. For those who are not, what they defend as “cultural goods” and “intellectual property” are just excuses for the status quo of keeping a community closed. Much of their “culture” will be protected, but the net result is the direct loss of many other precious ideas, and the subsequent loss of all the potential gains of sharing. This lost knowledge is a black hole in our life, which may start to swallow other values as well. Non-sharing culture misleads us with its absolute separation of Private and Public space. It makes creative action a binary choice between public and private, open and closed. This creates a gap in the spectrum of knowledge. Although this gap has the potential to become a valuable creative space, concerns about privacy make this gap hard to fill. We shouldn’t be surprised that, to be safe, most people keep their sharing private and stay “closed.” They may fear the Internet creates a potential for abuse that they can’t fight alone. However, the paradox is: The less you share, the less power you have. New Technologies and the Rise of Sharism Let’s track back to 1999, when there were only a few hundred pioneer bloggers around the world, and no more than ten times that many readers following each blog. Human history is always so: something important was happening, but the rest of the world hadn’t yet realized it. The shift toward easy-to-use online publishing triggered a soft revolution in just five years. People made a quick and easy transition from reading blogs, to leaving comments and taking part in online conversations, and then to the sudden realization that they should become bloggers themselves. More bloggers created more readers, and more readers made more blogs. The revolution was viral. Bloggers generate lively and timely information on the Internet, and connect to each other with RSS, hyperlinks, comments, trackbacks and quotes. The small-scale granularity of the content can fill discrete gaps in experience and thus record a new human history. Once you become a blogger, once you have accumulated so much social capital in such a small site, it’s hard to stop. We can’t explain this fact with a theory of addiction. It’s an impulse to share. It’s the energy of the memes that want to be passed from mouth to mouth and mind to mind. It’s more than just E-mail. It’s Sharism. Bloggers are always keen to keep the social context of their posts in mind, by asking themselves, “Who is going to see this?” Bloggers are agile in adjusting their tone−and privacy settings−to advance ideas and stay out of trouble. It’s not self-censorship, but a sense of smart expression. But once blogs reached the tipping point, they expanded into the blogosphere. This required a more delicate social networking system and content- sharing architecture. But people now understand that they can have better control over a wide spectrum of relationships. Like how Flickr allows people to share their photos widely, but safely. The checkbox-based privacy of Flickr may seem unfamiliar to a new user, but you can use it to toy with the mind-switches of Sharism. By checking a box we can choose to share or not to share. From my observations, I have seen photographers on Flickr become more open to sharing, while retaining flexible choices. The rapid emergence of Social Applications that can communicate and cooperate, by allowing people to output content from one service to another, is letting users pump their memes into a pipeline-like ecosystem. This interconnectedness allows memes to travel along multiple online social networks, and potentially reach a huge audience. As a result, such a Micro-pipeline system is making Social Media a true alternative to broadcast media. These new technologies are reviving Sharism in our closed culture. Local Practice, Global Gain If you happened to lose your Sharism in a bad educational or cultural setting, it’s hard to get it back. But it’s not impossible. A persistence of practice can lead to a full recovery. You can think of Sharism as a spiritual practice. But you must practice everyday. Otherwise, you might lose the power of sharing. Permanently. You might need something to spur you on, to keep you from quitting and returning to a closed mindset. Here’s an idea: put a sticky note on your desk that says, “What do you want to share today?” I’m not kidding. Then, if anything interesting comes your way: Share It! The easiest way to both start and keep sharing is by using different kinds of social software applications. Your first meme you want to share may be small, but you can amplify it with new technologies. Enlist some people from your network and invite them into a new social application. At first it might be hard to feel the gains of Sharism. The true test then is to see if you can keep track of the feedback that you get from sharing. You will realize that almost all sharing activities will generate positive results. The happiness that this will obtain is only the most immediate reward. But there are others. The first type of reward that you will get comes in the form of comments. Then you know you’ve provoked interest, appreciation, excitement. The second reward is access to all the other stuff being shared by friends in your network. Since you know and trust them, you will be that much more interested in what they have to share. Already, the return is a multiple of the small meme you first shared. But the third type of return is more dramatic still. Anything you share can be forwarded, circulated and republished via other people’s networks. This cascade effect can spread your work to the networked masses. Improvements in social software are making the speed of dissemination as fast as a mouse-click. You should get to know the Sharism-You. You’re about to become popular, and fast This brings us to the fourth and final type of return. It has a meaning not only for you, but for the whole of society. If you so choose, you may allow others to create derivative works from what you share. This one choice could easily snowball into more creations along the sharing path, from people at key nodes in the network who are all as passionate about creating and sharing as you are. After many iterative rounds of development, a large creative work may spring from your choice to share. Of course, you will get the credit that you asked for, and deserve. And it’s okay to seek financial rewards. But you will in every case get something just as substantial: Happiness. The more people who create in the spirit of Sharism, the easier it will be to attain well- balanced and equitable Social Media that is woven by people themselves. Media won’t be controlled by any single person but will rely on the even distribution of social networking. These “Shaeros” (Sharing Heroes) will naturally become the opinion leaders in the first wave of Social Media. However, these media rights will belong to everyone. You yourself can be both producer and consumer in such a system. Sharism Safeguards Your Rights Still, many questions will be raised about Sharism as an initiative in new age. The main one is copyright. One concern is that any loss of control over copyrighted content will lead to noticeable deficits in personal wealth, or just loss of control. 5 years ago, I would have said that this was a possibility. But things are changing today. The sharing environment is more protected than you might think. Many new social applications make it easy to set terms-of-use along your sharing path. Any infringement of those terms will be challenged not just by the law, but by your community. Your audience, who benefit form your sharing, can also be the gatekeepers of your rights. Even if you are a traditional copyright holder, this sounds ideal. Furthermore, by realizing all the immediate and emergent rewards that can be had by sharing, you may eventually find that copyright and “All Rights Reserved” are far from your mind. You will enjoy sharing too much to worry about who is keeping a copy. The new economic formula is, the more people remix your works, the higher the return. I want to point out that Sharism is not Communism, nor Socialism. As for those die- hard Communists we know, they have often abused people’s sharing nature and forced them to give up their rights, and their property. Socialism, that tender Communism, in our experience also lacked respect for these rights. Under these systems, the state owns all property. Under Sharism, you can keep ownership, if you want. But I like to share. And this is how I choose to spread ideas, and prosperity Sharism is totally based on your own consensus. It’s not a very hard concept to understand, especially since copyleft movements like the Free Software Foundation and Creative Commons have been around for years. These movements are redefining a more flexible spectrum of licenses for both developers and end-users to tag their works. Because the new licenses can be recognized by either humans or machines, it’s becoming easier to re-share those works in new online ecosystems. The Spirit of the Web, a Social Brain Sharism is the Spirit of the Age of Web 2.0. It has the consistency of a naturalized Epistemology and modernized Axiology, but also promises the power of a new Internet philosophy. Sharism will transform the world into an emergent Social Brain: a networked hybrid of people and software. We are Networked Neurons connected by the synapses of Social Software. This is an evolutionary leap, a small step for us and a giant one for human society. With new “hairy” emergent technologies sprouting all around us, we can generate higher connectivities and increase the throughput of our social links. The more open and strongly connected we social neurons are, the better the sharing environment will be for all people. The more collective our intelligence, the wiser our actions will be. People have always found better solutions through conversations. Now we can put it all online. Sharism will be the politics of the next global superpower. It will not be a country, but a new human network joined by Social Software. This may remain a distant dream, and even a well-defined public sharing policy might not be close at hand. But the ideas that I’m discussing can improve governments today. We can integrate our current and emerging democratic systems with new folksonomies (based on the collaborative, social indexing of information) to enable people to make queries, share data and remix information for public use. The collective intelligence of a vast and equitable sharing environment can be the gatekeeper of our rights, and a government watchdog. In the future, policymaking can be made more nuanced with the micro-involvement of the sharing community. This “Emergent Democracy” is more real-time than periodical parliamentary sessions. It will also increase the spectrum of our choices, beyond the binary options of “Yes” or “No” referenda. Representative democracy will become more timely and diligent, because we will represent ourselves within the system. Sharism will result in better social justice. In a healthy sharing environment, any evidence of injustice can get amplified to get the public’s attention. Anyone who has been abused can get real and instant support from her peers and her peers’ peers. Appeals to justice will take the form of petitions through multiple, interconnected channels. Using these tools, anyone can create a large social impact. With multiple devices and many social applications, each of us can become more sociable, and society more individual. We no longer have to act alone. Emergent democracy will only happen when Sharism becomes the literacy of the majority. Since Sharism can improve communication, collaboration and mutual understanding, I believe it has a place within the educational system. Sharism can be applied to any cultural discourse, CoP (Community of Practice) or problem-solving context. It is also an antidote to social depression, since sharelessness is just dragging our society down. In present or formerly totalitarian countries, this downward cycle is even more apparent. The future world will be a hybrid of human and machine that will generate better and faster decisions anytime, anywhere. The flow of information between minds will become more flexible and more productive. These vast networks of sharing will create a new social order−A Mind Revolution!
|
D. If humans are not constantly sharing, they will deteriorate and become unproductive
|
What was the only thing that mattered to Charles near the end?
A. Leaving one last note
B. Making it to his cave
C. Fighting the disease
D. Getting a final meal
|
"Phone Me in Central Park" By JAMES McCONNELL There should be an epitaph for every man, big or little, but a really grand and special one for Loner Charlie. [Transcriber's Note: This etext was produced from Planet Stories Fall 1954. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Charles turned over on his side to look at her. She lay quietly in the other bed, the most beautiful woman he had ever seen. She was blonde to perfection, exquisitely shaped, and the rich promise of her body was exposed to his view. "Why?" he thought as he looked at her. "Why did it have to happen like this?" The whole thing was still like a dream to him, and as yet he couldn't decide whether it was a good or a bad dream. A year ago she had been unattainable, a face to conjure with in erotic dreams, far beyond his ken. A year ago she had been a public idol, the most popular actress of the day. And he had been a nobody, full of a nobody's idle hopes and schemes. And now he was lying in the bed next to hers in her swank Manhattan apartment in the most exclusive hotel in town. The unrealness of the situation overwhelmed him. His mind was a picture of confused thoughts. Meanings and answers to his questions slithered out of his reach. "God," he said. It was not an exclamation, nor yet an expletive. It was a mere statement of fact. A thought teased at him. Charles looked at the woman again and decided that she still looked beautiful in spite of the harshness of the room's lighting. He touched buttons by the edge of the bed and the illumination quieted to a soft glow, wrapping her in a radiant halo. Charles smiled wanly and got up. He stood by the bed looking at her. "I could have fallen in love with you once. A year ago, perhaps, or longer. But not now. Not now." He turned away and walked to the window. "Now the world is dead. The whole world is dead." New York lay quietly below him. It was the hour of indecision when day has not quite made up its mind to leave and night has not yet attacked in force. The streetlights were already on, making geometric patterns through the dusk of Central Park. Some of the billboards were shining, their relays activated by darkness-sensitized solenoids. A reddish-orange pallor hung from the sky. It had been very pleasant that afternoon. She had given of herself freely, warmly, and Charles had accepted. But then he had known that she would. It was not him, it was the circumstances. Under the circumstances, she would have given herself to any man— "Why did it have to be her—or me? Why should it have to happen to anybody! Why!" She would have given herself to any man— His thoughts beat a rapid crescendo, activating emotions, stimulating sensations of angry rage. He wanted to cry, to weep angry tears of protest. To any man, WHO HAPPENED TO BE THE LAST MAN ON EARTH! Charles picked up a heavy book end off the table and crashed it through the thick pane of window glass. A gust of wind from the outside breezed through the shattered opening, attacking his olfactory patch with the retching smell of decaying flesh. Charles ignored it. Even smells had lost their customary meanings. He felt the rage build up inside again, tearing at his viscera. His stomach clenched up like an angry fist. "But I don't want to be the last man alive!" he shouted. "I don't know what to do! I don't know where to go, how to act! I just don't know—" A paroxysm of sobbing shook his body. Trembling, he dropped to his knees, his head against the cold firmness of the sill, his hands clutched tightly around the jagged edges of the window pane. In spite of the sharp pain that raced through his system, in spite of the bright, warm, red stream that trickled down his face, he knelt by the window for several minutes. " Maybe I'm not the last! " The thought struck him with suddenness, promisingly, edged with swelling comfort to fill his emptiness. Charles got up slowly, noticing for the first time that his fingers were badly cut. He wrapped a handkerchief around them and forgot them. He had to know—he had to find out. As he turned to leave, he noticed again the woman lying in radiant state upon the bed. He walked to her side and leaned over, kissing her gently on the forehead. As he straightened up, his leg caught against her arm, pushing it slightly. The woman's arm slipped from its position and dangled from the edge of the bed like a crazy pendulum. Charles picked it up and folded it across her now cold breasts. He started to pull the sheet over her nude form, then stopped, smiling at his conventionality. After all, it didn't make any difference now. The phonograph was near the door. On sudden impulse he switched it on, turned the volume up full, and in grim jest left it playing Rachmaninoff's Isle of the Dead on full automatic. The music haunted him down the hall to the elevator that he had to run himself. The lobby was littered with debris, human and otherwise. Charles ignored it. The street that led towards the Bureau of Vital Statistics was a mess of desolate carnage. Charles overlooked it. Shop fronts smashed, stores looted, gyro-cars wrecked, proud buildings defaced. "That was it," he said to himself. "Pride. We called this the 'Proud Era.' Everything was better and bigger and nicer to have. Buildings were taller, men were healthier, most of the problems of humanity seemed licked, or nearly so. It was a time of free power, each small unit of population, each section of town operating on perpetual, ever-lasting, automatic atomic piles. "We were free. We seemed, almost, to have accomplished something. The world was running well. No wonder we called it the 'Proud Era.' Life was fun, just a bowl of cherries, until...." Two years ago the animals had started dying. Strangely enough the rats had gone first, to anybody's notice. Sales of poison dropped, scientific laboratories chained to a perpetual rodent-cycle began to complain bitterly. Then the lovers who hunted out and haunted the lonely lanes through the countryside began to remark that the locusts were late that year. The Southern states joyously reported that mosquito control was working to an unprecedented degree. The largest cotton crop ever was forecast and rumors from Mexico had it that no one had died from scorpion bite in several weeks. A month later the meat animals, the birds and the household pets began dropping as rapidly as the flies which had dropped earlier. Congress was called into special session, as were all of the national governments around the world. The U.N. met at emergency sessions to cope with the situation. The president of the world-wide Society for the Prevention of Cruelty to Animals committed suicide. Within a year it was obvious to everyone that man was the only animal left on earth. The panic which had begun with the death of the animals was quieted somewhat by the fact that humans seemed immune to the pandemic. But the lakes full of dead fish caused a great stink and residents along the coasts began to move inland. Sales of perfumes and deodorants soared. Then just one year ago, the first human became infected with the strange malady. Within six months, half of the world's population was gone. Less than a month ago no more than a few thousand people remained in New York. And now.... "I've got to find out," Charles told himself. He meant it, of course, but in a sense he was afraid—afraid that his trip to the Bureau might give him an answer he didn't dare listen to. "But I've got to try." He walked on down the bloody street. Before the plague the Bureau of Vital Statistics had been one of man's crowning achievements. Housed as it was in a huge metallic globe of a building, it contained computers which kept exact account of every human on earth. Compulsory registration and the classification of each individual by means of the discrete patterns of his brain waves had accomplished for man what no ordinary census could have. The machine knew who was alive, who was dead, and where everybody was. Once a year the Bureau issued The Index, an exact accounting of Earth's four billion inhabitants. Four billion names and addresses, compressed into microprint, a tremendous achievement even for the "Proud Era." In all of his life, Charles had never once glanced at The Index. The average person had little necessity to do so since the Bureau information service would answer questions free of charge at any time. Reaching the gigantic building, Charles pushed aside the body of a young man and walked into the main foyer. Passing behind once-guarded doors, he entered the giant computer room and paused in admiration. Only once, before the plague, had he seen the interior of this room. But he still remembered it and he still recalled the powerful emotional experience it had been those many years ago. All children had to have a brain-wave recording made by the Bureau during the first month of their life. And again at the age of 10 each child returned to the Bureau for a recheck. It was for this latter recording that Charles had come to the Bureau some twenty-two years before and a friendly guard had let him peep briefly into the computer room. The impression of intense activity, of organized confusion, of mechanical wonder had remained with him the rest of his life. "So different now," he thought, surveying the room. "Now it's empty, so empty." The machine seemed to reflect the stillness, the very deadness of the world. The silence became unbearable. Charles walked to the master control panel. With newly acquired dexterity he switched the computer screens on and watched them glow to life. All around the world sensitive receiving stations pulsed to activity, sending out searching fingers, hunting for elusive patterns of neutral energy, mapping and tabulating the results. The main computer screen dominated one wall of the room. Other smaller screens clustered around it. On these screens could be graphed the population of any and every part of the globe. An illuminated counter immediately above it would give the numerical strength of the area being sampled while the screen would show population density by individual pinpoints of light that merged to form brightness patterns. "I'll try New York first," he said to himself, knowing that he was a coward, afraid to check the whole world from the start. "I'll start with New York and work up." Charles activated the switches that would flash a schematic map of New York on the screen. "There's bound to be somebody else left here. After all, there were at least twenty of us just a couple of days ago." And one of them, a beautiful woman, had invited him up to her apartment, not because she liked him, but because.... The main screen focused itself, the patterns shifting into a recognizable perceptual image. "Why, it was just yesterday (or was it the day before?) that ten of us, at least, met here to check the figures. There were lots of us alive then." Including the blond young woman who had died just this afternoon.... Charles stopped talking and forced his eyes upwards. Peripheral vision caught first the vague outlines of the lower part of the map. His eyes continued to move, slowly, reluctantly. They caught the over-all relief of Greater New York City—and then concentrated on the single, shining dot at the very heart of the map—and he understood. His eyes stabbed quickly for the counter above the screen. One. He gasped. The counter read one . Charles was by himself, the last person alive in all of New York City. He began to tremble violently. The silence of the room began to press quickly in on him. His frantic fingers searched for the computer controls. New York State. One. The entire United States. One. The western hemisphere, including islands. (Was that a point of light in Brazil? No. Just a ghost image). One. The Pacific area, Asia, Australia, Asia Minor, Russia and the Near East, Africa and then Europe. England! There was a light in England! Someone else still lived! The counter clicked forward. Two! His trembling stopped. He breathed again. "Of course. London was at least as populous as New York City before the plague. It's only logical that—" He stopped. For even as he spoke, the light winked out! The counter clicked again. One. Alone. Alone! Charles screamed. The bottom dropped out from under him! Why? Such a simple question, but in those three letters lay the essence of human nature. Why. The drive of curiosity. Stronger, in a way, than the so-called "basic" drives: hunger, thirst, sex, shelter, warmth, companionship, elimination. Certainly more decisive in the history of the race. Man began to think, to differentiate himself from the other animals, when he first asked the question: "Why?" But thinking about "why" didn't answer the question itself, Charles thought. He looked around him. He was sitting on a bench in Central Park, alone except for a few stray corpses. But the park was fairly free of bodies. "You've got about ten minutes warning," he said to himself. "I guess that most people wanted to die inside of something—inside of anything. Not out in the unprotected open." The silence was like a weight hanging around his neck. Not an insect noise, not the chirp of a bird, not the sound of a car nor the scream of a plane. Not even a breeze to whisper among the leaves, he thought. Civilization equals life equals noise. Silence equals.... Why. His mind kept returning to the question. Of all the people on earth, me. The last. Why me? Average, that's what he was. Height: 5'11". Weight: 165. Age: 32. Status: Married, once upon a time. The Norm, with no significant departures, all down the line. Church member, but not a good one. Could that be it? Could the most normal be the most perfect? Had he led the best of all possible lives? Was that it? Had God, in His infinite wisdom and mercy, spared his life, saved him, singled him out because he was most nearly a saint, most nearly Christ-like, most nearly.... Lies—His mind snapped back to reality. He half smiled. Saint? Christ? The Second Coming? He was no saint. Charles sighed. What about—? Chance. That was it! The laws of probability, the bell-shaped curve, normal distribution, rectilinear regression. More people per square foot in New York than elsewhere. The first person who died was from New York, so the last person who gave way to the disease should come from here too. Spin the wheel; throw the dice; toss the coin. So simple to explain by the laws of chance. No need for any underlying assumptions about good and evil, no need for teleological arguments concerning cause and effect. Simply explain it by chance. Somebody had to be the last to go and that was— "No," Charles said, standing up in the quiet of the spring evening. "No, chance won't do it. No man can reckon with chance. The mind rejects such things. There must be something beyond mere accident. There must be!" He sighed slowly. "So now I'm a hermit, whether or not I like it," he said in derision to the gravel path as he walked along it. "A hermit in the midst of a city of millions of—No, I forgot. There aren't any more people, are there?" It was hard to realize, even now. "A hermit, alone—and I haven't even got a cave...." Charles stopped walking suddenly. No cave, he thought. No place to sleep out the long one, no place to rest while time came to change things around and make them for the better. No place to hide. And suddenly it was the most important thing in life to him to find his "cave." It took him almost an hour to find the proper tools, and better than two hours more of hard, nighttime work to get the hole dug to his satisfaction. It took almost three hours to find the right sort of casket, durable but not too heavy for one man to handle. He carted it out to a grassy plot close to the center of the park where the grave was. He let the coffin down slowly into the depression, then piled up loose dirt on the sloping sides of the hole so that the rain would wash it down over him. "I can't very well bury myself," he said. "I guess it will rain after I'm gone." He looked carefully down at the metallic container. Wait now. There was something wrong, something missing. It was—oh, yes, he caught it. It was the stone. There wasn't any stone to go at the head of the grave. "I'll have to fix that." A sheet of metal, bent double, served for the monument proper. A nearby tool shed yielded up a can of paint and a brush. By the glow of one of the streetlights Charles worked out the inscription. "It ought to be something impressive," he thought out loud. "Something fitting the occasion." What did one say on these situations? There was so little chance to practice up for things like this. But it ought to be good, it ought to be proper. "'In this now hallowed corner of the planet Earth—' No. That sounds too ... too...." Make it simple, he thought. And he finally wrote: HERE LIES THE BODY OF THE LAST MAN ON EARTH Yes. That was it. Simple. Let whoever came afterwards figure out the rest. Let them decide. He smiled and finished the painting. Charles was hungry. He got up and started for one of the restaurants near the park. Later on, when there was more time, he'd find a piece of granite and move it to the plot. He could spend his free time carving on it, copying the inscription. He would make it into a real shrine; maybe he would practice up a bit and try to carve a statue to go with the stone. Somehow, though, since things were ready and it didn't make too much difference, it seemed to Charles that he'd probably have a long time to wait. "Maybe it's just a disease, and I'm immune. I was immune to smallpox. The vaccination never took. That's probably it." He smiled. Strange, but now he wanted very much to go on living, alone or not. There were things he could do, ways to keep occupied. He wouldn't mind it so much. But he wanted more and more desperately with each passing second to retain his foothold on the tenuous path of physical existence. The tantalizing thought of "why" puzzled its way back into his mind. But it seemed less pressing now that he had almost come to the conclusion that he would live for a long time. Later, in a few days perhaps, he would think about it. In a little while he'd have plenty of opportunity for hunting down the answer. This seemed good to him, for now he thought he almost had the answer, if there were an answer. He thought he had seen the solution peering out at him from the recesses of his mind, and he didn't like the expression on its face. Better to forget. Charles reached the broad boulevard. There was a large cafe just across from him, its front window caved in by a large truck. He stumbled and almost fell as he stepped from the curb. "Look at me, nervous as a cat." He was trembling noticeably as he started across the street. "I—" He started to say something, to think something. But some hidden part of his mind clamped down, obscuring the thought, rejecting the concept. The tremor turned to a shake before he reached the far curb, and the first burst of wild pain came as he laid his shoulder against the door to the restaurant. This was the way the plague began, but—His mind quickly repressed the idea. It couldn't be the plague. He was immune! Another burst of pulsating, shattering pain crashed through his body, tearing down the defenses of his mind, putting an end of his thoughts of immunity. Colors flared before his eyes, a persistent, irresistible susurrus flooded his ears. He wanted to protest, but there was no one to listen to him. He appealed to every divinity he knew, all the time knowing it would be useless. His body, out of his voluntary control, tried to run off in all directions at once. Charles struggled to end his body's disorganized responses, to channelize all his energy into one direction. His mind came back into action. He set up his goal; everything else seemed irrelevant: he had to get back to the park, to his hermit's cave, to his long, narrow home. He couldn't die until then. Ten minutes. He was allotted ten minutes before the end. It could have been ten years or ten seconds, for now objective time meant nothing to him. It was not a matter of measuring seconds and minutes. It was a matter of forgetting time and measuring space. He concentrated on the grave; he forced his body to become an unwilling machine. While he could, he walked, forcing himself on. When his legs gave way, he crawled. When his knees buckled, he rolled. When his stomach protested, he vomited. It made no difference. Charles refused to think. Machines, especially half-broken machines, do not think; they only work. Sweating, straining, bleeding, retching, he pushed himself towards his goal, trying to add one final touch of grace and custom to the rude irrationalness of it all. His eyes gave out a few feet from the pit. He felt his way towards it. Convulsions shook his body like a cat shakes a captive mouse. He humped his body forward between the seizures, hands outstretched, searching for the grave. And then he was upon it. One arm reached out for grass, and clutched bare space instead. He was home. He gathered energy from his final reservoirs of strength for one final movement that would throw him headlong into the shallow grave. He tensed his muscles, pulled his limbs up under him and started to roll into the hole. Instantly the thought struck him with paralyzing devastation. The answer to it all poked its face out from the recesses of his mind and sapped the last bit of his energy, corroding his nerves and dying muscles. Now he knew, and the knowing was the end of it. He collapsed at the edge of the pit. Only one arm hung loosely down into it, swinging senseless in the air, pointing accusingly at the empty coffin. The world will end, not with a bang, nor with a whimper, but with the last man's anguished cry at the unreasonableness of it all. Charles screamed. The large, invisible, ovular being that hung suspended over the Empire State Building rested from its exertion. Soon it was approached by another of its kind. "It is finished?" asked the second. "Yes. Just now. I am resting." "I can feel the emptiness of it." "It was very good. Where were you?" "On the next planet out. No beauty to it at all; no system. How was yours?" "Beautiful," said the first. "It went according to the strictest semantic relationship following the purest mathematical principles. They made it easy for me." "Good." "Well, where to now?" "There's another system about four thoughts away. We're due there soon." "All right. Let's go." "What's that you have there?" "Oh, this?" replied the first. "It's a higher neural order compendium the Things here made up. It's what I used." "You can't take it with you, you know. They don't allow souvenirs." "I know." "Well?" "All right, all right. You're so good, see if you can compute the scatter probability." The first being moved imperceptably and the heavy plastoid binding of the book disappeared. The thousands of pages dropped softly, caught at the wind like hungry sails, separated, and pulled by the fingers of gravity, went their disparate ways. Here a page scuttled into a broken window of the Chrysler Building (read the names: Aabat, Aabbs, Aabbt). Here a page landed upright on the head of one of the library lions and sloughed softly to the ground (read the names: Looman, Loomana, Loomanabsky). Here another page crept in between the cracks of a pier on the riverfront, dropping gently to the caressing eddies of the water (read the names: Smith, Smitha, Smitj). And here two pages danced down into Central Park, pirouetted, promenaded, and finally came to rest against a propped-up piece of metal (read the names: Whit, Whita, Whitacomb). It was not until the dusty morning sun stirred up the breezes that they fluttered down into the shallow hole beneath, unnoticed. The writing on the metal, until then partially obscured by the papers, became legible: HERE LIES THE BODY OF THE LAST MAN ON EARTH— CHARLES J. ZZYZST GO TO HELL!
|
B. Making it to his cave
|
What is not correct about the workers' description of the meteor shower?
A. The shower had caused a lot of damage to their equipment
B. Nobody was outside the city to get hit during the storm
C. They could identify fresh craters by locating footprints
D. It had occurred a couple of days ago
|
ALL DAY SEPTEMBER By ROGER KUYKENDALL Illustrated by van Dongen [Transcriber's Note: This etext was produced from Astounding Science Fiction June 1959. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Some men just haven't got good sense. They just can't seem to learn the most fundamental things. Like when there's no use trying—when it's time to give up because it's hopeless.... The meteor, a pebble, a little larger than a match head, traveled through space and time since it came into being. The light from the star that died when the meteor was created fell on Earth before the first lungfish ventured from the sea. In its last instant, the meteor fell on the Moon. It was impeded by Evans' tractor. It drilled a small, neat hole through the casing of the steam turbine, and volitized upon striking the blades. Portions of the turbine also volitized; idling at eight thousand RPM, it became unstable. The shaft tried to tie itself into a knot, and the blades, damaged and undamaged were spit through the casing. The turbine again reached a stable state, that is, stopped. Permanently stopped. It was two days to sunrise, where Evans stood. It was just before sunset on a spring evening in September in Sydney. The shadow line between day and night could be seen from the Moon to be drifting across Australia. Evans, who had no watch, thought of the time as a quarter after Australia. Evans was a prospector, and like all prospectors, a sort of jackknife geologist, selenologist, rather. His tractor and equipment cost two hundred and fifty thousand dollars. Fifty thousand was paid for. The rest was promissory notes and grubstake shares. When he was broke, which was usually, he used his tractor to haul uranium ore and metallic sodium from the mines at Potter's dike to Williamson Town, where the rockets landed. When he was flush, he would prospect for a couple of weeks. Once he followed a stampede to Yellow Crater, where he thought for a while that he had a fortune in chromium. The chromite petered out in a month and a half, and he was lucky to break even. Evans was about three hundred miles east of Williamson Town, the site of the first landing on the Moon. Evans was due back at Williamson Town at about sunset, that is, in about sixteen days. When he saw the wrecked turbine, he knew that he wouldn't make it. By careful rationing, he could probably stretch his food out to more than a month. His drinking water—kept separate from the water in the reactor—might conceivably last just as long. But his oxygen was too carefully measured; there was a four-day reserve. By diligent conservation, he might make it last an extra day. Four days reserve—plus one is five—plus sixteen days normal supply equals twenty-one days to live. In seventeen days he might be missed, but in seventeen days it would be dark again, and the search for him, if it ever began, could not begin for thirteen more days. At the earliest it would be eight days too late. "Well, man, 'tis a fine spot you're in now," he told himself. "Let's find out how bad it is indeed," he answered. He reached for the light switch and tried to turn it on. The switch was already in the "on" position. "Batteries must be dead," he told himself. "What batteries?" he asked. "There're no batteries in here, the power comes from the generator." "Why isn't the generator working, man?" he asked. He thought this one out carefully. The generator was not turned by the main turbine, but by a small reciprocating engine. The steam, however, came from the same boiler. And the boiler, of course, had emptied itself through the hole in the turbine. And the condenser, of course— "The condenser!" he shouted. He fumbled for a while, until he found a small flashlight. By the light of this, he reinspected the steam system, and found about three gallons of water frozen in the condenser. The condenser, like all condensers, was a device to convert steam into water, so that it could be reused in the boiler. This one had a tank and coils of tubing in the center of a curved reflector that was positioned to radiate the heat of the steam into the cold darkness of space. When the meteor pierced the turbine, the water in the condenser began to boil. This boiling lowered the temperature, and the condenser demonstrated its efficiency by quickly freezing the water in the tank. Evans sealed the turbine from the rest of the steam system by closing the shut-off valves. If there was any water in the boiler, it would operate the engine that drove the generator. The water would condense in the condenser, and with a little luck, melt the ice in there. Then, if the pump wasn't blocked by ice, it would return the water to the boiler. But there was no water in the boiler. Carefully he poured a cup of his drinking water into a pipe that led to the boiler, and resealed the pipe. He pulled on a knob marked "Nuclear Start/Safety Bypass." The water that he had poured into the boiler quickly turned into steam, and the steam turned the generator briefly. Evans watched the lights flicker and go out, and he guessed what the trouble was. "The water, man," he said, "there is not enough to melt the ice in the condenser." He opened the pipe again and poured nearly a half-gallon of water into the boiler. It was three days' supply of water, if it had been carefully used. It was one day's supply if used wastefully. It was ostentatious luxury for a man with a month's supply of water and twenty-one days to live. The generator started again, and the lights came on. They flickered as the boiler pressure began to fail, but the steam had melted some of the ice in the condenser, and the water pump began to function. "Well, man," he breathed, "there's a light to die by." The sun rose on Williamson Town at about the same time it rose on Evans. It was an incredibly brilliant disk in a black sky. The stars next to the sun shone as brightly as though there were no sun. They might have appeared to waver slightly, if they were behind outflung corona flares. If they did, no one noticed. No one looked toward the sun without dark filters. When Director McIlroy came into his office, he found it lighted by the rising sun. The light was a hot, brilliant white that seemed to pierce the darkest shadows of the room. He moved to the round window, screening his eyes from the light, and adjusted the polaroid shade to maximum density. The sun became an angry red brown, and the room was dark again. McIlroy decreased the density again until the room was comfortably lighted. The room felt stuffy, so he decided to leave the door to the inner office open. He felt a little guilty about this, because he had ordered that all doors in the survey building should remain closed except when someone was passing through them. This was to allow the air-conditioning system to function properly, and to prevent air loss in case of the highly improbable meteor damage. McIlroy thought that on the whole, he was disobeying his own orders no more flagrantly than anyone else in the survey. McIlroy had no illusions about his ability to lead men. Or rather, he did have one illusion; he thought that he was completely unfit as a leader. It was true that his strictest orders were disobeyed with cheerful contempt, but it was also true his mildest requests were complied with eagerly and smoothly. Everyone in the survey except McIlroy realized this, and even he accepted this without thinking about it. He had fallen into the habit of suggesting mildly anything that he wanted done, and writing orders he didn't particularly care to have obeyed. For example, because of an order of his stating that there would be no alcoholic beverages within the survey building, the entire survey was assured of a constant supply of home-made, but passably good liquor. Even McIlroy enjoyed the surreptitious drinking. "Good morning, Mr. McIlroy," said Mrs. Garth, his secretary. Morning to Mrs. Garth was simply the first four hours after waking. "Good morning indeed," answered McIlroy. Morning to him had no meaning at all, but he thought in the strictest sense that it would be morning on the Moon for another week. "Has the power crew set up the solar furnace?" he asked. The solar furnace was a rough parabola of mirrors used to focus the sun's heat on anything that it was desirable to heat. It was used mostly, from sun-up to sun-down, to supplement the nuclear power plant. "They went out about an hour ago," she answered, "I suppose that's what they were going to do." "Very good, what's first on the schedule?" "A Mr. Phelps to see you," she said. "How do you do, Mr. Phelps," McIlroy greeted him. "Good afternoon," Mr. Phelps replied. "I'm here representing the Merchants' Bank Association." "Fine," McIlroy said, "I suppose you're here to set up a bank." "That's right, I just got in from Muroc last night, and I've been going over the assets of the Survey Credit Association all morning." "I'll certainly be glad to get them off my hands," McIlroy said. "I hope they're in good order." "There doesn't seem to be any profit," Mr. Phelps said. "That's par for a nonprofit organization," said McIlroy. "But we're amateurs, and we're turning this operation over to professionals. I'm sure it will be to everyone's satisfaction." "I know this seems like a silly question. What day is this?" "Well," said McIlroy, "that's not so silly. I don't know either." "Mrs. Garth," he called, "what day is this?" "Why, September, I think," she answered. "I mean what day ." "I don't know, I'll call the observatory." There was a pause. "They say what day where?" she asked. "Greenwich, I guess, our official time is supposed to be Greenwich Mean Time." There was another pause. "They say it's September fourth, one thirty a.m. " "Well, there you are," laughed McIlroy, "it isn't that time doesn't mean anything here, it just doesn't mean the same thing." Mr. Phelps joined the laughter. "Bankers' hours don't mean much, at any rate," he said. The power crew was having trouble with the solar furnace. Three of the nine banks of mirrors would not respond to the electric controls, and one bank moved so jerkily that it could not be focused, and it threatened to tear several of the mirrors loose. "What happened here?" Spotty Cade, one of the electrical technicians asked his foreman, Cowalczk, over the intercommunications radio. "I've got about a hundred pinholes in the cables out here. It's no wonder they don't work." "Meteor shower," Cowalczk answered, "and that's not half of it. Walker says he's got a half dozen mirrors cracked or pitted, and Hoffman on bank three wants you to replace a servo motor. He says the bearing was hit." "When did it happen?" Cade wanted to know. "Must have been last night, at least two or three days ago. All of 'em too small for Radar to pick up, and not enough for Seismo to get a rumble." "Sounds pretty bad." "Could have been worse," said Cowalczk. "How's that?" "Wasn't anybody out in it." "Hey, Chuck," another technician, Lehman, broke in, "you could maybe get hurt that way." "I doubt it," Cowalczk answered, "most of these were pinhead size, and they wouldn't go through a suit." "It would take a pretty big one to damage a servo bearing," Cade commented. "That could hurt," Cowalczk admitted, "but there was only one of them." "You mean only one hit our gear," Lehman said. "How many missed?" Nobody answered. They could all see the Moon under their feet. Small craters overlapped and touched each other. There was—except in the places that men had obscured them with footprints—not a square foot that didn't contain a crater at least ten inches across, there was not a square inch without its half-inch crater. Nearly all of these had been made millions of years ago, but here and there, the rim of a crater covered part of a footprint, clear evidence that it was a recent one. After the sun rose, Evans returned to the lava cave that he had been exploring when the meteor hit. Inside, he lifted his filter visor, and found that the light reflected from the small ray that peered into the cave door lighted the cave adequately. He tapped loose some white crystals on the cave wall with his geologist's hammer, and put them into a collector's bag. "A few mineral specimens would give us something to think about, man. These crystals," he said, "look a little like zeolites, but that can't be, zeolites need water to form, and there's no water on the Moon." He chipped a number of other crystals loose and put them in bags. One of them he found in a dark crevice had a hexagonal shape that puzzled him. One at a time, back in the tractor, he took the crystals out of the bags and analyzed them as well as he could without using a flame which would waste oxygen. The ones that looked like zeolites were zeolites, all right, or something very much like it. One of the crystals that he thought was quartz turned out to be calcite, and one of the ones that he was sure could be nothing but calcite was actually potassium nitrate. "Well, now," he said, "it's probably the largest natural crystal of potassium nitrate that anyone has ever seen. Man, it's a full inch across." All of these needed water to form, and their existence on the Moon puzzled him for a while. Then he opened the bag that had contained the unusual hexagonal crystals, and the puzzle resolved itself. There was nothing in the bag but a few drops of water. What he had taken to be a type of rock was ice, frozen in a niche that had never been warmed by the sun. The sun rose to the meridian slowly. It was a week after sunrise. The stars shone coldly, and wheeled in their slow course with the sun. Only Earth remained in the same spot in the black sky. The shadow line crept around until Earth was nearly dark, and then the rim of light appeared on the opposite side. For a while Earth was a dark disk in a thin halo, and then the light came to be a crescent, and the line of dawn began to move around Earth. The continents drifted across the dark disk and into the crescent. The people on Earth saw the full moon set about the same time that the sun rose. Nickel Jones was the captain of a supply rocket. He made trips from and to the Moon about once a month, carrying supplies in and metal and ores out. At this time he was visiting with his old friend McIlroy. "I swear, Mac," said Jones, "another season like this, and I'm going back to mining." "I thought you were doing pretty well," said McIlroy, as he poured two drinks from a bottle of Scotch that Jones had brought him. "Oh, the money I like, but I will say that I'd have more if I didn't have to fight the union and the Lunar Trade Commission." McIlroy had heard all of this before. "How's that?" he asked politely. "You may think it's myself running the ship," Jones started on his tirade, "but it's not. The union it is that says who I can hire. The union it is that says how much I must pay, and how large a crew I need. And then the Commission ..." The word seemed to give Jones an unpleasant taste in his mouth, which he hurriedly rinsed with a sip of Scotch. "The Commission," he continued, making the word sound like an obscenity, "it is that tells me how much I can charge for freight." McIlroy noticed that his friend's glass was empty, and he quietly filled it again. "And then," continued Jones, "if I buy a cargo up here, the Commission it is that says what I'll sell it for. If I had my way, I'd charge only fifty cents a pound for freight instead of the dollar forty that the Commission insists on. That's from here to Earth, of course. There's no profit I could make by cutting rates the other way." "Why not?" asked McIlroy. He knew the answer, but he liked to listen to the slightly Welsh voice of Jones. "Near cost it is now at a dollar forty. But what sense is there in charging the same rate to go either way when it takes about a seventh of the fuel to get from here to Earth as it does to get from there to here?" "What good would it do to charge fifty cents a pound?" asked McIlroy. "The nickel, man, the tons of nickel worth a dollar and a half on Earth, and not worth mining here; the low-grade ores of uranium and vanadium, they need these things on Earth, but they can't get them as long as it isn't worth the carrying of them. And then, of course, there's the water we haven't got. We could afford to bring more water for more people, and set up more distilling plants if we had the money from the nickel. "Even though I say it who shouldn't, two-eighty a quart is too much to pay for water." Both men fell silent for a while. Then Jones spoke again: "Have you seen our friend Evans lately? The price of chromium has gone up, and I think he could ship some of his ore from Yellow Crater at a profit." "He's out prospecting again. I don't expect to see him until sun-down." "I'll likely see him then. I won't be loaded for another week and a half. Can't you get in touch with him by radio?" "He isn't carrying one. Most of the prospectors don't. They claim that a radio that won't carry beyond the horizon isn't any good, and one that will bounce messages from Earth takes up too much room." "Well, if I don't see him, you let him know about the chromium." "Anything to help another Welshman, is that the idea?" "Well, protection it is that a poor Welshman needs from all the English and Scots. Speaking of which—" "Oh, of course," McIlroy grinned as he refilled the glasses. " Slainte, McIlroy, bach. " [Health, McIlroy, man.] " Slainte mhor, bach. " [Great Health, man.] The sun was halfway to the horizon, and Earth was a crescent in the sky when Evans had quarried all the ice that was available in the cave. The thought grew on him as he worked that this couldn't be the only such cave in the area. There must be several more bubbles in the lava flow. Part of his reasoning proved correct. That is, he found that by chipping, he could locate small bubbles up to an inch in diameter, each one with its droplet of water. The average was about one per cent of the volume of each bubble filled with ice. A quarter of a mile from the tractor, Evans found a promising looking mound of lava. It was rounded on top, and it could easily be the dome of a bubble. Suddenly, Evans noticed that the gauge on the oxygen tank of his suit was reading dangerously near empty. He turned back to his tractor, moving as slowly as he felt safe in doing. Running would use up oxygen too fast. He was halfway there when the pressure warning light went on, and the signal sounded inside his helmet. He turned on his ten-minute reserve supply, and made it to the tractor with about five minutes left. The air purifying apparatus in the suit was not as efficient as the one in the tractor; it wasted oxygen. By using the suit so much, Evans had already shortened his life by several days. He resolved not to leave the tractor again, and reluctantly abandoned his plan to search for a large bubble. The sun stood at half its diameter above the horizon. The shadows of the mountains stretched out to touch the shadows of the other mountains. The dawning line of light covered half of Earth, and Earth turned beneath it. Cowalczk itched under his suit, and the sweat on his face prickled maddeningly because he couldn't reach it through his helmet. He pushed his forehead against the faceplate of his helmet and rubbed off some of the sweat. It didn't help much, and it left a blurred spot in his vision. That annoyed him. "Is everyone clear of the outlet?" he asked. "All clear," he heard Cade report through the intercom. "How come we have to blow the boilers now?" asked Lehman. "Because I say so," Cowalczk shouted, surprised at his outburst and ashamed of it. "Boiler scale," he continued, much calmer. "We've got to clean out the boilers once a year to make sure the tubes in the reactor don't clog up." He squinted through his dark visor at the reactor building, a gray concrete structure a quarter of a mile distant. "It would be pretty bad if they clogged up some night." "Pressure's ten and a half pounds," said Cade. "Right, let her go," said Cowalczk. Cade threw a switch. In the reactor building, a relay closed. A motor started turning, and the worm gear on the motor opened a valve on the boiler. A stream of muddy water gushed into a closed vat. When the vat was about half full, the water began to run nearly clear. An electric eye noted that fact and a light in front of Cade turned on. Cade threw the switch back the other way, and the relay in the reactor building opened. The motor turned and the gears started to close the valve. But a fragment of boiler scale held the valve open. "Valve's stuck," said Cade. "Open it and close it again," said Cowalczk. The sweat on his forehead started to run into his eyes. He banged his hand on his faceplate in an unconscious attempt to wipe it off. He cursed silently, and wiped it off on the inside of his helmet again. This time, two drops ran down the inside of his faceplate. "Still don't work," said Cade. "Keep trying," Cowalczk ordered. "Lehman, get a Geiger counter and come with me, we've got to fix this thing." Lehman and Cowalczk, who were already suited up started across to the reactor building. Cade, who was in the pressurized control room without a suit on, kept working the switch back and forth. There was light that indicated when the valve was open. It was on, and it stayed on, no matter what Cade did. "The vat pressure's too high," Cade said. "Let me know when it reaches six pounds," Cowalczk requested. "Because it'll probably blow at seven." The vat was a light plastic container used only to decant sludge out of the water. It neither needed nor had much strength. "Six now," said Cade. Cowalczk and Lehman stopped halfway to the reactor. The vat bulged and ruptured. A stream of mud gushed out and boiled dry on the face of the Moon. Cowalczk and Lehman rushed forward again. They could see the trickle of water from the discharge pipe. The motor turned the valve back and forth in response to Cade's signals. "What's going on out there?" demanded McIlroy on the intercom. "Scale stuck in the valve," Cowalczk answered. "Are the reactors off?" "Yes. Vat blew. Shut up! Let me work, Mac!" "Sorry," McIlroy said, realizing that this was no time for officials. "Let me know when it's fixed." "Geiger's off scale," Lehman said. "We're probably O.K. in these suits for an hour," Cowalczk answered. "Is there a manual shut-off?" "Not that I know of," Lehman answered. "What about it, Cade?" "I don't think so," Cade said. "I'll get on the blower and rouse out an engineer." "O.K., but keep working that switch." "I checked the line as far as it's safe," said Lehman. "No valve." "O.K.," Cowalczk said. "Listen, Cade, are the injectors still on?" "Yeah. There's still enough heat in these reactors to do some damage. I'll cut 'em in about fifteen minutes." "I've found the trouble," Lehman said. "The worm gear's loose on its shaft. It's slipping every time the valve closes. There's not enough power in it to crush the scale." "Right," Cowalczk said. "Cade, open the valve wide. Lehman, hand me that pipe wrench!" Cowalczk hit the shaft with the back of the pipe wrench, and it broke at the motor bearing. Cowalczk and Lehman fitted the pipe wrench to the gear on the valve, and turned it. "Is the light off?" Cowalczk asked. "No," Cade answered. "Water's stopped. Give us some pressure, we'll see if it holds." "Twenty pounds," Cade answered after a couple of minutes. "Take her up to ... no, wait, it's still leaking," Cowalczk said. "Hold it there, we'll open the valve again." "O.K.," said Cade. "An engineer here says there's no manual cutoff." "Like Hell," said Lehman. Cowalczk and Lehman opened the valve again. Water spurted out, and dwindled as they closed the valve. "What did you do?" asked Cade. "The light went out and came on again." "Check that circuit and see if it works," Cowalczk instructed. There was a pause. "It's O.K.," Cade said. Cowalczk and Lehman opened and closed the valve again. "Light is off now," Cade said. "Good," said Cowalczk, "take the pressure up all the way, and we'll see what happens." "Eight hundred pounds," Cade said, after a short wait. "Good enough," Cowalczk said. "Tell that engineer to hold up a while, he can fix this thing as soon as he gets parts. Come on, Lehman, let's get out of here." "Well, I'm glad that's over," said Cade. "You guys had me worried for a while." "Think we weren't worried?" Lehman asked. "And it's not over." "What?" Cade asked. "Oh, you mean the valve servo you two bashed up?" "No," said Lehman, "I mean the two thousand gallons of water that we lost." "Two thousand?" Cade asked. "We only had seven hundred gallons reserve. How come we can operate now?" "We picked up twelve hundred from the town sewage plant. What with using the solar furnace as a radiator, we can make do." "Oh, God, I suppose this means water rationing again." "You're probably right, at least until the next rocket lands in a couple of weeks." PROSPECTOR FEARED LOST ON MOON IPP Williamson Town, Moon, Sept. 21st. Scientific survey director McIlroy released a statement today that Howard Evans, a prospector is missing and presumed lost. Evans, who was apparently exploring the Moon in search of minerals was due two days ago, but it was presumed that he was merely temporarily delayed. Evans began his exploration on August 25th, and was known to be carrying several days reserve of oxygen and supplies. Director McIlroy has expressed a hope that Evans will be found before his oxygen runs out. Search parties have started from Williamson Town, but telescopic search from Palomar and the new satellite observatory are hindered by the fact that Evans is lost on the part of the Moon which is now dark. Little hope is held for radio contact with the missing man as it is believed he was carrying only short-range, intercommunications equipment. Nevertheless, receivers are ... Captain Nickel Jones was also expressing a hope: "Anyway, Mac," he was saying to McIlroy, "a Welshman knows when his luck's run out. And never a word did he say." "Like as not, you're right," McIlroy replied, "but if I know Evans, he'd never say a word about any forebodings." "Well, happen I might have a bit of Welsh second sight about me, and it tells me that Evans will be found." McIlroy chuckled for the first time in several days. "So that's the reason you didn't take off when you were scheduled," he said. "Well, yes," Jones answered. "I thought that it might happen that a rocket would be needed in the search." The light from Earth lighted the Moon as the Moon had never lighted Earth. The great blue globe of Earth, the only thing larger than the stars, wheeled silently in the sky. As it turned, the shadow of sunset crept across the face that could be seen from the Moon. From full Earth, as you might say, it moved toward last quarter. The rising sun shone into Director McIlroy's office. The hot light formed a circle on the wall opposite the window, and the light became more intense as the sun slowly pulled over the horizon. Mrs. Garth walked into the director's office, and saw the director sleeping with his head cradled in his arms on the desk. She walked softly to the window and adjusted the shade to darken the office. She stood looking at McIlroy for a moment, and when he moved slightly in his sleep, she walked softly out of the office. A few minutes later she was back with a cup of coffee. She placed it in front of the director, and shook his shoulder gently. "Wake up, Mr. McIlroy," she said, "you told me to wake you at sunrise, and there it is, and here's Mr. Phelps." McIlroy woke up slowly. He leaned back in his chair and stretched. His neck was stiff from sleeping in such an awkward position. "'Morning, Mr. Phelps," he said. "Good morning," Phelps answered, dropping tiredly into a chair. "Have some coffee, Mr. Phelps," said Mrs. Garth, handing him a cup. "Any news?" asked McIlroy. "About Evans?" Phelps shook his head slowly. "Palomar called in a few minutes back. Nothing to report and the sun was rising there. Australia will be in position pretty soon. Several observatories there. Then Capetown. There are lots of observatories in Europe, but most of them are clouded over. Anyway the satellite observatory will be in position by the time Europe is." McIlroy was fully awake. He glanced at Phelps and wondered how long it had been since he had slept last. More than that, McIlroy wondered why this banker, who had never met Evans, was losing so much sleep about finding him. It began to dawn on McIlroy that nearly the whole population of Williamson Town was involved, one way or another, in the search. The director turned to ask Phelps about this fact, but the banker was slumped in his chair, fast asleep with his coffee untouched. It was three hours later that McIlroy woke Phelps. "They've found the tractor," McIlroy said. "Good," Phelps mumbled, and then as comprehension came; "That's fine! That's just line! Is Evans—?" "Can't tell yet. They spotted the tractor from the satellite observatory. Captain Jones took off a few minutes ago, and he'll report back as soon as he lands. Hadn't you better get some sleep?" Evans was carrying a block of ice into the tractor when he saw the rocket coming in for a landing. He dropped the block and stood waiting. When the dust settled from around the tail of the rocket, he started to run forward. The air lock opened, and Evans recognized the vacuum suited figure of Nickel Jones. "Evans, man!" said Jones' voice in the intercom. "Alive you are!" "A Welshman takes a lot of killing," Evans answered. Later, in Evans' tractor, he was telling his story: "... And I don't know how long I sat there after I found the water." He looked at the Goldburgian device he had made out of wire and tubing. "Finally I built this thing. These caves were made of lava. They must have been formed by steam some time, because there's a floor of ice in all of 'em. "The idea didn't come all at once, it took a long time for me to remember that water is made out of oxygen and hydrogen. When I remembered that, of course, I remembered that it can be separated with electricity. So I built this thing. "It runs an electric current through water, lets the oxygen loose in the room, and pipes the hydrogen outside. It doesn't work automatically, of course, so I run it about an hour a day. My oxygen level gauge shows how long." "You're a genius, man!" Jones exclaimed. "No," Evans answered, "a Welshman, nothing more." "Well, then," said Jones, "are you ready to start back?" "Back?" "Well, it was to rescue you that I came." "I don't need rescuing, man," Evans said. Jones stared at him blankly. "You might let me have some food," Evans continued. "I'm getting short of that. And you might have someone send out a mechanic with parts to fix my tractor. Then maybe you'll let me use your radio to file my claim." "Claim?" "Sure, man, I've thousands of tons of water here. It's the richest mine on the Moon!" THE END
|
B. Nobody was outside the city to get hit during the storm
|
Which statement best describes Williamson's writing style?
A. It reflects his disdain for humankind's obsession with technological advancement
B. More authors have parlayed his method and style than any other science fiction author
C. It evolved to be flexible despite how it initially imitated the style of a singular author
D. It contains myriad farcical and parodic literary elements, which was uncommon during his time
|
Transcriber's Note: This etext was produced from Amazing Stories December 1961 and was first published in Amazing Stories November 1930. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed. Minor spelling and typographical errors have been corrected without note. A Classic Reprint from AMAZING STORIES, November, 1930 Copyright 1931, by Experimenter Publications Inc. The Cosmic Express By JACK WILLIAMSON Introduction by Sam Moskowitz The year 1928 was a great year of discovery for AMAZING STORIES . They were uncovering new talent at such a great rate, (Harl Vincent, David H. Keller, E. E. Smith, Philip Francis Nowlan, Fletcher Pratt and Miles J. Breuer), that Jack Williamson barely managed to become one of a distinguished group of discoveries by stealing the cover of the December issue for his first story The Metal Man. A disciple of A. Merritt, he attempted to imitate in style, mood and subject the magic of that late lamented master of fantasy. The imitation found great favor from the readership and almost instantly Jack Williamson became an important name on the contents page of AMAZING STORIES . He followed his initial success with two short novels , The Green Girl in AMAZING STORIES and The Alien Intelligence in SCIENCE WONDER STORIES , another Gernsback publication. Both of these stories were close copies of A. Merritt, whose style and method Jack Williamson parlayed into popularity for eight years. Yet the strange thing about it was that Jack Williamson was one of the most versatile science fiction authors ever to sit down at the typewriter. When the vogue for science-fantasy altered to super science, he created the memorable super lock-picker Giles Habilula as the major attraction in a rousing trio of space operas , The Legion of Space, The Cometeers and One Against the Legion. When grim realism was the order of the day, he produced Crucible of Power and when they wanted extrapolated theory in present tense, he assumed the disguise of Will Stewart and popularized the concept of contra terrene matter in science fiction with Seetee Ship and Seetee Shock. Finally, when only psychological studies of the future would do, he produced "With Folded Hands ..." "... And Searching Mind." The Cosmic Express is of special interest because it was written during Williamson's A. Merritt "kick," when he was writing little else but, and it gave the earliest indication of a more general capability. The lightness of the handling is especially modern, barely avoiding the farcical by the validity of the notion that wireless transmission of matter is the next big transportation frontier to be conquered. It is especially important because it stylistically forecast a later trend to accept the background for granted, regardless of the quantity of wonders, and proceed with the story. With only a few thousand scanning-disk television sets in existence at the time of the writing, the surmise that this media would be a natural for westerns was particularly astute. Jack Williamson was born in 1908 in the Arizona territory when covered wagons were the primary form of transportation and apaches still raided the settlers. His father was a cattle man, but for young Jack, the ranch was anything but glamorous. "My days were filled," he remembers, "with monotonous rounds of what seemed an endless, heart-breaking war with drought and frost and dust-storms, poison-weeds and hail, for the sake of survival on the Llano Estacado." The discovery of AMAZING STORIES was the escape he sought and his goal was to be a science fiction writer. He labored to this end and the first he knew that a story of his had been accepted was when he bought the December, 1929 issue of AMAZING STORIES . Since then, he has written millions of words of science fiction and has gone on record as follows: "I feel that science-fiction is the folklore of the new world of science, and the expression of man's reaction to a technological environment. By which I mean that it is the most interesting and stimulating form of literature today." Mr. Eric Stokes-Harding tumbled out of the rumpled bed-clothing, a striking slender figure in purple-striped pajamas. He smiled fondly across to the other of the twin beds, where Nada, his pretty bride, lay quiet beneath light silk covers. With a groan, he stood up and began a series of fantastic bending exercises. But after a few half-hearted movements, he gave it up, and walked through an open door into a small bright room, its walls covered with bookcases and also with scientific appliances that would have been strange to the man of four or five centuries before, when the Age of Aviation was beginning. Suddenly there was a sharp tingling sensation where they touched the polished surface. Yawning, Mr. Eric Stokes-Harding stood before the great open window, staring out. Below him was a wide, park-like space, green with emerald lawns, and bright with flowering plants. Two hundred yards across it rose an immense pyramidal building—an artistic structure, gleaming with white marble and bright metal, striped with the verdure of terraced roof-gardens, its slender peak rising to help support the gray, steel-ribbed glass roof above. Beyond, the park stretched away in illimitable vistas, broken with the graceful columned buildings that held up the great glass roof. Above the glass, over this New York of 2432 A. D., a freezing blizzard was sweeping. But small concern was that to the lightly clad man at the window, who was inhaling deeply the fragrant air from the plants below—air kept, winter and summer, exactly at 20° C. With another yawn, Mr. Eric Stokes-Harding turned back to the room, which was bright with the rich golden light that poured in from the suspended globes of the cold ato-light that illuminated the snow-covered city. With a distasteful grimace, he seated himself before a broad, paper-littered desk, sat a few minutes leaning back, with his hands clasped behind his head. At last he straightened reluctantly, slid a small typewriter out of its drawer, and began pecking at it impatiently. For Mr. Eric Stokes-Harding was an author. There was a whole shelf of his books on the wall, in bright jackets, red and blue and green, that brought a thrill of pleasure to the young novelist's heart when he looked up from his clattering machine. He wrote "thrilling action romances," as his enthusiastic publishers and television directors said, "of ages past, when men were men. Red-blooded heroes responding vigorously to the stirring passions of primordial life!" He was impartial as to the source of his thrills—provided they were distant enough from modern civilization. His hero was likely to be an ape-man roaring through the jungle, with a bloody rock in one hand and a beautiful girl in the other. Or a cowboy, "hard-riding, hard-shooting," the vanishing hero of the ancient ranches. Or a man marooned with a lovely woman on a desert South Sea island. His heroes were invariably strong, fearless, resourceful fellows, who could handle a club on equal terms with a cave-man, or call science to aid them in defending a beautiful mate from the terrors of a desolate wilderness. And a hundred million read Eric's novels, and watched the dramatization of them on the television screens. They thrilled at the simple, romantic lives his heroes led, paid him handsome royalties, and subconsciously shared his opinion that civilization had taken all the best from the life of man. Eric had settled down to the artistic satisfaction of describing the sensuous delight of his hero in the roasted marrow-bones of a dead mammoth, when the pretty woman in the other room stirred, and presently came tripping into the study, gay and vivacious, and—as her husband of a few months most justly thought—altogether beautiful in a bright silk dressing gown. Recklessly, he slammed the machine back into its place, and resolved to forget that his next "red-blooded action thriller" was due in the publisher's office at the end of the month. He sprang up to kiss his wife, held her embraced for a long happy moment. And then they went hand in hand, to the side of the room and punched a series of buttons on a panel—a simple way of ordering breakfast sent up the automatic shaft from the kitchens below. Nada Stokes-Harding was also an author. She wrote poems—"back to nature stuff"—simple lyrics of the sea, of sunsets, of bird songs, of bright flowers and warm winds, of thrilling communion with Nature, and growing things. Men read her poems and called her a genius. Even though the whole world had grown up into a city, the birds were extinct, there were no wild flowers, and no one had time to bother about sunsets. "Eric, darling," she said, "isn't it terrible to be cooped up here in this little flat, away from the things we both love?" "Yes, dear. Civilization has ruined the world. If we could only have lived a thousand years ago, when life was simple and natural, when men hunted and killed their meat, instead of drinking synthetic stuff, when men still had the joys of conflict, instead of living under glass, like hot-house flowers." "If we could only go somewhere—" "There isn't anywhere to go. I write about the West, Africa, South Sea Islands. But they were all filled up two hundred years ago. Pleasure resorts, sanatoriums, cities, factories." "If only we lived on Venus! I was listening to a lecture on the television, last night. The speaker said that the Planet Venus is younger than the Earth, that it has not cooled so much. It has a thick, cloudy atmosphere, and low, rainy forests. There's simple, elemental life there—like Earth had before civilization ruined it." "Yes, Kinsley, with his new infra-red ray telescope, that penetrates the cloud layers of the planet, proved that Venus rotates in about the same period as Earth; and it must be much like Earth was a million years ago." "Eric, I wonder if we could go there! It would be so thrilling to begin life like the characters in your stories, to get away from this hateful civilization, and live natural lives. Maybe a rocket—" The young author's eyes were glowing. He skipped across the floor, seized Nada, kissed her ecstatically. "Splendid! Think of hunting in the virgin forest, and bringing the game home to you! But I'm afraid there is no way.—Wait! The Cosmic Express." "The Cosmic Express?" "A new invention. Just perfected a few weeks ago, I understand. By Ludwig Von der Valls, the German physicist." "I've quit bothering about science. It has ruined nature, filled the world with silly, artificial people, doing silly, artificial things." "But this is quite remarkable, dear. A new way to travel—by ether!" "By ether!" "Yes. You know of course that energy and matter are interchangeable terms; both are simply etheric vibration, of different sorts." "Of course. That's elementary." She smiled proudly. "I can give you examples, even of the change. The disintegration of the radium atom, making helium and lead and energy . And Millikan's old proof that his Cosmic Ray is generated when particles of electricity are united to form an atom." "Fine! I thought you said you weren't a scientist." He glowed with pride. "But the method, in the new Cosmic Express, is simply to convert the matter to be carried into power, send it out as a radiant beam and focus the beam to convert it back into atoms at the destination." "But the amount of energy must be terrific—" "It is. You know short waves carry more energy than long ones. The Express Ray is an electromagnetic vibration of frequency far higher than that of even the Cosmic Ray, and correspondingly more powerful and more penetrating." The girl frowned, running slim fingers through golden-brown hair. "But I don't see how they get any recognizable object, not even how they get the radiation turned back into matter." "The beam is focused, just like the light that passes through a camera lens. The photographic lens, using light rays, picks up a picture and reproduces it again on the plate—just the same as the Express Ray picks up an object and sets it down on the other side of the world. "An analogy from television might help. You know that by means of the scanning disc, the picture is transformed into mere rapid fluctuations in the brightness of a beam of light. In a parallel manner, the focal plane of the Express Ray moves slowly through the object, progressively, dissolving layers of the thickness of a single atom, which are accurately reproduced at the other focus of the instrument—which might be in Venus! "But the analogy of the lens is the better of the two. For no receiving instrument is required, as in television. The object is built up of an infinite series of plane layers, at the focus of the ray, no matter where that may be. Such a thing would be impossible with radio apparatus because even with the best beam transmission, all but a tiny fraction of the power is lost, and power is required to rebuild the atoms. Do you understand, dear?" "Not altogether. But I should worry! Here comes breakfast. Let me butter your toast." A bell had rung at the shaft. She ran to it, and returned with a great silver tray, laden with dainty dishes, which she set on a little side table. They sat down opposite each other, and ate, getting as much satisfaction from contemplation of each other's faces as from the excellent food. When they had finished, she carried the tray to the shaft, slid it in a slot, and touched a button—thus disposing of the culinary cares of the morning. She ran back to Eric, who was once more staring distastefully at his typewriter. "Oh, darling! I'm thrilled to death about the Cosmic Express! If we could go to Venus, to a new life on a new world, and get away from all this hateful conventional society—" "We can go to their office—it's only five minutes. The chap that operates the machine for the company is a pal of mine. He's not supposed to take passengers except between the offices they have scattered about the world. But I know his weak point—" Eric laughed, fumbled with a hidden spring under his desk. A small polished object, gleaming silvery, slid down into his hand. "Old friendship, plus this, would make him—like spinach." Five minutes later Mr. Eric Stokes-Harding and his pretty wife were in street clothes, light silk tunics of loose, flowing lines—little clothing being required in the artificially warmed city. They entered an elevator and dropped thirty stories to the ground floor of the great building. There they entered a cylindrical car, with rows of seats down the sides. Not greatly different from an ancient subway car, except that it was air-tight, and was hurled by magnetic attraction and repulsion through a tube exhausted of air, at a speed that would have made an old subway rider gasp with amazement. In five more minutes their car had whipped up to the base of another building, in the business section, where there was no room for parks between the mighty structures that held the unbroken glass roofs two hundred stories above the concrete pavement. An elevator brought them up a hundred and fifty stories. Eric led Nada down a long, carpeted corridor to a wide glass door, which bore the words: COSMIC EXPRESS stenciled in gold capitals across it. As they approached, a lean man, carrying a black bag, darted out of an elevator shaft opposite the door, ran across the corridor, and entered. They pushed in after him. They were in a little room, cut in two by a high brass grill. In front of it was a long bench against the wall, that reminded one of the waiting room in an old railroad depot. In the grill was a little window, with a lazy, brown-eyed youth leaning on the shelf behind it. Beyond him was a great, glittering piece of mechanism, half hidden by the brass. A little door gave access to the machine from the space before the grill. The thin man in black, whom Eric now recognized as a prominent French heart-specialist, was dancing before the window, waving his bag frantically, raving at the sleepy boy. "Queek! I have tell you zee truth! I have zee most urgent necessity to go queekly. A patient I have in Paree, zat ees in zee most creetical condition!" "Hold your horses just a minute, Mister. We got a client in the machine now. Russian diplomat from Moscow to Rio de Janeiro.... Two hundred seventy dollars and eighty cents, please.... Your turn next. Remember this is just an experimental service. Regular installations all over the world in a year.... Ready now. Come on in." The youth took the money, pressed a button. The door sprang open in the grill, and the frantic physician leaped through it. "Lie down on the crystal, face up," the young man ordered. "Hands at your sides, don't breathe. Ready!" He manipulated his dials and switches, and pressed another button. "Why, hello, Eric, old man!" he cried. "That's the lady you were telling me about? Congratulations!" A bell jangled before him on the panel. "Just a minute. I've got a call." He punched the board again. Little bulbs lit and glowed for a second. The youth turned toward the half-hidden machine, spoke courteously. "All right, madam. Walk out. Hope you found the transit pleasant." "But my Violet! My precious Violet!" a shrill female voice came from the machine. "Sir, what have you done with my darling Violet?" "I'm sure I don't know, madam. You lost it off your hat?" "None of your impertinence, sir! I want my dog." "Ah, a dog. Must have jumped off the crystal. You can have him sent on for three hundred and—" "Young man, if any harm comes to my Violet—I'll—I'll—I'll appeal to the Society for the Prevention of Cruelty to Animals!" "Very good, madam. We appreciate your patronage." The door flew open again. A very fat woman, puffing angrily, face highly colored, clothing shimmering with artificial gems, waddled pompously out of the door through which the frantic French doctor had so recently vanished. She rolled heavily across the room, and out into the corridor. Shrill words floated back: "I'm going to see my lawyer! My precious Violet—" The sallow youth winked. "And now what can I do for you, Eric?" "We want to go to Venus, if that ray of yours can put us there." "To Venus? Impossible. My orders are to use the Express merely between the sixteen designated stations, at New York, San Francisco, Tokyo, London, Paris—" "See here, Charley," with a cautious glance toward the door, Eric held up the silver flask. "For old time's sake, and for this—" The boy seemed dazed at sight of the bright flask. Then, with a single swift motion, he snatched it out of Eric's hand, and bent to conceal it below his instrument panel. "Sure, old boy. I'd send you to heaven for that, if you'd give me the micrometer readings to set the ray with. But I tell you, this is dangerous. I've got a sort of television attachment, for focusing the ray. I can turn that on Venus—I've been amusing myself, watching the life there, already. Terrible place. Savage. I can pick a place on high land to set you down. But I can't be responsible for what happens afterward." "Simple, primitive life is what we're looking for. And now what do I owe you—" "Oh, that's all right. Between friends. Provided that stuff's genuine! Walk in and lie down on the crystal block. Hands at your sides. Don't move." The little door had swung open again, and Eric led Nada through. They stepped into a little cell, completely surrounded with mirrors and vast prisms and lenses and electron tubes. In the center was a slab of transparent crystal, eight feet square and two inches thick, with an intricate mass of machinery below it. Eric helped Nada to a place on the crystal, lay down at her side. "I think the Express Ray is focused just at the surface of the crystal, from below," he said. "It dissolves our substance, to be transmitted by the beam. It would look as if we were melting into the crystal." "Ready," called the youth. "Think I've got it for you. Sort of a high island in the jungle. Nothing bad in sight now. But, I say—how're you coming back? I haven't got time to watch you." "Go ahead. We aren't coming back." "Gee! What is it? Elopement? I thought you were married already. Or is it business difficulties? The Bears did make an awful raid last night. But you better let me set you down in Hong Kong." A bell jangled. "So long," the youth called. Nada and Eric felt themselves enveloped in fire. Sheets of white flame seemed to lap up about them from the crystal block. Suddenly there was a sharp tingling sensation where they touched the polished surface. Then blackness, blankness. The next thing they knew, the fires were gone from about them. They were lying in something extremely soft and fluid; and warm rain was beating in their faces. Eric sat up, found himself in a mud-puddle. Beside him was Nada, opening her eyes and struggling up, her bright garments stained with black mud. All about rose a thick jungle, dark and gloomy—and very wet. Palm-like, the gigantic trees were, or fern-like, flinging clouds of feathery green foliage high against a somber sky of unbroken gloom. They stood up, triumphant. "At last!" Nada cried. "We're free! Free of that hateful old civilization! We're back to Nature!" "Yes, we're on our feet now, not parasites on the machines." "It's wonderful to have a fine, strong man like you to trust in, Eric. You're just like one of the heroes in your books!" "You're the perfect companion, Nada.... But now we must be practical. We must build a fire, find weapons, set up a shelter of some kind. I guess it will be night, pretty soon. And Charley said something about savage animals he had seen in the television. "We'll find a nice dry cave, and have a fire in front of the door. And skins of animals to sleep on. And pottery vessels to cook in. And you will find seeds and grown grain." "But first we must find a flint-bed. We need flint for tools, and to strike sparks to make a fire with. We will probably come across a chunk of virgin copper, too—it's found native." Presently they set off through the jungle. The mud seemed to be very abundant, and of a most sticky consistence. They sank into it ankle deep at every step, and vast masses of it clung to their feet. A mile they struggled on, without finding where a provident nature had left them even a single fragment of quartz, to say nothing of a mass of pure copper. "A darned shame," Eric grumbled, "to come forty million miles, and meet such a reception as this!" Nada stopped. "Eric," she said, "I'm tired. And I don't believe there's any rock here, anyway. You'll have to use wooden tools, sharpened in the fire." "Probably you're right. This soil seemed to be of alluvial origin. Shouldn't be surprised if the native rock is some hundreds of feet underground. Your idea is better." "You can make a fire by rubbing sticks together, can't you?" "It can be done, I'm sure. I've never tried it, myself. We need some dry sticks, first." They resumed the weary march, with a good fraction of the new planet adhering to their feet. Rain was still falling from the dark heavens in a steady, warm downpour. Dry wood seemed scarce as the proverbial hen's teeth. "You didn't bring any matches, dear?" "Matches! Of course not! We're going back to Nature." "I hope we get a fire pretty soon." "If dry wood were gold dust, we couldn't buy a hot dog." "Eric, that reminds me that I'm hungry." He confessed to a few pangs of his own. They turned their attention to looking for banana trees, and coconut palms, but they did not seem to abound in the Venerian jungle. Even small animals that might have been slain with a broken branch had contrary ideas about the matter. At last, from sheer weariness, they stopped, and gathered branches to make a sloping shelter by a vast fallen tree-trunk. "This will keep out the rain—maybe—" Eric said hopefully. "And tomorrow, when it has quit raining—I'm sure we'll do better." They crept in, as gloomy night fell without. They lay in each other's arms, the body warmth oddly comforting. Nada cried a little. "Buck up," Eric advised her. "We're back to nature—where we've always wanted to be." With the darkness, the temperature fell somewhat, and a high wind rose, whipping cold rain into the little shelter, and threatening to demolish it. Swarms of mosquito-like insects, seemingly not inconvenienced in the least by the inclement elements, swarmed about them in clouds. Then came a sound from the dismal stormy night, a hoarse, bellowing roar, raucous, terrifying. Nada clung against Eric. "What is it, dear?" she chattered. "Must be a reptile. Dinosaur, or something of the sort. This world seems to be in about the same state as the Earth when they flourished there.... But maybe it won't find us." The roar was repeated, nearer. The earth trembled beneath a mighty tread. "Eric," a thin voice trembled. "Don't you think—it might have been better— You know the old life was not so bad, after all." "I was just thinking of our rooms, nice and warm and bright, with hot foods coming up the shaft whenever we pushed the button, and the gay crowds in the park, and my old typewriter." "Eric?" she called softly. "Yes, dear." "Don't you wish—we had known better?" "I do." If he winced at the "we" the girl did not notice. The roaring outside was closer. And suddenly it was answered by another raucous bellow, at considerable distance, that echoed strangely through the forest. The fearful sounds were repeated, alternately. And always the more distant seemed nearer, until the two sounds were together. And then an infernal din broke out in the darkness. Bellows. Screams. Deafening shrieks. Mighty splashes, as if struggling Titans had upset oceans. Thunderous crashes, as if they were demolishing forests. Eric and Nada clung to each other, in doubt whether to stay or to fly through the storm. Gradually the sound of the conflict came nearer, until the earth shook beneath them, and they were afraid to move. Suddenly the great fallen tree against which they had erected the flimsy shelter was rolled back, evidently by a chance blow from the invisible monsters. The pitiful roof collapsed on the bedraggled humans. Nada burst into tears. "Oh, if only—if only—" Suddenly flame lapped up about them, the same white fire they had seen as they lay on the crystal block. Dizziness, insensibility overcame them. A few moments later, they were lying on the transparent table in the Cosmic Express office, with all those great mirrors and prisms and lenses about them. A bustling, red-faced official appeared through the door in the grill, fairly bubbling apologies. "So sorry—an accident—inconceivable. I can't see how he got it! We got you back as soon as we could find a focus. I sincerely hope you haven't been injured." "Why—what—what—" "Why I happened in, found our operator drunk. I've no idea where he got the stuff. He muttered something about Venus. I consulted the auto-register, and found two more passengers registered here than had been recorded at our other stations. I looked up the duplicate beam coordinates, and found that it had been set on Venus. I got men on the television at once, and we happened to find you. "I can't imagine how it happened. I've had the fellow locked up, and the 'dry-laws' are on the job. I hope you won't hold us for excessive damages." "No, I ask nothing except that you don't press charges against the boy. I don't want him to suffer for it in any way. My wife and I will be perfectly satisfied to get back to our apartment." "I don't wonder. You look like you've been through—I don't know what. But I'll have you there in five minutes. My private car—" Mr. Eric Stokes-Harding, noted author of primitive life and love, ate a hearty meal with his pretty spouse, after they had washed off the grime of another planet. He spent the next twelve hours in bed. At the end of the month he delivered his promised story to his publishers, a thrilling tale of a man marooned on Venus, with a beautiful girl. The hero made stone tools, erected a dwelling for himself and his mate, hunted food for her, defended her from the mammoth saurian monsters of the Venerian jungles. The book was a huge success. THE END
|
C. It evolved to be flexible despite how it initially imitated the style of a singular author
|
Which of these is an irony represented as a main point in the story?
A. Men are more affected by the 27-day cycle than women are
B. Astronomers never talk to each other but only make progress when they do
C. The moon controls the tides but the sun controls emotions
D. Evil will haunt mankind as long as there is light from the Sun
|
DISTURBING SUN By PHILIP LATHAM Illustrated by Freas [Transcriber's Note: This etext was produced from Astounding Science Fiction May 1959. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] This, be it understood, is fiction—nothing but fiction—and not, under any circumstances, to be considered as having any truth whatever to it. It's obviously utterly impossible ... isn't it? An interview with Dr. I. M. Niemand, Director of the Psychophysical Institute of Solar and Terrestrial Relations, Camarillo, California. In the closing days of December, 1957, at the meeting of the American Association for the Advancement of Science in New York, Dr. Niemand delivered a paper entitled simply, "On the Nature of the Solar S-Regions." Owing to its unassuming title the startling implications contained in the paper were completely overlooked by the press. These implications are discussed here in an exclusive interview with Dr. Niemand by Philip Latham. LATHAM. Dr. Niemand, what would you say is your main job? NIEMAND. I suppose you might say my main job today is to find out all I can between activity on the Sun and various forms of activity on the Earth. LATHAM. What do you mean by activity on the Sun? NIEMAND. Well, a sunspot is a form of solar activity. LATHAM. Just what is a sunspot? NIEMAND. I'm afraid I can't say just what a sunspot is. I can only describe it. A sunspot is a region on the Sun that is cooler than its surroundings. That's why it looks dark. It isn't so hot. Therefore not so bright. LATHAM. Isn't it true that the number of spots on the Sun rises and falls in a cycle of eleven years? NIEMAND. The number of spots on the Sun rises and falls in a cycle of about eleven years. That word about makes quite a difference. LATHAM. In what way? NIEMAND. It means you can only approximately predict the future course of sunspot activity. Sunspots are mighty treacherous things. LATHAM. Haven't there been a great many correlations announced between sunspots and various effects on the Earth? NIEMAND. Scores of them. LATHAM. What is your opinion of these correlations? NIEMAND. Pure bosh in most cases. LATHAM. But some are valid? NIEMAND. A few. There is unquestionably a correlation between sunspots and disturbances of the Earth's magnetic field ... radio fade-outs ... auroras ... things like that. LATHAM. Now, Dr. Niemand, I understand that you have been investigating solar and terrestrial relationships along rather unorthodox lines. NIEMAND. Yes, I suppose some people would say so. LATHAM. You have broken new ground? NIEMAND. That's true. LATHAM. In what way have your investigations differed from those of others? NIEMAND. I think our biggest advance was the discovery that sunspots themselves are not the direct cause of the disturbances we have been studying on the Earth. It's something like the eruptions in rubeola. Attention is concentrated on the bright red papules because they're such a conspicuous symptom of the disease. Whereas the real cause is an invisible filterable virus. In the solar case it turned out to be these S-Regions. LATHAM. Why S-Regions? NIEMAND. We had to call them something. Named after the Sun, I suppose. LATHAM. You say an S-Region is invisible? NIEMAND. It is quite invisible to the eye but readily detected by suitable instrumental methods. It is extremely doubtful, however, if the radiation we detect is the actual cause of the disturbing effects observed. LATHAM. Just what are these effects? NIEMAND. Well, they're common enough, goodness knows. As old as the world, in fact. Yet strangely enough it's hard to describe them in exact terms. LATHAM. Can you give us a general idea? NIEMAND. I'll try. Let's see ... remember that speech from "Julius Caesar" where Cassius is bewailing the evil times that beset ancient Rome? I believe it went like this: "The fault, dear Brutus, is not in our stars but in ourselves that we are underlings." LATHAM. I'm afraid I don't see— NIEMAND. Well, Shakespeare would have been nearer the truth if he had put it the other way around. "The fault, dear Brutus, is not in ourselves but in our stars" or better "in the Sun." LATHAM. In the Sun? NIEMAND. That's right, in the Sun. I suppose the oldest problem in the world is the origin of human evil. Philosophers have wrestled with it ever since the days of Job. And like Job they have usually given up in despair, convinced that the origin of evil is too deep for the human mind to solve. Generally they have concluded that man is inherently wicked and sinful and that is the end of it. Now for the first time science has thrown new light on this subject. LATHAM. How is that? NIEMAND. Consider the record of history. There are occasional periods when conditions are fairly calm and peaceful. Art and industry flourished. Man at last seemed to be making progress toward some higher goal. Then suddenly— for no detectable reason —conditions are reversed. Wars rage. People go mad. The world is plunged into an orgy of bloodshed and misery. LATHAM. But weren't there reasons? NIEMAND. What reasons? LATHAM. Well, disputes over boundaries ... economic rivalry ... border incidents.... NIEMAND. Nonsense. Men always make some flimsy excuse for going to war. The truth of the matter is that men go to war because they want to go to war. They can't help themselves. They are impelled by forces over which they have no control. By forces outside of themselves. LATHAM. Those are broad, sweeping statements. Can't you be more specific? NIEMAND. Perhaps I'd better go back to the beginning. Let me see.... It all started back in March, 1955, when I started getting patients suffering from a complex of symptoms, such as profound mental depression, anxiety, insomnia, alternating with fits of violent rage and resentment against life and the world in general. These people were deeply disturbed. No doubt about that. Yet they were not psychotic and hardly more than mildly neurotic. Now every doctor gets a good many patients of this type. Such a syndrome is characteristic of menopausal women and some men during the climacteric, but these people failed to fit into this picture. They were married and single persons of both sexes and of all ages. They came from all walks of life. The onset of their attack was invariably sudden and with scarcely any warning. They would be going about their work feeling perfectly all right. Then in a minute the whole world was like some scene from a nightmare. A week or ten days later the attack would cease as mysteriously as it had come and they would be their old self again. LATHAM. Aren't such attacks characteristic of the stress and strain of modern life? NIEMAND. I'm afraid that old stress-and-strain theory has been badly overworked. Been hearing about it ever since I was a pre-med student at ucla . Even as a boy I can remember my grandfather deploring the stress and strain of modern life when he was a country doctor practicing in Indiana. In my opinion one of the most valuable contributions anthropologists have made in recent years is the discovery that primitive man is afflicted with essentially the same neurotic conditions as those of us who live a so-called civilized life. They have found savages displaying every symptom of a nervous breakdown among the mountain tribes of the Elgonyi and the Aruntas of Australia. No, Mr. Latham, it's time the stress-and-strain theory was relegated to the junk pile along with demoniac possession and blood letting. LATHAM. You must have done something for your patients— NIEMAND. A doctor must always do something for the patients who come to his office seeking help. First I gave them a thorough physical examination. I turned up some minor ailments—a slight heart murmur or a trace of albumin in the urine—but nothing of any significance. On the whole they were a remarkably healthy bunch of individuals, much more so than an average sample of the population. Then I made a searching inquiry into their personal life. Here again I drew a blank. They had no particular financial worries. Their sex life was generally satisfactory. There was no history of mental illness in the family. In fact, the only thing that seemed to be the matter with them was that there were times when they felt like hell. LATHAM. I suppose you tried tranquilizers? NIEMAND. Oh, yes. In a few cases in which I tried tranquilizing pills of the meprobamate type there was some slight improvement. I want to emphasize, however, that I do not believe in prescribing shotgun remedies for a patient. To my way of thinking it is a lazy slipshod way of carrying on the practice of medicine. The only thing for which I do give myself credit was that I asked my patients to keep a detailed record of their symptoms taking special care to note the time of exacerbation—increase in the severity of the symptoms—as accurately as possible. LATHAM. And this gave you a clue? NIEMAND. It was the beginning. In most instances patients reported the attack struck with almost the impact of a physical blow. The prodromal symptoms were usually slight ... a sudden feeling of uneasiness and guilt ... hot and cold flashes ... dizziness ... double vision. Then this ghastly sense of depression coupled with a blind insensate rage at life. One man said he felt as if the world were closing in on him. Another that he felt the people around him were plotting his destruction. One housewife made her husband lock her in her room for fear she would injure the children. I pored over these case histories for a long time getting absolutely nowhere. Then finally a pattern began to emerge. LATHAM. What sort of pattern? NIEMAND. The first thing that struck me was that the attacks all occurred during the daytime, between the hours of about seven in the morning and five in the evening. Then there were these coincidences— LATHAM. Coincidences? NIEMAND. Total strangers miles apart were stricken at almost the same moment. At first I thought nothing of it but as my records accumulated I became convinced it could not be attributed to chance. A mathematical analysis showed the number of coincidences followed a Poisson distribution very closely. I couldn't possibly see what daylight had to do with it. There is some evidence that mental patients are most disturbed around the time of full moon, but a search of medical literature failed to reveal any connection with the Sun. LATHAM. What did you do? NIEMAND. Naturally I said nothing of this to my patients. I did, however, take pains to impress upon them the necessity of keeping an exact record of the onset of an attack. The better records they kept the more conclusive was the evidence. Men and women were experiencing nearly simultaneous attacks of rage and depression all over southern California, which was as far as my practice extended. One day it occurred to me: if people a few miles apart could be stricken simultaneously, why not people hundreds or thousands of miles apart? It was this idea that prompted me to get in touch with an old colleague of mine I had known at UC medical school, Dr. Max Hillyard, who was in practice in Utica, New York. LATHAM. With what result? NIEMAND. I was afraid the result would be that my old roommate would think I had gone completely crazy. Imagine my surprise and gratification on receiving an answer by return mail to the effect that he also had been getting an increasing number of patients suffering with the same identical symptoms as my own. Furthermore, upon exchanging records we did find that in many cases patients three thousand miles apart had been stricken simultaneously— LATHAM. Just a minute. I would like to know how you define "simultaneous." NIEMAND. We say an attack is simultaneous when one occurred on the east coast, for example, not earlier or later than five minutes of an attack on the west coast. That is about as close as you can hope to time a subjective effect of this nature. And now another fact emerged which gave us another clue. LATHAM. Which was? NIEMAND. In every case of a simultaneous attack the Sun was shining at both New York and California. LATHAM. You mean if it was cloudy— NIEMAND. No, no. The weather had nothing to do with it. I mean the Sun had to be above the horizon at both places. A person might undergo an attack soon after sunrise in New York but there would be no corresponding record of an attack in California where it was still dark. Conversely, a person might be stricken late in the afternoon in California without a corresponding attack in New York where the Sun had set. Dr. Hillyard and I had been searching desperately for a clue. We had both noticed that the attacks occurred only during the daylight hours but this had not seemed especially significant. Here we had evidence pointing directly to the source of trouble. It must have some connection with the Sun. LATHAM. That must have had you badly puzzled at first. NIEMAND. It certainly did. It looked as if we were headed back to the Middle Ages when astrology and medicine went hand in hand. But since it was our only lead we had no other choice but to follow it regardless of the consequences. Here luck played somewhat of a part, for Hillyard happened to have a contact that proved invaluable to us. Several years before Hillyard had gotten to know a young astrophysicist, Henry Middletown, who had come to him suffering from a severe case of myositis in the arms and shoulders. Hillyard had been able to effect a complete cure for which the boy was very grateful, and they had kept up a desultory correspondence. Middletown was now specializing in radio astronomy at the government's new solar observatory on Turtle Back Mountain in Arizona. If it had not been for Middletown's help I'm afraid our investigation would never have gotten past the clinical stage. LATHAM. In what way was Middletown of assistance? NIEMAND. It was the old case of workers in one field of science being completely ignorant of what was going on in another field. Someday we will have to establish a clearing house in science instead of keeping it in tight little compartments as we do at present. Well, Hillyard and I packed up for Arizona with considerable misgivings. We were afraid Middletown wouldn't take our findings seriously but somewhat to our surprise he heard our story with the closest attention. I guess astronomers have gotten so used to hearing from flying saucer enthusiasts and science-fiction addicts that nothing surprises them any more. When we had finished he asked to see our records. Hillyard had them all set down for easy numerical tabulation. Middletown went to work with scarcely a word. Within an hour he had produced a chart that was simply astounding. LATHAM. Can you describe this chart for us? NIEMAND. It was really quite simple. But if it had not been for Middletown's experience in charting other solar phenomena it would never have occurred to us to do it. First, he laid out a series of about thirty squares horizontally across a sheet of graph paper. He dated these beginning March 1, 1955, when our records began. In each square he put a number from 1 to 10 that was a rough index of the number and intensity of the attacks reported on that day. Then he laid out another horizontal row below the first one dated twenty-seven days later. That is, the square under March 1st in the top row was dated March 28th in the row below it. He filled in the chart until he had an array of dozens of rows that included all our data down to May, 1958. When Middletown had finished it was easy to see that the squares of highest index number did not fall at random on the chart. Instead they fell in slightly slanting parallel series so that you could draw straight lines down through them. The connection with the Sun was obvious. LATHAM. In what way? NIEMAND. Why, because twenty-seven days is about the synodic period of solar rotation. That is, if you see a large spot at the center of the Sun's disk today, there is a good chance if it survives that you will see it at the same place twenty-seven days later. But that night Middletown produced another chart that showed the connection with the Sun in a way that was even more convincing. LATHAM. How was that? NIEMAND. I said that the lines drawn down through the days of greatest mental disturbance slanted slightly. On this second chart the squares were dated under one another not at intervals of twenty-seven days, but at intervals of twenty-seven point three days. LATHAM. Why is that so important? NIEMAND. Because the average period of solar rotation in the sunspot zone is not twenty-seven days but twenty-seven point three days. And on this chart the lines did not slant but went vertically downward. The correlation with the synodic rotation of the Sun was practically perfect. LATHAM. But how did you get onto the S-Regions? NIEMAND. Middletown was immediately struck by the resemblance between the chart of mental disturbance and one he had been plotting over the years from his radio observations. Now when he compared the two charts the resemblance between the two was unmistakable. The pattern shown by the chart of mental disturbance corresponded in a striking way with the solar chart but with this difference. The disturbances on the Earth started two days later on the average than the disturbances due to the S-Regions on the Sun. In other words, there was a lag of about forty-eight hours between the two. But otherwise they were almost identical. LATHAM. But if these S-Regions of Middletown's are invisible how could he detect them? NIEMAND. The S-Regions are invisible to the eye through an optical telescope, but are detected with ease by a radio telescope. Middletown had discovered them when he was a graduate student working on radio astronomy in Australia, and he had followed up his researches with the more powerful equipment at Turtle Back Mountain. The formation of an S-Region is heralded by a long series of bursts of a few seconds duration, when the radiation may increase up to several thousand times that of the background intensity. These noise storms have been recorded simultaneously on wavelengths of from one to fifteen meters, which so far is the upper limit of the observations. In a few instances, however, intense bursts have also been detected down to fifty cm. LATHAM. I believe you said the periods of mental disturbance last for about ten or twelve days. How does that tie-in with the S-Regions? NIEMAND. Very closely. You see it takes about twelve days for an S-Region to pass across the face of the Sun, since the synodic rotation is twenty-seven point three days. LATHAM. I should think it would be nearer thirteen or fourteen days. NIEMAND. Apparently an S-Region is not particularly effective when it is just coming on or just going off the disk of the Sun. LATHAM. Are the S-Regions associated with sunspots? NIEMAND. They are connected in this way: that sunspot activity and S-Region activity certainly go together. The more sunspots the more violent and intense is the S-Region activity. But there is not a one-to-one correspondence between sunspots and S-Regions. That is, you cannot connect a particular sunspot group with a particular S-Region. The same thing is true of sunspots and magnetic storms. LATHAM. How do you account for this? NIEMAND. We don't account for it. LATHAM. What other properties of the S-Regions have you discovered? NIEMAND. Middletown says that the radio waves emanating from them are strongly circularly polarized. Moreover, the sense of rotation remains constant while one is passing across the Sun. If the magnetic field associated with an S-Region extends into the high solar corona through which the rays pass, then the sense of rotation corresponds to the ordinary ray of the magneto-ionic theory. LATHAM. Does this mean that the mental disturbances arise from some form of electromagnetic radiation? NIEMAND. We doubt it. As I said before, the charts show a lag of about forty-eight hours between the development of an S-Region and the onset of mental disturbance. This indicates that the malignant energy emanating from an S-Region consists of some highly penetrating form of corpuscular radiation, as yet unidentified. [A] LATHAM. A question that puzzles me is why some people are affected by the S-Regions while others are not. NIEMAND. Our latest results indicate that probably no one is completely immune. All are affected in some degree. Just why some should be affected so much more than others is still a matter of speculation. LATHAM. How long does an S-Region last? NIEMAND. An S-Region may have a lifetime of from three to perhaps a dozen solar rotations. Then it dies out and for a time we are free from this malignant radiation. Then a new region develops in perhaps an entirely different region of the Sun. Sometimes there may be several different S-Regions all going at once. LATHAM. Why were not the S-Regions discovered long ago? NIEMAND. Because the radio exploration of the Sun only began since the end of World War II. LATHAM. How does it happen that you only got patients suffering from S-radiation since about 1955? NIEMAND. I think we did get such patients previously but not in large enough numbers to attract attention. Also the present sunspot cycle started its rise to maximum about 1954. LATHAM. Is there no way of escaping the S-radiation? NIEMAND. I'm afraid the only sure way is to keep on the unilluminated side of the Earth which is rather difficult to do. Apparently the corpuscular beam from an S-Region is several degrees wide and not very sharply defined, since its effects are felt simultaneously over the entire continent. Hillyard and Middletown are working on some form of shielding device but so far without success. LATHAM. What is the present state of S-Region activity? NIEMAND. At the present moment there happens to be no S-Region activity on the Sun. But a new one may develop at any time. Also, the outlook for a decrease in activity is not very favorable. Sunspot activity continues at a high level and is steadily mounting in violence. The last sunspot cycle had the highest maximum of any since 1780, but the present cycle bids fair to set an all time record. LATHAM. And so you believe that the S-Regions are the cause of most of the present trouble in the world. That it is not ourselves but something outside ourselves— NIEMAND. That is the logical outcome of our investigation. We are controlled and swayed by forces which in many cases we are powerless to resist. LATHAM. Could we not be warned of the presence of an S-Region? NIEMAND. The trouble is they seem to develop at random on the Sun. I'm afraid any warning system would be worse than useless. We would be crying WOLF! all the time. LATHAM. How may a person who is not particularly susceptible to this malignant radiation know that one of these regions is active? NIEMAND. If you have a feeling of restlessness and anxiety, if you are unable to concentrate, if you feel suddenly depressed and discouraged about yourself, or are filled with resentment toward the world, then you may be pretty sure that an S-Region is passing across the face of the Sun. Keep a tight rein on yourself. For it seems that evil will always be with us ... as long as the Sun shall continue to shine upon this little world. THE END [A] Middletown believes that the Intense radiation recently discovered from information derived from Explorer I and III has no connection with the corpuscular S-radiation.
|
D. Evil will haunt mankind as long as there is light from the Sun
|
What evidence does visualizing the attention give to show that it helps to obtain a more robust understanding of semantics and sentiments?
|
### Introduction
The rapid growth of social media platforms such as Twitter provides rich multimedia data in large scales for various research opportunities, such as sentiment analysis which focuses on automatically sentiment (positive and negative) prediction on given contents. Sentiment analysis has been widely used in real world applications by analyzing the online user-generated data, such as election prediction, opinion mining and business-related activity analysis. Emojis, which consist of various symbols ranging from cartoon facial expressions to figures such as flags and sports, are widely used in daily communications to express people's feelings . Since their first release in 2010, emojis have taken the place of emoticons (such as “:- INLINEFORM0 ” and “:-P”) BIBREF0 to create a new form of language for social media users BIBREF1 . According to recent science reports, there are 2,823 emojis in unicode standard in Emoji 11.0 , with over 50% of the Instagram posts containing one or more emojis BIBREF2 and 92% of the online population using emojis BIBREF3 . The extensive use of emojis has drawn a growing attention from researchers BIBREF4 , BIBREF5 because the emojis convey fruitful semantical and sentimental information to visually complement the textual information which is significantly useful in understanding the embedded emotional signals in texts BIBREF6 . For example, emoji embeddings have been proposed to understand the semantics behind the emojis BIBREF7 , BIBREF8 , and the embedding vectors can be used to visualize and predict emoji usages given their corresponding contexts. Previous work also shows that, it is useful to pre-train a deep neural network on an emoji prediction task with pre-trained emoji embeddings to learn the emotional signals of emojis for other tasks including sentiment, emotion and sarcasm prediction BIBREF9 . However, the previous literatures lack in considerations of the linguistic complexities and diversity of emoji. Therefore, previous emoji embedding methods fail to handle the situation when the semantics or sentiments of the learned emoji embeddings contradict the information from the corresponding contexts BIBREF5 , or when the emojis convey multiple senses of semantics and sentiments such as ( and ). In practice, emojis can either summarize and emphasis the original tune of their contexts, or express more complex semantics such as irony and sarcasm by being combined with contexts of contradictory semantics or sentiments. For the examples shown in Table TABREF3 , the emoji () is of consistent sentiment with text to emphasis the sentiment, but is of the opposite sentiment (positive) to the text sentiment (negative) example 3 and 4 to deliver a sense of sarcasm. Conventional emoji analysis can only extract single embedding of each emoji, and such embeddings will confuse the following sentiment analysis model by inconsistent sentiment signals from the input texts and emojis. Moreover, we consider the emoji effect modeling different from the conventional multimodal sentiment analysis which usually includes images and texts in that, image sentiment and text sentiment are usually assumed to be consistent BIBREF10 while it carries no such assumption for texts and emojis. To tackle such limitations, we propose a novel scheme that consists of an attention-based recurrent neural network (RNN) with robust bi-sense emoji embeddings. Inspired by the word sense embedding task in natural language processing (NLP) BIBREF11 , BIBREF12 , BIBREF13 where each sense of an ambiguous word responds to one unique embedding vector, the proposed bi-sense embedding is a more robust and fine-grained representation of the complicated semantics for emojis where each emoji is embedded into two distinct vectors, namely positive-sense and negative-sense vector, respectively. For our specific task which is Twitter sentiment analysis BIBREF14 , BIBREF15 , we initialize the bi-sense embedding vectors together with word embedding vectors using word embedding algorithm fasttext BIBREF16 by extracting two distinct embeddings for each emoji according to the sentiment of its corresponding textual contexts, namely bi-sense embedding. A long short-term memory (LSTM) based recurrent neural network is then used for predicting sentiments which is integrated with the pre-trained emoji embedding features by a context-guide and self-selected attention mechanism. Because most of the previous Twitter sentiment datasets exclude emojis and there exists little resource that contains sufficient emoji-tweets with sentiment labels, we construct our own emoji-tweets dataset by automatically generating weak labels using a rule-based sentiment analysis algorithm Vader BIBREF17 for pre-traning the networks, and manually labeling a subset of tweets for fine tuning and testing purposes. The experimental results demonstrate that the bi-sense emoji embedding is capable of extracting more distinguished information from emojis and outperforms the state-of-the-art sentiment analysis models with the proposed attention-based LSTM networks. We further visualize the bi-sense emoji embedding to obtain the sentiments and semantics learned by the proposed approach. The main contributions of this paper are summarized as follows. ### Sentiment Analysis
Sentiment analysis is to extract and quantify subjective information including the status of attitudes, emotions and opinions from a variety of contents such as texts, images and audios BIBREF18 . Sentiment analysis has been drawing great attentions because of its wide applications in business and government intelligence, political science, sociology and psychology BIBREF19 , BIBREF20 , BIBREF21 , BIBREF22 . From a technical perspective, textual sentiment analysis is first explored by researchers as an NLP task. Methods range from lexical-based approaches using features including keywords BIBREF23 , BIBREF24 where each word corresponds to a sentiment vector with entries representing the possibility of the word and each sentiment and phase-level features (n-grams and unigrams) BIBREF25 , BIBREF26 , to deep neural network based embedding approaches including skip-grams, continuous bag-of-words (CBoW) and skip-thoughts BIBREF27 , BIBREF28 , BIBREF16 , BIBREF29 . It was until recent years when researchers start focusing on image and multimodal sentiments BIBREF30 , BIBREF31 and analyzing how to take advantage of the cross-modality resources BIBREF10 , BIBREF32 . For multimodal sentiment analysis, an underlying assumption is that both modalities express similar sentiment and such similarity is enforced in order to train a robust sentiment inference model BIBREF10 . However, the same assumption does not stand in modeling textual tweets and emojis because the complexities of natural language exist extensively, such as the use of irony, jokes, sarcasm, etc. BIBREF9 . Models We set up the baselines and proposed models as follows: LSTM with text embedding: CNNs and LSTMs are widely used to encode textual contents for sentiment analysis in BIBREF45 , BIBREF46 and many online tutorials. Here we select the standard LSTM with pre-trained word embedding as input, and add one fully-connected layer with sigmoid activation top of the LSTM encoder (same as all other models), denoted as T-LSTM. LSTM with emoji embedding: We consider the emoji as one special word and input both pre-trained text and emoji embeddings into the same LSTM network, namely E-LSTM. Similarly, we concatenate the pre-trained bi-sense emoji embedding as one special word to feed into the LSTM network. This model is called BiE-LSTM. Attention-based LSTM with emojis:We also use the word-emoji embedding to calculate the emoji-word attention following Equation EQREF20 and EQREF21 , and the only difference is that we replace the attention-derived senti-emoji embedding with the pre-trained word-emoji embedding by fasttext, denoted as ATT-E-LSTM. LSTM with bi-sense emoji embedding (proposed): As we have introduced in Section SECREF13 , we propose two attention-based LSTM networks based on bi-sense emoji embedding, denoted as MATT-BiE-LSTM and WATT-BiE-LSTM. Evaluation We evaluate the baseline and proposed models on sentiment analysis by F1 scores and accuracies based on the auto-annotated testing set (AA-Sentiment) and human-annotated testing set (HA-Sentiment), as shown in Table TABREF25 . We only test the models after fine-tuning with a subset of the samples with human annotations because training exclusively on the samples with auto-generated weak labels results in relatively poor performances when tested with human annotated data indicating the models after fine-tuning are more robust. The F1 scores and accuracies are overall higher with the AA-Sentiment than the results with HA-sentiment, indicating that the HA-Sentiment is a more challenging task and the sentiments involved are more difficult to identify supported by their relatively lower sentiment scores returned from Vader. We still, however, observe competitive results from HA-Sentiment showing that the models are well-trained and robust to noisy labels with the help of fine-tuning with human annotated data. The T-LSTM baseline achieves decent performance in both experiments with accuracies of 86.6% and 70.7% showing that LSTM is an effective encoder for sentiment analysis as suggested by the references. The models with proposed bi-sense emoji embedding obtain accuracies over 82.4% and we observe improvements on the performance with the attention-based LSTM from our proposed model MATT-BiE-LSTM and WATT-BiE-LSTM, which is consistent with that ATT-E-LSTM ([email protected]%, [email protected]% on HA-Sentiment) outperforms significantly T-LSTM and E-LSTM. Emoji information is useful in sentiment analysis. Most models outperforms the baseline T-LSTM in both dataset suggesting that the emoji information is useful for sentiment analysis as a complement to the textual contents, even with the naive use of emoji embeddings (E-LSTM) when tested with HA-Sentiment. We observe that E-LSTM obtains similar performance to T-LSTM with AA-Sentiment but a significant gain over the T-LSTM when tested with HA-Sentiment indicating that sentiment information is helpful and necessary when the hidden sentiment is relatively subtle and the task is more challenging. Bi-sense emoji embedding helps. All the models using bi-sense emoji embedding perform significantly better than the baseline models without emoji feature or with word-emoji embedding. BiE-LSTM outperforms T-LSTM and E-LSTM significantly with the same utilization of emoji embedding indicates that the proposed bi-sense emoji embedding is capable of extracting more informative and distinguishable vectors over the use of conventional word embedding algorithms, which is consistent based on the comparisons between the proposed models (MATT-BiE-LSTM and WATT-BiE-LSTM) with bi-sense emoji embedding and the baseline model ATT-E-LSTM with word-emoji embedding and attention. Attention mechanism aligns and performs well with bi-sense embedding. MATT-BiE-LSTM and WATT-BiE-LSTM obtain similar performances when tested on both Vader and human annotated samples, though their ways of computing the attention (weights and vectors) are different that WATT computes attention weights and the senti-emoji embeddings guided by each word, and MATT obtains the senti-emoji embedding based on the LSTM encoder on the whole contexts and computes the attention weights of the senti-emoji embedding across all words. Both models outperforms the state-of-the-art baseline models including ATT-E-LSTM. The proposed attention-based LSTM can be further extended to handle tasks involving multi-sense embedding as inputs, such as the word-sense embedding in NLP, by using context-guide attention to self-select how much to attend on each sense of the embeddings each of which correspond to a distinct sense of semantics or sentiments. In this way we are able to take advantage of the more robust and fine-grained embeddings. ### Emojis and Sentiment Analysis
With the overwhelming development of Internet of Things (IOT), the growing accessibility and popularity of subjective contents have provided new opportunities and challenges for sentiment analysis BIBREF33 . For example, social medias such as Twitter and Instagram have been explored because the massive user-generated contents with rich user sentiments BIBREF25 , BIBREF34 , BIBREF35 where emojis (and emoticons) are extensively used. Non-verbal cues of sentiment, such as emoticon which is considered as the previous generation of emoji, has been studied for their sentiment effect before emojis take over BIBREF36 , BIBREF37 , BIBREF38 . For instance, BIBREF36 , BIBREF38 pre-define sentiment labels to emoticons and construct a emoticon-sentiment dictionary. BIBREF37 applies emoticons for smoothing noisy sentiment labels. Similar work from BIBREF39 first considers emoji as a component in extracting the lexical feature for further sentiment analysis. BIBREF40 constructs an emoji sentiment ranking based on the occurrences of emojis and the human-annotated sentiments of the corresponding tweets where each emoji is assigned with a sentiment score from negative to positive , similar to the SentiWordNet BIBREF41 . However, the relatively intuitive use of emojis by lexical- and dictionary-based approaches lacks insightful understanding of the complexed semantics of emojis. Therefore, inspired by the success of word semantic embedding algorithms such as BIBREF28 , BIBREF16 , BIBREF7 obtains semantic embeddings of each emoji by averaging the words from its descriptions and shows it is effective to take advantage of the emoji embedding for the task of Twitter sentiment analysis. BIBREF8 proposes a convoluntional neural network to predict the emoji occurrence and jointly learns the emoji embedding via a matching layer based on cosine similarities. Despite the growing popularity of Twitter sentiment analysis, there is a limited number of emoji datasets with sentiment labels available because previous studies usually filter out urls, emojis and sometimes emoticons. However, BIBREF9 shows that it is effective to extract sentiment information from emojis for emotion classification and sarcasm detection tasks in the absence of learning vector-based emoji representations by pre-training a deep neural network to predict the emoji occurrence. ### Methodology
We propose two mechanisms, namely Word-guide Attention-based LSTM and Multi-level Attention-based LSTM, to take advantage of bi-sense emoji embedding for the sentiment analysis task. The frameworks of these two methods are shown in Figure FIGREF10 and Figure FIGREF19 , respectively. Our workflow includes the following steps: initialization of bi-sense emoji embedding, generating senti-emoji embedding based on self-selected attention, and sentiment classification via the proposed attention-based LSTM networks. ### Bi-sense Embedding
Recent research shows great success in word embedding task such as word2vec and fasttext BIBREF27 , BIBREF16 . We use fasttext to initialize emoji embeddings by considering each emoji as a special word, together with word embeddings. The catch is, different from conventional approaches where each emoji responds to one embedding vector (as we call word-emoji embedding), we embed each emoji into two distinct vectors (bi-sense emoji embedding): we first assign two distinct tokens to each emoji, of which one is for the particular emoji used in positive sentimental contexts and the other one is for this emoji used in negative sentimental contexts (text sentiment initialized by Vader BIBREF17 , details will be discussed in Section SECREF23 ), respectively; the same fasttext training process is used to embed each token into a distinct vector, and we thus obtain the positive-sense and negative-sense embeddings for each emoji. The word2vec is based on the skip-gram model whose objective is to maximize the log likelihood calculated by summing the probabilities of current word occurrences given a set of the surrounding words. The fasttext model is different by formatting the problem as a binary classification task to predict the occurrence of each context word, with negative samples being randomly selected from the absent context words. Given an input word sequence INLINEFORM0 , and the context word set INLINEFORM1 and the set of negative word samples INLINEFORM2 of the current word INLINEFORM3 , the objective function is obtained based on binary logistic loss as in Equation EQREF12 : DISPLAYFORM0 where INLINEFORM0 denotes the logistic loss of the score function INLINEFORM1 which is computed by summing up the scalar products between the n-gram embeddings of the current word and the context word embedding which is different from word2vec where the score is the scalar product between the current word and the context word embedding. We select fasttext over word2vec mainly because its computational efficiency. In general, the two models yield competitive performances and the comparison between word embeddings is beyond our discussion. Therefore we only show the results derived by the fasttext initialization within the scope of this work. ### Word-guide Attention-based LSTM
Long short-term memory (LSTM) units have been extensively used to encode textual contents. The basic encoder model consists of a text embedding layer, LSTMs layer, and fully-connected layers for further tasks such as text classifications based on the encoded feature. The operations in an LSTM unit for time step INLINEFORM0 is formulated in Equation EQREF14 : DISPLAYFORM0 where INLINEFORM0 and INLINEFORM1 represent the current and previous hidden states, INLINEFORM2 denotes the current LSTM input and here we use the embedding INLINEFORM3 of the current word INLINEFORM4 , and INLINEFORM5 and INLINEFORM6 denote the weight matrices BIBREF42 . In order to take advantage of the bi-sense emoji embedding, we modify the input layer into the LSTM units. We first obtain the senti-emoji embedding as an weighted average of the bi-sense emoji embedding based on the self-selected attention mechanism. Let INLINEFORM7 represent the INLINEFORM8 -th sense embedding of emoji INLINEFORM9 ( INLINEFORM10 in our bi-sense embedding), and INLINEFORM11 denote the attention function conditioned on the current word embedding, the attention weight INLINEFORM12 and senti-emoji embedding vector INLINEFORM13 is formulated as follows: DISPLAYFORM0 We choose a fully-connected layer with ReLU activation as the attention function, and the attention vector INLINEFORM0 is concatenated with the word embedding as the new input of the LSTM. Thus the input vector INLINEFORM1 in Equation EQREF14 becomes INLINEFORM2 . The output of the final LSTM unit is then fed into a fully-connected layer with INLINEFORM3 activation to output the tweet sentiment and binary cross-entropy loss is used as the objection function (Equation EQREF16 ) where INLINEFORM4 is the total number of samples. The motivation behind this model is that each context word guides the attention weights in order to enforce the model to self-select which embedding sense it should attend on. Therefore we denote this model as the Word-guide Attention-based LSTM with Bi-sense emoji embedding (WATT-BiE-LSTM). DISPLAYFORM0 ### Multi-level Attention-based LSTM
There is another way of formulating the attention mechanism where the attention weights indicate how the image information (which is emoji in our case) is distributed through the context words as proposed in BIBREF43 , BIBREF44 . The modified senti-emoji embedding vector INLINEFORM0 is thus at the tweet-level instead of the word-level in Equation EQREF15 by replacing the INLINEFORM1 with the final state vector INLINEFORM2 outputted from the last LSTM unit, as shown in Equation EQREF18 : DISPLAYFORM0 The derived senti-emoji embedding INLINEFORM0 is then used to calculate an additional layer of attention following BIBREF43 , BIBREF44 . Given the input tweet sequence INLINEFORM1 , the attention weight INLINEFORM2 conditioned on the senti-emoji embedding is formulated as follows: DISPLAYFORM0 Therefore, we construct the new input INLINEFORM0 to each LSTM unit by concatenating the original word embedding and the attention vector in Equation EQREF21 to distribute the senti-emoji information to each step. This model is called Multi-level Attention-based LSTM with Bi-sense Emoji Embedding (MATT-BiE-LSTM). We choose the same binary cross-entropy as the loss function with the same network configuration with WATT-BiE-LSTM. DISPLAYFORM0 ### Data Collection and Annotation
Data Collection We construct our own Twitter sentiment dataset by crawling tweets through the REST API which consists of 350,000 users and is magnitude larger comparing to previous work. We collect up to 3,200 tweets from each user and follow the standard tweet preprocessing procedures to remove the tweets without emojis and tweets containing less than ten words, and contents including the urls, mentions, and emails. Data Annotation For acquiring the sentiment annotations, we first use Vader which is a rule-based sentiment analysis algorithm BIBREF17 for text tweets only to generate weak sentiment labels. The algorithm outputs sentiment scores ranging from -1 (negative) to 1 (positive) with neutral in the middle. We consider the sentiment analysis as a binary classification problem (positive sentiment and negative sentiment), we filter out samples with weak prediction scores within INLINEFORM0 and keep the tweets with strong sentiment signals. Emoji occurrences are calculated separately for positive tweets and negative tweets, and threshold is set to 2,000 to further filter out emojis which are less frequently used in at least one type of sentimental text. In the end, we have constructed a dataset with 1,492,065 tweets and 55 frequently used emojis in total. For the tweets with an absolute sentiment score over 0.70, we keep the auto-generated sentiment label as ground truth because the automatic annotation is reliable with high sentiment scores. On the other hand, we select a subset of the tweets with absolute sentiment scores between INLINEFORM1 for manual labeling by randomly sampling, following the distribution of emoji occurrences where each tweet is labeled by two graduate students. Tweets are discarded if the two annotations disagree with each other or they are labeled as neutral. In the end, we have obtained 4,183 manually labeled tweets among which 60% are used for fine-tuning and 40% are used for testing purposes. The remainder of the tweets with automatic annotations are divided into three sets: 60% are used for pre-training the bi-sense and conventional emoji embedding, 10% for validation and 30% are for testing. We do not include a “neutral” class because it is difficult to obtain valid neutral samples. For auto-generated labels, the neutrals are the samples with low absolute confidence scores and their sentiments are more likely to be model failures other than “true neutrals”. Moreover, based on the human annotations, most of the tweets with emojis convey non-neutral sentiment and only few neutral samples are observed during the manual labeling which are excluded from the manually labeled subset. In order to valid our motivation that emojis are also extensively used in tweets that contain contradictory information to the emoji sentiments, we calculate the emoji usage in Table TABREF22 according to the sentiment labels where Pos-Ratio means the percentage of each emoji occurs in the positive tweets over its total number of occurrences, AA and HA indicate automatic-annotation and human-annotation, respectively. We present the top-10 most frequently used emojis in our dataset and observe a slight difference in the Pos-Ratios between AA and HA dataset because of the randomness involved in the sampling process. Results from both of the datasets show a fair amount of emoji use in both positive and negative tweets. For example, it is interesting to notice that emoji () occurs more in the positive tweets in with the automatic annotations, while emojis with strong positive sentiment have also been used in negative tweets with about 5% occurrences, such as (, , and ). Given the averaged positive ratio among all emojis in the whole dataset is about 74% and that most emojis have been extensively used in tweets containing both positive and negative sentiments, it suggests that distinguishing the emoji occurrences in both sentiments via bi-sense embedding is worth investigating. Additionally, we observe the Pos-Ratios of the AA-sentiment and HA-sentiment have little differences which are due to two main reasons: 1) Some tweets we sampled to construct the HA-sentiment are discarded because the annotators have disagreements and we only keep the samples that we are confident about; 2) Tweets with absolute sentiment scores between (0.60,0.70) are selected for manual labeling as discussed in Section SECREF23 , which are lower than the tweets used to construct the AA-sentiment (0.7 and above). The lower sentiment scores indicate that Vader is less reliable on the samples of HA-sentiment dataset and the sentiments of these tweets are more likely to be affected by emojis. ### Qualitative Analysis
In order to obtain insights about why the more fine-grained bi-sense emoji embedding helps in understanding the complexed sentiments behind tweets, we visualize the attention weights for ATT-E-LSTM and MATT-BiE-LSTM for comparison. The example tweets with corresponding attention weights calculated by word-emoji embedding and senti-emoji embedding are shown in Figure FIGREF27 , where the contexts are presented in the captions. The emojis used are , , and , respectively. In Figure FIGREF27 (a), the ATT-E-LSTM model (baseline) assigns relatively more weights on the word “no” and “pressure”, while MATT-BiE-LSTM attends mostly on the word “happy” and “lovely”. The different attention distributions suggest that the proposed senti-emoji embedding is capable of recognizing words with strong sentiments that are closely related to the true sentiment even with the presence of words with conflicting sentiments, such as “pressure” and “happy”. while ATT-E-LSTM tends to pick up all sentimental words which could raise confusions. The senti-emoji embedding is capable of extracting representations of complexed semantics and sentiments which help guide the attentions even in cases when the word sentiment and emoji sentiment are somewhat contradictory to each other. From Figure FIGREF27 (b) and (c) we can observe that the ATT-E-LSTM assigns more weights on the sentiment-irrelevant words than the MATT-BiE-LSTM such as “hoodies”, “wait” and “after”, indicating that the proposed model is more robust to irrelevant words and concentrates better on important words. Because of the senti-emoji embedding obtained through bi-sense emoji embedding and the sentence-level LSTM encoding on the text input (described in Section SECREF13 ), we are able to construct a more robust embedding based on the semantic and sentiment information from the whole context compared to the word-emoji embedding used in ATT-E-LSTM which takes only word-level information into account. ### Bi-sense Emoji Embedding Visualization
To gain further insights on the bi-sense emoji embedding, we use t-SNE BIBREF47 to project high-dimensional bi-sense embedding vectors into a two-dimensional space and preserving the relative distances between the embedding vectors at the same time. In Figure FIGREF28 we visualize the bi-sense emoji embedding, positive-sense embedding, negative-sense embedding and the subtraction between positive and negative sense embeddings of each emoji, respectively. The subtraction of an emoji between its two sense embeddings indicates the semantic differences between emoji usages in positive and negative sentimental contexts, similarly to the objective of word embeddings BIBREF28 . The positive-sense of emoji ( and ), and the negative-sense of emoji (, and ) are embedded far from the two main clusters as observed in Figure FIGREF28 (a), suggesting that the semantics of these emojis are different from the other popular emojis. The positive-sense embedding and negative-sense embeddings are clustered well with no intersection with each other. Such observation supports our objective of applying bi-sense emoji embedding because there exist such significant differences in the semantics of each emoji when appears in positive and negative sentimental contexts, and it is well-motivated to consider the emoji usages individually according to the sentiment of the contexts to extract the more fine-grained bi-sense embedding. Additionally, we observe consistent patterns in the Figure FIGREF28 (b), (c) and (d) where the sentiments conveyed in the emojis become an important factor. For example, emojis with positive sentiments such as (, and ), and emojis with negative sentiment such as (, and ) are embedded into one clusters in both positive-sense and negative-sense space. The embedding subtractions of emojis in Figure FIGREF28 (d) shows the different usages of emojis across sentiments are similar between emojis and preserve the cluster patterns observed in Figure FIGREF28 (b) and (c). ### Conclusions
In this paper, we present a novel approach to the task of sentiment analysis and achieve the state-of-the-art performance. Different from the previous work, our method combines a more robust and fine-grained bi-sense emoji embedding that effectively represents complex semantic and sentiment information, with attention-based LSTM networks that selectively attend on the correlated sense of the emoji embeddings, and seamlessly fuse the obtained senti-emoji embeddings with the word embeddings for a better understanding of the rich semantics and sentiments involved. In the future, we plan to further extend our attention-based LSTM with bi-embedding work frame to tackle tasks involving multi-sense embedding such as the learning and applications of word-sense embedding. ### Acknowledgement
We would like to thank the support of New York State through the Goergen Institute for Data Science, and NSF Award #1704309. Table 1: Tweet examples with emojis. The sentiment ground truth is given in the second column. The examples show that inconsistent sentiments exist between emojis and texts. Figure 1: Sentiment analysis via bi-sense emoji embedding and attention-based LSTM network (WATT-BiE-LSTM). Figure 2: Multi-level attention-based LSTM with bi-sense emoji embedding (MATT-BiE-LSTM). Table 2: Top-10 Most Frequently Used Emojis. Table 3: Twitter Sentiment Analysis. Figure 3: Attention weights obtained by senti-emoji embedding and word-emoji embedding across words. Tweet contexts are given in sub-captions. Figure 4: t-SNE visualization of bi-sense emoji embedding. Positive-sense embeddings are paired with red circles, negative-sense embeddings are paired with green circles, and their subtractions are paired with yellow circles, respectively. Best viewed when zoomed in.
|
The different attention distributions suggest that the proposed senti-emoji embedding is capable of recognizing words with strong sentiments that are closely related to the true sentiment even with the presence of words with conflicting sentiments
|
How big are improvements with multilingual ASR training vs single language training?
|
### Introduction
Automatic speech recognition (ASR) technology has been made a dramatic progress and is currently brought to a pratical levels of performance assisted by large speech corpora and the introduction of deep learning techniques. However, this is not the case for low-resource languages which do not have large corpora like English and Japanese have. There are about 5,000 languages in the world over half of which are faced with the danger of extinction. Therefore, constructing ASR systems for these endangered languages is an important issue. The Ainu are an indigenous people of northern Japan and Sakhakin in Russia, but their language has been fading away ever since the Meiji Restoration and Modernization. On the other hand, active efforts to preserve their culture have been initiated by the Government of Japan, and exceptionally large oral recordings have been made. Nevertheless, a majority of the recordings have not been transcribed and utilized effectively. Since transcribing them requires expertise in the Ainu language, not so many people are able to work on this task. Hence, there is a strong demand for an ASR system for the Ainu language. We started a project of Ainu ASR and this article is the first report of this project. We have built an Ainu speech corpus based on data provided by the Ainu Museum and the Nibutani Ainu Culture Museum. The oral recordings in this data consist of folklore and folk songs, and we chose the former to construct the ASR model. The end-to-end method of speech recognition has been proposed recently and has achieved performance comparable to that of the conventional DNN-HMM hybrid modeling BIBREF0, BIBREF1, BIBREF2. End-to-end systems do not have a complex hierarchical structure and do not require expertise in target languages such as their phonology and morphology. In this study we adopt the attention mechanism BIBREF3, BIBREF4 and combine it with Connectionist Temporal Classification (CTC) BIBREF5, BIBREF6. In this work, we investigate the modeling unit and utilization of corpora of other languages. ### Overview of the Ainu Language
This section briefly overviews the background of the data collection, the Ainu language, and its writing system. After that, we describe how Ainu recordings are classified and review previous works dealing with the Ainu language. ### Overview of the Ainu Language ::: Background
The Ainu people had total population of about 20,000 in the mid-19th century BIBREF7 and they used to live widely distributed in the area that includes Hokkaido, Sakhalin, and the Kuril Islands. The number of native speakers, however, rapidly decreased through the assimilation policy after late 19th century. At present, there are only less than 10 native speakers, and UNESCO listed their language as critically endangered in 2009 BIBREF8. In response to this situation, Ainu folklore and songs have been actively recorded since the late 20th century in efforts initiated by the Government of Japan. For example, the Ainu Museum started audio recording of Ainu folklore in 1976 with the cooperation of a few Ainu elders which resulted in the collection of speech data with the total duration of roughly 700 hours. This kind of data should be a key to the understanding of Ainu culture, but most of it is not transcribed and fully studied yet. ### Overview of the Ainu Language ::: The Ainu Language and its Writing System
The Ainu language is an agglutinative language and has some similarities to Japanese. However, its genealogical relationship with other languages has not been clearly understood yet. Among its features such as closed syllables and personal verbal affixes, one important feature is that there are many compound words. For example, a word atuykorkamuy (means “a sea turtle”) can be disassembled into atuy (“the sea”), kor (“to have”), and kamuy (“god”). Although the Ainu people did not traditionally have a writing system, the Ainu language is currently written following the examples in a reference book “Akor itak” BIBREF9. With this writing system, it is transcribed with sixteen Roman letters {a, c, e, h, i, k, m, n, o, p, r, s, t, u, w, y}. Since each of these letters correspond to a unique pronunciation, we call them “phones” for convenience. In addition, the symbol {=} is used for connecting a verb and a personal affix and { ' } is used to represent the pharyngeal stop. For the purpose of transcribing recordings, consonant symbols {b, d, g, z} are additionally used to transcribe Japanese sounds the speakers utter. The symbols { _ , __ } are used to transcribe drops and liaisons of phones. An example is shown below. ### Overview of the Ainu Language ::: Types of Ainu Recordings
The Ainu oral traditions are classified into three types: “yukar” (heroic epics), “kamuy yukar” (mythic epics), and “uwepeker” (prose tales). Yukar and kamuy yukar are recited in the rhythm while uwepeker is not. In this study we focus on the the prose tales as the first step. ### Overview of the Ainu Language ::: Previous Work
There have so far been a few studies dealing with the Ainu language. ainulrec built a dependency tree bank in the scheme of Universal Dependencies. postag developed tools for part-of-speech (POS) tagging and word segmentation. Ainu speech recognition was tried by ainutrans with 2.5 hours of Ainu folklore data even though the Ainu language was not their main target. Their phone error rare was about 40% which is not an accuracy level for practical use yet. It appears that there has not been a substantial Ainu speech recognition study yet that utilizes corpora of a reasonable size. Therefore, our first step was to build a speech corpus for ASR based on the data sets provided by the Ainu Museum and the Nibutani Ainu Culture Museum. ### Ainu Speech Corpus
In this section we explain the content of the data sets and how we modified it for our ASR corpus. ### Ainu Speech Corpus ::: Numbers of Speakers and Episodes
The corpus we have prepared for ASR in this study is composed of text and speech. Table 1 shows the number of episodes and the total speech duration for each speaker. Among the total of eight speakers, the data of the speakers KM and UT is from the Ainu Museum, and the rest is from Nibutani Ainu Culture Museum. All speakers are female. The length of the recording for a speaker varies depending on the circumstances at the recording times. A sample text and its English translation are shown in Table 2. ### Ainu Speech Corpus ::: Data Annotation
For efficient training of ASR model, we have made some modifications to the provided data. First, from the transcripts explained in Section 2.1, the symbols {_ , __ , '} have been removed as seen in the example below. Though the equal symbol (`=') does not represent a sound, we keep it because it is used in almost all of the Ainu documents and provides grammatical information. To train an ASR system, the speech data needs to be segmented into a set of manageable chunks. For the ease of automatic processing, we chose to segment speech into inter-pausal units (IPUs) BIBREF10which is a stretch of speech bounded by pauses. The number of IPUs for each speaker is shown in Table 1. ### End-to-end Speech Recognition
In this section, the two approaches to end-to-end speech recognition that we adopt in this work are summarized. Then, we introduce four modeling units we explained, i.e., phone, syllable, word piece, and word. We also discuss multilingual training that we adopt for tackling the low resource problem. ### End-to-end Speech Recognition ::: End-to-end Modeling
End-to-end models have an architecture much simpler than that of conventional DNN-HMM hybrid models. Since they predict character or word symbols directly from acoustic features, pronunciation dictionaries and language modeling are not required explicitly. In this paper, we utilize two kinds of end-to-end models, namely, Connectionist Temporal Classification (CTC) and the attention-based encoder-decoder model. CTC augments the output symbol set with the “blank” symbol `$\phi $'. It outputs symbols by contracting frame-wise outputs from recurrent neural networks (RNNs). This is done by first collapsed repeating symbols and then removing all blank symbols as in the following example: The probability of an output sequence $\mathbf {L}$ for an input acoustic feature sequence $\mathbf {X}$, where $|\mathbf {L}| < |\mathbf {X}|$, is defined as follows. $\mathcal {B}$ is a function to contract the outputs of RNNs, so $\mathcal {B}^{-1}(\mathbf {L})$ means the set of symbol sequences which is reduced to $\mathbf {L}$. The model is trained to maximize (1). The attention-based encoder-decoder model is another method for mapping between two sequences with different lengths. It has two RNNs called the “encoder” and the “decoder”. In naive encoder-decoder model, the encoder converts the input sequence into a single context vector which is the last hidden state of the encoder RNN from which the decoder infers output symbols. In an attention-based model, the context vector $\mathbf {c}_l$ at $l$-th decoding step is the sum of the product of all encoder outputs $h_1, ... , h_\mathrm {T}$ and the $l$-th attention weight $\alpha _{1,l}, ... , \alpha _{\mathrm {T},l}$ as shown in (2). Here, $\mathrm {T}$ is the length of the encoder output. The attention weights $\alpha _{1,l}, ... , \alpha _{\mathrm {T},l}$ indicates the relative importances of the encoder output frames for the $l$-th decoding step and the model parameters to generate these weights are determined in an end-to-end training. In our model, the attention-based model and the CTC share the encoder and are optimized simultaneously as shown in Figure 1.BIBREF11 Long Short-Term Memory (LSTM) BIBREF12 is used for RNNs in the encoder and the decoder. ### End-to-end Speech Recognition ::: Modeling Units
In the conventional DNN-HMM hybrid modeling, the acoustic model outputs probabilities triphone states from each acoustic feature which is converted into the most likely word sequence. An end-to-end model, on the other hand, has some degree of freedom in the modeling unit other than phones, and there are some studies that use characters or words as a unit BIBREF13, BIBREF14. A word unit based end-to-end model can take long context into consideration at the inference time, but it has the data sparsity problem due to its large vocabulary size. Though phone unit based model does not have such a problem, it cannot grasp so long context. It depends on the size of available corpora to decide which to adopt. In addition to these both models, a word piece unit, which is defined by automatically dividing a word into frequent parts, has been proposed BIBREF15, BIBREF16, and its vocabulary size can be determined almost freely. In this paper, we investigate the modeling unit for the end-to-end Ainu speech recognition since the optimal unit for this size of corpus is not obvious. BIBREF17 It is presupposed that all units can be converted into word units automatically. The candidates are phone, syllable, word piece (WP), and word. Examples of them are shown in Table 3 and the details of each unit are described below. ### End-to-end Speech Recognition ::: Modeling Units ::: Phone
As mentioned in Section 2.1, we regard the Roman letters as phones. `=' and the special symbol `$\langle $wb$\rangle $', which means a word boundary, are added to make it possible to convert the output into a sequence of words like the `original' in Table 3. ### End-to-end Speech Recognition ::: Modeling Units ::: Syllable
A syllable of the Ainu language takes the form of either V, CV, VC, or CVC, where `C' and `V' mean consonant and vowel, respectively. The phones {a, e, i, o, u} are vowels and the rest of the Roman letters in Section 2.2 are consonants. In this work, every word is divided into syllables by the following procedure. A word with a single letter is unchanged. Two consecutive Cs and Vs are given a syllable boundary between them. R$^*${CC, VV}R$^*$$\rightarrow $ R$^*${C-C, V-V}R$^*$ (R $$ {C, V}) Put a syllable boundary after the segment-initial V if it is following by at least two phones. VCR$^+$$\rightarrow $ V-CR$^+$ Put a syllable boundary after CV repeatedly from left to right until only CV or CVC is left. (CV)$^*${CV, CVC} $\rightarrow $ (CV-)$^*${CV, CVC} In addition, `=' and `$\langle $wb$\rangle $' are added as explained in Section 4.2.1. through the model training process. This procedure does not always generate a morphologically relevant syllable segmentation. For example, a word isermakus (meaning “(for a god) to protect from behind”) is divided as i-ser-ma-kus, but the right syllabification is i-ser-mak-us. ### End-to-end Speech Recognition ::: Modeling Units ::: Word Piece
The byte pair encoding (BPE) BIBREF18 and the unigram language modeling BIBREF19 are alternative methods for dividing a word into word pieces. The former repeatedly replaces the most common character pair with a new single symbol until the vocabulary becomes the intended size. The latter decides the segmentation to maximize the likelihood of occurrence of the sequence. We adopt the latter and use the open-source software SentencePiece BIBREF20. With this tool, `$\langle $wb$\rangle $' and other units are often merged to constitute a single piece as seen in Table 3. ### End-to-end Speech Recognition ::: Modeling Units ::: Word
The original text can be segmented into words separated by spaces. To make the vocabulary smaller for the ease of training, `=' is treated as a word and infrequent words are replaced with a special label `$\langle $unk$\rangle $'. As seen in Table 3, `a=saha' is dealt with as three words (`a', `=', `saha') and the word `kokopan' is replaced with `$\langle $unk$\rangle $'. ### End-to-end Speech Recognition ::: Multilingual Training
When an enough amount of data is not available for the target languages, the ASR model training can be enhanced by taking advantage of data from other languages BIBREF21, BIBREF22. There are some similarities between Ainu and Japanese language BIBREF23. For instance, both have almost the same set of vowels and do not have consonant clusters (like `str' of `strike' in English). Hence, the multilingual training with a Japanese corpus is expected to be effective. In addition, an English corpus is used for the purpose of comparison. The corpora used are the JNAS corpus BIBREF24 (in Japanese) and the WSJ corpus BIBREF25 (in English). JNAS comprises roughly 80 hours from 320 speakers, and WSJ has about 70 hours of speech from 280 speakers. In the multilingual training, the encoder and the attention module are shared among the Ainu ASR model and the models for other languages, and they are trained using data for all languages. Figure 2 shows the architecture for the multilingual learning with two corpora. When the input acoustic features are from the Ainu ASR corpus, they go through the shared encoder and attention module and are delivered into the decoder on the left side in Figure 2 as a context vector. In this case, the right-side decoder is not trained. ### Experimental Evaluation
In this section the setting and results of ASR experiments are described and the results are discussed. ### Experimental Evaluation ::: Data Setup
The ASR experiments were performed in speaker-open condition as well as speaker-closed condition. In the speaker-closed condition, two episodes were set aside from each speaker as development and test sets. Thereafter, the total sizes of the development and test sets turns out to be 1585 IPUs spanning 2 hours 23 minutes and 1841 IPUs spanning 2 hours and 48 minutes respectively. The ASR model is trained with the rest data. In the speaker-open condition, all the data except for the test speaker's were used for training As it would be difficult to train the model if all of the data of speaker KM or UT were removed, experiments using their speaker-open conditions were not conducted. ### Experimental Evaluation ::: Experimental Setting
The input acoustic features were 120-dimensional vectors made by frame stacking BIBREF26 three 40-dimensional log-mel filter banks features at contiguous time frames. The window length and the frame shift were set to be 25ms and 10ms. The encoder was composed of five BiLSTM layers and the attention-based decoder had a single layer of LSTM. Each LSTM had 320 cells and their weights were randomly initialized using a uniform distribution DBLP:journals/corr/HeZR015 with biases of zero. The fully connected layers were initialized following $\mathcal {U}{(-0.1, 0.1)}$. The weight decay BIBREF27 whose rate was $10^{-5}$ and the dropout BIBREF28 following $\mathcal {B}e(0.2)$ were used to alleviate overfitting. The parameters were optimized with Adam BIBREF29. The learning rate was $10^{-3}$ at first and was multiplied by $10^{-1}$ at the beginning of 31st and 36th epoch BIBREF30. The mini-batch size was 30 and the utterances (IPUs) were sorted in an ascending order of length. To stabilize the training, we removed utterances longer than 12 seconds. The loss function of the model was a linear sum of the loss from CTC and the attention-based decoder, where $\lambda $ was set to be 0.5. Through all experiments, the phone labels are used to train the auxiliary CTC task because it is reported that the hierarchical architecture, using few and general labels in the auxiliary task, improves the performance BIBREF31. Strictly speaking, the number of each modeling units depends on the training set, but there are roughly 25-phone, 500-syllable, and 5,000-word units including special symbols that represent the start and end of a sentence. The words occurring less than twice were replaced with `$\langle $unk$\rangle $'. The vocabulary size for word piece modeling was set to be 500. These settings were based on the results of preliminary experiments with the development set. For the multilingual training, we made three training scripts by concatenating the script of Ainu and other languages (JNAS, WSJ, JNAS and WSJ). The model was trained by these scripts until 30th epoch. From 31$^{\rm {st}}$ and 40th epoch, the model was fine-turned by the Ainu script. Phone units are used for JNAS and WSJ throughout the experiments. ### Experimental Evaluation ::: Results
Table 4 shows the phone error rates (PERs) and word error rates (WERs) for the speaker-closed and speaker-open settings. The `average' is weighted by the numbers of tokens in the ground truth transcriptions for speaker-wise evaluation sets. The word recognition accuracy reached about 80% in the speaker-closed setting. In the speaker-open setting it was 60% on average and varied greatly from speaker to speaker (from 50% to 70%). The best phone accuracies in the speaker-closed and speaker-open settings were about 94% and 86%. Regardless of the settings, the syllable-based modeling yielded the best WER and PER. This suggests that syllables provide reasonable coverage and constraints for the Ainu language in a corpus of this size. The PERs of the word unit model were larger than those of other units. This is because the word model often outputs the `$\langle $unk$\rangle $' symbols while other unit models are able to output symbols similar in sound as below. In this example, the PER of the syllable model is 5% and that of the word model is 30% even though the WERs are the same. (The output of the syllable model is rewritten into words using the `$\langle $wb$\rangle $' symbol.) WERs are generally much larger than PERs and it is further aggravated with the Ainu language. This is because, as mentioned in Section 2.1, the Ainu language has a lot of compound words and the model may be confused about whether the output is multiple words or a single compound word. The actual outputs frequently contain errors as below. The WER of this example is 57% though the PER is zero. The results of multilingual training in which the modeling unit is syllables are presented in Table 5. All error rates are the weighted averages of all evaluated speakers. Here, `+ both' represents the result of training with both JNAS and WSJ corpora. The multilingual training is effective in the speaker-open setting, providing a relative WER improvement of 10%. The JNAS corpus was more helpful than the WSJ corpus because of the similarities between Ainu and Japanese language. ### Summary
In this study, we first developed a speech corpus for Ainu ASR and then, using the end-to-end model with CTC and the attention mechanism, compared four modeling units: phones, syllables, word pieces, and words. The best performance was obtained with the syllable unit, with which WERs in the speaker-closed and speaker-open settings were respectively about 20% and 40% while PERs were about 6% and 14%. Multilingual training using the JNAS improved the performance in the speaker-open setting. Future tasks include reducing the between-speaker performance differences by using speaker adaptation techniques. ### Acknowledgement
The data sets used in this study are provided by the Ainu Museum and Nibutani Ainu Culture Museum. The authors would like to thank Prof. Osami Okuda of Sapporo Gakuin University for his useful advices on the Ainu language. Table 1: Speaker-wise details of the corpus Table 2: Text excerpted from the prose tale ‘The Boy Who Became Porosir God’ spoken by KM. Figure 1: The attention model with CTC auxiliary task. Table 3: Examples of four modeling units. Figure 2: The architecture of the multilingual learning with two corpora. ‘FC’ and ‘CE’ means ‘fully connected’ and ‘cross-entropy’ respectively. Table 4: ASR performance for each speaker and modeling unit. The lowest error rates for each unit are highlighted. Table 5: Results of multilingual training.
|
relative WER improvement of 10%.
|
Does adversarial learning have stronger performance gains for text classification, or for NER?
|
### Introduction
Contextual word embeddings BIBREF0 , BIBREF1 , BIBREF2 have been successfully applied to various NLP tasks, including named entity recognition, document classification, and textual entailment. The multilingual version of BERT (which is trained on Wikipedia articles from 100 languages and equipped with a 110,000 shared wordpiece vocabulary) has also demonstrated the ability to perform `zero-resource' cross-lingual classification on the XNLI dataset BIBREF3 . Specifically, when multilingual BERT is finetuned for XNLI with English data alone, the model also gains the ability to handle the same task in other languages. We believe that this zero-resource transfer learning can be extended to other multilingual datasets. In this work, we explore BERT's zero-resource performance on the multilingual MLDoc classification and CoNLL 2002/2003 NER tasks. We find that the baseline zero-resource performance of BERT exceeds the results reported in other work, even though cross-lingual resources (e.g. parallel text, dictionaries, etc.) are not used during BERT pretraining or finetuning. We apply adversarial learning to further improve upon this baseline, achieving state-of-the-art zero-resource results. There are many recent approaches to zero-resource cross-lingual classification and NER, including adversarial learning BIBREF4 , BIBREF5 , BIBREF6 , BIBREF7 , using a model pretrained on parallel text BIBREF8 , BIBREF9 , BIBREF10 and self-training BIBREF11 . Due to the newness of the subject matter, the definition of `zero-resource' varies somewhat from author to author. For the experiments that follow, `zero-resource' means that, during model training, we do not use labels from non-English data, nor do we use human or machine-generated parallel text. Only labeled English text and unlabeled non-English text are used during training, and hyperparameters are selected using English evaluation sets. Our contributions are the following: ### Adversarial Learning
Language-adversarial training BIBREF12 was proposed for generating bilingual dictionaries without parallel data. This idea was extended to zero-resource cross-lingual tasks in NER BIBREF5 , BIBREF6 and text classification BIBREF4 , where we would expect that language-adversarial techniques induce features that are language-independent. ### Self-training Techniques
Self-training, where an initial model is used to generate labels on an unlabeled corpus for the purpose of domain or cross-lingual adaptation, was studied in the context of text classification BIBREF11 and parsing BIBREF13 , BIBREF14 . A similar idea based on expectation-maximization, where the unobserved label is treated as a latent variable, has also been applied to cross-lingual text classification in BIBREF15 . ### Translation as Pretraining
BIBREF8 and BIBREF9 use the encoders from machine translation models as a starting point for task-specific finetuning, which permits various degrees of multilingual transfer. BIBREF10 add an additional masked translation task to the BERT pretraining process, and the authors observed an improvement in the cross-lingual setting over using the monolingual masked text task alone. ### Model Training
We present an overview of the adversarial training process in Figure FIGREF1 . We used the pretrained cased multilingual BERT model as the initialization for all of our experiments. Note that the BERT model has 768 units. We always use the labeled English data of each corpus. We use the non-English text portion (without the labels) for the adversarial training. We formulate the adversarial task as a binary classification problem (i.e. English versus non-English.) We add a language discriminator module which uses the BERT embeddings to classify whether the input sentence was written in English or the non-English language. We also add a generator loss which encourages BERT to produce embeddings that are difficult for the discriminator to classify correctly. In this way, the BERT model learns to generate embeddings that do not contain language-specific information. The pseudocode for our procedure can be found in Algorithm SECREF11 . In the description that follows, we use a batch size of 1 for clarity. For language-adversarial training for the classification task, we have 3 loss functions: the task-specific loss INLINEFORM0 , the generator loss INLINEFORM1 , and the discriminator loss INLINEFORM2 : INLINEFORM3 INLINEFORM4 where INLINEFORM0 is the number of classes for the task, INLINEFORM1 (dim: INLINEFORM2 ) is the task-specific prediction, INLINEFORM3 (dim: scalar) is the probability that the input is in English, INLINEFORM4 (dim: INLINEFORM5 ) is the mean-pooled BERT output embedding for the input word-pieces INLINEFORM6 , INLINEFORM7 is the BERT parameters, INLINEFORM8 (dim: INLINEFORM9 , INLINEFORM10 , INLINEFORM11 , scalar) are the output projections for the task-specific loss and discriminator respectively, INLINEFORM12 (dim: INLINEFORM13 ) is the one-hot vector representation for the task label and INLINEFORM14 (dim: scalar) is the binary label for the adversarial task (i.e. 1 or 0 for English or non-English). In the case of NER, the task-specific loss has an additional summation over the length of the sequence: INLINEFORM0 INLINEFORM1 where INLINEFORM0 (dim: INLINEFORM1 ) is the prediction for the INLINEFORM2 word, INLINEFORM3 is the number of words in the sentence, INLINEFORM4 (dim: INLINEFORM5 ) is the matrix of one-hot entity labels, and INLINEFORM6 (dim: INLINEFORM7 ) refers to the BERT embedding of the INLINEFORM8 word. The generator and discriminator losses remain the same for NER, and we continue to use the mean-pooled BERT embedding during adversarial training. We then take the gradients with respect to the 3 losses and the relevant parameter subsets. The parameter subsets are INLINEFORM0 , INLINEFORM1 , and INLINEFORM2 . We apply the gradient updates sequentially at a 1:1:1 ratio. During BERT finetuning, the learning rates for the task loss, generator loss and discriminator loss were kept constant; we do not apply a learning rate decay. All hyperparameters were tuned on the English dev sets only, and we use the Adam optimizer in all experiments. We report results based on the average of 4 training runs. [ht] Pseudocode for adversarial training on the multilingual text classification task. The batch size is set at 1 for clarity. The parameter subsets are INLINEFORM0 , INLINEFORM1 , and INLINEFORM2 . Input: pre-trained BERT model INLINEFORM3 , data iterators for English and the non-English language INLINEFORM4 , learning rates INLINEFORM5 for each loss function, initializations for discriminator output projection INLINEFORM6 , task-specific output projection INLINEFORM7 , and BERT parameters INLINEFORM8 [1] not converged INLINEFORM9 get English text and task-specific labels INLINEFORM10 INLINEFORM11 compute the prediction for the task INLINEFORM12 compute task-specific loss INLINEFORM13 update model based on task-specific loss INLINEFORM14 get non-English and English text INLINEFORM15 INLINEFORM16 discriminator prediction on non-English text INLINEFORM17 discriminator prediction on English text INLINEFORM18 compute discriminator loss INLINEFORM19 update model based on discriminator loss INLINEFORM20 INLINEFORM21 INLINEFORM22 INLINEFORM23 INLINEFORM24 compute generator loss INLINEFORM25 update model based on generator loss ### MLDoc Classification Results
We finetuned BERT on the English portion of the MLDoc corpus BIBREF16 . The MLDoc task is a 4-class classification problem, where the data is a class-balanced subset of the Reuters News RCV1 and RCV2 datasets. We used the english.train.1000 dataset for the classification loss, which contains 1000 labeled documents. For language-adversarial training, we used the text portion of german.train.10000, french.train.10000, etc. without the labels. We used a learning rate of INLINEFORM0 for the task loss, INLINEFORM1 for the generator loss and INLINEFORM2 for the discriminator loss. In Table TABREF13 , we report the classification accuracy for all of the languages in MLDoc. Generally, adversarial training improves the accuracy across all languages, and the improvement is sometimes dramatic versus the BERT non-adversarial baseline. In Figure FIGREF15 , we plot the zero-resource German and Japanese test set accuracy as a function of the number of steps taken, with and without adversarial training. The plot shows that the variation in the test accuracy is reduced with adversarial training, which suggests that the cross-lingual performance is more consistent when adversarial training is applied. (We note that the batch size and learning rates are the same for all the languages in MLDoc, so the variation seen in Figure FIGREF15 are not affected by those factors.) ### CoNLL NER Results
We finetuned BERT on the English portion of the CoNLL 2002/2003 NER corpus BIBREF19 . We followed the text preprocessing in BIBREF0 . We used a learning rate of INLINEFORM0 for the task loss, INLINEFORM1 for the generator loss and INLINEFORM2 for the discriminator loss. In Table TABREF19 , we report the F1 scores for all of the CoNLL NER languages. When combined with adversarial learning, the BERT cross-lingual F1 scores increased for German over the non-adversarial baseline, and the scores remained largely the same for Spanish and Dutch. Regardless, the BERT zero-resource performance far exceeds the results published in previous work. BIBREF17 and BIBREF18 do use some cross-lingual resources (like bilingual dictionaries) in their experiments, but it appears that BERT with multilingual pretraining performs better, even though it does not have access to cross-lingual information. ### Alignment of Embeddings for Parallel Documents
If language-adversarial training encourages language-independent features, then the English documents and their translations should be close in the embedding space. To examine this hypothesis, we take the English documents from the MLDoc training corpus and translate them into German, Spanish, French, etc. using Amazon Translate. We construct the embeddings for each document using BERT models finetuned on MLDoc. We mean-pool each document embedding to create a single vector per document. We then calculate the cosine similarity between the embeddings for the English document and its translation. In Table TABREF21 , we observe that the median cosine similarity increases dramatically with adversarial training, which suggests that the embeddings became more language-independent. ### Discussion
For many of the languages examined, we were able to improve on BERT's zero-resource cross-lingual performance on the MLDoc classification and CoNLL NER tasks. Language-adversarial training was generally effective, though the size of the effect appears to depend on the task. We observed that adversarial training moves the embeddings of English text and their non-English translations closer together, which may explain why it improves cross-lingual performance. Future directions include adding the language-adversarial task during BERT pre-training on the multilingual Wikipedia corpus, which may further improve zero-resource performance, and finding better stopping criteria for zero-resource cross-lingual tasks besides using the English dev set. ### Acknowledgments
We would like to thank Jiateng Xie, Julian Salazar and Faisal Ladhak for the helpful comments and discussions. Figure 1: Overview of the adversarial training process for classification and NER. All input text is in the form of a sequence of word pieces. LD, LG, LT refer to the discriminator, generator and task-specific losses. Parameters of each component is in round brackets. Figure 2: German and Japanese MLDoc test accuracy versus the number of training steps, with and without adversarial training. The blue line shows the performance of the non-adversarial BERT baseline. The red line shows the performance with adversarial training. Table 1: Classification accuracy on the MLDoc test sets. We present results for BERT finetuned on labeled English data and BERT finetuned on labeled English data with language-adversarial training. Our results are averaged across 4 training runs, and hyperparameters are tuned on English dev data. Table 2: F1 scores on the CoNLL 2002/2003 NER test sets. We present results for BERT finetuned on labeled English data and BERT finetuned on labeled English data with language-adversarial training. Our results are averaged across 4 training runs, and hyperparameters are tuned on English dev data. Table 3: Median cosine similarity between the mean-pooled BERT embeddings of MLDoc English documents and their translations, with and without language-adversarial training. The median cosine similarity increased with adversarial training for every language pair, which suggests that the adversarial loss encourages BERT to learn language-independent representations.
|
classification
|
Which dialog datasets did they experiment with?
|
### Introduction
Task-oriented dialogue system, which helps users to achieve specific goals with natural language, is attracting more and more research attention. With the success of the sequence-to-sequence (Seq2Seq) models in text generation BIBREF0, BIBREF1, BIBREF2, BIBREF3, BIBREF4, several works tried to model the task-oriented dialogue as the Seq2Seq generation of response from the dialogue history BIBREF5, BIBREF6, BIBREF7. This kind of modeling scheme frees the task-oriented dialogue system from the manually designed pipeline modules and heavy annotation labor for these modules. Different from typical text generation, the successful conversations for task-oriented dialogue system heavily depend on accurate knowledge base (KB) queries. Taking the dialogue in Figure FIGREF1 as an example, to answer the driver's query on the gas station, the dialogue system is required to retrieve the entities like “200 Alester Ave” and “Valero”. For the task-oriented system based on Seq2Seq generation, there is a trend in recent study towards modeling the KB query as an attention network over the entire KB entity representations, hoping to learn a model to pay more attention to the relevant entities BIBREF6, BIBREF7, BIBREF8, BIBREF9. Though achieving good end-to-end dialogue generation with over-the-entire-KB attention mechanism, these methods do not guarantee the generation consistency regarding KB entities and sometimes yield responses with conflict entities, like “Valero is located at 899 Ames Ct” for the gas station query (as shown in Figure FIGREF1). In fact, the correct address for Valero is 200 Alester Ave. A consistent response is relatively easy to achieve for the conventional pipeline systems because they query the KB by issuing API calls BIBREF10, BIBREF11, BIBREF12, and the returned entities, which typically come from a single KB row, are consistently related to the object (like the “gas station”) that serves the user's request. This indicates that a response can usually be supported by a single KB row. It's promising to incorporate such observation into the Seq2Seq dialogue generation model, since it encourages KB relevant generation and avoids the model from producing responses with conflict entities. To achieve entity-consistent generation in the Seq2Seq task-oriented dialogue system, we propose a novel framework which query the KB in two steps. In the first step, we introduce a retrieval module — KB-retriever to explicitly query the KB. Inspired by the observation that a single KB row usually supports a response, given the dialogue history and a set of KB rows, the KB-retriever uses a memory network BIBREF13 to select the most relevant row. The retrieval result is then fed into a Seq2Seq dialogue generation model to filter the irrelevant KB entities and improve the consistency within the generated entities. In the second step, we further perform attention mechanism to address the most correlated KB column. Finally, we adopt the copy mechanism to incorporate the retrieved KB entity. Since dialogue dataset is not typically annotated with the retrieval results, training the KB-retriever is non-trivial. To make the training feasible, we propose two methods: 1) we use a set of heuristics to derive the training data and train the retriever in a distant supervised fashion; 2) we use Gumbel-Softmax BIBREF14 as an approximation of the non-differentiable selecting process and train the retriever along with the Seq2Seq dialogue generation model. Experiments on two publicly available datasets (Camrest BIBREF11 and InCar Assistant BIBREF6) confirm the effectiveness of the KB-retriever. Both the retrievers trained with distant-supervision and Gumbel-Softmax technique outperform the compared systems in the automatic and human evaluations. Analysis empirically verifies our assumption that more than 80% responses in the dataset can be supported by a single KB row and better retrieval results lead to better task-oriented dialogue generation performance. ### Definition
In this section, we will describe the input and output of the end-to-end task-oriented dialogue system, and the definition of Seq2Seq task-oriented dialogue generation. ### Definition ::: Dialogue History
Given a dialogue between a user ($u$) and a system ($s$), we follow eric:2017:SIGDial and represent the $k$-turned dialogue utterances as $\lbrace (u_{1}, s_{1} ), (u_{2} , s_{2} ), ... , (u_{k}, s_{k})\rbrace $. At the $i^{\text{th}}$ turn of the dialogue, we aggregate dialogue context which consists of the tokens of $(u_{1}, s_{1}, ..., s_{i-1}, u_{i})$ and use $\mathbf {x} = (x_{1}, x_{2}, ..., x_{m})$ to denote the whole dialogue history word by word, where $m$ is the number of tokens in the dialogue history. ### Definition ::: Knowledge Base
In this paper, we assume to have the access to a relational-database-like KB $B$, which consists of $|\mathcal {R}|$ rows and $|\mathcal {C}|$ columns. The value of entity in the $j^{\text{th}}$ row and the $i^{\text{th}}$ column is noted as $v_{j, i}$. ### Definition ::: Seq2Seq Dialogue Generation
We define the Seq2Seq task-oriented dialogue generation as finding the most likely response $\mathbf {y}$ according to the input dialogue history $\mathbf {x}$ and KB $B$. Formally, the probability of a response is defined as where $y_t$ represents an output token. ### Our Framework
In this section, we describe our framework for end-to-end task-oriented dialogues. The architecture of our framework is demonstrated in Figure FIGREF3, which consists of two major components including an memory network-based retriever and the seq2seq dialogue generation with KB Retriever. Our framework first uses the KB-retriever to select the most relevant KB row and further filter the irrelevant entities in a Seq2Seq response generation model to improve the consistency among the output entities. While in decoding, we further perform the attention mechanism to choose the most probable KB column. We will present the details of our framework in the following sections. ### Our Framework ::: Encoder
In our encoder, we adopt the bidirectional LSTM BIBREF15 to encode the dialogue history $\mathbf {x}$, which captures temporal relationships within the sequence. The encoder first map the tokens in $\mathbf {x}$ to vectors with embedding function $\phi ^{\text{emb}}$, and then the BiLSTM read the vector forwardly and backwardly to produce context-sensitive hidden states $(\mathbf {h}_{1}, \mathbf {h}_2, ..., \mathbf {h}_{m})$ by repeatedly applying the recurrence $\mathbf {h}_{i}=\text{BiLSTM}\left( \phi ^{\text{emb}}\left( x_{i}\right) , \mathbf {h}_{i-1}\right)$. ### Our Framework ::: Vanilla Attention-based Decoder
Here, we follow eric:2017:SIGDial to adopt the attention-based decoder to generation the response word by word. LSTM is also used to represent the partially generated output sequence $(y_{1}, y_2, ...,y_{t-1})$ as $(\tilde{\mathbf {h}}_{1}, \tilde{\mathbf {h}}_2, ...,\tilde{\mathbf {h}}_t)$. For the generation of next token $y_t$, their model first calculates an attentive representation $\tilde{\mathbf {h}}^{^{\prime }}_t$ of the dialogue history as Then, the concatenation of the hidden representation of the partially outputted sequence $\tilde{\mathbf {h}}_t$ and the attentive dialogue history representation $\tilde{\mathbf {h}}^{^{\prime }}_t$ are projected to the vocabulary space $\mathcal {V}$ by $U$ as to calculate the score (logit) for the next token generation. The probability of next token $y_t$ is finally calculated as ### Our Framework ::: Entity-Consistency Augmented Decoder
As shown in section SECREF7, we can see that the generation of tokens are just based on the dialogue history attention, which makes the model ignorant to the KB entities. In this section, we present how to query the KB explicitly in two steps for improving the entity consistence, which first adopt the KB-retriever to select the most relevant KB row and the generation of KB entities from the entities-augmented decoder is constrained to the entities within the most probable row, thus improve the entity generation consistency. Next, we perform the column attention to select the most probable KB column. Finally, we show how to use the copy mechanism to incorporate the retrieved entity while decoding. ### Our Framework ::: Entity-Consistency Augmented Decoder ::: KB Row Selection
In our framework, our KB-retriever takes the dialogue history and KB rows as inputs and selects the most relevant row. This selection process resembles the task of selecting one word from the inputs to answer questions BIBREF13, and we use a memory network to model this process. In the following sections, we will first describe how to represent the inputs, then we will talk about our memory network-based retriever ### Our Framework ::: Entity-Consistency Augmented Decoder ::: KB Row Selection ::: Dialogue History Representation:
We encode the dialogue history by adopting the neural bag-of-words (BoW) followed the original paper BIBREF13. Each token in the dialogue history is mapped into a vector by another embedding function $\phi ^{\text{emb}^{\prime }}(x)$ and the dialogue history representation $\mathbf {q}$ is computed as the sum of these vectors: $\mathbf {q} = \sum ^{m}_{i=1} \phi ^{\text{emb}^{\prime }} (x_{i}) $. ### Our Framework ::: Entity-Consistency Augmented Decoder ::: KB Row Selection ::: KB Row Representation:
In this section, we describe how to encode the KB row. Each KB cell is represented as the cell value $v$ embedding as $\mathbf {c}_{j, k} = \phi ^{\text{value}}(v_{j, k})$, and the neural BoW is also used to represent a KB row $\mathbf {r}_{j}$ as $\mathbf {r}_{j} = \sum _{k=1}^{|\mathcal {C}|} \mathbf {c}_{j,k}$. ### Our Framework ::: Entity-Consistency Augmented Decoder ::: KB Row Selection ::: Memory Network-Based Retriever:
We model the KB retrieval process as selecting the row that most-likely supports the response generation. Memory network BIBREF13 has shown to be effective to model this kind of selection. For a $n$-hop memory network, the model keeps a set of input matrices $\lbrace R^{1}, R^{2}, ..., R^{n+1}\rbrace $, where each $R^{i}$ is a stack of $|\mathcal {R}|$ inputs $(\mathbf {r}^{i}_1, \mathbf {r}^{i}_2, ..., \mathbf {r}^{i}_{|\mathcal {R}|})$. The model also keeps query $\mathbf {q}^{1}$ as the input. A single hop memory network computes the probability $\mathbf {a}_j$ of selecting the $j^{\text{th}}$ input as For the multi-hop cases, layers of single hop memory network are stacked and the query of the $(i+1)^{\text{th}}$ layer network is computed as and the output of the last layer is used as the output of the whole network. For more details about memory network, please refer to the original paper BIBREF13. After getting $\mathbf {a}$, we represent the retrieval results as a 0-1 matrix $T \in \lbrace 0, 1\rbrace ^{|\mathcal {R}|\times \mathcal {|C|}}$, where each element in $T$ is calculated as In the retrieval result, $T_{j, k}$ indicates whether the entity in the $j^{\text{th}}$ row and the $k^{\text{th}}$ column is relevant to the final generation of the response. In this paper, we further flatten T to a 0-1 vector $\mathbf {t} \in \lbrace 0, 1\rbrace ^{|\mathcal {E}|}$ (where $|\mathcal {E}|$ equals $|\mathcal {R}|\times \mathcal {|C|}$) as our retrieval row results. ### Our Framework ::: Entity-Consistency Augmented Decoder ::: KB Column Selection
After getting the retrieved row result that indicates which KB row is the most relevant to the generation, we further perform column attention in decoding time to select the probable KB column. For our KB column selection, following the eric:2017:SIGDial we use the decoder hidden state $(\tilde{\mathbf {h}}_{1}, \tilde{\mathbf {h}}_2, ...,\tilde{\mathbf {h}}_t)$ to compute an attention score with the embedding of column attribute name. The attention score $\mathbf {c}\in R^{|\mathcal {E}|}$ then become the logits of the column be selected, which can be calculated as where $\mathbf {c}_j$ is the attention score of the $j^{\text{th}}$ KB column, $\mathbf {k}_j$ is represented with the embedding of word embedding of KB column name. $W^{^{\prime }}_{1}$, $W^{^{\prime }}_{2}$ and $\mathbf {t}^{T}$ are trainable parameters of the model. ### Our Framework ::: Entity-Consistency Augmented Decoder ::: Decoder with Retrieved Entity
After the row selection and column selection, we can define the final retrieved KB entity score as the element-wise dot between the row retriever result and the column selection score, which can be calculated as where the $v^{t}$ indicates the final KB retrieved entity score. Finally, we follow eric:2017:SIGDial to use copy mechanism to incorporate the retrieved entity, which can be defined as where $\mathbf {o}_t$’s dimensionality is $ |\mathcal {V}|$ +$|\mathcal {E}|$. In $\mathbf {v}^t$ , lower $ |\mathcal {V}|$ is zero and the rest$|\mathcal {E}|$ is retrieved entity scores. ### Training the KB-Retriever
As mentioned in section SECREF9, we adopt the memory network to train our KB-retriever. However, in the Seq2Seq dialogue generation, the training data does not include the annotated KB row retrieval results, which makes supervised training the KB-retriever impossible. To tackle this problem, we propose two training methods for our KB-row-retriever. 1) In the first method, inspired by the recent success of distant supervision in information extraction BIBREF16, BIBREF17, BIBREF18, BIBREF19, we take advantage of the similarity between the surface string of KB entries and the reference response, and design a set of heuristics to extract training data for the KB-retriever. 2) In the second method, instead of training the KB-retriever as an independent component, we train it along with the training of the Seq2Seq dialogue generation. To make the retrieval process in Equation DISPLAY_FORM13 differentiable, we use Gumbel-Softmax BIBREF14 as an approximation of the $\operatornamewithlimits{argmax}$ during training. ### Training the KB-Retriever ::: Training with Distant Supervision
Although it's difficult to obtain the annotated retrieval data for the KB-retriever, we can “guess” the most relevant KB row from the reference response, and then obtain the weakly labeled data for the retriever. Intuitively, for the current utterance in the same dialogue which usually belongs to one topic and the KB row that contains the largest number of entities mentioned in the whole dialogue should support the utterance. In our training with distant supervision, we further simplify our assumption and assume that one dialogue which is usually belongs to one topic and can be supported by the most relevant KB row, which means for a $k$-turned dialogue, we construct $k$ pairs of training instances for the retriever and all the inputs $(u_{1}, s_{1}, ..., s_{i-1}, u_{i} \mid i \le k)$ are associated with the same weakly labeled KB retrieval result $T^*$. In this paper, we compute each row's similarity to the whole dialogue and choose the most similar row as $T^*$. We define the similarity of each row as the number of matched spans with the surface form of the entities in the row. Taking the dialogue in Figure FIGREF1 for an example, the similarity of the 4$^\text{th}$ row equals to 4 with “200 Alester Ave”, “gas station”, “Valero”, and “road block nearby” matching the dialogue context; and the similarity of the 7$^\text{th}$ row equals to 1 with only “road block nearby” matching. In our model with the distantly supervised retriever, the retrieval results serve as the input for the Seq2Seq generation. During training the Seq2Seq generation, we use the weakly labeled retrieval result $T^{*}$ as the input. ### Training the KB-Retriever ::: Training with Gumbel-Softmax
In addition to treating the row retrieval result as an input to the generation model, and training the kb-row-retriever independently, we can train it along with the training of the Seq2Seq dialogue generation in an end-to-end fashion. The major difficulty of such a training scheme is that the discrete retrieval result is not differentiable and the training signal from the generation model cannot be passed to the parameters of the retriever. Gumbel-softmax technique BIBREF14 has been shown an effective approximation to the discrete variable and proved to work in sentence representation. In this paper, we adopt the Gumbel-Softmax technique to train the KB retriever. We use as the approximation of $T$, where $\mathbf {g}_{j}$ are i.i.d samples drawn from $\text{Gumbel}(0,1)$ and $\tau $ is a constant that controls the smoothness of the distribution. $T^{\text{approx}}_{j}$ replaces $T^{\text{}}_{j}$ in equation DISPLAY_FORM13 and goes through the same flattening and expanding process as $\mathbf {V}$ to get $\mathbf {v}^{\mathbf {t}^{\text{approx}^{\prime }}}$ and the training signal from Seq2Seq generation is passed via the logit To make training with Gumbel-Softmax more stable, we first initialize the parameters by pre-training the KB-retriever with distant supervision and further fine-tuning our framework. ### Training the KB-Retriever ::: Experimental Settings
We choose the InCar Assistant dataset BIBREF6 including three distinct domains: navigation, weather and calendar domain. For weather domain, we follow wen2018sequence to separate the highest temperature, lowest temperature and weather attribute into three different columns. For calendar domain, there are some dialogues without a KB or incomplete KB. In this case, we padding a special token “-” in these incomplete KBs. Our framework is trained separately in these three domains, using the same train/validation/test split sets as eric:2017:SIGDial. To justify the generalization of the proposed model, we also use another public CamRest dataset BIBREF11 and partition the datasets into training, validation and testing set in the ratio 3:1:1. Especially, we hired some human experts to format the CamRest dataset by equipping the corresponding KB to every dialogues. All hyper-parameters are selected according to validation set. We use a three-hop memory network to model our KB-retriever. The dimensionalities of the embedding is selected from $\lbrace 100, 200\rbrace $ and LSTM hidden units is selected from $\lbrace 50, 100, 150, 200, 350\rbrace $. The dropout we use in our framework is selected from $\lbrace 0.25, 0.5, 0.75\rbrace $ and the batch size we adopt is selected from $\lbrace 1,2\rbrace $. L2 regularization is used on our model with a tension of $5\times 10^{-6}$ for reducing overfitting. For training the retriever with distant supervision, we adopt the weight typing trick BIBREF20. We use Adam BIBREF21 to optimize the parameters in our model and adopt the suggested hyper-parameters for optimization. We adopt both the automatic and human evaluations in our experiments. ### Training the KB-Retriever ::: Baseline Models
We compare our model with several baselines including: Attn seq2seq BIBREF22: A model with simple attention over the input context at each time step during decoding. Ptr-UNK BIBREF23: Ptr-UNK is the model which augments a sequence-to-sequence architecture with attention-based copy mechanism over the encoder context. KV Net BIBREF6: The model adopted and argumented decoder which decodes over the concatenation of vocabulary and KB entities, which allows the model to generate entities. Mem2Seq BIBREF7: Mem2Seq is the model that takes dialogue history and KB entities as input and uses a pointer gate to control either generating a vocabulary word or selecting an input as the output. DSR BIBREF9: DSR leveraged dialogue state representation to retrieve the KB implicitly and applied copying mechanism to retrieve entities from knowledge base while decoding. In InCar dataset, for the Attn seq2seq, Ptr-UNK and Mem2seq, we adopt the reported results from madotto2018mem2seq. In CamRest dataset, for the Mem2Seq, we adopt their open-sourced code to get the results while for the DSR, we run their code on the same dataset to obtain the results. ### Results
Follow the prior works BIBREF6, BIBREF7, BIBREF9, we adopt the BLEU and the Micro Entity F1 to evaluate our model performance. The experimental results are illustrated in Table TABREF30. In the first block of Table TABREF30, we show the Human, rule-based and KV Net (with*) result which are reported from eric:2017:SIGDial. We argue that their results are not directly comparable because their work uses the entities in thier canonicalized forms, which are not calculated based on real entity value. It's noticing that our framework with two methods still outperform KV Net in InCar dataset on whole BLEU and Entity F metrics, which demonstrates the effectiveness of our framework. In the second block of Table TABREF30, we can see that our framework trained with both the distant supervision and the Gumbel-Softmax beats all existing models on two datasets. Our model outperforms each baseline on both BLEU and F1 metrics. In InCar dataset, Our model with Gumbel-Softmax has the highest BLEU compared with baselines, which which shows that our framework can generate more fluent response. Especially, our framework has achieved 2.5% improvement on navigate domain, 1.8% improvement on weather domain and 3.5% improvement on calendar domain on F1 metric. It indicates that the effectiveness of our KB-retriever module and our framework can retrieve more correct entity from KB. In CamRest dataset, the same trend of improvement has been witnessed, which further show the effectiveness of our framework. Besides, we observe that the model trained with Gumbel-Softmax outperforms with distant supervision method. We attribute this to the fact that the KB-retriever and the Seq2Seq module are fine-tuned in an end-to-end fashion, which can refine the KB-retriever and further promote the dialogue generation. ### Results ::: The proportion of responses that can be supported by a single KB row
In this section, we verify our assumption by examining the proportion of responses that can be supported by a single row. We define a response being supported by the most relevant KB row as all the responded entities are included by that row. We study the proportion of these responses over the test set. The number is 95% for the navigation domain, 90% for the CamRest dataset and 80% for the weather domain. This confirms our assumption that most responses can be supported by the relevant KB row. Correctly retrieving the supporting row should be beneficial. We further study the weather domain to see the rest 20% exceptions. Instead of being supported by multiple rows, most of these exceptions cannot be supported by any KB row. For example, there is one case whose reference response is “It 's not rainy today”, and the related KB entity is sunny. These cases provide challenges beyond the scope of this paper. If we consider this kind of cases as being supported by a single row, such proportion in the weather domain is 99%. ### Results ::: Generation Consistency
In this paper, we expect the consistent generation from our model. To verify this, we compute the consistency recall of the utterances that have multiple entities. An utterance is considered as consistent if it has multiple entities and these entities belong to the same row which we annotated with distant supervision. The consistency result is shown in Table TABREF37. From this table, we can see that incorporating retriever in the dialogue generation improves the consistency. ### Results ::: Correlation between the number of KB rows and generation consistency
To further explore the correlation between the number of KB rows and generation consistency, we conduct experiments with distant manner to study the correlation between the number of KB rows and generation consistency. We choose KBs with different number of rows on a scale from 1 to 5 for the generation. From Figure FIGREF32, as the number of KB rows increase, we can see a decrease in generation consistency. This indicates that irrelevant information would harm the dialogue generation consistency. ### Results ::: Visualization
To gain more insights into how the our retriever module influences the whole KB score distribution, we visualized the KB entity probability at the decoding position where we generate the entity 200_Alester_Ave. From the example (Fig FIGREF38), we can see the $4^\text{th}$ row and the $1^\text{th}$ column has the highest probabilities for generating 200_Alester_Ave, which verify the effectiveness of firstly selecting the most relevant KB row and further selecting the most relevant KB column. ### Results ::: Human Evaluation
We provide human evaluation on our framework and the compared models. These responses are based on distinct dialogue history. We hire several human experts and ask them to judge the quality of the responses according to correctness, fluency, and humanlikeness on a scale from 1 to 5. In each judgment, the expert is presented with the dialogue history, an output of a system with the name anonymized, and the gold response. The evaluation results are illustrated in Table TABREF37. Our framework outperforms other baseline models on all metrics according to Table TABREF37. The most significant improvement is from correctness, indicating that our model can retrieve accurate entity from KB and generate more informative information that the users want to know. ### Related Work
Sequence-to-sequence (Seq2Seq) models in text generation BIBREF0, BIBREF1, BIBREF2, BIBREF3, BIBREF4 has gained more popular and they are applied for the open-domain dialogs BIBREF24, BIBREF25 in the end-to-end training method. Recently, the Seq2Seq can be used for learning task oriented dialogs and how to query the structured KB is the remaining challenges. Properly querying the KB has long been a challenge in the task-oriented dialogue system. In the pipeline system, the KB query is strongly correlated with the design of language understanding, state tracking, and policy management. Typically, after obtaining the dialogue state, the policy management module issues an API call accordingly to query the KB. With the development of neural network in natural language processing, efforts have been made to replacing the discrete and pre-defined dialogue state with the distributed representation BIBREF10, BIBREF11, BIBREF12, BIBREF26. In our framework, our retrieval result can be treated as a numeric representation of the API call return. Instead of interacting with the KB via API calls, more and more recent works tried to incorporate KB query as a part of the model. The most popular way of modeling KB query is treating it as an attention network over the entire KB entities BIBREF6, BIBREF27, BIBREF8, BIBREF28, BIBREF29 and the return can be a fuzzy summation of the entity representations. madotto2018mem2seq's practice of modeling the KB query with memory network can also be considered as learning an attentive preference over these entities. wen2018sequence propose the implicit dialogue state representation to query the KB and achieve the promising performance. Different from their modes, we propose the KB-retriever to explicitly query the KB, and the query result is used to filter the irrelevant entities in the dialogue generation to improve the consistency among the output entities. ### Conclusion
In this paper, we propose a novel framework to improve entities consistency by querying KB in two steps. In the first step, inspired by the observation that a response can usually be supported by a single KB row, we introduce the KB retriever to return the most relevant KB row, which is used to filter the irrelevant KB entities and encourage consistent generation. In the second step, we further perform attention mechanism to select the most relevant KB column. Experimental results show the effectiveness of our method. Extensive analysis further confirms the observation and reveal the correlation between the success of KB query and the success of task-oriented dialogue generation. ### Acknowledgments
We thank the anonymous reviewers for their helpful comments and suggestions. This work was supported by the National Natural Science Foundation of China (NSFC) via grant 61976072, 61632011 and 61772153. Figure 1: An example of a task-oriented dialogue that incorporates a knowledge base (KB). The fourth row in KB supports the second turn of the dialogue. A dialogue system will produce a response with conflict entities if it includes the POI in the fourth row and the address in the fifth row, like “Valero is located at 899 Ames Ct”. Figure 2: The workflow of our Seq2Seq task-oriented dialogue generation model with KB-retriever. For simplification, we draw the single-hop memory network instead of the multiple-hop one we use in our model. Table 1: Comparison of our model with baselines Figure 3: Correlation between the number of KB rows and generation consistency on navigation domain. Table 2: The generation consistency and Human Evaluation on navigation domain. Cons. represents Consistency. Cor. represents Correctness. Flu. represents Fluency and Hum. represents Humanlikeness. Figure 4: KB score distribution. The distribution is the timestep when generate entity 200 Alester Ave for response “ Valero is located at 200 Alester Ave”
|
Camrest, InCar Assistant
|
What visual information characterizes tones?
|
### Introduction
Lip reading, also known as visual speech recognition, aims to predict the sentence being spoken, given a silent video of a talking face. In noisy environments, where speech recognition is difficult, visual speech recognition offers an alternative way to understand speech. Besides, lip reading has practical potential in improved hearing aids, security, and silent dictation in public spaces. Lip reading is essentially a difficult problem, as most lip reading actuations, besides the lips and sometimes tongue and teeth, are latent and ambiguous. Several seemingly identical lip movements can produce different words. Thanks to the recent development of deep learning, English-based lip reading methods have made great progress, at both word-level BIBREF0 , BIBREF1 and sentence-level BIBREF2 , BIBREF3 . However, as the language of the most number of speakers, there is only a little work for Chinese Mandarin lip reading in the multimedia community. Yang et al. BIBREF4 present a naturally-distributed large-scale benchmark for Chinese Mandarin lip-reading in the wild, named LRW-1000, which contains 1,000 classes with 718,018 samples from more than 2,000 individual speakers. Each class corresponds to the syllables of a Mandarin word composed of one or several Chinese characters. However, they perform only word classification for Chinese Mandarin lip reading but not at the complete sentence level. LipCH-Net BIBREF5 is the first paper aiming for sentence-level Chinese Mandarin lip reading. LipCH-Net is a two-step end-to-end architecture, in which two deep neural network models are employed to perform the recognition of Picture-to-Pinyin (mouth motion pictures to pronunciations) and the recognition of Pinyin-to-Hanzi (pronunciations to texts) respectively. Then a joint optimization is performed to improve the overall performance. Belong to two different language families, English and Chinese Mandarin have many differences. The most significant one might be that: Chinese Mandarin is a tone language, while English is not. The tone is the use of pitch in language to distinguish lexical or grammatical meaning - that is, to distinguish or to inflect words . Even two words look the same on the face when pronounced, they can have different tones, thus have different meanings. For example, even though "UTF8gbsn练习" (which means practice) and "UTF8gbsn联系" (which means contact) have different meanings, but they have the same mouth movement. This increases ambiguity when lip reading. So the tone is an important factor for Chinese Mandarin lip reading. Based on the above considerations, in this paper, we present CSSMCM, a sentence-level Chinese Mandarin lip reading network, which contains three sub-networks. Same as BIBREF5 , in the first sub-network, pinyin sequence is predicted from the video. Different from BIBREF5 , which predicts pinyin characters from video, pinyin is taken as a whole in CSSMCM, also known as syllables. As we know, Mandarin Chinese is a syllable-based language and syllables are their logical unit of pronunciation. Compared with pinyin characters, syllables are a longer linguistic unit, and can reduce the difficulty of syllable choices in the decoder by sequence-to-sequence attention-based models BIBREF6 . Chen et al. BIBREF7 find that there might be a relationship between the production of lexical tones and the visible movements of the neck, head, and mouth. Motivated by this observation, in the second sub-network, both video and pinyin sequence is used as input to predict tone. Then in the third sub-network, video, pinyin, and tone sequence work together to predict the Chinese character sequence. At last, three sub-networks are jointly finetuned to improve overall performance. As there is no public sentence-level Chinese Mandarin lip reading dataset, we collect a new Chinese Mandarin Lip Reading dataset called CMLR based on China Network Television broadcasts containing talking faces together with subtitles of what is said. In summary, our major contributions are as follows. ### The Proposed Method
In this section, we present CSSMCM, a lip reading model for Chinese Mandarin. As mention in Section SECREF1 , pinyin and tone are both important for Chinese Mandarin lip reading. Pinyin represents how to pronounce a Chinese character and is related to mouth movement. Tone can alleviate the ambiguity of visemes (several speech sounds that look the same) to some extent and can be inferred from visible movements. Based on this, the lip reading task is defined as follow: DISPLAYFORM0 The meaning of these symbols is given in Table TABREF5 . As shown in Equation ( EQREF6 ), the whole problem is divided into three parts, which corresponds to pinyin prediction, tone prediction, and character prediction separately. Each part will be described in detail below. ### Pinyin Prediction Sub-network
The pinyin prediction sub-network transforms video sequence into pinyin sequence, which corresponds to INLINEFORM0 in Equation ( EQREF6 ). This sub-network is based on the sequence-to-sequence architecture with attention mechanism BIBREF8 . We name the encoder and decoder the video encoder and pinyin decoder, for the encoder process video sequence, and the decoder predicts pinyin sequence. The input video sequence is first fed into the VGG model BIBREF9 to extract visual feature. The output of conv5 of VGG is appended with global average pooling BIBREF10 to get the 512-dim feature vector. Then the 512-dim feature vector is fed into video encoder. The video encoder can be denoted as: DISPLAYFORM0 When predicting pinyin sequence, at each timestep INLINEFORM0 , video encoder outputs are attended to calculate a context vector INLINEFORM1 : DISPLAYFORM0 DISPLAYFORM1 ### Tone Prediction Sub-network
As shown in Equation ( EQREF6 ), tone prediction sub-network ( INLINEFORM0 ) takes video and pinyin sequence as inputs and predict corresponding tone sequence. This problem is modeled as a sequence-to-sequence learning problem too. The corresponding model architecture is shown in Figure FIGREF8 . In order to take both video and pinyin information into consideration when producing tone, a dual attention mechanism BIBREF3 is employed. Two independent attention mechanisms are used for video and pinyin sequence. Video context vectors INLINEFORM0 and pinyin context vectors INLINEFORM1 are fused when predicting a tone character at each decoder step. The video encoder is the same as in Section SECREF7 and the pinyin encoder is: DISPLAYFORM0 The tone decoder takes both video encoder outputs and pinyin encoder outputs to calculate context vector, and then predicts tones: DISPLAYFORM0 DISPLAYFORM1 ### Character Prediction Sub-network
The character prediction sub-network corresponds to INLINEFORM0 in Equation ( EQREF6 ). It considers all the pinyin sequence, tone sequence and video sequence when predicting Chinese character. Similarly, we also use attention based sequence-to-sequence architecture to model this equation. Here the attention mechanism is modified into triplet attention mechanism: DISPLAYFORM0 DISPLAYFORM1 For the following needs, the formula of tone encoder is also listed as follows: DISPLAYFORM0 ### CSSMCM Architecture
The architecture of the proposed approach is demonstrated in Figure FIGREF32 . For better display, the three attention mechanisms are not shown in the figure. During the training of CSSMCM, the outputs of pinyin decoder are fed into pinyin encoder, the outputs of tone decoder into tone encoder: DISPLAYFORM0 DISPLAYFORM1 We replace Equation ( EQREF14 ) with Equation ( EQREF28 ), Equation ( EQREF26 ) with Equation ( EQREF29 ). Then, the three sub-networks are jointly trained and the overall loss function is defined as follows: DISPLAYFORM0 where INLINEFORM0 and INLINEFORM1 stand for loss of pinyin prediction sub-network, tone prediction sub-network and character prediction sub-network respectively, as defined below. DISPLAYFORM0 ### Training Strategy
To accelerate training and reduce overfitting, curriculum learning BIBREF3 is employed. The sentences are grouped into subsets according to the length of less than 11, 12-17, 18-23, more than 24 Chinese characters. Scheduled sampling proposed by BIBREF11 is used to eliminate the discrepancy between training and inference. At the training stage, the sampling rate from the previous output is selected from 0.7 to 1. Greedy decoder is used for fast decoding. ### Dataset
In this section, a three-stage pipeline for generating the Chinese Mandarin Lip Reading (CMLR) dataset is described, which includes video pre-processing, text acquisition, and data generation. This three-stage pipeline is similar to the method mentioned in BIBREF3 , but considering the characteristics of our Chinese Mandarin dataset, we have optimized some steps and parts to generate a better quality lip reading dataset. The three-stage pipeline is detailed below. Video Pre-processing. First, national news program "News Broadcast" recorded between June 2009 and June 2018 is obtained from China Network Television website. Then, the HOG-based face detection method is performed BIBREF12 , followed by an open source platform for face recognition and alignment. The video clip set of eleven different hosts who broadcast the news is captured. During the face detection step, using frame skipping can improve efficiency while ensuring the program quality. Text Acquisition. Since there is no subtitle or text annotation in the original "News Broadcast" program, FFmpeg tools are used to extract the corresponding audio track from the video clip set. Then through the iFLYTEK ASR, the corresponding text annotation of the video clip set is obtained. However, there is some noise in these text annotation. English letters, Arabic numerals, and rare punctuation are deleted to get a more pure Chinese Mandarin lip reading dataset. Data Generation. The text annotation acquired in the previous step also contains timestamp information. Therefore, video clip set is intercepted according to these timestamp information, and then the corresponding word, phrase, or sentence video segment of the text annotation are obtained. Since the text timestamp information may have a few uncertain errors, some adjustments are made to the start frame and the end frame when intercepting the video segment. It is worth noting that through experiments, we found that using OpenCV can capture clearer video segment than the FFmpeg tools. Through the three-stage pipeline mentioned above, we can obtain the Chinese Mandarin Lip Reading (CMLR) dataset containing more than 100,000 sentences, 25,000 phrases, 3,500 characters. The dataset is randomly divided into training set, validation set, and test set in a ratio of 7:1:2. Details are listed in Table TABREF37 . ### Implementation Details
The input images are 64 INLINEFORM0 128 in dimension. Lip frames are transformed into gray-scale, and the VGG network takes every 5 lip frames as an input, moving 2 frames at each timestep. For all sub-networks, a two-layer bi-direction GRU BIBREF13 with a cell size of 256 is used for the encoder and a two-layer uni-direction GRU with a cell size of 512 for the decoder. For character and pinyin vocabulary, we keep characters and pinyin that appear more than 20 times. [sos], [eos] and [pad] are also included in these three vocabularies. The final vocabulary size is 371 for pinyin prediction sub-network, 8 for tone prediction sub-network (four tones plus a neutral tone), and 1,779 for character prediction sub-network. The initial learning rate was 0.0001 and decreased by 50% every time the training error did not improve for 4 epochs. CSSMCM is implemented using pytorch library and trained on a Quadro 64C P5000 with 16GB memory. The total end-to-end model was trained for around 12 days. ### Compared Methods and Evaluation Protocol
WAS: The architecture used in BIBREF3 without the audio input. The decoder output Chinese character at each timestep. Others keep unchanged to the original implementation. LipCH-Net-seq: For a fair comparison, we use sequence-to-sequence with attention framework to replace the Connectionist temporal classification (CTC) loss BIBREF14 used in LipCH-Net BIBREF5 when converting picture to pinyin. CSSMCM-w/o video: To evaluate the necessity of video information when predicting tone, the video stream is removed when predicting tone and Chinese characters. In other word, video is only used when predicting the pinyin sequence. The tone is predicted from the pinyin sequence. Tone information and pinyin information work together to predict Chinese character. We tried to implement the Lipnet architecture BIBREF2 to predict Chinese character at each timestep. However, the model did not converge. The possible reasons are due to the way CTC loss works and the difference between English and Chinese Mandarin. Compared to English, which only contains 26 characters, Chinese Mandarin contains thousands of Chinese characters. When CTC calculates loss, it first adds blank between every character in a sentence, that causes the number of the blank label is far more than any other Chinese character. Thus, when Lipnet starts training, it predicts only the blank label. After a certain epoch, "UTF8gbsn的" character will occasionally appear until the learning rate decays to close to zero. For all experiments, Character Error Rate (CER) and Pinyin Error Rate (PER) are used as evaluation metrics. CER is defined as INLINEFORM0 , where INLINEFORM1 is the number of substitutions, INLINEFORM2 is the number of deletions, INLINEFORM3 is the number of insertions to get from the reference to the hypothesis and INLINEFORM4 is the number of words in the reference. PER is calculated in the same way as CER. Tone Error Rate (TER) is also included when analyzing CSSMCM, which is calculated in the same way as above. ### Results
Table TABREF40 shows a detailed comparison between various sub-network of different methods. Comparing P2T and VP2T, VP2T considers video information when predicting the pinyin sequence and achieves a lower error rate. This verifies the conjecture of BIBREF7 that the generation of tones is related to the motion of the head. In terms of overall performance, CSSMCM exceeds all the other architecture on the CMLR dataset and achieves 32.48% character error rate. It is worth noting that CSSMCM-w/o video achieves the worst result (42.23% CER) even though its sub-networks perform well when trained separately. This may be due to the lack of visual information to support, and the accumulation of errors. CSSMCM using tone information performs better compared to LipCH-Net-seq, which does not use tone information. The comparison results show that tone is important when lip reading, and when predicting tone, visual information should be considered. Table TABREF41 shows some generated sentences from different methods. CSSMCM-w/o video architecture is not included due to its relatively lower performance. These are sentences other methods fail to predict but CSSMCM succeeds. The phrase "UTF8gbsn实惠" (which means affordable) in the first example sentence, has a tone of 2, 4 and its corresponding pinyin are shi, hui. WAS predicts it as "UTF8gbsn事会" (which means opportunity). Although the pinyin prediction is correct, the tone is wrong. LipCH-Net-seq predicts "UTF8gbsn实惠" as "UTF8gbsn吃贵" (not a word), which have the same finals "ui" and the corresponding mouth shapes are the same. It's the same in the second example. "UTF8gbsn前, 天, 年" have the same finals and mouth shapes, but the tone is different. These show that when predicting characters with the same lip shape but different tones, other methods are often unable to predict correctly. However, CSSMCM can leverage the tone information to predict successfully. Apart from the above results, Table TABREF42 also lists some failure cases of CSSMCM. The characters that CSSMCM predicts wrong are usually homophones or characters with the same final as the ground truth. In the first example, "UTF8gbsn价" and "UTF8gbsn下" have the same final, ia, while "UTF8gbsn一" and "UTF8gbsn医" are homophones in the second example. Unlike English, if one character in an English word is predicted wrong, the understanding of the transcriptions has little effect. However, if there is a character predicted wrong in Chinese words, it will greatly affect the understandability of transcriptions. In the second example, CSSMCM mispredicts "UTF8gbsn医学" ( which means medical) to "UTF8gbsn一水" (which means all). Although their first characters are pronounced the same, the meaning of the sentence changed from Now with the progress of medical science and technology in our country to It is now with the footsteps of China's Yishui Technology. ### Attention Visualisation
Figure FIGREF44 (a) and Figure FIGREF44 (b) visualise the alignment of video frames and Chinese characters predicted by CSSMCM and WAS respectively. The ground truth sequence is "UTF8gbsn同时他还向媒体表示". Comparing Figure FIGREF44 (a) with Figure FIGREF44 (b), the diagonal trend of the video attention map got by CSSMCM is more obvious. The video attention is more focused where WAS predicts wrong, i.e. the area corresponding to "UTF8gbsn还向". Although WAS mistakenly predicts the "UTF8gbsn媒体" as "UTF8gbsn么体", the "UTF8gbsn媒体" and the "UTF8gbsn么体" have the same mouth shape, so the attention concentrates on the correct frame. It's interesting to mention that in Figure FIGREF47 , when predicting the INLINEFORM0 -th character, attention is concentrated on the INLINEFORM1 -th tone. This may be because attention is applied to the outputs of the encoder, which actually includes all the information from the previous INLINEFORM2 timesteps. The attention to the tone of INLINEFORM3 -th timestep serves as the language model, which reduces the options for generating the character at INLINEFORM4 -th timestep, making prediction more accurate. ### Summary and Extension
In this paper, we propose the CSSMCM, a Cascade Sequence-to-Sequence Model for Chinese Mandarin lip reading. CSSMCM is designed to predicting pinyin sequence, tone sequence, and Chinese character sequence one by one. When predicting tone sequence, a dual attention mechanism is used to consider video sequence and pinyin sequence at the same time. When predicting the Chinese character sequence, a triplet attention mechanism is proposed to take all the video sequence, pinyin sequence, and tone sequence information into consideration. CSSMCM consistently outperforms other lip reading architectures on the proposed CMLR dataset. Lip reading and speech recognition are very similar. In Chinese Mandarin speech recognition, there have been kinds of different acoustic representations like syllable initial/final approach, syllable initial/final with tone approach, syllable approach, syllable with tone approach, preme/toneme approach BIBREF15 and Chinese Character approach BIBREF16 . In this paper, the Chinese character is chosen as the output unit. However, we find that the wrongly predicted characters severely affect the understandability of transcriptions. Using larger output units, like Chinese words, maybe can alleviate this problem. Fig. 1. The tone prediction sub-network. Table 1. Symbol Definition Fig. 2. The character prediction sub-network. Fig. 3. The overall of the CSSMCM network. The attention module is omitted for sake of simplicity. Table 2. The CMLR dataset. Division of training, validation and test data; and the number of sentences, phrases and characters of each partition. Table 3. The detailed comparison between CSSMCM and other methods on the CMLR dataset. V, P, T, C stand for video, pinyin, tone and character. V2P stands for the transformation from video sequence to pinyin sequence. VP2T represents the input are video and pinyin sequence and the output is sequence of tone. OVERALL means to combine the sub-networks and make a joint optimization. Table 4. Examples of sentences that CSSMCM correctly predicts while other methods do not. The pinyin and tone sequence corresponding to the Chinese character sentence are also displayed together. GT stands for ground truth. Table 5. Failure cases of CSSMCM. Fig. 4. Video-to-text alignment using CSSMCM (a) and WAS (b). Fig. 5. Aligenment between output characters and predicted tone sequences using CSSMCM.
|
video sequence is first fed into the VGG model BIBREF9 to extract visual feature
|
Who is Beula and what is her connection to the narrator?
A. Beula is the narrator’s pet elephant. Her baby belongs to Captain Hannah, linking the two men even though they don’t like each other.
B. Beula is Captain Hannah’s pet elephant. The narrator sold her Captain Hannah years ago, leading to a business relationship between the two men.
C. Beula is Captain Hannah’s pet elephant. Her baby belongs to the narrator, linking the captain and the narrator.
D. Beula is the narrator’s pet elephant. Her baby was sold to Captain Hannah, which led to a business relationship between the two men.
|
CAKEWALK TO GLORYANNA BY L. J. STECHER, JR. [Transcriber's Note: This etext was produced from Worlds of Tomorrow June 1963 Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] The job was easy. The profit was enormous. The only trouble was—the cargo had a will of its own! Captain Hannah climbed painfully down from the Delta Crucis , hobbled across the spaceport to where Beulah and I were waiting to greet him and hit me in the eye. Beulah—that's his elephant, but I have to take care of her for him because Beulah's baby belongs to me and Beulah has to take care of it—kept us apart until we both cooled down a little. Then, although still somewhat dubious about it, she let us go together across the field to the spaceport bar. I didn't ask Captain Hannah why he had socked me. Although he has never been a handsome man, he usually has the weathered and austere dignity that comes from plying the remote reaches among the stars. Call it the Look of Eagles. Captain Hannah had lost the Look of Eagles. His eyes were swollen almost shut; every inch of him that showed was a red mass of welts piled on more welts, as though he had tangled with a hive of misanthropic bees. The gold-braided hat of his trade was not clamped in its usual belligerent position slightly over one eye. It was riding high on his head, apparently held up by more of the ubiquitous swellings. I figured that he figured that I had something to do with the way he looked. "Shipping marocca to Gloryanna III didn't turn out to be a cakewalk after all?" I suggested. He glared at me in silence. "Perhaps you would like a drink first, and then you would be willing to tell me about it?" I decided that his wince was intended for a nod, and ordered rhial. I only drink rhial when I've been exposed to Captain Hannah. It was almost a pleasure to think that I was responsible, for a change, for having him take the therapy. "A Delta Class freighter can carry almost anything," he said at last, in a travesty of his usual forceful voice. "But some things it should never try." He lapsed back into silence after this uncharacteristic admission. I almost felt sorry for him, but just then Beulah came racking across the field with her two-ton infant in tow, to show her off to Hannah. I walled off my pity. He had foisted those two maudlin mastodons off onto me in one of our earlier deals, and if I had somehow been responsible for his present troubles, it was no more than he deserved. I rated winning for once. "You did succeed in getting the marocca to Gloryanna III?" I asked anxiously, after the elephants had been admired and sent back home. The success of that venture—even if the job had turned out to be more difficult than we had expected—meant an enormous profit to both of us. The fruit of the marocca is delicious and fabulously expensive. The plant grew only on the single planet Mypore II. Transshipped seeds invariably failed to germinate, which explained its rarity. The Myporians were usually, and understandably, bitterly, opposed to letting any of the living plants get shipped off their planet. But when I offered them a sizable piece of cash plus a perpetual share of the profits for letting us take a load of marocca plants to Gloryanna III, they relented and, for the first time in history, gave their assent. In fact, they had seemed delighted. "I got them there safely," said Captain Hannah. "And they are growing all right?" I persisted. "When I left, marocca was growing like mad," said Captain Hannah. I relaxed and leaned back in my chair. I no longer felt the need of rhial for myself. "Tell me about it," I suggested. "It was you who said that we should carry those damn plants to Gloryanna III," he said balefully. "I ought to black your other eye." "Simmer down and have some more rhial," I told him. "Sure I get the credit for that. Gloryanna III is almost a twin to Mypore II. You know that marocca takes a very special kind of environment. Bright sun most of the time—that means an almost cloudless environment. A very equable climate. Days and nights the same length and no seasons—that means no ecliptical and no axial tilt. But our tests showed that the plants had enough tolerance to cause no trouble in the trip in Delta Crucis ." A light dawned. "Our tests were no good?" "Your tests were no good," agreed the captain with feeling. "I'll tell you about it first, and then I'll black your other eye," he decided. "You'll remember that I warned you that we should take some marocca out into space and solve any problems we might find before committing ourselves to hauling a full load of it?" asked Captain Hannah. "We couldn't," I protested. "The Myporians gave us a deadline. If we had gone through all of that rigamarole, we would have lost the franchise. Besides, they gave you full written instructions about what to do under all possible circumstances." "Sure. Written in Myporian. A very difficult language to translate. Especially when you're barricaded in the head." I almost asked him why he had been barricaded in the bathroom of the Delta Crucis , but I figured it was safer to let him tell me in his own way, in his own time. "Well," he said, "I got into parking orbit around Mypore without any trouble. The plastic film kept the water in the hydroponic tanks without any trouble, even in a no-gravity condition. And by the time I had lined up for Gloryanna and Jumped, I figured, like you said, that the trip would be a cakewalk. "Do you remember how the plants always keep their leaves facing the sun? They twist on their stems all day, and then they go on twisting them all night, still pointing at the underground sun, so that they're aimed right at sunrise. So the stem looks like a corkscrew?" I nodded. "Sure. That's why they can't stand an axial tilt. They 'remember' the rate and direction of movement, and keep it up during the night time. So what? We had that problem all figured out." "You think so? That solution was one of yours, too, wasn't it?" He gazed moodily at his beaker of rhial. "I must admit it sounded good to me, too. In Limbo, moving at multiple light-speeds, the whole Universe, of course, turns into a bright glowing spot in our direction of motion, with everything else dark. So I lined up the Delta Crucis perpendicular to her direction of motion, put a once-every-twenty-one hour spin on her to match the rotation rates of Mypore II and Gloryanna III, and uncovered the view ports to let in the light. It gradually brightened until 'noon time', with the ports pointing straight at the light source, and then dimmed until we had ten and one-half hours of darkness. "Of course, it didn't work." "For Heaven's sake, why not?" "For Heaven's sake why should it? With no gravity for reference, how were the plants supposed to know that the 'sun' was supposed to be moving?" "So what did you do?" I asked, when that had sunk in. "If the stem doesn't keep winding, the plants die; and they can only take a few extra hours of night time before they run down." "Oh," said Captain Hannah in quiet tones of controlled desperation, "it was very simple. I just put enough spin on the ship to make artificial gravity, and then I strung a light and moved it every fifteen minutes for ten and one-half hours, until I had gone halfway around the room. Then I could turn the light off and rest for ten and one-half hours. The plants liked it fine. "Of course, first I had to move all the hydroponic tanks from their original positions perpendicular to the axial thrust line of the ship to a radial position. And because somehow we had picked up half of the plants in the northern hemisphere of Mypore and the other half in the southern hemisphere, it turned out that half of the plants had a sinistral corkscrew and the other half had a dextral. So I had to set the plants up in two different rooms, and run an artificial sun for each, going clockwise with one, widdershins with the other. "I won't even talk about what I went through while I was shifting the hydroponic tanks, when all the plastic membranes that were supposed to keep the water in place started to break." "I'd like to know," I said sincerely. He stared at me in silence for a moment. "Well, it filled the cabin with great solid bubbles of water. Water bubbles will oscillate and wobble like soap bubbles," he went on dreamily, "but of course, they're not empty, like soap bubbles. The surface acts a little like a membrane, so that sometimes two of the things will touch and gently bounce apart without joining. But just try touching one of them. You could drown—I almost did. Several times. "I got a fire pump—an empty one. You know the kind; a wide cylinder with a piston with a handle, and a hose that you squirt the water out of, or can suck water in with. The way you use it is, you float up on a big ball of water, with the pump piston down—closed. You carefully poke the end of the hose into the ball of water, letting only the metal tip touch. Never the hose. If you let the hose touch, the water runs up it and tries to drown you. Then you pull up on the piston, and draw all the water into the cylinder. Of course, you have to hold the pump with your feet while you pull the handle with your free hand." "Did it work?" I asked eagerly. "Eventually. Then I stopped to think of what to do with the water. It was full of minerals and manure and such, and I didn't want to introduce it into the ship's tanks." "But you solved the problem?" "In a sense," said the captain. "I just emptied the pump back into the air, ignored the bubbles, repositioned the tanks, put spin on the ship and then ladled the liquid back into the tanks with a bucket." "Didn't you bump into a lot of the bubbles and get yourself dunked a good deal while you were working with the tanks?" He shrugged. "I couldn't say. By that time I was ignoring them. It was that or suicide. I had begun to get the feeling that they were stalking me. So I drew a blank." "Then after that you were all right, except for the tedium of moving the lights around?" I asked him. I answered myself at once. "No. There must be more. You haven't told me why you hid out in the bathroom, yet." "Not yet," said Captain Hannah. "Like you, I figured I had the situation fairly well under control, but like you, I hadn't thought things through. The plastic membranes hadn't torn when we brought the tanks in board the Delta Crucis . It never occurred to me to hunt around for the reasons for the change. But I wouldn't have had long to hunt anyway, because in a few hours the reasons came looking for me. "They were a tiny skeeter-like thing. A sort of midge or junior grade mosquito. They had apparently been swimming in the water during their larval stage. Instead of making cocoons for themselves, they snipped tiny little pieces of plastic to use as protective covers in the pupal stage. I guess they were more like butterflies than mosquitoes in their habits. And now they were mature. "There were thousands and thousands of them, and each one of them made a tiny, maddening whine as it flew." "And they bit? That explains your bumps?" I asked sympathetically. "Oh, no. These things didn't bite, they itched. And they got down inside of everything they could get down inside, and clung. That included my ears and my eyes and my nose. "I broke out a hand sprayer full of a DDT solution, and sprayed it around me to try to clear the nearby air a little, so that I could have room to think. The midges loved it. But the plants that were in reach died so fast that you could watch their leaves curl up and drop off. "I couldn't figure whether to turn up the fans and dissipate the cloud—by spreading it all through the ship—or whether to try to block off the other plant room, and save it at least. So I ended up by not doing anything, which was the right thing to do. No more plants died from the DDT. "So then I did a few experiments, and found that the regular poison spray in the ship's fumigation system worked just fine. It killed the bugs without doing the plants any harm at all. Of course, the fumigation system is designed to work with the fumigator off the ship, because it's poisonous to humans too. "I finally blocked the vents and the door edges in the head, after running some remote controls into there, and then started the fumigation system going. While I was sitting there with nothing much to do, I tried to translate what I could of the Myporian instructions. It was on page eleven that it mentioned casually that the midges—the correct word is carolla—are a necessary part of the life cycle of the marocca. The larvae provide an enzyme without which the plants die. "Of course. I immediately stopped slapping at the relatively few midges that had made their way into the head with me, and started to change the air in the ship to get rid of the poison. I knew it was too late before I started, and for once I was right. "The only live midges left in the ship were the ones that had been with me during the fumigation process. I immediately tried to start a breeding ground for midges, but the midges didn't seem to want to cooperate. Whatever I tried to do, they came back to me. I was the only thing they seemed to love. I didn't dare bathe, or scratch, or even wriggle, for fear of killing more of them. And they kept on itching. It was just about unbearable, but I bore it for three interminable days while the midges died one by one. It was heartbreaking—at least, it was to me. "And it was unnecessary, too. Because apparently the carolla had already laid their eggs, or whatever it is that they do, before I had fumigated them. After my useless days of agony, a new batch came swarming out. And this time there were a few of a much larger thing with them—something like an enormous moth. The new thing just blundered around aimlessly. "I lit out for the head again, to keep away from that intolerable whining. This time I took a luxurious shower and got rid of most of the midges that came through the door with me. I felt almost comfortable, in fact, until I resumed my efforts to catch up on my reading. "The mothlike things—they are called dingleburys—also turn out to provide a necessary enzyme. They are supposed to have the same timing of their life cycle as the carolla. Apparently the shaking up I had given their larvae in moving the tanks and dipping the water up in buckets and all that had inhibited them in completing their cycle the first time around. "And the reason they had the same life cycle as the carolla was that the adult dinglebury will eat only the adult carolla, and it has to fill itself full to bursting before it will reproduce. If I had the translation done correctly, they were supposed to dart gracefully around, catching carolla on the wing and stuffing themselves happily. "I had to find out what was wrong with my awkward dingleburys. And that, of course, meant going out into the ship again. But I had to do that anyway, because it was almost 'daylight', and time for me to start shifting the lights again. "The reason for the dingleburys' problem is fairly obvious. When you set up artificial gravity by spinning a ship, the gravity is fine down near the skin where the plants are. But the gravity potential is very high, and it gets very light up where things fly around, going to zero on the middle line of the ship. And the unfamiliar gravity gradient, together with the Coriolis effect and all, makes the poor dingleburys dizzy, so they can't catch carolla. "And if you think I figured all that out about dingleburys getting dizzy at the time, in that madhouse of a ship, then you're crazy. What happened was that I saw that there was one of the creatures that didn't seem to be having any trouble, but was acting like the book said it should. I caught it and examined it. The poor thing was blind, and was capturing her prey by sound alone. "So I spent the whole day—along with my usual chore of shifting the lights—blindfolding dingleburys. Which is a hell of a sport for a man who is captain of his own ship." I must say that I agreed with him, but it seemed to be a good time for me to keep my mouth shut. "Well, after the dingleburys had eaten and propagated, they became inquisitive. They explored the whole ship, going into places I wouldn't have believed it to be possible for them to reach, including the inside of the main computer, which promptly shorted out. I finally figured that one of the things had managed to crawl up the cooling air exhaust duct, against the flow of air, to see what was going on inside. "I didn't dare to get rid of the things without checking my book, of course, so it was back to the head for me. 'Night' had come again—and it was the only place I could get any privacy. There were plenty of the carolla left to join me outside. "I showered and swatted and started to read. I got as far as where it said that the dingleburys continued to be of importance, and then I'm afraid I fell asleep. "I got up with the sun the next morning. Hell, I had to, considering that it was I who turned the sun on! I found that the dingleburys immediately got busy opening small buds on the stems of the marocca plants. Apparently they were pollinating them. I felt sure that these buds weren't the marocca blossoms from which the fruit formed—I'd seen a lot of those while we were on Mypore II and they were much bigger and showier than these little acorn-sized buds. "Of course, I should have translated some more of my instruction book, but I was busy. "Anyway, the action of the dingleburys triggered the violent growth phase of the marocca plants. Did you know that they plant marocca seedlings, back on Mypore II, at least a hundred feet apart? If you'll recall, a mature field, which was the only kind we ever saw, is one solid mass of green growth. "The book says that it takes just six hours for a marocca field to shift from the seedling stage to the mature stage. It didn't seem that long. You could watch the stuff grow—groping and crawling along; one plant twining with another as they climbed toward the light. "It was then that I began to get worried. If they twined around the light, they would keep me from moving it, and they would shadow it so it wouldn't do its job right. In effect, their growth would put out the sun. "I thought of putting up an electrically charged fence around the light, but the bugs had put most of my loose equipment out of action, so I got a machete. When I took a swing at one of the vines, something bit me on the back of the neck so hard it almost knocked me down. It was one of the dingleburys, and it was as mad as blazes. It seems that one of the things they do is to defend the marocca against marauders. That was the first of my welts, and it put me back in the head in about two seconds. "And what's more, I found that I couldn't kill the damn things. Not if I wanted to save the plants. The growth only stops at the end of six hours, after the blossoms appear and are visited by the dingleburys. No dingleburys, no growth stoppage. "So for the next several hours I had to keep moving those lights, and keep them clear of the vines, and keep the vines from shadowing each other to the point where they curled up and died, and I had to do it gently , surrounded by a bunch of worried dingleburys. "Every time they got a little too worried, or I slipped and bumped into a plant too hard, or looked crosseyed at them, they bit me. If you think I look bad now, you should have seen me just about the time the blossoms started to burst. "I was worried about those blossoms. I felt sure that they would smell terrible, or make me sick, or hypnotize me, or something. But they just turned out to be big, white, odorless flowers. They did nothing for me or to me. They drove the dingleburys wild, though, I'm happy to say. Made them forget all about me. "While they were having their orgy, I caught up on my reading. It was necessary for me to cut back the marocca vines. For one thing, I couldn't get up to the area of the bridge. For another, the main computer was completely clogged. I could use the auxiliary, on the bridge, if I could get to it, but it's a poor substitute. For another thing, I would have to cut the stuff way back if I was ever going to get the plants out of the ship. And I was a little anxious to get my Delta Crucis back to normal as soon as possible. But before cutting, I had to translate the gouge. "It turns out that it's all right to cut marocca as soon as it stops growing. To keep the plants from dying, though, you have to mulch the cuttings and then feed them back to the plants, where the roots store whatever they need against the time of the next explosive period of growth. Of course, if you prefer you can wait for the vines to die back naturally, which takes several months. "There was one little catch, of course. The cuttings from the vines will poison the plants if they are fed back to them without having been mixed with a certain amount of processed mulch. Enzymes again. And there was only one special processor on board. "I was the special processor. That's what the instructions said—I translated very carefully—it required an 'organic processor'. "So I had to eat pounds of that horrible tasting stuff every day, and process it the hard way. "I didn't even have time to scratch my bites. I must have lost weight everywhere but in the swollen places, and they looked worse than they do now. The doctor says it may take a year before the bumps all go away—if they ever do—but I have improved a lot already. "For a while I must have been out of my head. I got so caught up in the rhythm of the thing that I didn't even notice when we slipped out of Limbo into real space near Gloryanna III. It was three days, the Control Tower on Gloryanna III told me, that they tried continuously to raise me on the communications gear before I heard the alarm bell and answered them, so I had to do a good deal of backtracking before I could get into parking orbit around the planet, and then set Delta Crucis down safely. Even as shaky as I was, Delta Crucis behaved like a lady. "I hadn't chopped off all of the new growth, although I had the plants down to manageable size. Some of the blossoms left on the plants had formed fruit, and the fruit had ripened and dried, and the seeds had developed fully. They were popping and spreading fine dust-like spores all over the ship, those last few hours before I landed. "By that time, though, an occasional sneezing fit and watering eyes didn't bother me any. I was far beyond the point where hay fever could add to my troubles. "When I opened the airlock door, though, the spores drifting outside set the customs inspectors to sneezing and swearing more than seemed reasonable at the time." Captain Hannah inhaled a sip of rhial, and seemed to be enjoying the powerful stuff. He acted as if he thought he had finished. "Well, go on," I urged him. "The marocca plants were still in good shape, weren't they?" Hannah nodded. "They were growing luxuriously." He nodded his head a couple of more times, in spite of the discomfort it must have given him. He said, "They made me burn the entire crop right away, of course. They didn't get all of the carolla or dingleburys, though. Or spores." "Gloryanna III is the original home planet of marocca. They hated the stuff, of course, but they liked the profit. Then, when a plague almost wiped out the dingleburys, they introduced khorram furs as a cash crop. It wasn't as lucrative, but it was so much more pleasant that they outlawed marocca. Took them almost fifty years to stamp it out completely. Meanwhile, some clever native shipped a load of the stuff to Mypore II. He took his time, did it without any trouble and made his fortune. And got out again quickly. "The Gloryannans were going to hold my Delta Crucis as security to pay for the cost of stamping out marocca all over again—those spores sprout fast—and for a time I was worried. "Of course, when I showed them our contract—that you alone were responsible for everything once I landed the plants safely on Gloryanna III, they let me go. "They'll send you the bill. They don't figure it will take them more than a few months to complete the job." Captain Hannah stopped talking and stood up, painfully and a little unsteadily. I'm afraid I didn't even notice when he blacked my other eye. I was too busy reaching for the rhial. END
|
C. Beula is Captain Hannah’s pet elephant. Her baby belongs to the narrator, linking the captain and the narrator.
|
Before his departure, Peter recalls a line from a film. Why does it come to mind for him?
A. He recognizes that he will be a changed, mutated man when he returns. He literally will come back "not as a boy."
B. He's trying to convince himself that he and humanity will be able to come back, with the emphasis on "We'll come back."
C. The situation is grave. Like men who go off to war, the journey will change them. He won't be coming home as the same "boy."
D. He's not sure he'll be coming back, and the song is bittersweet for him.
|
THE AVENGER By STUART FLEMING Karson was creating a superman to fight the weird super-monsters who had invaded Earth. But he was forgetting one tiny thing—like calls to like. [Transcriber's Note: This etext was produced from Planet Stories Spring 1944. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Peter Karson was dead. He had been dead for some time now, but the dark blood was still oozing from the crushed ruin of his face, trickling down into his sodden sleeve, and falling, drop by slow drop, from his fingertips. His head was tilted over the back of the chair at a queer, unnatural angle, so that the light made deep pools of shadow where his eyes had been. There was no sound in the room except for the small splashing the blood made as it dropped into the sticky pool on the floor. The great banks of machinery around the walls were silent. I knew that they would never come to life again. I rose and walked over to the window. Outside, the stars were as before: tiny, myriad points of light, infinitely far away. They had not changed, and yet they were suddenly no longer friendly. They were cold and alien. It was I who had changed: something inside me was dead, like the machinery, and like Peter. It was a kind of indefinable emptiness. I do not think it was what Peter called an emotion; and yet it had nothing to do with logic, either. It was just an emptiness—a void that could not be filled by eating or drinking. It was not a longing. I had no desire that things should be otherwise than they were. I did not even wish that Peter were not dead, for reason had told me that he had to die. That was the end of it. But the void was still there, unexplainable and impossible to ignore. For the first time in all my life I had found a problem that I could not solve. Strange, disturbing sensations stirred and whispered within me, nagging, gnawing. And suddenly—something moved on the skin of my cheek. I raised a hand to it, slowly. A tear was trickling down my cheek. Young Peter Karson put the last black-print down and sighed with satisfaction. His dream was perfect; the Citadel was complete, every minutest detail provided for—on paper. In two weeks they would be laying the core, and then the metal giant itself would begin to grow, glittering, pulsing with each increment of power, until at last it lay finished, a living thing. Then there would remain only the task of blasting the great, shining ship out into the carefully-calculated orbit that would be its home. In his mind's eye he could see it, slowly wheeling, like a second satellite, about the Earth; endlessly gathering knowledge into its insatiable mechanisms. He could see, too, the level on level of laboratories and storerooms that filled its interlocking segments; the meteor deflectors, the air renewal system, the mighty engines at the stern—all the children of his brain. Out there, away from the muffling, distorting, damnable blanket of atmosphere, away from Earth's inexorable gravitational pull, would be a laboratory such as man had never seen. The ship would be filled with the sounds of busy men and women, wresting secrets from the reluctant ether. A new chemistry, a new physics; perhaps even a new biochemistry. A discordant note suddenly entered his fantasy. He looked up, conscious of the walls of his office again, but could see nothing unusual. Still, that thin, dark whisper of dread was at the back of his mind. Slowly, as if reluctantly compelled, he turned around to face the window at his back. There, outside the window, fifty stories up, a face was staring impassively in at him. That was the first impression he got; just a face, staring. Then he saw, with a queer, icy chill, that the face was blood-red and subtly inhuman. It tapered off into a formless, shriveled body. For a moment or an eternity it hung there, unsupported, the bulging eyes staring at him. Then it grew misty at the edges. It dissolved slowly away and was gone. "Lord!" he said. He stared after it, stunned into immobility. Down in the street somewhere, a portable video was shrilling a popular song; after a moment he heard the faint swish of a tube car going past. Everything was normal. Nothing, on examination, seemed to have changed. But the world had grown suddenly unreal. One part of his brain had been shocked into its shell. It was hiding from the thing that had hurt it, and it refused to respond. But the other part was going calmly, lucidly on, quite without his volition. It considered the possibility that he had gone temporarily insane, and decided that this was probable. Hardly knowing what he did, he found a cigarette and lit it. His hands were shaking. He stared at them dully, and then he reached over to the newsbox on his desk, and switched it on. There were flaring red headlines. Relief washed over him, leaving him breathless. He was horrified, of course, but only abstractedly. For the moment he could only be glad that what he had seen was terrible reality rather than even more terrible illusion. INVADERS APPEAR IN BOSTON. 200 DEAD Then lines of type, and farther down: 50 CHILDREN DISAPPEAR FROM PARIS MATERNITY CENTER He pressed the stud. The roll was full of them. MOON SHIP DESTROYED IN TRANSIT NO COMMUNICATION FROM ANTARCTICA IN 6 HOURS STRANGE FORCE DEFLECTS PLANES FROM SAHARA AREA WORLD POLICE MOBILIZING The item below the last one said: Pacifica, June 7—The World Police are mobilizing, for the first time in fifty years. The order was made public early this morning by R. Stein, Secretary of the Council, who said in part: "The reason for this ... order must be apparent to all civilized peoples. For the Invaders have spared no part of this planet in their depredations: they have laid Hong Kong waste; they have terrorized London; they have destroyed the lives of citizens in every member state and in every inhabited area. There can be few within reach of printed reports or my words who have not seen the Invaders, or whose friends have not seen them. "The peoples of the world, then, know what they are, and know that we face the most momentous struggle in our history. We face an enemy superior to ourselves in every way . "Since the Invaders first appeared in Wood River, Oregon, 24 hours ago, they have not once acknowledged our attempts to communicate, or in any way taken notice of our existence as reasoning beings. They have treated us precisely as we, in less enlightened days, might have treated a newly-discovered race of lower animals. They have not attacked our centers of government, nor immobilized our communications, nor laid siege to our defenses. But in instance after instance, they have done as they would with us. They have examined us, dissected us, driven us mad, killed us with no discernable provocation; and this is more intolerable than any normal invasion. "I have no fear that the people of Earth will fail to meet this challenge, for there is no alternative. Not only our individual lives are threatened, but our existence as a race. We must, and will, destroy the Invaders!" Peter sank back in his chair, the full shock of it striking him for the first time. " Will we?" he asked himself softly. It was only two stories down the moving ramp to Lorelei Cooper's laboratory. Peter took it in fifteen seconds, running, and stumbled to a halt in front of the door marked "Radiation." She had set her door mechanism to "Etaoin Shrdlu," principally because he hated double-talk. He mouthed the syllables, had to repeat them because he put an accent in the wrong place, and squeezed through the door as soon as it opened far enough to admit him. Lorelei, beautiful in spite of dark-circled eyes and a smear of grease on her chin, looked up from a huge ledger at the end of the room. One blonde eyebrow arched in the quizzical expression he knew so well. "What makes, Peter my love?" she asked, and bent back to the ledger. Then she did a double-take, looked at his face intently, and said, "Darling, what's wrong?" He said, "Have you seen the news recently?" She frowned. "Why, no—Harry and I have been working for thirty-six hours straight. Haven't seen anybody, haven't heard anything. Why?" "You wouldn't believe me. Where's your newsbox?" She came around the desk and put her hands on his shoulders. "Pete, you know I haven't one—it bores me or upsets me, depending on whether there's trouble or not. What—" "I'm sorry, I forgot," he said. "But you have a scanner?" "Yes, of course. But really, Pete—" "You'll understand in a minute. Turn it on, Lorelei." She gazed at him levelly for a moment, kissed him impulsively, and then walked over to the video panel on the wall and swept a mountain of papers away from in front of it. She turned the selector dial to "News" and pressed the stud. A faint wash of color appeared on the panel, strengthened slowly, and suddenly leapt into full brilliance. Lorelei caught her breath. It was a street scene in the Science City of Manhattan, flooded by the warm spring sunshine. Down on the lowest level, visible past the transport and passenger tubes, the parks and moving ways should have been dotted with colorful, holiday crowds. The people were there, yes but they were flowing away in a swiftly-widening circle. They disappeared into buildings, and the ways snatched them up, and in a heartbeat they were gone. There were left only two blood-red, malignant monstrosities somehow defiling the air they floated in; and below them, a pitiful huddle of flesh no longer recognizable as human beings. They were not dead, those men and women, but they wanted to be. Their bodies had been impossibly joined, fused together into a single obscene, floundering mass of helpless protoplasm. The thin moaning that went up from them was more horrible than any cry of agony. "The Invaders are here, citizens," the commentator was saying in a strangled voice. "Stay off the streets. Hide yourselves. Stay off the streets...." His voice droned on, but neither of them heard it. Lorelei buried her head on his chest, clutching at him desperately. "Peter!" she said faintly. "Why do they broadcast such things?" "They have to," he told her grimly. "There will be panics and suicides, and they know it; but they have to do it. This isn't like a war, where the noncombatants' morale has to be kept up. There aren't going to be any noncombatants, this time. Everybody in the world has to know about them, so that he can fight them—and then it may not be enough." The viewpoint of the teleo sender changed as the two red beings soared away from their victims and angled slowly up the street. Peter reached out to switch off the scanner, and froze. The girl felt his muscles tense abruptly, looked back at the scene. The Invaders were floating up the sloping side of a tall, pure white structure that dominated the rest. "That's the Atlas building," she said unbelievingly. "Us!" "Yes." Silently, they counted stories as the two beings rose. Forty-five ... forty-six ... forty-seven ... forty-eight. Inevitably, they halted. Then they faded slowly. It was impossible to say whether they had gone through the solid wall, or simply melted away. The man and woman clung together, waiting. There was a thick, oppressive silence, full of small rustlings and other faint sounds that were no longer normal. Then, very near, a man screamed in a high, inhuman voice. The screamed dwindled into a throaty gurgle and died, leaving silence again. Peter's lips were cold with sweat. Tiny nerves in his face and arms were jumping convulsively. His stomach crawled. He thrust the girl away from him and started toward the inner room. "Wait here," he mouthed. She was after him, clinging to his arms. "No, Peter! Don't go in there! Peter! " But he pushed her away again, woodenly, and stalked forward. There was a space in the middle of the room where machinery had been cleared away to make room for an incompleted setup. Peter walked down the narrow aisle, past bakelite-sheathed mechanisms and rows of animal cages, and paused just short of it. The two red beings were there, formless bodies hazy in midair, the distorted, hairless skulls in profile, staring at something outside his range of vision. Peter forced himself forward another step. Little Harry Kanin, Lorelei's assistant, was crumpled in a corner, half supported by the broad base of an X-ray chamber. His face was flaccid and bloated. His glazed eyes, impassive yet somehow pleading, stared at nothingness straight ahead of him. The Invaders ignored Peter, staring expressionlessly down at Kanin. In a moment Peter realized what they were doing to him. He stood, paralyzed with horror, and watched it happen. The little man's body was sagging, ever so slowly, as if he were relaxing tiredly. His torso was telescoping, bit by bit; his spread legs grew wider and more shapeless, his cheeks caved in and his skull grew gradually flatter. When it was over, the thing that had been Kanin was a limp, boneless puddle of flesh. Peter could not look at it. There was a scream in his throat that would not come out. He was beyond fear, beyond agony. He turned to the still-hovering monsters and said in a terrible voice, "Why? Why?" The nearest being turned slowly to regard him. Its lips did not move, but there was a tiny sound in Peter's brain, a thin, dry whispering. The scream was welling up. He fought it down and listened. " Wurnkomellilonasendiktolsasangkanmiamiamimami.... " The face was staring directly into his, the bulging eyes hypnotic. The ears were small, no more than excresences of skin. The narrow lips seemed sealed together; a thin, slimy ichor drooled from them. There were lines in the face, but they were lines of age, not emotion. Only the eyes were alive. " ... raswilopreatadvuonistuwurncchtusanlgkelglawwalinom.... " "I can't understand," he cried wildly. "What do you want?" " ... morofelcovisyanmamiwurlectaunntous. " He heard a faint sound behind him, and whirled. It was the first time he had realized that Lorelei had followed him. She stood there, swaying, very pale, looking at the red Invaders. Her eyes swiveled slowly.... " Opreniktoulestritifenrelngetnaktwiltoctpre. " His voice was hoarse. "Don't look! Don't—Go back!" The horrible, mindless noise in his throat was almost beyond his power to repress. His insides writhed to thrust it out. She didn't see him. Her eyes glazed, and she dropped limply to the floor. The scream came out then. Before he knew, even, that he could hold it back no longer, his mouth was wide open, his muscles tensed, his fingernails slicing his palms. It echoed with unbelievable volume in the room. It was a scream to split eardrums; a scream to wake the dead. Somebody said, "Doctor!" He wanted to say, "Yes, get a doctor. Lorelei—" but his mouth only twitched feebly. He couldn't seem to get it to work properly. He tried again. "Doctor." "Yes?" A gentle, masculine voice. He opened his eyes with an effort. There was a blurred face before him; in a moment it grew clearer. The strong, clean-shaven chin contrasted oddly with the haggard circles under the eyes. There was a clean, starched odor. "Where am I?" he said. He tried to turn his head, but a firm hand pressed him back into the sheets. "You're in a hospital. Just lie quietly, please." He tried to get up again. "Where's Lorelei?" "She's well, and you'll see her soon. Now lie quietly. You've been a very sick man." Peter sank back in the bed. The room was coming into focus. He looked around him slowly. He felt very weak, but perfectly lucid. "Yes...." he said. "How long have I been here, Doctor?" The man hesitated, looked at him intently. "Three months," he said. He turned and gave low-voiced instructions to a nurse, and then went away. Peter's head began spinning just a little. Glass clinked from a metal stand near his head; the nurse bent over him with a glass half full of milky fluid. It tasted awful, but she made him drink it all. In a moment he began to relax, and the room got fuzzy again. Just before he drifted off, he said sleepily, "You can't—fool me. It's been more —than three—months." He was right. All the nurses, and even Dr. Arnold, were evasive, but he kept asking them why he couldn't see Lorelei, and finally he wormed it out of them. It had been nine and a half months, not three, and he'd been in a coma all that time. Lorelei, it seemed, had recovered much sooner. "She was only suffering from ordinary shock," Arnold explained. "Seeing that assistant of hers—it was enough to knock anybody out, especially a woman. But you stood actual mental contact with them for approximately five minutes. Yes, we know—you talked a lot. It's a miracle you're alive, and rational." "But where is she?" Peter complained. "You still haven't explained why I haven't been able to see her." Arnold frowned. "All right," he said. "I guess you're strong enough to take it. She's underground, with the rest of the women and children, and a good two-thirds of the male population. That's where you'll go, as soon as you're well enough to be moved. We started digging in six months ago." "But why?" Peter whispered. Arnold's strong jaw knotted. "We're hiding," he said. "Everything else has failed." Peter couldn't think of anything to say. Dr. Arnold's voice went on after a moment, musingly. "We're burrowing into the earth, like worms. It didn't take us long to find out we couldn't kill them. They didn't even take any notice of our attempts to do so, except once. That was when a squadron of the Police caught about fifty of them together at one time, and attacked with flame guns and a new secret weapon. It didn't hurt them, but it annoyed them. It was the first time they'd been annoyed, I think. They blew up half a state, and it's still smoldering." "And since then?" Peter asked huskily. "Since then, we've been burrowing. All the big cities.... It would be an impossible task if we tried to include all the thinly-populated areas, of course, but it doesn't matter. By the time we excavate enough to take care of a quarter of the earth's population, the other three-quarters will be dead, or worse." "I wonder," Peter said shakily, "if I am strong enough to take it." Arnold laughed harshly. "You are. You've got to be. You're part of our last hope, you see." "Our last hope?" "Yes. You're a scientist." "I see," said Peter. And for the first time, he thought of the Citadel . No plan leaped full-born into his mind, but, maybe , he thought, there's a chance .... It wasn't very big, the thing that had been his shining dream. It lay there in its rough cradle, a globe of raw dura-steel not more than five hundred meters in diameter, where the Citadel was to have been a thousand. It wouldn't house a hundred scientists, eagerly delving into the hinterland of research. The huge compartments weren't filled with the latest equipment for chemical and physical experiment; instead, there was compressed oxygen there, and concentrated food, enough to last a lifetime. It was a new world, all by itself; or else it was a tomb. And there was one other change, one that you couldn't see from the outside. The solid meters of lead in its outer skin, the shielding to keep out cosmic rays, were gone. A man had just finished engraving the final stroke on its nameplate, to the left of the airlock— The Avenger . He stepped away now, and joined the group a little distance away, silently waiting. Lorelei said, "You can't do it. I won't let you! Peter—" "Darling," he began wearily. "Don't throw your life away! Give us time—there must be another way." "There's no other way," Peter said. He gripped her arms tightly, as if he could compel her to understand by the sheer pressure of his fingers. "Darling, listen to me. We've tried everything. We've gone underground, but that's only delaying the end. They still come down here, only not as many. The mortality rate is up, the suicide rate is up, the birth rate is down, in spite of anything we can do. You've seen the figures: we're riding a curve that ends in extinction fifty years from now. "They'll live, and we'll die, because they're a superior race. We're a million years too far back even to understand what they are or where they came from. Besides them, we're apes. There's only one answer." She was crying now, silently, with great racking sobs that shook her slender body. But he went remorselessly on. "Out there, in space, the cosmics change unshielded life. They make tentacles out of arms; or scales out of hair; or twelve toes, or a dozen ears—or a better brain. Out of those millions of possible mutations, there's one that will save the human race. We can't fight them , but a superman could. That's our only chance. Lorelei—darling—don't you see that?" She choked, "But why can't you take me along?" He stared unseeingly past her wet, upturned face. "You know why," he said bitterly. "Those rays are strong. They don't only work on embryos; they change adult life forms, too. I have one chance in seven of staying alive. You'd have one chance in a million of staying beautiful. I couldn't stand that. I'd kill myself, and then humanity would die, too. You'd be their murderer." Her sobs gradually died away. She straightened slowly until he no longer had to support her, but all the vitality and resilience was gone out of her body. "All right," she said in a lifeless voice. "You'll come back, Peter." He turned away suddenly, not trusting himself to kiss her goodbye. A line from an old film kept echoing through his head. " They'll come back—but not as boys !" We'll come back, but not as men. We'll come back, but not as elephants. We'll come back, but not as octopi. He was trembling violently. He ran the last few steps, stumbled into the airlock, and pressed the stud that would seal the door behind him. We'll come back.... He heard the massive disk sink home, closing him off. Then he sank down on the floor of the airlock and put his head in shaking hands. After a while he roused himself, closed the inner door of the lock behind him, and walked down the long corridor into the control chamber. The shining banks of keys were there, waiting for his touch; he slumped down before them and listlessly closed the contact of the visiplate. He swung its field slowly, scanning for the last time the bare walls of the underground chamber, making sure that all the spectators had retired out of the way of the blast. Then his clawed fingers poised over the keys, hovered a moment, and thrust down. Acceleration pressed him deep into his chair. In the visiplate, the heavy doors that closed the tunnel above him flashed back, one by one. The energy-charged screen flickered off to let him pass, and closed smoothly behind him. The last doors, cleverly camouflaged, slipped back into place and then dwindled in the distance. It was done. He flashed on out, past the moon, past Mars, over the asteroid belt. The days merged into weeks, then months, and finally, far out, The Avenger curved into an orbit and held it. The great motors died, and the silence pressed in about him. Already he could feel the invisible rays burning resistlessly through his flesh as if it were water, shifting the cells of his body, working its slow, monstrous alchemy upon him. Peter waited until the changes were unmistakably evident in his skin and hair, and then he smashed all the mirrors in the ship. The embryos were pulsing with unnatural life, even in the suspended animation of their crystal cells. One by one he allowed them to mature, and after weeks or years destroyed the monstrosities that came from the incubators. Time went by, meaninglessly. He ate when he was hungry, slept when his driving purpose let him, and worked unceasingly, searching for the million-to-one chance. He stared sometimes through changed eyes at the tiny blue star that was Earth, wondering if the race he had left behind still burrowed in its worm-tunnels, digging deeper and deeper away from the sunlight. But after a time he ceased even to wonder. And one changeling-child he did not destroy. He fed knowledge to its eager brain, and watched it through the swift years, with a dawning hope.... Peter closed the diary. "The rest you know, Robert," he said. "Yes," I told him. "I was that child. I am the millionth mutation you were searching for." His eyes glowed suddenly in their misshapen sockets. "You are. Your brain is as superior to mine as mine is to an anthropoid's. You solve instinctively problems that would take our mechanical computers hours of work. You are a superman." "I am without your imperfections," I said, flexing my arms. He rose and strode nervously over to the window. I watched him as he stood there, outlined against the blazing galaxies. He had changed but little in the years that I had known him. His lank gray hair straggled over his sunken eyes; his cheeks were blobbed with excresences of flesh; one corner of his mouth was drawn up in a perpetual grin. He had a tiny sixth finger on his left hand. He turned again, and I saw the old scar on his cheek where I had once accidentally drawn one of my talons across his face. "And now," he said softly, "we will go home. I've waited so long—keeping the control chamber and the engine room locked away from you, not telling you, even, about Earth until now—because I had to be sure. But now, the waiting is over. "They're still there, I'm sure of it—the people, and the Invaders. You can kill the Invaders, Robert." He looked at me, a little oddly, almost as if he had some instinctive knowledge of what was to come. But he went on swiftly, "On Earth we had a saying: 'Fight fire with fire.' That is the way it will be with you. You are completely, coldly logical, just as they are. You can understand them, and so you can conquer them." I said, "That is the reason why we will not go back to Earth." He stared at me, his jaw slack, his hands trembling. "What—what did you say?" I repeated it patiently. "But why?" he cried, sinking down into the chair before me. In an instant all the joy had gone out of him. I could not understand his suffering, but I could recognize it. "You yourself have said it," I told him. "I am a being of logic, just as the beings who have invaded your planet are. I do not comprehend the things which you call hate, fear, joy and love, as they do not. If I went to Earth, I would use your people to further my knowledge, just as the invaders do. I would have no reason to kill the invaders. They are more nearly kin to me than your people." Peter's eyes were dull, his limbs slumped. For a moment I thought that the shock had deranged his mind. His voice trembled when he said, "But if I ask you to kill them, and not my people?" "To do so would be illogical." He waved his hands helplessly. "Gratitude?" he muttered. "No, you don't understand that, either." Then he cried suddenly, "But I am your friend, Robert!" "I do not understand 'friend,'" I said. I did understand "gratitude," a little. It was a reciprocal arrangement: I did what Peter wished, so long as I did not actively want to do otherwise, because he had done things for me. Very well, then we must not go back. It was very simple, but I knew that he could not comprehend it. I tried to explain it to him, however. But he only stared at me, with an expression on his face that I had never seen there before, and that, somehow, I did not like to see. It was disquieting, and so I hastened to the end that I knew was inevitable.
|
A. He recognizes that he will be a changed, mutated man when he returns. He literally will come back "not as a boy."
|
What equations are used for the trainable gating network?
|
### Conditional Computation
Exploiting scale in both training data and model size has been central to the success of deep learning. When datasets are sufficiently large, increasing the capacity (number of parameters) of neural networks can give much better prediction accuracy. This has been shown in domains such as text BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , images BIBREF4 , BIBREF5 , and audio BIBREF6 , BIBREF7 . For typical deep learning models, where the entire model is activated for every example, this leads to a roughly quadratic blow-up in training costs, as both the model size and the number of training examples increase. Unfortunately, the advances in computing power and distributed computation fall short of meeting such demand. Various forms of conditional computation have been proposed as a way to increase model capacity without a proportional increase in computational costs BIBREF8 , BIBREF9 , BIBREF10 , BIBREF11 , BIBREF12 , BIBREF13 , BIBREF14 . In these schemes, large parts of a network are active or inactive on a per-example basis. The gating decisions may be binary or sparse and continuous, stochastic or deterministic. Various forms of reinforcement learning and back-propagation are proposed for trarining the gating decisions. While these ideas are promising in theory, no work to date has yet demonstrated massive improvements in model capacity, training time, or model quality. We blame this on a combination of the following challenges: Modern computing devices, especially GPUs, are much faster at arithmetic than at branching. Most of the works above recognize this and propose turning on/off large chunks of the network with each gating decision. Large batch sizes are critical for performance, as they amortize the costs of parameter transfers and updates. Conditional computation reduces the batch sizes for the conditionally active chunks of the network. Network bandwidth can be a bottleneck. A cluster of GPUs may have computational power thousands of times greater than the aggregate inter-device network bandwidth. To be computationally efficient, the relative computational versus network demands of an algorithm must exceed this ratio. Embedding layers, which can be seen as a form of conditional computation, are handicapped by this very problem. Since the embeddings generally need to be sent across the network, the number of (example, parameter) interactions is limited by network bandwidth instead of computational capacity. Depending on the scheme, loss terms may be necessary to achieve the desired level of sparsity per-chunk and/or per example. BIBREF13 use three such terms. These issues can affect both model quality and load-balancing. Model capacity is most critical for very large data sets. The existing literature on conditional computation deals with relatively small image recognition data sets consisting of up to 600,000 images. It is hard to imagine that the labels of these images provide a sufficient signal to adequately train a model with millions, let alone billions of parameters. In this work, we for the first time address all of the above challenges and finally realize the promise of conditional computation. We obtain greater than 1000x improvements in model capacity with only minor losses in computational efficiency and significantly advance the state-of-the-art results on public language modeling and translation data sets. ### Our Approach: The Sparsely-Gated Mixture-of-Experts Layer
Our approach to conditional computation is to introduce a new type of general purpose neural network component: a Sparsely-Gated Mixture-of-Experts Layer (MoE). The MoE consists of a number of experts, each a simple feed-forward neural network, and a trainable gating network which selects a sparse combination of the experts to process each input (see Figure FIGREF8 ). All parts of the network are trained jointly by back-propagation. While the introduced technique is generic, in this paper we focus on language modeling and machine translation tasks, which are known to benefit from very large models. In particular, we apply a MoE convolutionally between stacked LSTM layers BIBREF15 , as in Figure FIGREF8 . The MoE is called once for each position in the text, selecting a potentially different combination of experts at each position. The different experts tend to become highly specialized based on syntax and semantics (see Appendix SECREF84 Table TABREF92 ). On both language modeling and machine translation benchmarks, we improve on best published results at a fraction of the computational cost. ### Related work on Mixtures of Experts
Since its introduction more than two decades ago BIBREF16 , BIBREF17 , the mixture-of-experts approach has been the subject of much research. Different types of expert architectures hae been proposed such as SVMs BIBREF18 , Gaussian Processes BIBREF19 , BIBREF20 , BIBREF21 , Dirichlet Processes BIBREF22 , and deep networks. Other work has focused on different expert configurations such as a hierarchical structure BIBREF23 , infinite numbers of experts BIBREF24 , and adding experts sequentially BIBREF25 . BIBREF26 suggest an ensemble model in the format of mixture of experts for machine translation. The gating network is trained on a pre-trained ensemble NMT model. The works above concern top-level mixtures of experts. The mixture of experts is the whole model. BIBREF10 introduce the idea of using multiple MoEs with their own gating networks as parts of a deep model. It is intuitive that the latter approach is more powerful, since complex problems may contain many sub-problems each requiring different experts. They also allude in their conclusion to the potential to introduce sparsity, turning MoEs into a vehicle for computational computation. Our work builds on this use of MoEs as a general purpose neural network component. While BIBREF10 uses two stacked MoEs allowing for two sets of gating decisions, our convolutional application of the MoE allows for different gating decisions at each position in the text. We also realize sparse gating and demonstrate its use as a practical way to massively increase model capacity. ### The Structure of the Mixture-of-Experts layer
The Mixture-of-Experts (MoE) layer consists of a set of INLINEFORM0 “expert networks" INLINEFORM1 , and a “gating network" INLINEFORM2 whose output is a sparse INLINEFORM3 -dimensional vector. Figure FIGREF8 shows an overview of the MoE module. The experts are themselves neural networks, each with their own parameters. Although in principle we only require that the experts accept the same sized inputs and produce the same-sized outputs, in our initial investigations in this paper, we restrict ourselves to the case where the models are feed-forward networks with identical architectures, but with separate parameters. Let us denote by INLINEFORM0 and INLINEFORM1 the output of the gating network and the output of the INLINEFORM2 -th expert network for a given input INLINEFORM3 . The output INLINEFORM4 of the MoE module can be written as follows: DISPLAYFORM0 We save computation based on the sparsity of the output of INLINEFORM0 . Wherever INLINEFORM1 , we need not compute INLINEFORM2 . In our experiments, we have up to thousands of experts, but only need to evaluate a handful of them for every example. If the number of experts is very large, we can reduce the branching factor by using a two-level hierarchical MoE. In a hierarchical MoE, a primary gating network chooses a sparse weighted combination of “experts", each of which is itself a secondary mixture-of-experts with its own gating network. In the following we focus on ordinary MoEs. We provide more details on hierarchical MoEs in Appendix SECREF60 . Our implementation is related to other models of conditional computation. A MoE whose experts are simple weight matrices is similar to the parameterized weight matrix proposed in BIBREF12 . A MoE whose experts have one hidden layer is similar to the block-wise dropout described in BIBREF13 , where the dropped-out layer is sandwiched between fully-activated layers. ### Gating Network
A simple choice of non-sparse gating function BIBREF17 is to multiply the input by a trainable weight matrix INLINEFORM0 and then apply the INLINEFORM1 function. DISPLAYFORM0 We add two components to the Softmax gating network: sparsity and noise. Before taking the softmax function, we add tunable Gaussian noise, then keep only the top k values, setting the rest to INLINEFORM0 (which causes the corresponding gate values to equal 0). The sparsity serves to save computation, as described above. While this form of sparsity creates some theoretically scary discontinuities in the output of gating function, we have not yet observed this to be a problem in practice. The noise term helps with load balancing, as will be discussed in Appendix SECREF51 . The amount of noise per component is controlled by a second trainable weight matrix INLINEFORM1 . DISPLAYFORM0 DISPLAYFORM1 We train the gating network by simple back-propagation, along with the rest of the model. If we choose INLINEFORM0 , the gate values for the top k experts have nonzero derivatives with respect to the weights of the gating network. This type of occasionally-sensitive behavior is described in BIBREF9 with respect to noisy rectifiers. Gradients also back-propagate through the gating network to its inputs. Our method differs here from BIBREF13 who use boolean gates and a REINFORCE-style approach to train the gating network. ### The Shrinking Batch Problem
On modern CPUs and GPUs, large batch sizes are necessary for computational efficiency, so as to amortize the overhead of parameter loads and updates. If the gating network chooses INLINEFORM0 out of INLINEFORM1 experts for each example, then for a batch of INLINEFORM2 examples, each expert receives a much smaller batch of approximately INLINEFORM3 examples. This causes a naive MoE implementation to become very inefficient as the number of experts increases. The solution to this shrinking batch problem is to make the original batch size as large as possible. However, batch size tends to be limited by the memory necessary to store activations between the forwards and backwards passes. We propose the following techniques for increasing the batch size: In a conventional distributed training setting, multiple copies of the model on different devices asynchronously process distinct batches of data, and parameters are synchronized through a set of parameter servers. In our technique, these different batches run synchronously so that they can be combined for the MoE layer. We distribute the standard layers of the model and the gating network according to conventional data-parallel schemes, but keep only one shared copy of each expert. Each expert in the MoE layer receives a combined batch consisting of the relevant examples from all of the data-parallel input batches. The same set of devices function as data-parallel replicas (for the standard layers and the gating networks) and as model-parallel shards (each hosting a subset of the experts). If the model is distributed over INLINEFORM0 devices, and each device processes a batch of size INLINEFORM1 , each expert receives a batch of approximately INLINEFORM2 examples. Thus, we achieve a factor of INLINEFORM3 improvement in expert batch size. In the case of a hierarchical MoE (Section SECREF60 ), the primary gating network employs data parallelism, and the secondary MoEs employ model parallelism. Each secondary MoE resides on one device. This technique allows us to increase the number of experts (and hence the number of parameters) by proportionally increasing the number of devices in the training cluster. The total batch size increases, keeping the batch size per expert constant. The memory and bandwidth requirements per device also remain constant, as do the step times, as does the amount of time necessary to process a number of training examples equal to the number of parameters in the model. It is our goal to train a trillion-parameter model on a trillion-word corpus. We have not scaled our systems this far as of the writing of this paper, but it should be possible by adding more hardware. In our language models, we apply the same MoE to each time step of the previous layer. If we wait for the previous layer to finish, we can apply the MoE to all the time steps together as one big batch. Doing so increases the size of the input batch to the MoE layer by a factor of the number of unrolled time steps. We suspect that even more powerful models may involve applying a MoE recurrently. For example, the weight matrices of a LSTM or other RNN could be replaced by a MoE. Sadly, such models break the convolutional trick from the last paragraph, since the input to the MoE at one timestep depends on the output of the MoE at the previous timestep. BIBREF27 describe a technique for drastically reducing the number of stored activations in an unrolled RNN, at the cost of recomputing forward activations. This would allow for a large increase in batch size. ### Network Bandwidth
Another major performance concern in distributed computing is network bandwidth. Since the experts are stationary (see above) and the number of gating parameters is small, most of the communication involves sending the inputs and outputs of the experts across the network. To maintain computational efficiency, the ratio of an expert's computation to the size of its input and output must exceed the ratio of computational to network capacity of the computing device. For GPUs, this may be thousands to one. In our experiments, we use experts with one hidden layer containing thousands of RELU-activated units. Since the weight matrices in the expert have sizes INLINEFORM0 _ INLINEFORM1 _ INLINEFORM2 and INLINEFORM3 _ INLINEFORM4 _ INLINEFORM5 , the ratio of computation to input and output is equal to the size of the hidden layer. Conveniently, we can increase computational efficiency simply by using a larger hidden layer, or more hidden layers. ### Balancing Expert Utilization
We have observed that the gating network tends to converge to a state where it always produces large weights for the same few experts. This imbalance is self-reinforcing, as the favored experts are trained more rapidly and thus are selected even more by the gating network. BIBREF10 describe the same phenomenon, and use a hard constraint at the beginning of training to avoid this local minimum. BIBREF13 include a soft constraint on the batch-wise average of each gate. We take a soft constraint approach. We define the importance of an expert relative to a batch of training examples to be the batchwise sum of the gate values for that expert. We define an additional loss INLINEFORM0 , which is added to the overall loss function for the model. This loss is equal to the square of the coefficient of variation of the set of importance values, multiplied by a hand-tuned scaling factor INLINEFORM1 . This additional loss encourages all experts to have equal importance. DISPLAYFORM0 DISPLAYFORM1 While this loss function can ensure equal importance, experts may still receive very different numbers of examples. For example, one expert may receive a few examples with large weights, and another may receive many examples with small weights. This can cause memory and performance problems on distributed hardware. To solve this problem, we introduce a second loss function, INLINEFORM0 , which ensures balanced loads. Appendix SECREF51 contains the definition of this function, along with experimental results. ### 1 Billion Word Language Modeling Benchmark
This dataset, introduced by BIBREF28 consists of shuffled unique sentences from news articles, totaling approximately 829 million words, with a vocabulary of 793,471 words. The best previously published results BIBREF2 use models consisting of one or more stacked Long Short-Term Memory (LSTM) layers BIBREF15 , BIBREF29 . The number of parameters in the LSTM layers of these models vary from 2 million to 151 million. Quality increases greatly with parameter count, as do computational costs. Results for these models form the top line of Figure FIGREF32 -right. Our models consist of two stacked LSTM layers with a MoE layer between them (see Figure FIGREF8 ). We vary the sizes of the layers and the number of experts. For full details on model architecture, training regimen, additional baselines and results, see Appendix SECREF65 . To investigate the effects of adding capacity, we trained a series of MoE models all with roughly equal computational costs: about 8 million multiply-and-adds per training example per timestep in the forwards pass, excluding the softmax layer. We call this metric (ops/timestep). We trained models with flat MoEs containing 4, 32, and 256 experts, and models with hierarchical MoEs containing 256, 1024, and 4096 experts. Each expert had about 1 million parameters. For all the MoE layers, 4 experts were active per input. The results of these models are shown in Figure FIGREF32 -left. The model with 4 always-active experts performed (unsurprisingly) similarly to the computationally-matched baseline models, while the largest of the models (4096 experts) achieved an impressive 24% lower perplexity on the test set. In addition to the largest model from the previous section, we trained two more MoE models with similarly high capacity (4 billion parameters), but higher computation budgets. These models had larger LSTMs, and fewer but larger and experts. Details can be found in Appendix UID77 . Results of these three models form the bottom line of Figure FIGREF32 -right. Table TABREF33 compares the results of these models to the best previously-published result on this dataset . Even the fastest of these models beats the best published result (when controlling for the number of training epochs), despite requiring only 6% of the computation. We trained our models using TensorFlow BIBREF30 on clusters containing 16-32 Tesla K40 GPUs. For each of our models, we determine computational efficiency in TFLOPS/GPU by dividing the number of floating point operations required to process one training batch by the observed step time and the number of GPUs in the cluster. The operation counts used here are higher than the ones we report in our ops/timestep numbers in that we include the backwards pass, we include the importance-sampling-based training of the softmax layer, and we count a multiply-and-add as two separate operations. For all of our MoE models, the floating point operations involved in the experts represent between 37% and 46% of the total. For our baseline models wtih no MoE, observed computational efficiency ranged from 1.07-1.29 TFLOPS/GPU. For our low-computation MoE models, computation efficiency ranged from 0.74-0.90 TFLOPS/GPU, except for the 4-expert model which did not make full use of the available parallelism. Our highest-computation MoE model was more efficient at 1.56 TFLOPS/GPU, likely due to the larger matrices. These numbers represent a significant fraction of the theoretical maximum of 4.29 TFLOPS/GPU claimed by NVIDIA. Detailed results are in Appendix SECREF65 , Table TABREF76 . ### 100 Billion Word Google News Corpus
On the 1-billion-word corpus, adding additional capacity seems to produce diminishing returns as the number of parameters in the MoE layer exceeds 1 billion, as can be seen in Figure FIGREF32 -left. We hypothesized that for a larger training set, even higher capacities would produce significant quality improvements. We constructed a similar training set consisting of shuffled unique sentences from Google's internal news corpus, totalling roughly 100 billion words. Similarly to the previous section, we tested a series of models with similar computational costs of about 8 million ops/timestep. In addition to a baseline LSTM model, we trained models augmented with MoE layers containing 32, 256, 1024, 4096, 16384, 65536, and 131072 experts. This corresponds to up to 137 billion parameters in the MoE layer. Details on architecture, training, and results are given in Appendix SECREF78 . Figure FIGREF37 shows test perplexity as a function of capacity after training on 10 billion words (top line) and 100 billion words (bottom line). When training over the full 100 billion words, test perplexity improves significantly up to 65536 experts (68 billion parameters), dropping 39% lower than the computationally matched baseline, but degrades at 131072 experts, possibly a result of too much sparsity. The widening gap between the two lines demonstrates (unsurprisingly) that increased model capacity helps more on larger training sets. Even at 65536 experts (99.994% layer sparsity), computational efficiency for the model stays at a respectable 0.72 TFLOPS/GPU. ### Machine Translation (Single Language Pair)
Our model was a modified version of the GNMT model described in BIBREF3 . To reduce computation, we decreased the number of LSTM layers in the encoder and decoder from 9 and 8 to 3 and 2 respectively. We inserted MoE layers in both the encoder (between layers 2 and 3) and the decoder (between layers 1 and 2). Each MoE layer contained up to 2048 experts each with about two million parameters, adding a total of about 8 billion parameters to the models. Further details on model architecture, testing procedure and results can be found in Appendix SECREF84 . We benchmarked our method on the WMT'14 En INLINEFORM0 Fr and En INLINEFORM1 De corpora, whose training sets have 36M sentence pairs and 5M sentence pairs, respectively. The experimental protocols were also similar to those in BIBREF3 : newstest2014 was used as the test set to compare against previous work BIBREF31 , BIBREF32 , BIBREF3 , while the combination of newstest2012 and newstest2013 was used as the development set. We also tested the same model on a Google's Production English to French data. Tables TABREF42 , TABREF43 , and TABREF44 show the results of our largest models, compared with published results. Our approach achieved BLEU scores of 40.56 and 26.03 on the WMT'14 En INLINEFORM0 Fr and En INLINEFORM1 De benchmarks. As our models did not use RL refinement, these results constitute significant gains of 1.34 and 1.12 BLEU score on top of the strong baselines in BIBREF3 . The perplexity scores are also better. On the Google Production dataset, our model achieved 1.01 higher test BLEU score even after training for only one sixth of the time. ### Multilingual Machine Translation
BIBREF35 train a single GNMT BIBREF3 model on a very large combined dataset of twelve language pairs. Results are somewhat worse than those for 12 separately trained single-pair GNMT models. This is not surprising, given that the twelve models have 12 times the capacity and twelve times the aggregate training of the one model. We repeat this experiment with a single MoE-augmented model. See Appendix SECREF84 for details on model architecture. We train our model on the same dataset as BIBREF35 and process the same number of training examples (about 3 billion sentence pairs). Our training time was shorter due to the lower computational budget of our model. Results for the single-pair GNMT models, the multilingual GNMT model and the multilingual MoE model are given in Table TABREF50 . The MoE model achieves 19% lower perplexity on the dev set than the multilingual GNMT model. On BLEU score, the MoE model significantly beats the multilingual GNMT model on 11 of the 12 language pairs (by as much as 5.84 points), and even beats the monolingual GNMT models on 8 of 12 language pairs. The poor performance on English INLINEFORM0 Korean seems to be a result of severe overtraining, as for the rarer language pairs a small number of real examples were highly oversampled in the training corpus. ### Conclusion
This work is the first to demonstrate major wins from conditional computation in deep networks. We carefully identified the design considerations and challenges of conditional computing and addressed them with a combination of algorithmic and engineering solutions. While we focused on text, conditional computation may help in other domains as well, provided sufficiently large training sets. We look forward to seeing many novel implementations and applications of conditional computation in the years to come. ### Appendices
tocsectionAppendices ### Load-Balancing Loss
As discussed in section SECREF4 , for load-balancing purposes, we want to define an additional loss function to encourage experts to receive roughly equal numbers of training examples. Unfortunately, the number of examples received by an expert is a discrete quantity, so it can not be used in back-propagation. Instead, we define a smooth estimator INLINEFORM0 of the number of examples assigned to each expert for a batch INLINEFORM1 of inputs. The smoothness allows us to back-propagate gradients through the estimator. This is the purpose of the noise term in the gating function. We define INLINEFORM2 as the probability that INLINEFORM3 is nonzero, given a new random choice of noise on element INLINEFORM4 , but keeping the already-sampled choices of noise on the other elements. To compute INLINEFORM5 , we note that the INLINEFORM6 is nonzero if and only if INLINEFORM7 is greater than the INLINEFORM8 -greatest element of INLINEFORM9 excluding itself. The probability works out to be: DISPLAYFORM0 Where INLINEFORM0 means the kth highest component of INLINEFORM1 , excluding component INLINEFORM2 . Simplifying, we get: DISPLAYFORM0 Where INLINEFORM0 is the CDF of the standard normal distribution. DISPLAYFORM0 We can now define the load loss to be the square of the coefficient of variation of the load vector, multiplied by a hand-tuned scaling factor INLINEFORM0 . DISPLAYFORM0 To avoid out-of-memory errors, we need to initialize the network in a state of approximately equal expert load (since the soft constraints need some time to work). To accomplish this, we initialize the matrices INLINEFORM0 and INLINEFORM1 to all zeros, which yields no signal and some noise. We trained a set of models with identical architecture (the MoE-256 model described in Appendix SECREF65 ), using different values of INLINEFORM0 and INLINEFORM1 . We trained each model for 10 epochs, then measured perplexity on the test set. We also measured the coefficients of variation in INLINEFORM2 and INLINEFORM3 , as well as ratio of the load on the most overloaded expert to the average load. This last value is significant for load balancing purposes on distributed hardware. All of these metrics were averaged over several training batches. Results are reported in Table TABREF58 . All the combinations containing at least one the two losses led to very similar model quality, where having no loss was much worse. Models with higher values of INLINEFORM0 had lower loads on the most overloaded expert. ### Hierachical Mixture of Experts
If the number of experts is very large, we can reduce the branching factor by using a two-level hierarchical MoE. In a hierarchical MoE, a primary gating network chooses a sparse weighted combination of “experts", each of which is itself a secondary mixture-of-experts with its own gating network. If the hierarchical MoE consists of INLINEFORM0 groups of INLINEFORM1 experts each, we denote the primary gating network by INLINEFORM2 , the secondary gating networks by INLINEFORM3 , and the expert networks by INLINEFORM4 . The output of the MoE is given by: DISPLAYFORM0 Our metrics of expert utilization change to the following: DISPLAYFORM0 DISPLAYFORM1 INLINEFORM0 and INLINEFORM1 deonte the INLINEFORM2 functions for the primary gating network and INLINEFORM3 secondary gating network respectively. INLINEFORM4 denotes the subset of INLINEFORM5 for which INLINEFORM6 . It would seem simpler to let INLINEFORM0 , but this would not have a gradient with respect to the primary gating network, so we use the formulation above. ### 1 Billion Word Language Modeling Benchmark - Experimental Details
Our model consists of five layers: a word embedding layer, a recurrent Long Short-Term Memory (LSTM) layer BIBREF15 , BIBREF29 , a MoE layer, a second LSTM layer, and a softmax layer. The dimensionality of the embedding layer, the number of units in each LSTM layer, and the input and output dimensionality of the MoE layer are all equal to 512. For every layer other than the softmax, we apply drouput BIBREF43 to the layer output, dropping each activation with probability INLINEFORM0 , otherwise dividing by INLINEFORM1 . After dropout, the output of the previous layer is added to the layer output. This residual connection encourages gradient flow BIBREF37 . Each expert in the MoE layer is a feed forward network with one ReLU-activated hidden layer of size 1024 and an output layer of size 512. Thus, each expert contains INLINEFORM0 parameters. The output of the MoE layer is passed through a sigmoid function before dropout. We varied the number of experts between models, using ordinary MoE layers with 4, 32 and 256 experts and hierarchical MoE layers with 256, 1024 and 4096 experts. We call the resulting models MoE-4, MoE-32, MoE-256, MoE-256-h, MoE-1024-h and MoE-4096-h. For the hierarchical MoE layers, the first level branching factor was 16, corresponding to the number of GPUs in our cluster. We use Noisy-Top-K Gating (see Section UID14 ) with INLINEFORM1 for the ordinary MoE layers and INLINEFORM2 at each level of the hierarchical MoE layers. Thus, each example is processed by exactly 4 experts for a total of 4M ops/timestep. The two LSTM layers contribute 2M ops/timestep each for the desired total of 8M. The MoE-4 model does not employ sparsity, since all 4 experts are always used. In addition, we trained four more computationally-matched baseline models with no sparsity: MoE-1-Wide: The MoE layer consists of a single "expert" containing one ReLU-activated hidden layer of size 4096. MoE-1-Deep: The MoE layer consists of a single "expert" containing four ReLU-activated hidden layers, each with size 1024. 4xLSTM-512: We replace the MoE layer with two additional 512-unit LSTM layers. LSTM-2048-512: The model contains one 2048-unit LSTM layer (and no MoE). The output of the LSTM is projected down to 512 dimensions BIBREF41 . The next timestep of the LSTM receives the projected output. This is identical to one of the models published in BIBREF2 . We re-ran it to account for differences in training regimen, and obtained results very similar to the published ones. The models were trained on a cluster of 16 K40 GPUs using the synchronous method described in Section SECREF3 . Each batch consisted of a set of sentences totaling roughly 300,000 words. In the interest of time, we limited training to 10 epochs, (27,000 steps). Training took 12-16 hours for all models, except for MoE-4, which took 18 hours (since all the expert computation was performed on only 4 of 16 GPUs). We used the Adam optimizer BIBREF39 . The base learning rate was increased linearly for the first 1000 training steps, and decreased after that so as to be proportional to the inverse square root of the step number. The Softmax output layer was trained efficiently using importance sampling similarly to the models in BIBREF2 . For each model, we performed a hyper-parmeter search to find the best dropout probability, in increments of 0.1. To ensure balanced expert utilization we set INLINEFORM0 and INLINEFORM1 , as described in Section SECREF4 and Appendix SECREF51 . We evaluate our model using perplexity on the holdout dataset, used by BIBREF28 , BIBREF2 . We follow the standard procedure and sum over all the words including the end of sentence symbol. Results are reported in Table TABREF76 . For each model, we report the test perplexity, the computational budget, the parameter counts, the value of INLINEFORM0 , and the computational efficiency. We ran two additional models (MoE-34M and MoE-143M) to investigate the effects of adding more computation in the presence of a large MoE layer. These models have computation budgets of 34M and 143M ops/timestep. Similar to the models above, these models use a MoE layer between two LSTM layers. The dimensionality of the embedding layer, and the input and output dimensionality of the MoE layer are set to 1024 instead of 512. For MoE-34M, the LSTM layers have 1024 units. For MoE-143M, the LSTM layers have 4096 units and an output projection of size 1024 BIBREF41 . MoE-34M uses a hierarchical MoE layer with 1024 experts, each with a hidden layer of size 2048. MoE-143M uses a hierarchical MoE layer with 256 experts, each with a hidden layer of size 8192. Both models have 4B parameters in the MoE layers. We searched for the best INLINEFORM0 for each model, and trained each model for 10 epochs. The two models achieved test perplexity of INLINEFORM0 and INLINEFORM1 respectively, showing that even in the presence of a large MoE, more computation is still useful. Results are reported at the bottom of Table TABREF76 . The larger of the two models has a similar computational budget to the best published model from the literature, and training times are similar. Comparing after 10 epochs, our model has a lower test perplexity by INLINEFORM2 . ### 100 Billion Word Google News Corpus - Experimental Details
The models are similar in structure to the 8-million-operations-per-timestep models described in the previous section. We vary the number of experts between models, using an ordinary MoE layer with 32 experts and hierarchical MoE layers with 256, 1024, 4096, 16384, 65536 and 131072 experts. For the hierarchical MoE layers, the first level branching factors are 32, 32, 64, 128, 256 and 256, respectively. Models are trained on a cluster of 32 Tesla K40 GPUs, except for the last two models, which are trained on clusters of 64 and 128 GPUs so as to have enough memory for all the parameters. For all models, training batch sizes are approximately 2.5 million words. Models are trained once-through over about 100 billion words. We implement several memory optimizations in order to fit up to 1 billion parameters per GPU. First, we do not store the activations of the hidden layers of the experts, but instead recompute them on the backwards pass. Secondly, we modify the optimizer on the expert parameters to require less auxiliary storage: The Adam optimizer BIBREF39 keeps first and second moment estimates of the per-parameter gradients. This triples the required memory. To avoid keeping a first-moment estimator, we set INLINEFORM0 . To reduce the size of the second moment estimator, we replace it with a factored approximation. For a matrix of parameters, instead of maintaining a full matrix of second-moment estimators, we maintain vectors of row-wise and column-wise averages of that matrix. At each step, the matrix of estimators is taken to be the outer product of those two vectors divided by the mean of either one. This technique could similarly be applied to Adagrad BIBREF36 . We evaluate our model using perplexity on a holdout dataset. Results are reported in Table TABREF81 . Perplexity after 100 billion training words is 39% lower for the 68-billion-parameter MoE model than for the baseline model. It is notable that the measured computational efficiency of the largest model (0.30 TFLOPS/GPU) is very low compared to the other models. This is likely a result of the fact that, for purposes of comparison to the other models, we did not increase the training batch size proportionally to the number of GPUs. For comparison, we include results for a computationally matched baseline model consisting of 4 LSTMs, and for an unpruned 5-gram model with Kneser-Ney smoothing BIBREF40 . ### Machine Translation - Experimental Details
Our model is a modified version of the GNMT model described in BIBREF3 . To reduce computation, we decrease the number of LSTM layers in the encoder and decoder from 9 and 8 to 3 and 2 respectively. We insert MoE layers in both the encoder (between layers 2 and 3) and the decoder (between layers 1 and 2). We use an attention mechanism between the encoder and decoder, with the first decoder LSTM receiving output from and providing input for the attention . All of the layers in our model have input and output dimensionality of 512. Our LSTM layers have 2048 hidden units, with a 512-dimensional output projection. We add residual connections around all LSTM and MoE layers to encourage gradient flow BIBREF37 . Similar to GNMT, to effectively deal with rare words, we used sub-word units (also known as “wordpieces") BIBREF42 for inputs and outputs in our system. We use a shared source and target vocabulary of 32K wordpieces. We also used the same beam search technique as proposed in BIBREF3 . We train models with different numbers of experts in the MoE layers. In addition to a baseline model with no MoE layers, we train models with flat MoE layers containing 32 experts, and models with hierarchical MoE layers containing 512 and 2048 experts. The flat MoE layers use INLINEFORM0 and the hierarchical MoE models use INLINEFORM1 at each level of the gating network. Thus, each input is processed by exactly 4 experts in each MoE layer. Each expert in the MoE layer is a feed forward network with one hidden layer of size 2048 and ReLU activation. Thus, each expert contains INLINEFORM2 parameters. The output of the MoE layer is passed through a sigmoid function. We use the strictly-balanced gating function described in Appendix SECREF93 . We used the same model architecture as for the single-language-pair models, with the following exceptions: We used noisy-top-k gating as described in Section UID14 , not the scheme from Appendix SECREF93 . The MoE layers in the encoder and decoder are non-hierarchical MoEs with INLINEFORM0 experts, and INLINEFORM1 . Each expert has a larger hidden layer of size 8192. This doubles the amount of computation in the MoE layers, raising the computational budget of the entire model from 85M to 102M ops/timestep. We trained our networks using the Adam optimizer BIBREF39 . The base learning rate was increased linearly for the first 2000 training steps, held constant for an additional 8000 steps, and decreased after that so as to be proportional to the inverse square root of the step number. For the single-language-pair models, similarly to BIBREF3 , we applied dropout BIBREF43 to the output of all embedding, LSTM and MoE layers, using INLINEFORM0 . Training was done synchronously on a cluster of up to 64 GPUs as described in section SECREF3 . Each training batch consisted of a set of sentence pairs containing roughly 16000 words per GPU. To ensure balanced expert utilization we set INLINEFORM0 and INLINEFORM1 , as described in Section SECREF4 and Appendix SECREF51 . We evaluated our models using the perplexity and the standard BLEU score metric. We reported tokenized BLEU score as computed by the multi-bleu.pl script, downloaded from the public implementation of Moses (on Github), which was also used in BIBREF31 . Tables TABREF42 , TABREF43 and TABREF44 in Section SECREF39 show comparisons of our results to other published methods. Figure FIGREF91 shows test perplexity as a function of number of words in the (training data's) source sentences processed for models with different numbers of experts. As can be seen from the Figure, as we increased the number of experts to approach 2048, the test perplexity of our model continued to improve. We found that the experts indeed become highly specialized by syntax and/or semantics, as can be seen in Table TABREF92 . For example, one expert is used when the indefinite article “a" introduces the direct object in a verb phrase indicating importance or leadership. ### Strictly Balanced Gating
Due to some peculiarities in our infrastructure which have since been fixed, at the time we ran some of the machine translation experiments, our models ran faster if every expert received exactly the same batch size. To accommodate this, we used a different gating function which we describe below. Recall that we define the softmax gating function to be: DISPLAYFORM0 To obtain a sparse gating vector, we multiply INLINEFORM0 component-wise with a sparse mask INLINEFORM1 and normalize the output. The mask itself is a function of INLINEFORM2 and specifies which experts are assigned to each input example: DISPLAYFORM0 To implement top-k gating in this formulation, we would let INLINEFORM0 , where: DISPLAYFORM0 To force each expert to receive the exact same number of examples, we introduce an alternative mask function, INLINEFORM0 , which operates over batches of input vectors. Instead of keeping the top INLINEFORM1 values per example, we keep the top INLINEFORM2 values per expert across the training batch, where INLINEFORM3 , so that each example is sent to an average of INLINEFORM4 experts. DISPLAYFORM0 As our experiments suggest and also observed in BIBREF38 , using a batchwise function during training (such as INLINEFORM0 ) requires modifications to the inference when we may not have a large batch of examples. Our solution to this is to train a vector INLINEFORM1 of per-expert threshold values to approximate the effects of the batchwise mask. We use the following mask at inference time: DISPLAYFORM0 To learn the threshold values, we apply an additional loss at training time which is minimized when the batchwise mask and the threshold mask are identical. DISPLAYFORM0 ### Attention Function
The attention mechanism described in GNMT BIBREF3 involves a learned “Attention Function" INLINEFORM0 which takes a “source vector" INLINEFORM1 and a “target vector" INLINEFORM2 , and must be computed for every source time step INLINEFORM3 and target time step INLINEFORM4 . In GNMT, the attention function is implemented as a feed forward neural network with a hidden layer of size INLINEFORM5 . It can be expressed as: DISPLAYFORM0 Where INLINEFORM0 and INLINEFORM1 are trainable weight matrices and INLINEFORM2 is a trainable weight vector. For performance reasons, in our models, we used a slightly different attention function: DISPLAYFORM0 With our attention function, we can simultaneously compute the attention function on multiple source time steps and multiple target time steps using optimized matrix multiplications. We found little difference in quality between the two functions. Figure 1: A Mixture of Experts (MoE) layer embedded within a recurrent language model. In this case, the sparse gating function selects two experts to perform computations. Their outputs are modulated by the outputs of the gating network. Figure 2: Model comparison on 1-Billion-Word Language-Modeling Benchmark. On the left, we plot test perplexity as a function of model capacity for models with similar computational budgets of approximately 8-million-ops-per-timestep. On the right, we plot test perplexity as a function of computational budget. The top line represents the LSTM models from (Jozefowicz et al., 2016). The bottom line represents 4-billion parameter MoE models with different computational budgets. Table 1: Summary of high-capacity MoE-augmented models with varying computational budgets, vs. best previously published results (Jozefowicz et al., 2016). Details in Appendix C. Figure 3: Language modeling on a 100 billion word corpus. Models have similar computational budgets (8 million ops/timestep). Table 2: Results on WMT’14 En→ Fr newstest2014 (bold values represent best results). Table 4: Results on the Google Production En→ Fr dataset (bold values represent best results). Table 5: Multilingual Machine Translation (bold values represent best results). Table 7: Model comparison on 1 Billion Word Language Modeling Benchmark. Models marked with * are from (Jozefowicz et al., 2016). Table 8: Model comparison on 100 Billion Word Google News Dataset Figure 4: Perplexity on WMT’14 En→ Fr (left) and Google Production En→ Fr (right) datasets as a function of number of words processed. The large differences between models at the beginning of training are due to different batch sizes. All models incur the same computational budget (85M ops/timestep) except the one with no experts. Table 9: Contexts corresponding to a few of the 2048 experts in the MoE layer in the encoder portion of the WMT’14 En→ Fr translation model. For each expert i, we sort the inputs in a training batch in decreasing order of G(x)i, and show the words surrounding the corresponding positions in the input sentences.
|
DISPLAYFORM0, DISPLAYFORM0 DISPLAYFORM1
|
What dataset is used?
|
### Introduction
How infants discover the words of their native languages is a long-standing question in developmental psychology BIBREF0 . Machine learning has contributed much to this discussion by showing that predictive models of language are capable of inferring the existence of word boundaries solely based on statistical properties of the input BIBREF1 , BIBREF2 , BIBREF3 . Unfortunately, the best language models, measured in terms of their ability to model language, segment quite poorly BIBREF4 , BIBREF5 , while the strongest models in terms of word segmentation are far too weak to adequately predict language BIBREF3 , BIBREF6 . Moreover, since language acquisition is ultimately a multimodal process, neural models which simplify working with multimodal data offer opportunities for future research. However, as BIBREF7 have argued, current neural models' inability to discover meaningful words is too far behind the current (non-neural) state-of-the-art to be a useful foundation. In this paper, we close this gap by introducing a neural model (§ SECREF2 ) of natural language sentences that explicitly discovers and models word-like units from completely unsegmented sequences of characters. The model generates text as a sequence of segments, where each segment is generated either character-by-character from a sequence model or as a single draw from a lexical memory of multi-character units. The segmentation decisions and decisions about the generation mechanism for each segment are latent. In order to efficiently deal with an exponential number of possible segmentations, we use a conditional semi-Markov model. The characters inside each segment are generated using non-Markovian processes, conditional on the previously generated characters (the previous segmentation decisions are forgotten). This conditional independence assumption—forgetting previous segmenation decisions—enables us to calculate and differentiate exact marginal likelihood over all possible discrete segmentation decisions with a dynamic programming algorithm, while letting the model retain the most relevant information about the generation history. There are two components to make the model work. One is a lexical memory. The memory stores pairs of a vector (key) and a string (value) appearing in the training set and the vector representation of each strings are randomly initialized and learned during training. The other is a regularizer (§ SECREF3 ) to prevent the model from overfitting to the training data. Since the lexical memory stores strings that appeared in the training data, each sentence could be generated as a single unit, thus the model can fit to the training data perfectly while generalizing poorly. The regularizer penalizes based on the expectation of the powered length of each segment. Although the length of each segment is not differentiable, the expectation is differentiable and can be computed efficiently together with the marginal likelihood for each sentence in a single forward pass. Our evaluation (§ SECREF4 –§ SECREF6 ), therefore, looks at both language modeling performance and the quality of the induced segmentations. First, we look at the segmentations induced by our model. We find that these correspond closely to human intuitions about word segments, competitive with the best existing models. These segments are obtained in models whose hyperparameters are tuned to optimize validation likelihood, whereas tuning the hyperparameters based on likelihood on our benchmark models produces poor segmentations. Second, we confirm findings BIBREF8 , BIBREF9 that show that word segmentation information leads to better language models compared to pure character models. However, in contrast to previous work, we do so without observing the segment boundaries, including in Chinese, where word boundaries are not part of the orthography. Finally, we find that both the lexicon and the regularizer are crucial for good performance, particularly in word segmentation—removing either or both significantly harms performance. ### Model
We now describe the segmental neural language model (SNLM). Refer to Figure FIGREF1 for an illustration. The SNLM generates a character sequence INLINEFORM0 , where each INLINEFORM1 is a character in a finite character set INLINEFORM2 . Each sequence INLINEFORM3 is the concatenation of a sequence of segments INLINEFORM4 where INLINEFORM5 measures the length of the sequence in segments and each segment INLINEFORM6 is a sequence of characters, INLINEFORM7 . Intuitively, each INLINEFORM8 corresponds to one word. Let INLINEFORM9 represent the concatenation of the characters of the segments INLINEFORM10 to INLINEFORM11 , discarding segmentation information; thus INLINEFORM12 . For example if INLINEFORM13 , the underlying segmentation might be INLINEFORM14 (with INLINEFORM15 and INLINEFORM16 ), or INLINEFORM17 , or any of the INLINEFORM18 segmentation possibilities for INLINEFORM19 . The SNLM defines the distribution over INLINEFORM0 as the marginal distribution over all segmentations that give rise to INLINEFORM1 , i.e., DISPLAYFORM0 To define the probability of INLINEFORM0 , we use the chain rule, rewriting this in terms of a product of the series of conditional probabilities, INLINEFORM1 . The process stops when a special end-sequence segment INLINEFORM2 is generated. To ensure that the summation in Eq. EQREF2 is tractable, we assume the following: DISPLAYFORM0 which amounts to a conditional semi-Markov assumption—i.e., non-Markovian generation happens inside each segment, but the segment generation probability does not depend on memory of the previous segmentation decisions, only upon the sequence of characters INLINEFORM0 corresponding to the prefix character sequence INLINEFORM1 . This assumption has been employed in a number of related models to permit the use of LSTMs to represent rich history while retaining the convenience of dynamic programming inference algorithms BIBREF5 , BIBREF10 , BIBREF11 . ### Segment generation
We model INLINEFORM0 as a mixture of two models, one that generates the segment using a sequence model and the other that generates multi-character sequences as a single event. Both are conditional on a common representation of the history, as is the mixture proportion. To represent INLINEFORM0 , we use an LSTM encoder to read the sequence of characters, where each character type INLINEFORM1 has a learned vector embedding INLINEFORM2 . Thus the history representation at time INLINEFORM3 is INLINEFORM4 . This corresponds to the standard history representation for a character-level language model, although in general we assume that our modeled data is not delimitered by whitespace. The first component model, INLINEFORM0 , generates INLINEFORM1 by sampling a sequence of characters from a LSTM language model over INLINEFORM2 and a two extra special symbols, an end-of-word symbol INLINEFORM3 and the end-of-sequence symbol INLINEFORM4 discussed above. The initial state of the LSTM is a learned transformation of INLINEFORM5 , the initial cell is INLINEFORM6 , and different parameters than the history encoding LSTM are used. During generation, each letter that is sampled (i.e., each INLINEFORM7 ) is fed back into the LSTM in the usual way and the probability of the character sequence decomposes according to the chain rule. The end-of-sequence symbol can never be generated in the initial position. The second component model, INLINEFORM0 , samples full segments from lexical memory. Lexical memory is a key-value memory containing INLINEFORM1 entries, where each key, INLINEFORM2 , a vector, is associated with a value INLINEFORM3 . The generation probability of INLINEFORM4 is defined as INLINEFORM5 where INLINEFORM0 is 1 if the INLINEFORM1 th value in memory is INLINEFORM2 and 0 otherwise, and INLINEFORM3 is a matrix obtained by stacking the INLINEFORM4 's. Note that this generation process will assign zero probability to most strings, but the alternate character model can generate anything in INLINEFORM5 . In this work, we fix the INLINEFORM0 's to be subsequences of at least length 2, and up to a maximum length INLINEFORM1 that are observed at least INLINEFORM2 times in the training data. These values are tuned as hyperparameters (See Appendix SECREF10 for details of the reported experiments). The mixture proportion, INLINEFORM0 , determines how likely the character generator is to be used at time INLINEFORM1 (the lexicon is used with probability INLINEFORM2 ). It is defined by as INLINEFORM3 . The total generation probability of INLINEFORM0 is thus: INLINEFORM1 ### Inference
We are interested in two inference questions: first, given a sequence INLINEFORM0 , evaluate its (log) marginal likelihood; second, given INLINEFORM1 , find the most likely decomposition into segments INLINEFORM2 . To efficiently compute the marginal likelihood, we use a variant of the forward algorithm for semi-Markov models BIBREF12 , which incrementally computes a sequence of probabilities, INLINEFORM0 , where INLINEFORM1 is the marginal likelihood of generating INLINEFORM2 and concluding a segment at time INLINEFORM3 . Although there are an exponential number of segmental decompositions of INLINEFORM4 , these values can be computed using INLINEFORM5 space and INLINEFORM6 time as: DISPLAYFORM0 By letting INLINEFORM0 , then INLINEFORM1 . The most probable segmentation of a sequence INLINEFORM0 can be computed by replacing the summation with a INLINEFORM1 operator in Eq. EQREF12 and maintaining backpointers. ### Expected length regularization
When the lexical memory contains all the substrings in the training data, the model easily overfits by copying the longest continuation from the memory. To prevent overfitting, we introduce a regularizer that penalizes based on the expectation of the exponentiated (by a hyperparameter INLINEFORM0 ) length of each segment: INLINEFORM1 This can be understood as a regularizer based on the double exponential prior identified to be effective in previous work BIBREF13 , BIBREF6 . This expectation is a differentiable function of the model parameters. Because of the linearity of the penalty across segments, it can be computed efficiently using the above dynamic programming algorithm under the expectation semiring BIBREF14 . This is particular efficient since the expectation semiring jointly computes the expectation and marginal likelihood. ### Training Objective
The model parameters are trained by minimizing the penalized log likelihood of a training corpus INLINEFORM0 of unsegmented sentences, INLINEFORM1 ### Datasets
We evaluate our model on both English and Chinese segmentation. For both languages we used standard datasets for word segmentation and language modeling. For all datasets, we used train, validation and test splits. Since our model assumes a closed character set, we removed validation and test samples which contain characters that do not appear in the training set. In the English corpora, whitespace characters are removed. In Chinese, they are not present to begin with. Refer to Appendix SECREF9 for dataset statistics. ### English
The Brent corpus is a standard corpus used in statistical modeling of child language acquisition BIBREF15 , BIBREF16 . The corpus contains transcriptions of utterances directed at 13- to 23-month-old children. The corpus has two variants: an orthographic one (BR-text) and a phonemic one (BR-phono), where each character corresponds to a single English phoneme. As the Brent corpus does not have a standard train and test split, and we want to tune the parameters by measuring the fit to held-out data, we used the first 80% of the utterances for training and the next 10% for validation and the rest for test. We use the commonly used version of the PTB prepared by BIBREF17 . However, since we removed space symbols from the corpus, our cross entropy results cannot be compared to those usually reported on this dataset. ### Chinese
Since Chinese orthography does not mark spaces between words, there have been a number of efforts to annotate word boundaries. We evaluate against two corpora that have been manually segmented according different segmentation standards. The Beijing University Corpus was one of the corpora used for the International Chinese Word Segmentation Bakeoff BIBREF18 . We use the Penn Chinese Treebank Version 5.1 BIBREF19 . It generally has a coarser segmentation than PKU (e.g., in CTB a full name, consisting of a given name and family name, is a single token), and it is a larger corpus. ### Experiments
We compare our model to benchmark Bayesian models, which are currently the best known unsupervised word discovery models, as well as to a simple deterministic segmentation criterion based on surprisal peaks BIBREF1 on language modeling and segmentation performance. Although the Bayeisan models are shown to able to discover plausible word-like units, we found that a set of hyper-parameters that provides best performance with such model on language modeling does not produce good structures as reported in previous works. This is problematic since there is no objective criteria to find hyper-parameters in fully unsupervised manner when the model is applied to completely unknown languages or domains. Thus, our experiments are designed to assess how well the models infers word segmentations of unsegmented inputs when they are trained and tuned to maximize the likelihood of the held-out text. ### Results
In this section, we first do a careful comparison of segmentation performance on the phonemic Brent corpus (BR-phono) across several different segmentation baselines, and we find that our model obtains competitive segmentation performance. Additionally, ablation experiments demonstrate that both lexical memory and the proposed expected length regularization are necessary for inferring good segmentations. We then show that also on other corpora, we likewise obtain segmentations better than baseline models. Finally, we also show that our model has superior performance, in terms of held-out perplexity, compared to a character-level LSTM language model. Thus, overall, our results show that we can obtain good segmentations on a variety of tasks, while still having very good language modeling performance. ### Related Work
Learning to discover and represent temporally extended structures in a sequence is a fundamental problem in many fields. For example in language processing, unsupervised learning of multiple levels of linguistic structures such as morphemes BIBREF25 , words BIBREF3 and phrases BIBREF26 have been investigated. Recently, speech recognition have benefited from techniques that enable the discovery of subword units BIBREF27 , BIBREF5 ; however, in this work the optimally discovered substrings look very unlike orthographic words. The model proposed by BIBREF5 is essentially our model without a lexicon or the expected length regularization, i.e., ( INLINEFORM0 memory, INLINEFORM1 length). Beyond language, temporal abstraction in sequential decision making processes has been investigated for a long time in reinforcement learning. Option discovery in hierarchical reinforcement learning is formalized similarly to the approach we take (using semi-Markov decision processes where we use semi-Markov generative models), and the motivation is the same: high level options/words have very different relationships to each other than primitive actions/characters BIBREF28 , BIBREF29 , BIBREF30 . ### Conclusion
We introduced the segmental neural language model which combines a lexicon and a character-level word generator to produce a model that both improves language modeling performance over word-agnostic character LSTMs, and it discovers latent words as well as the best existing approaches for unsupervised word discovering. This constellation of results suggests that structure discovery and predictive modeling need not be at odds with one another: the structures we observe in nature are worth modeling, even with powerful learners. ### Dataset statistics
Table. TABREF34 summarize dataset statistics. ### SNLM Model Configuration
For each RNN based model we used 512 dimensions for the character embeddings and the LSTMs have 512 hidden units. All the parameters, including character projection parameters, are randomly sampled from uniform distribution from INLINEFORM0 to INLINEFORM1 . The initial hidden and memory state of the LSTMs are initialized with zero. A dropout rate of 0.5 was used for all but the recurrent connections. To restrict the size of memory, we stored substrings which appeared INLINEFORM0 -times in the training corpora and tuned INLINEFORM1 with grid search. The maximum length of subsequences INLINEFORM2 was tuned on the held-out likelihood using a grid search. Tab. TABREF35 summarizes the parameters for each dataset. Note that we did not tune the hyperparameters on segmentation quality to ensure that the models are trained in a purely unsupervised manner assuming no reference segmentations are available. ### Learning
The models were trained with the Adam update rule BIBREF22 with a learning rate of 0.01. The learning rate is divided by 4 if there is no improvement on development data. The maximum norm of the gradients was clipped at 1.0. Figure 1: Fragment of the segmental neural language model, as it is used to evaluate the marginal likelihood of a sequence. At the indicated time, the model has previously generated the sequence Canyou, and four possible continuations are shown. Table 1: Summary of segmentation performance on phoneme version of the Brent Corpus (BRphono). Table 2: Summary of segmentation performance on other corpora. Table 3: Examples of predicted segmentations on English and Chinese. Table 4: Test set language modeling performance (bpc). Table 5: Summary of Dataset Statistics. Table 6: Hyperparameter values used.
|
Brent corpus, PTB , Beijing University Corpus, Penn Chinese Treebank
|
What is the implied name of the green creatures Horst and his gang are herding?
A. Free Birthers
B. Slims
C. Squat Plodders
D. Losels
|
DOWN TO THE WORLDS OF MEN BY ALEXEI PANSHIN The ancient rule was sink or swim—swim in the miasma of a planet without spaceflight, or sink to utter destruction! [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, July 1963. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] I The horses and packs were loaded before we went aboard the scoutship. The scout bay is no more than a great oversized airlock with a dozen small ships squatting over their tubes, but it was the last of the Ship that I might ever see, so I took a long final look from the top of the ramp. There were sixteen of us girls and thirteen boys. We took our places in the seats in the center of the scout. Riggy Allen made a joke that nobody bothered to laugh at, and then we were all silent. I was feeling lost and just beginning to enjoy it when Jimmy Dentremont came over to me. He's red-headed and has a face that makes him look about ten. An intelligent runt like me. He said what I expected. "Mia, do you want to go partners if we can get together when we get down?" I guess he thought that because we were always matched on study I liked him. Well, I did when I wasn't mad at him, but now I had that crack he'd made about being a snob in mind, so I said, "Not likely. I want to come back alive." It wasn't fair, but it was a good crack and he went back to his place without saying anything. My name is Mia Havero. I'm fourteen, of course, or I wouldn't be telling this. I'm short, dark and scrawny, though I don't expect that scrawniness to last much longer. Mother is very good looking. In the meantime, I've got brains as a consolation. After we were all settled, George Fuhonin, the pilot, raised the ramps. We sat there for five minutes while they bled air out of our tube and then we just ... dropped. My stomach turned flips. We didn't have to leave that way, but George thinks it's fun to be a hot pilot. Thinking it over, I was almost sorry I'd been stinking to Jimmy D. He's the only competition I have my own age. The trouble is, you don't go partners with the competition, do you? Besides, there was still that crack about being a snob. The planet chosen for our Trial was called Tintera. The last contact the Ship had had with it—and we were the ones who dropped them—was almost 150 years ago. No contact since. That had made the Council debate a little before they dropped us there, but they decided it was all right in the end. It didn't make any practical difference to us kids because they never tell you anything about the place they're going to drop you. All I knew was the name. I wouldn't have known that much if Daddy weren't Chairman of the Council. I felt like crawling in a corner of the ship and crying, but nobody else was breaking down, so I didn't. I did feel miserable. I cried when I said good-by to Mother and Daddy—a real emotional scene—but that wasn't in public. It wasn't the chance of not coming back that bothered me really, because I never believed that I wouldn't. The thought that made me unhappy was that I would have to be on a planet for a whole month. Planets make me feel wretched. The gravity is always wrong, for one thing. Either your arches and calves ache or every time you step you think you're going to trip on a piece of fluff and break your neck. There are vegetables everywhere and little grubby things just looking for you to crawl on. If you can think of anything creepier than that, you've got a real nasty imagination. Worst of all, planets stink. Every single one smells—I've been on enough to know that. A planet is all right for a Mud-eater, but not for me. We have a place in the Ship like that—the Third Level—but it's only a thousand square miles and any time it gets on your nerves you can go up a level or down a level and be back in civilization. When we reached Tintera, they started dropping us. We swung over the sea from the morning side and then dropped low over gray-green forested hills. Finally George spotted a clear area and dropped into it. They don't care what order you go in, so Jimmy D. jumped up, grabbed his gear and then led his horse down the ramp. I think he was still smarting from the slap I'd given him. In a minute we were airborne again. I wondered if I would ever see Jimmy—if he would get back alive. It's no game we play. When we turn fourteen, they drop us on the nearest colonized planet and come back one month later. That may sound like fun to you, but a lot of us never come back alive. Don't think I was helpless. I'm hell on wheels. They don't let us grow for fourteen years and then kick us out to die. They prepare us. They do figure, though, that if you can't keep yourself alive by the time you're fourteen, you're too stupid, foolish or unlucky to be any use to the Ship. There's sense behind it. It means that everybody on the Ship is a person who can take care of himself if he has to. Daddy says that something has to be done in a closed society to keep the population from decaying mentally and physically, and this is it. And it helps to keep the population steady. I began to check my gear out—sonic pistol, pickup signal so I could be found at the end of the month, saddle and cinches, food and clothes. Venie Morlock has got a crush on Jimmy D., and when she saw me start getting ready to go, she began to check her gear, too. At our next landing, I grabbed Ninc's reins and cut Venie out smoothly. It didn't have anything to do with Jimmy. I just couldn't stand to put off the bad moment any longer. The ship lifted impersonally away from Ninc and me like a rising bird, and in just a moment it was gone. Its gray-blue color was almost the color of the half-overcast sky, so I was never sure when I saw it last. II The first night was hell, I guess because I'm not used to having the lights out. That's when you really start to feel lonely, being alone in the dark. When the sun disappears, somehow you wonder in your stomach if it's really going to come back. But I lived through it—one day in thirty gone. I rode in a spiral search pattern during the next two days. I had three things in mind—stay alive, find people and find some of the others. The first was automatic. The second was to find out if there was a slot I could fit into for a month. If not, I would have to find a place to camp out, as nasty as that would be. The third was to join forces, though not with that meatball Jimmy D. No, he isn't really a meatball. The trouble is that I don't take nothing from nobody, especially him, and he doesn't take nothing from nobody, especially me. So we do a lot of fighting. I had a good month for Trial. My birthday is in November—too close to Year End Holiday for my taste, but this year it was all right. It was spring on Tintera, but it was December in the Ship, and after we got back we had five days of Holiday to celebrate. It gave me something to look forward to. In two days of riding, I ran onto nothing but a few odd-looking animals. I shot one small one and ate it. It turned out to taste pretty good, though not as good as a slice from Hambone No. 4, to my mind the best meat vat on the Ship. I've eaten things so gruey-looking that I wondered that anybody had the guts to try them in the first place and they've turned out to taste good. And I've seen things that looked good that I couldn't keep on my stomach. So I guess I was lucky. On the third day, I found the road. I brought Ninc down off the hillside, losing sight of the road in the trees, and then reaching it in the level below. It was narrow and made of sand spread over a hard base. Out of the marks in the sand, I could pick out the tracks of horses and both narrow and wide wheels. Other tracks I couldn't identify. One of the smartest moves in history was to include horses when they dropped the colonies. I say "they" because, while we did the actual dropping, the idea originated with the whole evac plan back on Earth. Considering how short a time it was in which the colonies were established, there was not time to set up industry, so they had to have draft animals. The first of the Great Ships was finished in 2025. One of the eight, as well as the two that were being built then, went up with everything else in the Solar System in 2041. In that sixteen years 112 colonies were planted. I don't know how many of those planets had animals that could have been substituted but, even if they had, they would have had to be domesticated from scratch. That would have been stupid. I'll bet that half the colonies would have failed if they hadn't had horses. We'd come in from the west over the ocean, so I traveled east on the road. That much water makes me nervous, and roads have to go somewhere. I came on my first travelers three hours later. I rounded a tree-lined bend, ducking an overhanging branch, and pulled Ninc to a stop. There were five men on horseback herding a bunch of the ugliest creatures alive. They were green and grotesque. They had squat bodies, long limbs and knobby bulges at their joints. They had square, flat animal masks for faces. But they walked on their hind legs and they had paws that were almost hands, and that was enough to make them seem almost human. They made a wordless, chilling, lowing sound as they milled and plodded along. I started Ninc up again and moved slowly to catch up with them. All the men on horseback had guns in saddle boots. They looked as nervous as cats with kittens. One of them had a string of packhorses on a line and he saw me and called to another who seemed to be the leader. That one wheeled his black horse and rode back toward me. He was a middle-aged man, maybe as old as my Daddy. He was large and he had a hard face. Normal enough, but hard. He pulled to a halt when we reached each other, but I kept going. He had to come around and follow me. I believe in judging a person by his face. A man can't help the face he owns, but he can help the expression he wears on it. If a man looks mean, I generally believe that he is. This one looked mean. That was why I kept riding. He said, "What be you doing out here, boy? Be you out of your head? There be escaped Losels in these woods." I told you I hadn't finished filling out yet, but I hadn't thought it was that bad. I wasn't ready to make a fight over the point, though. Generally, I can't keep my bloody mouth shut, but now I didn't say anything. It seemed smart. "Where be you from?" he asked. I pointed to the road behind us. "And where be you going?" I pointed ahead. No other way to go. He seemed exasperated. I have that effect sometimes. Even on Mother and Daddy, who should know better. We were coming up on the others now, and the man said, "Maybe you'd better ride on from here with us. For protection." He had an odd way of twisting his sounds, almost as though he had a mouthful of mush. I wondered whether he were just an oddball or whether everybody here spoke the same way. I'd never heard International English spoken any way but one, even on the planet Daddy made me visit with him. One of the other outriders came easing by then. I suppose they'd been watching us all the while. He called to the hard man. "He be awfully small, Horst. I doubt me a Losel'd even notice him at all. We mought as well throw him back again." The rider looked at me. When I didn't dissolve in terror as he expected, he shrugged and one of the other men laughed. The hard man said to the others, "This boy will be riding along with us to Forton for protection." I looked down at the plodding, unhappy creatures they were driving along and one looked back at me with dull, expressionless golden eyes. I felt uncomfortable. I said, "I don't think so." What the man did then surprised me. He said, "I do think so," and reached for the rifle in his saddle boot. I whipped my sonic pistol out so fast that he was caught leaning over with the rifle half out. His jaw dropped. He knew what I held and he didn't want to be fried. I said, "Ease your rifles out and drop them gently to the ground." They did, watching me all the while with wary expressions. When all the rifles were on the ground, I said, "All right, let's go." They didn't want to move. They didn't want to leave the rifles. I could see that. Horst didn't say anything. He just watched me with narrowed eyes. But one of the others held up a hand and in wheedling tones said, "Look here, kid...." "Shut up," I said, in as mean a voice as I could muster, and he did. It surprised me. I didn't think I sounded that mean. I decided he just didn't trust the crazy kid not to shoot. After twenty minutes of easy riding for us and hard walking for the creatures, I said, "If you want your rifles, you can go back and get them now." I dug my heels into Ninc's sides and rode on. At the next bend I looked back and saw four of them holding their packhorses and the creatures still while one beat a dust-raising retreat down the road. I put this episode in the "file and hold for analysis" section in my mind and rode on, feeling good. I think I even giggled once. Sometimes I even convince myself that I'm hell on wheels. III When I was nine, my Daddy gave me a painted wooden doll that my great-grandmother brought from Earth. The thing is that inside it, nestled one in another, are eleven more dolls, each one smaller than the last. I like to watch people when they open it for the first time. My face must have been like that as I rode along the road. The country leveled into a great rolling valley and the trees gave way to great farms and fields. In the fields, working, were some of the green creatures, which surprised me since the ones I'd seen before hadn't seemed smart enough to count to one, let alone do any work. But it relieved me. I thought they might have been eating them or something. I passed two crossroads and started to meet more people, but nobody questioned me. I met people on horseback, and twice I met trucks moving silently past. And I overtook a wagon driven by the oldest man I've seen in my life. He waved to me, and I waved back. Near the end of the afternoon I came to the town, and there I received a jolt that sickened me. By the time I came out on the other side, I was sick. My hands were cold and sweaty and my head was spinning, and I wanted to kick Ninc to a gallop. I rode slowly in, looking all around, missing nothing. The town was all stone, wood and brick. Out of date. Out of time, really. There were no machines more complicated than the trucks I'd seen earlier. At the edge of town, I passed a newspaper office with a headline pasted in the window—INVASION! I remember that. I wondered about it. But I looked most closely at the people. In all that town, I didn't see one girl over ten years old and no grown-up women at all. There were little kids, there were boys and there were men, but no girls. All the boys and men wore pants, and so did I, which must have been why Horst and his buddies assumed I was a boy. It wasn't flattering; but I decided I'd not tell anybody different until I found what made the clocks tick on this planet. But that wasn't what bothered me. It was the kids. My God! They swarmed. I saw a family come out of a house—a father and four children. It was the most foul thing I've ever seen. It struck me then—these people were Free Birthers! I felt a wave of nausea and I closed my eyes until it passed. The first thing you learn in school is that if it weren't for idiot and criminal people like these, Earth would never have been destroyed. The evacuation would never have had to take place, and eight billion people wouldn't have died. There wouldn't have been eight billion people. But, no. They bred and they spread and they devoured everything in their path like a cancer. They gobbled up all the resources that Earth had and crowded and shoved one another until the final war came. I am lucky. My great-great-grandparents were among those who had enough foresight to see what was coming. If it hadn't been for them and some others like them, there wouldn't be any humans left anywhere. And I wouldn't be here. That may not scare you, but it scares me. What happened before, when people didn't use their heads and wound up blowing the Solar System apart, is something nobody should forget. The older people don't let us forget. But these people had, and that the Council should know. For the first time since I landed on Tintera, I felt really frightened. There was too much going on that I didn't understand. I felt a blind urge to get away, and when I reached the edge of town, I whomped Ninc a good one and gave him his head. I let him run for almost a mile before I pulled him down to a walk again. I couldn't help wishing for Jimmy D. Whatever else he is, he's smart and brains I needed. How do you find out what's going on? Eavesdrop? That's a lousy method. For one thing, people can't be depended on to talk about the things you want to hear. For another, you're likely to get caught. Ask somebody? Who? Make the mistake of bracing a fellow like Horst and you might wind up with a sore head and an empty pocket. The best thing I could think of was to find a library, but that might be a job. I'd had two bad shocks on this day, but they weren't the last. In the late afternoon, when the sun was starting to sink and a cool wind was starting to ripple the tree leaves, I saw the scoutship high in the sky. The dying sun colored it a deep red. Back again? I wondered what had gone wrong. I reached down into my saddlebag and brought out my contact signal. The scoutship swung up in the sky in a familiar movement calculated to drop the stomach out of everybody aboard. George Fuhonin's style. I triggered the signal, my heart turning flips all the while. I didn't know why he was back, but I wasn't really sorry. The ship swung around until it was coming back on a path almost over my head, going in the same direction. Then it went into a slip and started bucking so hard that I knew this wasn't hot piloting at all, just plain idiot stutter-fingered stupidity at the controls. As it skidded by me overhead, I got a good look at it and knew that it wasn't one of ours. Not too different, but not ours. One more enigma. Where was it from? Not here. Even if you know how, and we wouldn't tell these Mud-eaters how, a scoutship is something that takes an advanced technology to build. I felt defeated and tired. Not much farther along the road, I came to a campsite with two wagons pulled in for the night, and I couldn't help but pull in myself. The campsite was large and had two permanent buildings on it. One was a well enclosure and the other was little more than a high-walled pen. It didn't even have a roof. I set up camp and ate my dinner. In the wagon closest to me were a man, his wife and their three children. The kids were running around and playing, and one of them ran close to the high-walled pen. His father came and pulled him away. The kids weren't to blame for their parents, but when one of them said hello to me, I didn't even answer. I know how lousy I would feel if I had two or three brothers and sisters, but it didn't strike me until that moment that it wouldn't even seem out of the ordinary to these kids. Isn't that horrible? About the time I finished eating, and before it grew dark, the old man I had seen earlier in the day drove his wagon in. He fascinated me. He had white hair, something I had read about in stories but had never seen before. When nightfall came, they started a large fire. Everybody gathered around. There was singing for awhile, and then the father of the children tried to pack them off to bed. But they weren't ready to go, so the old man started telling them a story. In the old man's odd accent, and sitting there in the campfire light surrounded by darkness, it seemed just right. It was about an old witch named Baba Yaga who lived in the forest in a house that stood on chicken legs. She was the nasty stepmother of a nice little girl, and to get rid of the kid, she sent her on a phony errand into the deep dark woods at nightfall. I could appreciate the poor girl's position. All the little girl had to help her were the handkerchief, the comb and the pearl that she had inherited from her dear dead mother. But, as it turned out, they were just enough to defeat nasty old Baba Yaga and bring the girl safely home. I wished for the same for myself. The old man had just finished and they were starting to drag the kids off to bed when there was a commotion on the road at the edge of the camp. I looked but my eyes were adjusted to the light of the fire and I couldn't see far into the dark. A voice there said, "I'll be damned if I'll take another day like this one, Horst. We should have been here hours ago. It be your fault we're not." Horst growled a retort. I decided that it was time for me to leave the campfire. I got up and eased away as Horst and his men came up to the fire, and cut back to where Ninc was parked. I grabbed up my blankets and mattress and started to roll them up. I had a pretty good idea now what they used the high-walled pen for. I should have known that they would have to pen the animals up for the night. I should have used my head. I hadn't and now it was time to take leave. I never got the chance. I was just heaving the saddle up on Ninc when I felt a hand on my shoulder and I was swung around. "Well, well. Horst, look who we have here," he called. It was the one who'd made the joke about me being beneath the notice of a Losel. He was alone with me now, but with that call the others would be up fast. I brought the saddle around as hard as I could and then up, and he went down. He started to get up again, so I dropped the saddle on him and reached inside my jacket for my gun. Somebody grabbed me then from behind and pinned my arms to my side. I opened my mouth to scream—I have a good scream—but a rough smelly hand clamped down over it before I had a chance to get more than a lungful of air. I bit down hard—5000 lbs. psi, I'm told—but he didn't let me go. I started to kick, but Horst jerked me off my feet and dragged me off. When we were behind the pen and out of earshot of the fire, he stopped dragging me and dropped me in a heap. "Make any noise," he said, "and I'll hurt you." That was a silly way to put it, but somehow it said more than if he'd threatened to break my arm or my head. It left him a latitude of things to do if he pleased. He examined his hand. There was enough moonlight for that. "I ought to club you anyway," he said. The one I'd dropped the saddle on came up then. The others were putting the animals in the pen. He started to kick me, but Horst stopped him. "No," he said. "Look through the kid's gear, bring the horse and what we can use." The other one didn't move. "Get going, Jack," Horst said in a menacing tone and they stood toe to toe for a long moment before Jack finally backed down. It seemed to me that Horst wasn't so much objecting to me being kicked, but was rather establishing who did the kicking in his bunch. But I wasn't done yet. I was scared, but I still had the pistol under my jacket. Horst turned back to me and I said, "You can't do this and get away with it." He said, "Look, boy. You may not know it, but you be in a lot of trouble. So don't give me a hard time." He still thought I was a boy. It was not time to correct him, but I didn't like to see the point go unchallenged. It was unflattering. "The courts won't let you get away with this," I said. I'd passed a courthouse in the town with a carved motto over the doors: EQUAL JUSTICE UNDER THE LAW or TRUTH OUR SHIELD AND JUSTICE OUR SWORD or something stuffy like that. He laughed, not a phony, villian-type laugh, but a real laugh, so I knew I'd goofed. "Boy, boy. Don't talk about the courts. I be doing you a favor. I be taking what I can use of your gear, but I be letting you go. You go to court and they'll take everything and lock you up besides. I be leaving you your freedom." "Why would they be doing that?" I asked. I slipped my hand under my jacket. "Every time you open your mouth you shout that you be off one of the Ships," Horst said. "That be enough. They already have one of you brats in jail in Forton." I was about to bring my gun out when up came Jack leading Ninc, with all my stuff loaded on. I mentally thanked him. He said, "The kid's got some good equipment. But I can't make out what this be for." He held out my pickup signal. Horst looked at it, then handed it back. "Throw it away," he said. I leveled my gun at them—Hell on Wheels strikes again! I said, "Hand that over to me." Horst made a disgusted sound. "Don't make any noise," I said, "or you'll fry. Now hand it over." I stowed it away, then paused with one hand on the leather horn of the saddle. "What's the name of the kid in jail in Forton." "I can't remember," he said. "But it be coming to me. Hold on." I waited. Then suddenly my arm was hit a numbing blow from behind and the gun went flying. Jack pounced after it and Horst said, "Good enough," to the others who'd come up behind me. I felt like a fool. Horst stalked over and got the signal. He dropped it on the ground and said in a voice far colder than mine could ever be, because it was natural and mine wasn't, "The piece be yours." Then he tromped on it until it cracked and fell apart. Then he said, "Pull a gun on me twice. Twice." He slapped me so hard that my ears rang. "You dirty little punk." I said calmly, "You big louse." It was a time I would have done better to keep my mouth shut. All I can remember is a flash of pain as his fist crunched against the side of my face and then nothing. Brains are no good if you don't use them.
|
D. Losels
|
How many questions per image on average are available in dataset?
|
### Introduction
Increases in life expectancy in the last century have resulted in a large number of people living to old ages and will result in a double number of dementia cases by the middle of the century BIBREF0BIBREF1. The most common form of dementia is Alzheimer disease which contributes to 60–70% of cases BIBREF2. Research focused on identifying treatments to slow down the evolution of Alzheimer's disease is a very active pursuit, but it has been only successful in terms of developing therapies that eases the symptoms without addressing the cause BIBREF3BIBREF4. Besides, people with dementia might have some barriers to access to the therapies, such as cost, availability and displacement to the care home or hospital, where the therapy takes place. We believe that Artificial Intelligence (AI) can contribute in innovative systems to give accessibility and offer new solutions to the patients needs, as well as help relatives and caregivers to understand the illness of their family member or patient and monitor the progress of the dementia. Therapies such as reminiscence, that stimulate memories of the patient's past, have well documented benefits on social, mental and emotional well-being BIBREF5BIBREF6, making them a very desirable practice, especially for older adults. Reminiscence therapy in particular involves the discussion of events and past experiences using tangible prompts such as pictures or music to evoke memories and stimulate conversation BIBREF7. With this aim, we explore multi-modal deep learning architectures to be used to develop an intuitive, easy to use, and robust dialogue system to automatize the reminiscence therapy for people affected by mild cognitive impairment or at early stages of Alzheimer's disease. We propose a conversational agent that simulates a reminiscence therapist by asking questions about the patient's experiences. Questions are generated from pictures provided by the patient, which contain significant moments or important people in user's life. Moreover, to engage the user in the conversation we propose a second model which generates comments on user's answers. A chatbot model trained with a dataset containing simple conversations between different people. The activity pretends to be challenging for the patient, as the questions may require the user to exercise the memory. Our contributions include: Automation of the Reminiscence therapy by using a multi-modal approach that generates questions from pictures, without using a reminiscence therapy dataset. An end-to-end deep learning approach which do not require hand-crafted rules and it is ready to be used by mild cognitive impairment patients. The system is designed to be intuitive and easy to use for the users and could be reached by any smartphone with internet connection. ### Related Work
The origin of chatbots goes back to 1966 with the creation of ELIZA BIBREF8 by Joseph Weizenbaum at MIT. Its implementation consisted in pattern matching and substitution methodology. Recently, data driven approaches have drawn significant attention. Existing work along this line includes retrieval-based methods BIBREF9BIBREF10 and generation-based methodsBIBREF11BIBREF12. In this work we focus on generative models, where sequence-to-sequence algorithm that uses RNNs to encode and decode inputs into responses is a current best practice. Our conversational agent uses two architectures to simulate a specialized reminiscence therapist. The block in charge of generating questions is based on the work Show, Attend and Tell BIBREF13. This work generates descriptions from pictures, also known as image captioning. In our case, we focus on generating questions from pictures. Our second architecture is inspired by Neural Conversational Model from BIBREF14 where the author presents an end-to-end approach to generate simple conversations. Building an open-domain conversational agent is a challenging problem. As addressed in BIBREF15 and BIBREF16, the lack of a consistent personality and lack of long-term memory which produces some meaningless responses in these models are still unresolved problems. Some works have proposed conversational agents for older adults with a variety of uses, such as stimulate conversation BIBREF17 , palliative care BIBREF18 or daily assistance. An example of them is ‘Billie’ reported in BIBREF19 which is a virtual agent that uses facial expression for a more natural behavior and is focused on managing user’s calendar, or ‘Mary’ BIBREF20 that assists the users by organizing their tasks offering reminders and guidance with household activities. Both of the works perform well on its specific tasks, but report difficulties to maintain a casual conversation. Other works focus on the content used in Reminiscence therapy. Like BIBREF21 where the authors propose a system that recommends multimedia content to be used in therapy, or Visual Dialog BIBREF22 where the conversational agent is the one that has to answer the questions about the image. ### Methodology
In this section we explain the main two components of our model, as well as how the interaction with the model works. We named it Elisabot and its goal is to mantain a dialog with the patient about her user’s life experiences. Before starting the conversation, the user must introduce photos that should contain significant moments for him/her. The system randomly chooses one of these pictures and analyses the content. Then, Elisabot shows the selected picture and starts the conversation by asking a question about the picture. The user should give an answer, even though he does not know it, and Elisabot makes a relevant comment on it. The cycle starts again by asking another relevant question about the image and the flow is repeated for 4 to 6 times until the picture is changed. The Figure FIGREF3 summarizes the workflow of our system. Elisabot is composed of two models: the model in charge of asking questions about the image which we will refer to it as VQG model, and the Chatbot model which tries to make the dialogue more engaging by giving feedback to the user's answers. ### Methodology ::: VQG model
The algorithm behind VQG consists in an Encoder-Decoder architecture with attention. The Encoder takes as input one of the given photos $I$ from the user and learns its information using a CNN. CNNs have been widely studied for computer vision tasks. The CNN provides the image's learned features to the Decoder which generates the question $y$ word by word by using an attention mechanism with a Long Short-Term Memory (LSTM). The model is trained to maximize the likelihood $p(y|I)$ of producing a target sequence of words: where $K$ is the size of the vocabulary and $C$ is the length of the caption. Since there are already Convolutional Neural Networks (CNNs) trained on large datasets to represent images with an outstanding performance, we make use of transfer learning to integrate a pre-trained model into our algorithm. In particular, we use a ResNet-101 BIBREF23 model trained on ImageNet. We discard the last 2 layers, since these layers classify the image into categories and we only need to extract its features. ### Methodology ::: Chatbot network
The core of our chatbot model is a sequence-to-sequence BIBREF24. This architecture uses a Recurrent Neural Network (RNN) to encode a variable-length sequence to obtain a large fixed dimensional vector representation and another RNN to decode the vector into a variable-length sequence. The encoder iterates through the input sentence one word at each time step producing an output vector and a hidden state vector. The hidden state vector is passed to the next time step, while the output vector is stored. We use a bidirectional Gated Recurrent Unit (GRU), meaning we use two GRUs one fed in sequential order and another one fed in reverse order. The outputs of both networks are summed at each time step, so we encode past and future context. The final hidden state $h_t^{enc}$ is fed into the decoder as the initial state $h_0^{dec}$. By using an attention mechanism, the decoder uses the encoder’s context vectors, and internal hidden states to generate the next word in the sequence. It continues generating words until it outputs an $<$end$>$ token, representing the end of the sentence. We use an attention layer to multiply attention weights to encoder's outputs to focus on the relevant information when decoding the sequence. This approach have shown better performance on sequence-to-sequence models BIBREF25. ### Datasets
One of the first requirements to develop an architecture using a machine learning approach is a training dataset. The lack of open-source datasets containing dialogues from reminiscence therapy lead as to use a dataset with content similar to the one used in the therapy. In particular, we use two types of datasets to train our models: A dataset that maps pictures with questions, and an open-domain conversation dataset. The details of the two datasets are as follows. ### Datasets ::: MS-COCO, Bing and Flickr datasets
We use MS COCO, Bing and Flickr datasets from BIBREF26 to train the model that generates questions. These datasets contain natural questions about images with the purpose of knowing more about the picture. As can be seen in the Figure FIGREF8, questions cannot be answered by only looking at the image. Each source contains 5,000 images with 5 questions per image, adding a total of 15,000 images with 75,000 questions. COCO dataset includes images of complex everyday scenes containing common objects in their natural context, but it is limited in terms of the concepts it covers. Bing dataset contains more event related questions and has a wider range of questions longitudes (between 3 and 20 words), while Flickr questions are shorter (less than 6 words) and the images appear to be more casual. ### Datasets ::: Persona-chat and Cornell-movie corpus
We use two datasets to train our chatbot model. The first one is the Persona-chat BIBREF15 which contains dialogues between two people with different profiles that are trying to know each other. It is complemented by the Cornell-movie dialogues dataset BIBREF27, which contains a collection of fictional conversations extracted from raw movie scripts. Persona-chat's sentences have a maximum of 15 words, making it easier to learn for machines and a total of 162,064 utterances over 10,907 dialogues. While Cornell-movie dataset contains 304,713 utterances over 220,579 conversational exchanges between 10,292 pairs of movie characters. ### Validation
An important aspect of dialogue response generation systems is how to evaluate the quality of the generated response. This section presents the training procedure and the quantitative evaluation of the model, together with some qualitative results. ### Validation ::: Implementation
Both models are trained using Stochastic Gradient Descent with ADAM optimization BIBREF28 and a learning rate of 1e-4. Besides, we use dropout regularization BIBREF29 which prevents from over-fitting by dropping some units of the network. The VQG encoder is composed of 2048 neuron cells, while the VQG decoder has an attention layer of 512 followed by an embedding layer of 512 and a LSTM with the same size. We use a dropout of 50% and a beam search of 7 for decoding, which let as obtain up to 5 output questions. The vocabulary we use consists of all words seen 3 or more times in the training set, which amounts to 11.214 unique tokens. Unknown words are mapped to an $<$unk$>$ token during training, but we do not allow the decoder to produce this token at test time. We also set a maximum sequence length of 6 words as we want simple questions easy to understand and easy to learn by the model. In the Chatbot model we use a hidden size of 500 and Dropout regularization of 25%. For decoding we use greedy search, which consists in making the optimal token choice at each step. We first train it with Persona-chat and then fine-tune it with Cornell dataset. The vocabulary we use consists of all words seen 3 or more times in Persona-chat dataset and we set a maximum sequence length of 12 words. For the hyperparameter setting, we use a batch size of 64. ### Validation ::: Quantitative evaluation
We use the BLEU BIBREF30 metric on the validation set for the VQG model training. BLEU is a measure of similitude between generated and target sequences of words, widely used in natural language processing. It assumes that valid generated responses have significant word overlap with the ground truth responses. We use it because in this case we have five different references for each of the generated questions. We obtain a BLEU score of 2.07. Our chatbot model instead, only have one reference ground truth in training when generating a sequence of words. We considered that it was not a good metric to apply as in some occasions responses have the same meaning, but do not share any words in common. Thus, we save several models with different hyperparameters and at different number of training iterations and compare them using human evaluation, to chose the model that performs better in a conversation. ### Validation ::: Qualitative results
Our first goal was to generate meaningful questions from the provided pictures. Table TABREF16 contains some generated questions by our VQG model for each of the proposed images. These images were not in the training set as they were taken from photo albums, so the model was the first time that had these images as input. By looking at the questions, we can easily realise that the model is not only able to generate questions grammatically correct, but to understand the content of the image and ask about it. Furthermore, we not only wanted to generate only a question per image, but to bring out up to five questions for a deeper conversation. We used different kind of pictures as we wanted a robust model able to work with all kind of images. In the Table TABREF16 we can see both, old gray and colorful photos, both with vertical and horizontal shapes. Most of the pictures we selected for testing were showing people, because these are the type of pictures used in reminiscence therapy, as they evoke memories from the relationships with that persons. We also tested pictures showing pets, cars and motorbikes as some people are very attached to them, triggering strong emotions. Most of the generated questions could be asked by a person. Nonetheless, we found some of the questions such as How did the car get damaged? that do not correspond with the image's content, or are not well formulated like What body of dog is that?, but can be easily understood. About the chatbot module, we test it manually by having a conversation with it. In the following lines, we can see two samples of a conversation, where each sentence starting with "$>$" is an input to our seq2seq model. In this first sample, the chatbot model is clearly overfitted as it repeats the same sentence twice. While in the second sample, we can see that the model is able to follow the conversation. Overfitted chatbot model: $>$ hi Elisabot: hello ! how are you ? $>$ fine and you? Elisabot : i am good do you have any hobbies ? $>$ yes i like to ski Elisabot: i love to play sports . it is my favorite $>$ I have a sister Elisabot : i have a dog . i love them . $>$ I have a dog too Elisabot: i have a dog . i love them $>$ ok Elisabot : i am not really a good person $>$ why? Elisabot : i love to play sports . it is my favorite Final chatbot model: $>$ hello Elisabot: hello how are you ? $>$ fine and you? Elisabot : i m great ! $>$ I have a sister, do you have any brother or sister? Elisabot : i have a iphone but i have no idea . $>$ ok Elisabot : i am a pro fan of thrones $>$ me too Elisabot : i like to eat healthy $>$ have you seen the last chapter? Elisabot : no i have not . $>$ where do you live? Elisabot : i live in the mountains ### Usability study
As most of the metrics correlate very weakly with human judgements in the non-technical domain BIBREF31 we decide to evaluate our system with a simple user study with two patients. We present the user interface built and the feedback obtained from the patients. ### Usability study ::: User interface
We developed a user interface for Elisabot with Telegram, an instant messaging application available for smartphones or computers. We select it because it is easy to use and it offers an API for developers to connect bots to the Telegram system. It enables to create special accounts for bots which do not require a phone number to set up. Telegram is only the interface for the code running in the server. The bot is executed via an HTTP-request to the API. Users can start a conversation with Elisabot by typing @TherapistElisabot in the searcher and executing the command /start, as can be seen in the Figure FIGREF31. Messages, commands and requests sent by users are passed to the software running on the server. We add /change, /yes and /exit commands to enable more functionalities. /Change gives the opportunity to the user to change the image in case the user does not want to talk about it, /yes accepts the image which is going to talk about and /exit finishes the dialogue with Elisabot. The commands can be executed either by tapping on the linked text or typing them. ### Feedback from patients
We designed a usability study where users with and without mild cognitive impairment interacted with the system with the help of a doctor and one of the authors. The purpose was to study the acceptability and feasibility of the system with patients of mild cognitive impairment. The users were all older than 60 years old. The sessions lasted 30 minutes and were carried out by using a laptop computer connected to Telegram. As Elisabot's language is English we translated the questions to the users and the answers to Elisabot. Figure FIGREF38 is a sample of the session we did with mild cognitive impairment patients from anonymized institution and location. The picture provided by the patient (Figure FIGREF37 is blurred for user's privacy rights. In this experiment all the generated questions were right according to the image content, but the feedback was wrong for some of the answers. We can see that it was the last picture of the session as when Elisabot asks if the user wants to continue or leave, and he decides to continue, Elisabot finishes the session as there are no more pictures remaining to talk about. At the end of the session, we administrated a survey to ask participants the following questions about their assessment of Elisabot: Did you like it? Did you find it engaging? How difficult have you found it? Responses were given on a five-point scale ranging from strongly disagree (1) to strongly agree (5) and very easy (1) to very difficult (5). The results were 4.6 for amusing and engaging and 2.6 for difficulty. Healthy users found it very easy to use (1/5) and even a bit silly, because of some of the generated questions and comments. Nevertheless, users with mild cognitive impairment found it engaging (5/5) and challenging (4/5), because of the effort they had to make to remember the answers for some of the generated questions. All the users had in common that they enjoyed doing the therapy with Elisabot. ### Conclusions
We presented a dialogue system for handling sessions of 30 minutes of reminiscence therapy. Elisabot, our conversational agent leads the therapy by showing a picture and generating some questions. The goal of the system is to improve users mood and stimulate their memory and communication skills. Two models were proposed to generate the dialogue system for the reminiscence therapy. A visual question generator composed of a CNN and a LSTM with attention and a sequence-to-sequence model to generate feedback on the user's answers. We realize that fine-tuning our chatbot model with another dataset improved the generated dialogue. The manual evaluation shows that our model can generate questions and feedback well formulated grammatically, but in some occasions not appropriate in content. As expected, it has tendency to produce non-specific answers and to loss its consistency in the comments with respect to what it has said before. However, the overall usability evaluation of the system by users with mild cognitive impairment shows that they found the session very entertaining and challenging. They had to make an effort to remember the answers for some of the questions, but they were very satisfied when they achieved it. Though, we see that for the proper performance of the therapy is essential a person to support the user to help remember the experiences that are being asked. This project has many possible future lines. In our future work, we suggest to train the model including the Reddit dataset which could improve the chatbot model, as it has many open-domain conversations. Moreover, we would like to include speech recognition and generation, as well as real-time text translation, to make Elisabot more autonomous and open to older adults with reading and writing difficulties. Furthermore, the lack of consistency in the dialogue might be avoided by improving the architecture including information about passed conversation into the model. We also think it would be a good idea to recognize feelings from the user's answers and give a feedback according to them. ### Acknowledgements
Marioan Caros was funded with a scholarship from the Fundacion Vodafona Spain. Petia Radeva was partially funded by TIN2018-095232-B-C21, 2017 SGR 1742, Nestore, Validithi, and CERCA Programme/Generalitat de Catalunya. We acknowledge the support of NVIDIA Corporation with the donation of Titan Xp GPUs. Figure 1: Scheme of the interaction with Elisabot Figure 2: Samples from Bing 2a), Coco 2b) and Flickr 2c) datasets Table 1: Generated questions Figure 3: Elisabot running on Telegram application Figure 5: Sample of the session study with mild cognitive impairment patient
|
5 questions per image
|
Why are the police willing to risk the life of Gerri to kill Lane?
A. Lane is too dangerous to be left alive. They can't risk him escaping just so they can rescue Gerri.
B. They think Lane may be infected with a biological weapon.
C. The police don't care if they kill Martians.
D. They don't believe that Gerri is in the room with Lane.
|
MUTINEER By ROBERT J. SHEA For every weapon there was a defense, but not against the deadliest weapon—man himself! Raging , Trooper Lane hovered three thousand feet above Tammany Square. The cool cybrain surgically implanted in him was working on the problem. But Lane had no more patience. They'd sweat, he thought, hating the chill air-currents that threw his hovering body this way and that. He glared down at the three towers bordering on the Square. He spat, and watched the little white speck fall, fall. Lock me up in barracks. All I wanted was a little time off. Did I fight in Chi for them? Damn right I did. Just a little time off, so I shouldn't blow my top. Now the lid's gone. He was going over all their heads. He'd bowled those city cops over like paper dolls, back at the Armory. The black dog was on Lane's back. Old Mayor himself was going to hear about it. Why not? Ain't old Mayor the CinC of the Newyork Troopers? The humming paragrav-paks embedded beneath his shoulder blades held him motionless above Newyork's three administrative towers. Tammany Hall. Mayor's Palace. Court House. Lane cursed his stupidity. He hadn't found out which one was which ahead of time. They keep Troopers in the Armory and teach them how to fight. They don't teach them about their own city, that they'll be fighting for. There's no time. From seven years old up, Troopers have too much to learn about fighting. The Mayor was behind one of those thousands of windows. Old cybrain, a gift from the Trooper surgeons, compliments of the city, would have to figure out which one. Blood churned in his veins, nerves shrieked with impatience. Lane waited for the electronic brain to come up with the answer. Then his head jerked up, to a distant buzz. There were cops coming. Two black paragrav-boats whirred along the translucent underside of Newyork's anti-missile force-shield, the Shell. Old cybrain better be fast. Damn fast! The cybrain jolted an impulse through his spine. Lane somersaulted. Cybrain had taken charge of his motor nerves. Lane's own mind was just along for the ride. His body snapped into a stiff dive position. He began to plummet down, picking up speed. His mailed hands glittered like arrowheads out in front. They pointed to a particular window in one of the towers. A predatory excitement rippled through him as he sailed down through the air. It was like going into battle again. A little red-white-and-green flag fluttered on a staff below the window. Whose flag? The city flag was orange and blue. He shrugged away the problem. Cybrain knew what it was doing. The little finger of his right hand vibrated in its metal sheath. A pale vibray leaped from the lensed fingertip. Breakthrough! The glasstic pane dissolved. Lane streamed through the window. The paragrav-paks cut off. Lane dropped lightly to the floor, inside the room, in battle-crouch. A 3V set was yammering. A girl screamed. Lane's hand shot out automatically. A finger vibrated. Out of the corner of his eye, Lane saw the girl fold to the floor. There was no one else in the room. Lane, still in a crouch, chewed his lip. The Mayor? His head swung around and he peered at the 3V set. He saw his own face. "Lashing police with his vibray," said the announcer, "Lane broke through the cordon surrounding Manhattan Armory. Two policemen were killed, four others seriously injured. Tammany Hall has warned that this man is extremely dangerous. Citizens are cautioned to keep clear of him. Lane is an insane killer. He is armed with the latest military weapons. A built-in electronic brain controls his reflexes—" "At ease with that jazz," said Lane, and a sheathed finger snapped out. There was a loud bang. The 3V screen dissolved into a puddle of glasstic. The Mayor. Lane strode to the window. The two police boats were hovering above the towers. Lane's mailed hand snapped open a pouch at his belt. He flipped a fist-sized cube to the floor. The force-bomb "exploded"—swelled or inflated, really, but with the speed of a blast. Lane glanced out the window. A section of the energy globe bellied out from above. It shaded the view from his window and re-entered the tower wall just below. Now the girl. He turned back to the room. "Wake up, outa-towner." He gave the blonde girl a light dose of the vibray to slap her awake. "Who are you?" she said, shakily. Lane grinned. "Trooper Lane, of the Newyork Special Troops, is all." He threw her a mock salute. "You from outa-town, girlie. I ain't seen a Newyork girl with yellow hair in years. Orange or green is the action. Whatcha doing in the Mayor's room?" The girl pushed herself to her feet. Built, Lane saw. She was pretty and clean-looking, very out-of-town. She held herself straight and her blue-violet eyes snapped at him. "What the devil do you think you're doing, soldier? I am a diplomat of the Grassroots Republic of Mars. This is an embassy, if you know what that means." "I don't," said Lane, unconcerned. "Well, you should have had brains enough to honor the flag outside this window. That's the Martian flag, soldier. If you've never heard of diplomatic immunity, you'll suffer for your ignorance." Her large, dark eyes narrowed. "Who sent you?" "My cybrain sent me." She went openmouthed. "You're Lane ." "I'm the guy they told you about on the 3V. Where's the Mayor? Ain't this his place?" "No. No, you're in the wrong room. The wrong building. That's the Mayor's suite over there." She pointed. "See where the balcony is? This is the Embassy suite. If you want the Mayor you'll have to go over there." "Whaddaya know," said Lane. "Cybrain didn't know, no more than me." The girl noticed the dark swell of the force-globe. "What's that out there?" "Force-screen. Nothing gets past, except maybe a full-size blaster-beam. Keeps cops out. Keeps you in. You anybody important?" "I told you, I'm an ambassador. From Mars. I'm on a diplomatic mission." "Yeah? Mars a big city?" She stared at him, violet eyes wide. "The planet Mars." "Planet? Oh, that Mars. Sure, I've heard of it—you gotta go by spaceship. What's your name?" "Gerri Kin. Look, Lane, holding me is no good. It'll just get you in worse trouble. What are you trying to do?" "I wanna see the Mayor. Me and my buddies, we just come back from fighting in Chi, Gerri. We won. They got a new Mayor out there in Chi. He takes orders from Newyork." Gerri Kin said, "That's what the force-domes did. The perfect defense. But also the road to the return to city-states. Anarchy." Lane said, "Yeah? Well, we done what they wanted us to do. We did the fighting for them. So we come back home to Newyork and they lock us up in the Armory. Won't pay us. Won't let us go nowhere. They had cops guarding us. City cops." Lane sneered. "I busted out. I wanna see the Mayor and find out why we can't have time off. I don't play games, Gerri. I go right to the top." Lane broke off. There was a hum outside the window. He whirled and stared out. The rounded black hulls of the two police paragrav-boats were nosing toward the force-screen. Lane could read the white numbers painted on their bows. A loudspeaker shouted into the room: "Come out of there, Lane, or we'll blast you out." "You can't," Lane called. "This girl from Mars is here." "I repeat, Lane—come out or we'll blast you out." Lane turned to the girl. "I thought you were important." She stood there with her hands together, calmly looking at him. "I am. But you are too, to them. Mars is millions of miles away, and you're right across the Square from the Mayor's suite." "Yeah, but—" Lane shook his head and turned back to the window. "All right, look! Move them boats away and I'll let this girl out!" "No deal, Lane. We're coming in." The police boats backed away slowly, then shot straight up, out of the line of vision. Lane looked down at the Square. Far below, the long, gleaming barrel of a blaster cannon caught the dim light filtering down through Newyork's Shell. The cannon trundled into the Square on its olive-drab, box-shaped caterpillar mounting and took up a position equidistant from the bases of the three towers. Now a rumble of many voices rose from below. Lane stared down to see a large crowd gathering in Tammany Square. Sound trucks were rolling to a stop around the edges of the crowd. The people were all looking up. Lane looked across the Square. The windows of the tower opposite, the ones he could see clearly, were crowded with faces. There were white dot faces on the balcony that Gerri Kin had pointed out as the Mayor's suite. The voice of a 3V newscaster rolled up from the Square, reechoing against the tower walls. "Lane is holding the Martian Ambassador, Gerri Kin, hostage. You can see the Martian tricolor behind his force-globe. Police are bringing up blaster cannon. Lane's defense is a globe of energy similar to the one which protects Newyork from aerial attack." Lane grinned back at Gerri Kin. "Whole town's down there." Then his grin faded. Nice-looking, nice-talking girl like this probably cared a lot more about dying than he did. Why the hell didn't they give him a chance to let her out? Maybe he could do it now. Cybrain said no. It said the second he dropped his force-screen, they'd blast this room to hell. Poor girl from Mars, she didn't have a chance. Gerri Kin put her hand to her forehead. "Why did you have to pick my room? Why did they send me to this crazy city? Private soldiers. Twenty million people living under a Shell like worms in a corpse. Earth is sick and it's going to kill me. What's going to happen?" Lane looked sadly at her. Only two kinds of girls ever went near a Trooper—the crazy ones and the ones the city paid. Why did he have to be so near getting killed when he met one he liked? Now that she was showing a little less fear and anger, she was talking straight to him. She was good, but she wasn't acting as if she was too good for him. "They'll start shooting pretty quick," said Lane. "I'm sorry about you." "I wish I could write a letter to my parents," she said. "What?" "Didn't you understand what I said?" "What's a letter?" "You don't know where Mars is. You don't know what a letter is. You probably can't even read and write!" Lane shrugged. He carried on the conversation disinterestedly, professionally relaxed before battle. "What's these things I can't do? They important?" "Yes. The more I see of this city and its people, the more important I realize they are. You know how to fight, don't you? I'll bet you're perfect with those weapons." "Listen. They been training me to fight since I was a little kid. Why shouldn't I be a great little fighter?" "Specialization," said the girl from Mars. "What?" "Specialization. Everyone I've met in this city is a specialist. SocioSpecs run the government. TechnoSpecs run the machinery. Troopers fight the wars. And ninety per cent of the people don't work at all because they're not trained to do anything." "The Fans," said Lane. "They got it soft. That's them down there, come to watch the fight." "You know why you were kept in the Armory, Lane? I heard them talking about it, at the dinner I went to last night." "Why?" "Because they're afraid of the Troopers. You men did too good a job out in Chi. You are the deadliest weapon that has ever been made. You. Single airborne infantrymen!" Lane said, "They told us in Trooper Academy that it's the men that win the wars." "Yes, but people had forgotten it until the SocioSpecs of Newyork came up with the Troopers. Before the Troopers, governments concentrated on the big weapons, the missiles, the bombs. And the cities, with the Shells, were safe from bombs. They learned to be self-sufficient under the Shells. They were so safe, so isolated, that national governments collapsed. But you Troopers wiped out that feeling of security, when you infiltrated Chi and conquered it." "We scared them, huh?" Gerri said, "You scared them so much that they were afraid to let you have a furlough in the city when you came back. Afraid you Troopers would realize that you could easily take over the city if you wanted to. You scared them so much that they'll let me be killed. They'll actually risk trouble with Mars just to kill you." "I'm sorry about you. I mean it, I like—" At that moment a titanic, ear-splitting explosion hurled him to the carpet, deafened and blinded him. He recovered and saw Gerri a few feet away, dazed, groping on hands and knees. Lane jumped to the window, looked quickly, sprang back. Cybrain pumped orders to his nervous system. "Blaster cannon," he said. "But just one. Gotcha, cybrain. I can beat that." He picked up the black box that generated his protective screen. Snapping it open with thumb-pressure, he turned a small dial. Then he waited. Again an enormous, brain-shattering concussion. Again Lane and Gerri were thrown to the floor. But this time there was a second explosion and a blinding flash from below. Lane laughed boyishly and ran to the window. "Look!" he called to Gerri. There was a huge gap in the crowd below. The pavement was blackened and shattered to rubble. In and around the open space sprawled dozens of tiny black figures, not moving. "Backfire," said Lane. "I set the screen to throw their blaster beam right back at them." "And they knew you might—and yet they let a crowd congregate!" Gerri reeled away from the window, sick. Lane said, "I can do that a couple times more, but it burns out the force-globe. Then I'm dead." He heard the 3V newscaster's amplified voice: "—approximately fifty killed. But Lane is through now. He has been able to outthink police with the help of his cybrain. Now police are feeding the problem to their giant analogue computer in the sub-basement of the Court House. The police analogue computer will be able to outthink Lane's cybrain, will predict Lane's moves in advance. Four more blaster cannon are coming down Broadway—" "Why don't they clear those people out of the Square?" Gerri cried. "What? Oh, the Fans—nobody clears them out." He paused. "I got one more chance to try." He raised a mailed glove to his mouth and pressed a small stud in the wrist. He said, "Trooper HQ, this is Lane." A voice spoke in his helmet. "Lane, this is Trooper HQ. We figured you'd call." "Get me Colonel Klett." Thirty seconds passed. Lane could hear the clank of caterpillar treads as the mobile blaster cannon rolled into Tammany Square. The voice of the commanding officer of the Troopers rasped into Lane's ear: "Meat-head! You broke out against my orders! Now look at you!" "I knew you didn't mean them orders, sir." "If you get out of there alive, I'll hang you for disobeying them!" "Yes, sir. Sir, there's a girl here—somebody important—from Mars. You know, the planet. Sir, she told me we could take over the city if we got loose. That right, sir?" There was a pause. "Your girl from Mars is right, Lane. But it's too late now. If we had moved first, captured the city government, we might have done it. But they're ready for us. They'd chop us down with blaster cannon." "Sir, I'm asking for help. I know you're on my side." "I am, Lane." The voice of Colonel Klett was lower. "I'd never admit it if you had a chance of getting out of there alive. You've had it, son. I'd only lose more men trying to rescue you. When they feed the data into that analogue computer, you're finished." "Yes, sir." "I'm sorry, Lane." "Yes, sir. Over and out." Lane pressed the stud on his gauntlet again. He turned to Gerri. "You're okay. I wish I could let you out. Old cybrain says I can't. Says if I drop the force-globe for a second, they'll fire into the room, and then we'll both be dead." Gerri stood with folded arms and looked at him. "Do what you have to do. As far as I can see, you're the only person in this city that has even a little bit of right on his side." Lane laughed. "Any of them purple-haired broads I know would be crazy scared. You're different." "When my grandparents landed on Mars, they found out that selfishness was a luxury. Martians can't afford it." Lane frowned with the effort of thinking. "You said I had a little right on my side. That's a good feeling. Nobody ever told me to feel that way about myself before. It'll be better to die knowing that." "I know," she said. The amplified voice from below said, "The police analogue computer is now hooked directly to the controls of the blaster cannon battery. It will outguess Lane's cybrain and check his moves ahead of time." Lane looked at Gerri. "How about giving me a kiss before they get us? Be nice if I kissed a girl like you just once in my life." She smiled and walked forward. "You deserve it, Lane." He kissed her and it filled him with longings for things he couldn't name. Then he stepped back and shook his head. "It ain't right you should get killed. If I take a dive out that window, they shoot at me, not in here." "And kill you all the sooner." "Better than getting burned up in this lousy little room. You also got right on your side. There's too many damn Troopers and not enough good persons like you. Old cybrain says stay here, but I don't guess I will. I'm gonna pay you back for that kiss." "But you're safe in here!" "Worry about yourself, not about me." Lane picked up the force-bomb and handed it to her. "When I say now, press this. Then take your hand off, real fast. It'll shut off the screen for a second." He stepped up on to the window ledge. Automatically, the cybrain cut in his paragrav-paks. "So long, outa-towner. Now! " He jumped. He was hurtling across the Square when the blaster cannons opened up. They weren't aimed at the window where the little red-white-and-green tricolor was flying. But they weren't aimed at Lane, either. They were shooting wild. Which way now? Looks like I got a chance. Old cybrain says fly right for the cannons. He saw the Mayor's balcony ahead. Go to hell, old cybrain. I'm doing all right by myself. I come to see the Mayor, and I'm gonna see him. Lane plunged forward. He heard the shouts of frightened men. He swooped over the balcony railing. A man was pointing a blaster pistol at him. There were five men on the balcony—emergency! Years of training and cybrain took over. Lane's hand shot out, fingers vibrating. As he dropped to the balcony floor in battle-crouch, the men slumped around him. He had seen the man with the blaster pistol before. It was the Mayor of Newyork. Lane stood for a moment in the midst of the sprawled men, the shrieks of the crowd floating up to him. Then he raised his glove to his lips. He made contact with Manhattan Armory. "Colonel Klett, sir. You said if we captured the city government we might have a chance. Well, I captured the city government. What do we do with it now?" Lane was uncomfortable in his dress uniform. First there had been a ceremony in Tammany Square inaugurating Newyork's new Military Protectorate, and honoring Trooper Lane. Now there was a formal dinner. Colonel Klett and Gerri Kin sat on either side of Lane. Klett said, "Call me an opportunist if you like, Miss Kin, my government will be stable, and Mars can negotiate with it." He was a lean, sharp-featured man with deep grooves in his face, and gray hair. Gerri shook her head. "Recognition for a new government takes time. I'm going back to Mars, and I think they'll send another ambassador next time. Nothing personal—I just don't like it here." Lane said, "I'm going to Mars, too." "Did she ask you to?" demanded Klett. Lane shook his head. "She's got too much class for me. But I like what she told me about Mars. It's healthy, like." Klett frowned. "If I thought there was a gram of talent involved in your capture of the Mayor, Lane, I'd never release you from duty. But I know better. You beat that analogue computer by sheer stupidity—by disregarding your cybrain." Lane said, "It wasn't so stupid if it worked." "That's what bothers me. It calls for a revision in our tactics. We've got a way of beating those big computers now, should anyone use them against us." "I just didn't want her to be hurt." "Exactly. The computer could outguess a machine, like your cybrain. But you introduced a totally unpredictable factor—human emotion. Which proves what I, as a military man, have always maintained—that the deadliest weapon in man's arsenal is still, and will always be, the individual soldier." "What you just said there, sir," said Lane. "That's why I'm leaving Newyork." "What do you mean?" asked Colonel Klett. "I'm tired of being a weapon, sir. I want to be a human being." END Work is the elimination of the traces of work. —Michelangelo Transcriber's Note: This etext was produced from If July 1959. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed. Minor spelling and typographical errors have been corrected without note.
|
A. Lane is too dangerous to be left alive. They can't risk him escaping just so they can rescue Gerri.
|
How do they obtain distant supervision rules for predicting relations?
|
### Introduction
This work discusses two information extraction systems for identifying temporal information in clinical text, submitted to SemEval-2016 Task 12 : Clinical TempEval BIBREF0 . We participated in tasks from both phases: (1) identifying text spans of time and event mentions; and (2) predicting relations between clinical events and document creation time. Temporal information extraction is the task of constructing a timeline or ordering of all events in a given document. In the clinical domain, this is a key requirement for medical reasoning systems as well as longitudinal research into the progression of disease. While timestamps and the structured nature of the electronic medical record (EMR) directly capture some aspects of time, a large amount of information on the progression of disease is found in the unstructured text component of the EMR where temporal structure is less obvious. We examine a deep-learning approach to sequence labeling using a vanilla recurrent neural network (RNN) with word embeddings, as well as a joint inference, structured prediction approach using Stanford's knowledge base construction framework DeepDive BIBREF1 . Our DeepDive application outperformed the RNN and scored similarly to 2015's best-in-class extraction systems, even though it only used a small set of context window and dictionary features. Extraction performance, however lagged this year's best system submission. For document creation time relations, we again use DeepDive. Our system examined a simple temporal distant supervision rule for labeling time expressions and linking them to nearby event mentions via inference rules. Overall system performance was better than this year's median submission, but again fell short of the best system. ### Methods and Materials
Phase 1 of the challenge required parsing clinical documents to identify Timex3 and Event temporal entity mentions in text. Timex3 entities are expressions of time, ranging from concrete dates to phrases describing intervals like “the last few months." Event entities are broadly defined as anything relevant to a patient's clinical timeline, e.g., diagnoses, illnesses, procedures. Entity mentions are tagged using a document collection of clinic and pathology notes from the Mayo Clinic called the THYME (Temporal History of Your Medical Events) corpus BIBREF2 . We treat Phase 1 as a sequence labeling task and examine several models for labeling entities. We discuss our submitted tagger which uses a vanilla RNN and compare its performance to a DeepDive-based system, which lets us encode domain knowledge and sequence structure into a probabilistic graphic model. For Phase 2, we are given all test set entities and asked to identify the temporal relationship between an Event mention and corresponding document creation time. This relation is represented as a classification problem, assigning event attributes from the label set {Before, Overlap, Before/Overlap, After}. We use DeepDive to define several inference rules for leveraging neighboring pairs of Event and Timex3 mentions to better reason about temporal labels. ### Recurrent Neural Networks
Vanilla (or Elman-type) RNNs are recursive neural networks with a linear chain structure BIBREF3 . RNNs are similar to classical feedforward neural networks, except that they incorporate an additional hidden context layer that forms a time-lagged, recurrent connection (a directed cycle) to the primary hidden layer. In the canonical RNN design, the output of the hidden layer at time step INLINEFORM0 is retained in the context layer and fed back into the hidden layer at INLINEFORM1 this enables the RNN to explicitly model some aspects of sequence history. (see Figure FIGREF4 ). Each word in our vocabulary is represented as an INLINEFORM0 -dimensional vector in a lookup table of INLINEFORM1 x INLINEFORM2 parameters (i.e., our learned embedding matrix). Input features then consist of a concatenation of these embeddings to represent a context window surrounding our target word. The output layer then emits a probability distribution in the dimension of the candidate label set. The lookup table is shared across all input instances and updated during training. Formally our RNN definition follows BIBREF4 : INLINEFORM0 where INLINEFORM0 is our concatenated context window of word embeddings, INLINEFORM1 is our hidden layer, INLINEFORM2 is the input-to-hidden layer matrix, INLINEFORM3 is the hidden layer-to-context layer matrix, and INLINEFORM4 is the activation function (logistic in this work). INLINEFORM0 The output layer INLINEFORM0 consists of a softmax activation function INLINEFORM1 INLINEFORM0 INLINEFORM1 where INLINEFORM0 is the output layer matrix. Training is done using batch gradient descent using one sentence per batch. Our RNN implementation is based on code available as part of Theano v0.7 BIBREF5 . For baseline RNN models, all embedding parameters are initialized randomly in the range [-1.0, 1.0]. For all other word-based models, embedding vectors are initialized or pre-trained with parameters trained on different clinical corpora. Pre-training generally improves classification performance over random initialization and provides a mechanism to leverage large collections of unlabeled data for use in semi-supervised learning BIBREF6 . We create word embeddings using two collections of clinical documents: the MIMIC-III database containing 2.4M notes from critical care patients at Beth Israel Deaconess Medical Center BIBREF7 ; and the University of Iowa Hospitals and Clinics (UIHC) corpus, containing 15M predominantly inpatient notes (see Table TABREF6 ). All word embeddings in this document are trained with word2vec BIBREF8 using the Skip-gram model, trained with a 10 token window size. We generated 100 and 300 dimensional embeddings based on prior work tuning representation sizes in clinical domains BIBREF9 . We train RNN models for three tasks in Phase 1: a character-level RNN for tokenization; and two word-level RNNs for POS tagging and entity labeling. Word-level RNNs are pre-trained with the embeddings described above, while character-level RNNs are randomly initialized. All words are normalized by lowercasing tokens and replacing digits with N, e.g., 01-Apr-2016 becomes NN-apr-NNNN to improve generalizability and restrict vocabulary size. Characters are left as unnormalized input. In the test data set, unknown words/characters are represented using the special token <UNK> . All hyperparameters were selected using a randomized grid search. Tokenization: Word tokenization and sentence boundary detection are done simultaneously using a character-level RNN. Each character is assigned a tag from 3 classes: WORD(W) if a character is a member of a token that does not end a sentence; END(E) for a token that does end a sentence, and whitespace O. We use IOB2 tagging to encode the range of token spans. Models are trained using THYME syntactic annotations from colon and brain cancer notes. Training data consists of all sentences, padded with 5 characters from the left and right neighboring sentences. Each character is represented by a 16-dimensional embedding (from an alphabet of 90 characters) and an 11 character context window. The final prediction task input is one, long character sequence per-document. We found that the tokenizer consistently made errors conflating E and W classes (e.g., B-W, I-E, I-E) so after tagging, we enforce an additional consistency constraint on B-* and I-* tags so that contiguous BEGIN/INSIDE spans share the same class. Part-of-speech Tagging: We trained a POS tagger using THYME syntactic annotations. A model using 100-dimensional UIHC-CN embeddings (clinic notes) and a context window of INLINEFORM0 2 words performed best on held out test data, with an accuracy of 97.67% and F INLINEFORM1 = 0.973. TIMEX3 and EVENT Span Tagging: We train separate models for each entity type, testing different pre-training schemes using 100 and 300-dimensional embeddings trained on our large, unlabeled clinical corpora. Both tasks use context windows of INLINEFORM0 2 words (i.e., concatenated input of 5 INLINEFORM1 -d word embeddings) and a learning rate of 0.01. We use 80 hidden units for 100-dimensional embeddings models and 256 units for 300-dimensional models. Output tags are in the IOB2 tagging format. ### DeepDive
DeepDive developers build domain knowledge into applications using a combination of distant supervision rules, which use heuristics to generate noisy training examples, and inference rules which use factors to define relationships between random variables. This design pattern allows us to quickly encode domain knowledge into a probabilistic graphical model and do joint inference over a large space of random variables. For example, we want to capture the relationship between Event entities and their closest Timex3 mentions in text since that provides some information about when the Event occurred relative to document creation time. Timex3s lack a class DocRelTime, but we can use a distant supervision rule to generate a noisy label that we then leverage to predict neighboring Event labels. We also know that the set of all Event/Timex3 mentions within a given note section, such as patient history, provides discriminative information that should be shared across labels in that section. DeepDive lets us easily define these structures by linking random variables (in this case all entity class labels) with factors, directly encoding domain knowledge into our learning algorithm. Phase 1: Our baseline tagger consists of three inference rules: logistic regression, conditional random fields (CRF), and skip-chain CRF BIBREF10 . In CRFs, factor edges link adjoining words in a linear chain structure, capturing label dependencies between neighboring words. Skip-chain CRFs generalize this idea to include skip edges, which can connect non-neighboring words. For example, we can link labels for all identical words in a given window of sentences. We use DeepDive's feature library, ddlib, to generate common textual features like context windows and dictionary membership. We explored combinations of left/right windows of 2 neighboring words and POS tags, letter case, and entity dictionaries for all vocabulary identified by the challenge's baseline memorization rule, i.e., all phrases that are labeled as true entities INLINEFORM0 50% of the time in the training set. Feature Ablation Tests We evaluate 3 feature set combinations to determine how each contributes predictive power to our system. Run 1: dictionary features, letter case Run 2: dictionary features, letter case, context window ( INLINEFORM0 2 normalized words) Run 3: dictionary features, letter case, context window ( INLINEFORM0 2 normalized words), POS tags Phase 2: In order to predict the relationship between an event and the creation time of its parent document, we assign a DocRelTime random variable to every Timex3 and Event mention. For Events, these values are provided by the training data, for Timex3s we have to compute class labels. Around 42% of Timex3 mentions are simple dates (“12/29/08", “October 16", etc.) and can be naively canonicalized to a universal timestamp. This is done using regular expressions to identify common date patterns and heuristics to deal with incomplete dates. The missing year in “October 16", for example, can be filled in using the nearest preceding date mention; if that isn't available we use the document creation year. These mentions are then assigned a class using the parent document's DocTime value and any revision timestamps. Other Timex3 mentions are more ambiguous so we use a distant supervision approach. Phrases like “currently" and “today's" tend to occur near Events that overlap the current document creation time, while “ago" or “ INLINEFORM0 -years" indicate past events. These dominant temporal associations can be learned from training data and then used to label Timex3s. Finally, we define a logistic regression rule to predict entity DocRelTime values as well as specify a linear skip-chain factor over Event mentions and their nearest Timex3 neighbor, encoding the baseline system heuristic directly as an inference rule. ### Phase 1
Word tokenization performance was high, F INLINEFORM0 =0.993 while sentence boundary detection was lower with F INLINEFORM1 = 0.938 (document micro average F INLINEFORM2 = 0.985). Tokenization errors were largely confined to splitting numbers and hyphenated words (“ex-smoker" vs. “ex - smoker") which has minimal impact on upstream sequence labeling. Sentence boundary errors were largely missed terminal words, creating longer sentences, which is preferable to short, less informative sequences in terms of impact on RNN mini-batches. Tables TABREF13 and TABREF14 contain results for all sequence labeling models. For Timex3 spans, the best RNN ensemble model performed poorly compared to the winning system (0.706 vs. 0.795). DeepDive runs 2-3 performed as well as 2015's best system, but also fell short of the top system (0.730 vs. 0.795). Event spans were easier to tag and RNN models compared favorably with DeepDive, the former scoring higher recall and the latter higher precision. Both approaches scored below this year's best system (0.885 vs. 0.903). ### Phase 2
Finally, Table TABREF16 contains our DocRelTime relation extraction. Our simple distant supervision rule leads to better performance than then median system submission, but also falls substantially short of current state of the art. ### Discussion
Randomly initialized RNNs generally weren't competitive to our best performing structured prediction models (DeepDive runs 2-3) which isn't surprising considering the small amount of training data available compared to typical deep-learning contexts. There was a statistically significant improvement for RNNs pre-trained with clinical text word2vec embeddings, reflecting the consensus that embeddings capture some syntactic and semantic information that must otherwise be manually encoded as features. Performance was virtually the same across all embedding types, independent of corpus size, note type, etc. While embeddings trained on more data perform better in semantic tasks like synonym detection, its unclear if that representational strength is important here. Similar performance might also just reflect the general ubiquity with which temporal vocabulary occurs in all clinical note contexts. Alternatively, vanilla RNNs rarely achieve state-of-the-art performance in sequence labeling tasks due to well-known issues surrounding the vanishing or exploding gradient effect BIBREF12 . More sophisticated recurrent architectures with gated units such as Long Short-Term Memory (LSTM), BIBREF13 and gated recurrent unit BIBREF14 or recursive structures like Tree-LSTM BIBREF15 have shown strong representational power in other sequence labeling tasks. Such approaches might perform better in this setting. DeepDive's feature generator libraries let us easily create a large space of binary features and then let regularization address overfitting. In our extraction system, just using a context window of INLINEFORM0 2 words and dictionaries representing the baseline memorization rules was enough to achieve median system performance. POS tag features had no statistically significant impact on performance in either Event/Timex3 extraction. For classifying an Event's document creation time relation, our DeepDive application essentially implements the joint inference version of the baseline memorization rule, leveraging entity proximity to increase predictive performance. A simple distant supervision rule that canonicalizes Timex3 timestamps and predicts nearby Event's lead to a slight performance boost, suggesting that using a larger collection of unlabeled note data could lead to further increases. While our systems did not achieve current state-of-the-art performance, DeepDive matched last year's top submission for Timex3 and Event tagging with very little upfront engineering – around a week of dedicated development time. One of the primary goals of this work was to avoid an over-engineered extraction pipeline, instead relying on feature generation libraries or deep learning approaches to model underlying structure. Both systems explored in this work were successful to some extent, though future work remains in order to close the performance gap between these approaches and current state-of-the-art systems. ### Acknowledgments
This work was supported by the Mobilize Center, a National Institutes of Health Big Data to Knowledge (BD2K) Center of Excellence supported through Grant U54EB020405. Figure 1: Simple Recurrent Neural Network. U is the input × hidden layer weight matrix. V is the context layer × hidden layer matrix, and W is the output weight matrix. Dotted lines indicate recurrent edge weights. Table 1: Summary statistics for embedding corpora. Table 2: TIMEX3 spans extraction performance for the test set (mean of 5 runs) [1] Baseline and BluLab scores are provided in (Bethard et al., 2015) Table 4: Phase 2: EVENT Document Creation Time Relation extraction measures (baseline precision/recall scores not provided). Table 3: EVENT spans extraction performance.
|
dominant temporal associations can be learned from training data
|
What is the Bureau of Vital Statistics and what is its purpose?
A. It holds a computer whose design is thought to be humanity’s greatest achievement. The computer keeps track of all humans, monitoring their health, their lifespan, and where they are on Earth.
B. It holds a computer whose design is thought to be humanity’s greatest achievement. The computer monitors whether certain countries are more susceptible to alien invasion.
C. It holds a computer whose design is thought to be humanity’s greatest achievement. The computer keeps track of what is happening on nearby planets.
D. It holds a computer that keeps track of how many people are currently infected by the plague—a technology thought to be humanity’s greatest achievement.
|
"Phone Me in Central Park" By JAMES McCONNELL There should be an epitaph for every man, big or little, but a really grand and special one for Loner Charlie. [Transcriber's Note: This etext was produced from Planet Stories Fall 1954. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Charles turned over on his side to look at her. She lay quietly in the other bed, the most beautiful woman he had ever seen. She was blonde to perfection, exquisitely shaped, and the rich promise of her body was exposed to his view. "Why?" he thought as he looked at her. "Why did it have to happen like this?" The whole thing was still like a dream to him, and as yet he couldn't decide whether it was a good or a bad dream. A year ago she had been unattainable, a face to conjure with in erotic dreams, far beyond his ken. A year ago she had been a public idol, the most popular actress of the day. And he had been a nobody, full of a nobody's idle hopes and schemes. And now he was lying in the bed next to hers in her swank Manhattan apartment in the most exclusive hotel in town. The unrealness of the situation overwhelmed him. His mind was a picture of confused thoughts. Meanings and answers to his questions slithered out of his reach. "God," he said. It was not an exclamation, nor yet an expletive. It was a mere statement of fact. A thought teased at him. Charles looked at the woman again and decided that she still looked beautiful in spite of the harshness of the room's lighting. He touched buttons by the edge of the bed and the illumination quieted to a soft glow, wrapping her in a radiant halo. Charles smiled wanly and got up. He stood by the bed looking at her. "I could have fallen in love with you once. A year ago, perhaps, or longer. But not now. Not now." He turned away and walked to the window. "Now the world is dead. The whole world is dead." New York lay quietly below him. It was the hour of indecision when day has not quite made up its mind to leave and night has not yet attacked in force. The streetlights were already on, making geometric patterns through the dusk of Central Park. Some of the billboards were shining, their relays activated by darkness-sensitized solenoids. A reddish-orange pallor hung from the sky. It had been very pleasant that afternoon. She had given of herself freely, warmly, and Charles had accepted. But then he had known that she would. It was not him, it was the circumstances. Under the circumstances, she would have given herself to any man— "Why did it have to be her—or me? Why should it have to happen to anybody! Why!" She would have given herself to any man— His thoughts beat a rapid crescendo, activating emotions, stimulating sensations of angry rage. He wanted to cry, to weep angry tears of protest. To any man, WHO HAPPENED TO BE THE LAST MAN ON EARTH! Charles picked up a heavy book end off the table and crashed it through the thick pane of window glass. A gust of wind from the outside breezed through the shattered opening, attacking his olfactory patch with the retching smell of decaying flesh. Charles ignored it. Even smells had lost their customary meanings. He felt the rage build up inside again, tearing at his viscera. His stomach clenched up like an angry fist. "But I don't want to be the last man alive!" he shouted. "I don't know what to do! I don't know where to go, how to act! I just don't know—" A paroxysm of sobbing shook his body. Trembling, he dropped to his knees, his head against the cold firmness of the sill, his hands clutched tightly around the jagged edges of the window pane. In spite of the sharp pain that raced through his system, in spite of the bright, warm, red stream that trickled down his face, he knelt by the window for several minutes. " Maybe I'm not the last! " The thought struck him with suddenness, promisingly, edged with swelling comfort to fill his emptiness. Charles got up slowly, noticing for the first time that his fingers were badly cut. He wrapped a handkerchief around them and forgot them. He had to know—he had to find out. As he turned to leave, he noticed again the woman lying in radiant state upon the bed. He walked to her side and leaned over, kissing her gently on the forehead. As he straightened up, his leg caught against her arm, pushing it slightly. The woman's arm slipped from its position and dangled from the edge of the bed like a crazy pendulum. Charles picked it up and folded it across her now cold breasts. He started to pull the sheet over her nude form, then stopped, smiling at his conventionality. After all, it didn't make any difference now. The phonograph was near the door. On sudden impulse he switched it on, turned the volume up full, and in grim jest left it playing Rachmaninoff's Isle of the Dead on full automatic. The music haunted him down the hall to the elevator that he had to run himself. The lobby was littered with debris, human and otherwise. Charles ignored it. The street that led towards the Bureau of Vital Statistics was a mess of desolate carnage. Charles overlooked it. Shop fronts smashed, stores looted, gyro-cars wrecked, proud buildings defaced. "That was it," he said to himself. "Pride. We called this the 'Proud Era.' Everything was better and bigger and nicer to have. Buildings were taller, men were healthier, most of the problems of humanity seemed licked, or nearly so. It was a time of free power, each small unit of population, each section of town operating on perpetual, ever-lasting, automatic atomic piles. "We were free. We seemed, almost, to have accomplished something. The world was running well. No wonder we called it the 'Proud Era.' Life was fun, just a bowl of cherries, until...." Two years ago the animals had started dying. Strangely enough the rats had gone first, to anybody's notice. Sales of poison dropped, scientific laboratories chained to a perpetual rodent-cycle began to complain bitterly. Then the lovers who hunted out and haunted the lonely lanes through the countryside began to remark that the locusts were late that year. The Southern states joyously reported that mosquito control was working to an unprecedented degree. The largest cotton crop ever was forecast and rumors from Mexico had it that no one had died from scorpion bite in several weeks. A month later the meat animals, the birds and the household pets began dropping as rapidly as the flies which had dropped earlier. Congress was called into special session, as were all of the national governments around the world. The U.N. met at emergency sessions to cope with the situation. The president of the world-wide Society for the Prevention of Cruelty to Animals committed suicide. Within a year it was obvious to everyone that man was the only animal left on earth. The panic which had begun with the death of the animals was quieted somewhat by the fact that humans seemed immune to the pandemic. But the lakes full of dead fish caused a great stink and residents along the coasts began to move inland. Sales of perfumes and deodorants soared. Then just one year ago, the first human became infected with the strange malady. Within six months, half of the world's population was gone. Less than a month ago no more than a few thousand people remained in New York. And now.... "I've got to find out," Charles told himself. He meant it, of course, but in a sense he was afraid—afraid that his trip to the Bureau might give him an answer he didn't dare listen to. "But I've got to try." He walked on down the bloody street. Before the plague the Bureau of Vital Statistics had been one of man's crowning achievements. Housed as it was in a huge metallic globe of a building, it contained computers which kept exact account of every human on earth. Compulsory registration and the classification of each individual by means of the discrete patterns of his brain waves had accomplished for man what no ordinary census could have. The machine knew who was alive, who was dead, and where everybody was. Once a year the Bureau issued The Index, an exact accounting of Earth's four billion inhabitants. Four billion names and addresses, compressed into microprint, a tremendous achievement even for the "Proud Era." In all of his life, Charles had never once glanced at The Index. The average person had little necessity to do so since the Bureau information service would answer questions free of charge at any time. Reaching the gigantic building, Charles pushed aside the body of a young man and walked into the main foyer. Passing behind once-guarded doors, he entered the giant computer room and paused in admiration. Only once, before the plague, had he seen the interior of this room. But he still remembered it and he still recalled the powerful emotional experience it had been those many years ago. All children had to have a brain-wave recording made by the Bureau during the first month of their life. And again at the age of 10 each child returned to the Bureau for a recheck. It was for this latter recording that Charles had come to the Bureau some twenty-two years before and a friendly guard had let him peep briefly into the computer room. The impression of intense activity, of organized confusion, of mechanical wonder had remained with him the rest of his life. "So different now," he thought, surveying the room. "Now it's empty, so empty." The machine seemed to reflect the stillness, the very deadness of the world. The silence became unbearable. Charles walked to the master control panel. With newly acquired dexterity he switched the computer screens on and watched them glow to life. All around the world sensitive receiving stations pulsed to activity, sending out searching fingers, hunting for elusive patterns of neutral energy, mapping and tabulating the results. The main computer screen dominated one wall of the room. Other smaller screens clustered around it. On these screens could be graphed the population of any and every part of the globe. An illuminated counter immediately above it would give the numerical strength of the area being sampled while the screen would show population density by individual pinpoints of light that merged to form brightness patterns. "I'll try New York first," he said to himself, knowing that he was a coward, afraid to check the whole world from the start. "I'll start with New York and work up." Charles activated the switches that would flash a schematic map of New York on the screen. "There's bound to be somebody else left here. After all, there were at least twenty of us just a couple of days ago." And one of them, a beautiful woman, had invited him up to her apartment, not because she liked him, but because.... The main screen focused itself, the patterns shifting into a recognizable perceptual image. "Why, it was just yesterday (or was it the day before?) that ten of us, at least, met here to check the figures. There were lots of us alive then." Including the blond young woman who had died just this afternoon.... Charles stopped talking and forced his eyes upwards. Peripheral vision caught first the vague outlines of the lower part of the map. His eyes continued to move, slowly, reluctantly. They caught the over-all relief of Greater New York City—and then concentrated on the single, shining dot at the very heart of the map—and he understood. His eyes stabbed quickly for the counter above the screen. One. He gasped. The counter read one . Charles was by himself, the last person alive in all of New York City. He began to tremble violently. The silence of the room began to press quickly in on him. His frantic fingers searched for the computer controls. New York State. One. The entire United States. One. The western hemisphere, including islands. (Was that a point of light in Brazil? No. Just a ghost image). One. The Pacific area, Asia, Australia, Asia Minor, Russia and the Near East, Africa and then Europe. England! There was a light in England! Someone else still lived! The counter clicked forward. Two! His trembling stopped. He breathed again. "Of course. London was at least as populous as New York City before the plague. It's only logical that—" He stopped. For even as he spoke, the light winked out! The counter clicked again. One. Alone. Alone! Charles screamed. The bottom dropped out from under him! Why? Such a simple question, but in those three letters lay the essence of human nature. Why. The drive of curiosity. Stronger, in a way, than the so-called "basic" drives: hunger, thirst, sex, shelter, warmth, companionship, elimination. Certainly more decisive in the history of the race. Man began to think, to differentiate himself from the other animals, when he first asked the question: "Why?" But thinking about "why" didn't answer the question itself, Charles thought. He looked around him. He was sitting on a bench in Central Park, alone except for a few stray corpses. But the park was fairly free of bodies. "You've got about ten minutes warning," he said to himself. "I guess that most people wanted to die inside of something—inside of anything. Not out in the unprotected open." The silence was like a weight hanging around his neck. Not an insect noise, not the chirp of a bird, not the sound of a car nor the scream of a plane. Not even a breeze to whisper among the leaves, he thought. Civilization equals life equals noise. Silence equals.... Why. His mind kept returning to the question. Of all the people on earth, me. The last. Why me? Average, that's what he was. Height: 5'11". Weight: 165. Age: 32. Status: Married, once upon a time. The Norm, with no significant departures, all down the line. Church member, but not a good one. Could that be it? Could the most normal be the most perfect? Had he led the best of all possible lives? Was that it? Had God, in His infinite wisdom and mercy, spared his life, saved him, singled him out because he was most nearly a saint, most nearly Christ-like, most nearly.... Lies—His mind snapped back to reality. He half smiled. Saint? Christ? The Second Coming? He was no saint. Charles sighed. What about—? Chance. That was it! The laws of probability, the bell-shaped curve, normal distribution, rectilinear regression. More people per square foot in New York than elsewhere. The first person who died was from New York, so the last person who gave way to the disease should come from here too. Spin the wheel; throw the dice; toss the coin. So simple to explain by the laws of chance. No need for any underlying assumptions about good and evil, no need for teleological arguments concerning cause and effect. Simply explain it by chance. Somebody had to be the last to go and that was— "No," Charles said, standing up in the quiet of the spring evening. "No, chance won't do it. No man can reckon with chance. The mind rejects such things. There must be something beyond mere accident. There must be!" He sighed slowly. "So now I'm a hermit, whether or not I like it," he said in derision to the gravel path as he walked along it. "A hermit in the midst of a city of millions of—No, I forgot. There aren't any more people, are there?" It was hard to realize, even now. "A hermit, alone—and I haven't even got a cave...." Charles stopped walking suddenly. No cave, he thought. No place to sleep out the long one, no place to rest while time came to change things around and make them for the better. No place to hide. And suddenly it was the most important thing in life to him to find his "cave." It took him almost an hour to find the proper tools, and better than two hours more of hard, nighttime work to get the hole dug to his satisfaction. It took almost three hours to find the right sort of casket, durable but not too heavy for one man to handle. He carted it out to a grassy plot close to the center of the park where the grave was. He let the coffin down slowly into the depression, then piled up loose dirt on the sloping sides of the hole so that the rain would wash it down over him. "I can't very well bury myself," he said. "I guess it will rain after I'm gone." He looked carefully down at the metallic container. Wait now. There was something wrong, something missing. It was—oh, yes, he caught it. It was the stone. There wasn't any stone to go at the head of the grave. "I'll have to fix that." A sheet of metal, bent double, served for the monument proper. A nearby tool shed yielded up a can of paint and a brush. By the glow of one of the streetlights Charles worked out the inscription. "It ought to be something impressive," he thought out loud. "Something fitting the occasion." What did one say on these situations? There was so little chance to practice up for things like this. But it ought to be good, it ought to be proper. "'In this now hallowed corner of the planet Earth—' No. That sounds too ... too...." Make it simple, he thought. And he finally wrote: HERE LIES THE BODY OF THE LAST MAN ON EARTH Yes. That was it. Simple. Let whoever came afterwards figure out the rest. Let them decide. He smiled and finished the painting. Charles was hungry. He got up and started for one of the restaurants near the park. Later on, when there was more time, he'd find a piece of granite and move it to the plot. He could spend his free time carving on it, copying the inscription. He would make it into a real shrine; maybe he would practice up a bit and try to carve a statue to go with the stone. Somehow, though, since things were ready and it didn't make too much difference, it seemed to Charles that he'd probably have a long time to wait. "Maybe it's just a disease, and I'm immune. I was immune to smallpox. The vaccination never took. That's probably it." He smiled. Strange, but now he wanted very much to go on living, alone or not. There were things he could do, ways to keep occupied. He wouldn't mind it so much. But he wanted more and more desperately with each passing second to retain his foothold on the tenuous path of physical existence. The tantalizing thought of "why" puzzled its way back into his mind. But it seemed less pressing now that he had almost come to the conclusion that he would live for a long time. Later, in a few days perhaps, he would think about it. In a little while he'd have plenty of opportunity for hunting down the answer. This seemed good to him, for now he thought he almost had the answer, if there were an answer. He thought he had seen the solution peering out at him from the recesses of his mind, and he didn't like the expression on its face. Better to forget. Charles reached the broad boulevard. There was a large cafe just across from him, its front window caved in by a large truck. He stumbled and almost fell as he stepped from the curb. "Look at me, nervous as a cat." He was trembling noticeably as he started across the street. "I—" He started to say something, to think something. But some hidden part of his mind clamped down, obscuring the thought, rejecting the concept. The tremor turned to a shake before he reached the far curb, and the first burst of wild pain came as he laid his shoulder against the door to the restaurant. This was the way the plague began, but—His mind quickly repressed the idea. It couldn't be the plague. He was immune! Another burst of pulsating, shattering pain crashed through his body, tearing down the defenses of his mind, putting an end of his thoughts of immunity. Colors flared before his eyes, a persistent, irresistible susurrus flooded his ears. He wanted to protest, but there was no one to listen to him. He appealed to every divinity he knew, all the time knowing it would be useless. His body, out of his voluntary control, tried to run off in all directions at once. Charles struggled to end his body's disorganized responses, to channelize all his energy into one direction. His mind came back into action. He set up his goal; everything else seemed irrelevant: he had to get back to the park, to his hermit's cave, to his long, narrow home. He couldn't die until then. Ten minutes. He was allotted ten minutes before the end. It could have been ten years or ten seconds, for now objective time meant nothing to him. It was not a matter of measuring seconds and minutes. It was a matter of forgetting time and measuring space. He concentrated on the grave; he forced his body to become an unwilling machine. While he could, he walked, forcing himself on. When his legs gave way, he crawled. When his knees buckled, he rolled. When his stomach protested, he vomited. It made no difference. Charles refused to think. Machines, especially half-broken machines, do not think; they only work. Sweating, straining, bleeding, retching, he pushed himself towards his goal, trying to add one final touch of grace and custom to the rude irrationalness of it all. His eyes gave out a few feet from the pit. He felt his way towards it. Convulsions shook his body like a cat shakes a captive mouse. He humped his body forward between the seizures, hands outstretched, searching for the grave. And then he was upon it. One arm reached out for grass, and clutched bare space instead. He was home. He gathered energy from his final reservoirs of strength for one final movement that would throw him headlong into the shallow grave. He tensed his muscles, pulled his limbs up under him and started to roll into the hole. Instantly the thought struck him with paralyzing devastation. The answer to it all poked its face out from the recesses of his mind and sapped the last bit of his energy, corroding his nerves and dying muscles. Now he knew, and the knowing was the end of it. He collapsed at the edge of the pit. Only one arm hung loosely down into it, swinging senseless in the air, pointing accusingly at the empty coffin. The world will end, not with a bang, nor with a whimper, but with the last man's anguished cry at the unreasonableness of it all. Charles screamed. The large, invisible, ovular being that hung suspended over the Empire State Building rested from its exertion. Soon it was approached by another of its kind. "It is finished?" asked the second. "Yes. Just now. I am resting." "I can feel the emptiness of it." "It was very good. Where were you?" "On the next planet out. No beauty to it at all; no system. How was yours?" "Beautiful," said the first. "It went according to the strictest semantic relationship following the purest mathematical principles. They made it easy for me." "Good." "Well, where to now?" "There's another system about four thoughts away. We're due there soon." "All right. Let's go." "What's that you have there?" "Oh, this?" replied the first. "It's a higher neural order compendium the Things here made up. It's what I used." "You can't take it with you, you know. They don't allow souvenirs." "I know." "Well?" "All right, all right. You're so good, see if you can compute the scatter probability." The first being moved imperceptably and the heavy plastoid binding of the book disappeared. The thousands of pages dropped softly, caught at the wind like hungry sails, separated, and pulled by the fingers of gravity, went their disparate ways. Here a page scuttled into a broken window of the Chrysler Building (read the names: Aabat, Aabbs, Aabbt). Here a page landed upright on the head of one of the library lions and sloughed softly to the ground (read the names: Looman, Loomana, Loomanabsky). Here another page crept in between the cracks of a pier on the riverfront, dropping gently to the caressing eddies of the water (read the names: Smith, Smitha, Smitj). And here two pages danced down into Central Park, pirouetted, promenaded, and finally came to rest against a propped-up piece of metal (read the names: Whit, Whita, Whitacomb). It was not until the dusty morning sun stirred up the breezes that they fluttered down into the shallow hole beneath, unnoticed. The writing on the metal, until then partially obscured by the papers, became legible: HERE LIES THE BODY OF THE LAST MAN ON EARTH— CHARLES J. ZZYZST GO TO HELL!
|
A. It holds a computer whose design is thought to be humanity’s greatest achievement. The computer keeps track of all humans, monitoring their health, their lifespan, and where they are on Earth.
|
Why had Roger been trained by Opal?
A. because Opal wanted to further his experiment
B. because Opal needed help building a new gateway
C. because Opal was looking for someone to take his place
D. because Opal was unable to bring other men back
|
JUDAS RAM BY SAM MERWIN, Jr. Illustrated by JAMES VINCENT [Transcriber's Note: This etext was produced from Galaxy Science Fiction December 1950. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] The house was furnished with all luxuries, including women. If it only had a lease that could be broken— Roger Tennant, crossing the lawn, could see two of the three wings of the house, which radiated spoke-like from its heptagonal central portion. The wing on the left was white, with slim square pillars, reminiscent of scores of movie sets of the Deep South. That on the right was sundeck solar-house living-machine modern, something like a montage of shoeboxes. The wing hidden by the rest of the house was, he knew, spired, gabled and multicolored, like an ancient building in pre-Hitler Cracow. Dana was lying under a tree near the door, stretched out on a sort of deck chair with her eyes closed. She wore a golden gown, long and close-fitting and slit up the leg like the gown of a Chinese woman. Above it her comely face was sullen beneath its sleek cocoon of auburn hair. She opened her eyes at his approach and regarded him with nothing like favor. Involuntarily he glanced down at the tartan shorts that were his only garment to make sure that they were on properly. They were. He had thought them up in a moment of utter boredom and they were extremely comfortable. However, the near-Buchanan tartan did not crease or even wrinkle when he moved. Their captors had no idea of how a woven design should behave. "Waiting for me?" Tennant asked the girl. She said, "I'd rather be dead. Maybe I am. Maybe we're all dead and this is Hell." He stood over her and looked down until she turned away her reddening face. He said, "So it's going to be you again, Dana. You'll be the first to come back for a second run." "Don't flatter yourself," she replied angrily. She sat up, pushed back her hair, got to her feet a trifle awkwardly because of the tight-fitting tubular gown. "If I could do anything about it...." "But you can't," he told her. "They're too clever." "Is this crop rotation or did you send for me?" she asked cynically. "If you did, I wish you hadn't. You haven't asked about your son." "I don't even want to think about him," said Tennant. "Let's get on with it." He could sense the restless stirring of the woman within Dana, just as he could feel the stirring toward her within himself—desire that both of them loathed because it was implanted within them by their captors. They walked toward the house. It didn't look like a prison—or a cage. Within the dome of the barrier, it looked more like a well-kept if bizarre little country estate. There was clipped lawn, a scattering of trees, even a clear little brook that chattered unending annoyance at the small stones which impeded its flow. But the lawn was not of grass—it was of a bright green substance that might have been cellophane but wasn't, and it sprouted from a fabric that might have been canvas but was something else. The trees looked like trees, only their trunks were bark all the way through—except that it was not bark. The brook was practically water, but the small stones over which it flowed were of no earthly mineral. They entered the house, which had no roof, continued to move beneath a sky that glowed with light which did not come from a sun or moon. It might have been a well-kept if bizarre little country estate, but it wasn't. It was a prison, a cage. The other two women were sitting in the heptagonal central hall. Eudalia, who had borne twin girls recently, was lying back, newly thin and dark of skin and hair, smoking a scentless cigarette. A tall woman, thirtyish, she wore a sort of shimmering green strapless evening gown. Tennant wondered how she maintained it in place, for despite her recent double motherhood, she was almost flat of bosom. He asked her how she was feeling. "Okay, I guess," she said. "The way they manage it, there's nothing to it." She had a flat, potentially raucous voice. Eudalia had been a female foreman in a garment-cutting shop before being captured and brought through. "Good," he said. "Glad to hear it." He felt oddly embarrassed. He turned to Olga, broad, blonde and curiously vital, who sat perfectly still, regarding him over the pregnant swell of her dirndl-clad waist. Olga had been a waitress in a mining town hash-house near Scranton. Tennant wanted to put an encouraging hand on her shoulder, to say something that might cheer her up, for she was by far the youngest of the three female captives, barely nineteen. But with the eyes of the other two, especially Dana, upon him, he could not. "I guess I wasn't cut out to be a Turk," he said. "I don't feel at ease in a harem, even when it's supposedly my own." "You're not doing so badly," Dana replied acidly. "Lay off—he can't help it," said Eudalia unexpectedly. "He doesn't like it any better than we do." "But he doesn't have to—have them," objected Olga. She had a trace of Polish accent that was not unpleasant. In fact, Tennant thought, only her laughter was unpleasant, a shrill, uncontrolled burst of staccato sound that jarred him to his heels. Olga had not laughed of late, however. She was too frightened. "Let's get the meal ordered," said Dana and they were all silent, thinking of what they wanted to eat but would not enjoy when it came. Tennant finished with his order, then got busy with his surprise. It arrived before the meal, materializing against one of the seven walls of the roofless chamber. It was a large cabinet on slender straight legs that resembled dark polished wood. Tennant went to it, opened a hingeless door and pushed a knob on the inner surface. At once the air was hideous with the acerate harmony of a singing commercial.... ... so go soak your head, be it gold, brown or red, in Any-tone Shampoo! A disc jockey's buoyant tones cut in quickly as the final ooooo faded. "This is Grady Martin, your old night-owl, coming to you with your requests over Station WZZX, Manhattan. Here's a wire from Theresa McManus and the girls in the family entrance of Conaghan's Bar and Grill on West...." Tennant watched the girls as a sweet-voiced crooner began to ply an unfamiliar love lyric to a melody whose similarity to a thousand predecessors doomed it to instant success. Olga sat up straight, her pale blue eyes round with utter disbelief. She looked at the radio, at Tennant, at the other two women, then back at the machine. She murmured something in Polish that was inaudible, but her expression showed that it must have been wistful. Eudalia grinned at Tennant and, rising, did a sort of tap dance to the music, then whirled back into her chair, green dress ashimmer, and sank into it just to listen. Dana stood almost in the center of the room, carmine-tipped fingers clasped beneath the swell of her breasts. She might have been listening to Brahms or Debussy. Her eyes glowed with the salty brilliance of emotion and she was almost beautiful. " Rog! " she cried softly when the music stopped. "A radio and WZZX! Is it—are they—real?" "As real as you or I," he told her. "It took quite a bit of doing, getting them to put a set together. And I wasn't sure that radio would get through. TV doesn't seem to. Somehow it brings things closer...." Olga got up quite suddenly, went to the machine and, after frowning at it for a moment, tuned in another station from which a Polish-speaking announcer was followed by polka music. She leaned against the wall, resting one smooth forearm on the top of the machine. Her eyes closed and she swayed a little in time to the polka beat. Tennant caught Dana looking at him and there was near approval in her expression—approval that faded quickly as soon as she caught his gaze upon her. The food arrived then and they sat down at the round table to eat it. Tennant's meat looked like steak, it felt like steak, but, lacking the aroma of steak, it was almost tasteless. This was so with all of their foods, with their cigarettes, with everything in their prison—or their cage. Their captors were utterly without a human conception of smell, living, apparently, in a world without odor at all. Dana said suddenly, "I named the boy Tom, after somebody I hate almost as much as I hate you." Eudalia laid down her fork with a clatter and regarded Dana disapprovingly. "Why take it out on Rog?" she asked bluntly. "He didn't ask to come here any more than we did. He's got a wife back home. Maybe you want him to fall in love with you? Maybe you're jealous because he doesn't? Well, maybe he can't! And maybe it wouldn't work, the way things are arranged here." "Thanks, Eudalia," said Tennant. "I think I can defend myself. But she's right, Dana. We're as helpless as—laboratory animals. They have the means to make us do whatever they want." "Rog," said Dana, looking suddenly scared, "I'm sorry I snapped at you. I know it's not your fault. I'm— changing ." He shook his head. "No, Dana, you're not changing. You're adapting. We all are. We seem to be in a universe of different properties as well as different dimensions. We're adjusting. I can do a thing or two myself that seem absolutely impossible." "Are we really in the fourth dimension?" Dana asked. Of the three of them, she alone had more than a high-school education. "We may be in the eleventh for all I know," he told her. "But I'll settle for the fourth—a fourth dimension in space, if that makes scientific sense, because we don't seem to have moved in time. I wasn't sure of that, though, till we got the radio." "Why haven't they brought more of us through?" Eudalia asked, tamping out ashes in a tray that might have been silver. "I'm not sure," he said thoughtfully. "I think it's hard for them. They have a hell of a time bringing anyone through alive, and lately they haven't brought anyone through—not alive." "Why do they do it—the other way, I mean?" asked Dana. Tennant shrugged. "I don't know. I've been thinking about it. I suppose it's because they're pretty human." " Human! " Dana was outraged. "Do you call it human to—" "Hold on," he said. "They pass through their gateway to Earth at considerable danger and, probably, expense of some kind. Some of them don't come back. They kill those of us who put up a fight. Those who don't—or can't—they bring back with them. Live or dead, we're just laboratory specimens." "Maybe," Eudalia conceded doubtfully. Then her eyes blazed. "But the things they do—stuffing people, mounting their heads, keeping them on display in their—their whatever they live in. You call that human, Rog?" "Were you ever in a big-game hunter's trophy room?" Tennant asked quietly. "Or in a Museum of Natural History? A zoo? A naturalist's lab? Or even, maybe, photographed as a baby on a bear-skin rug?" "I was," said Olga. "But that's not the same thing." "Of course not," he agreed. "In the one instance, we're the hunters, the breeders, the trophy collectors. In the other"—he shrugged—"we're the trophies." There was a long silence. They finished eating and then Dana stood up and said, "I'm going out on the lawn for a while." She unzipped her golden gown, stepped out of it to reveal a pair of tartan shorts that matched his, and a narrow halter. "You thought those up while we ate," he said. It annoyed him to be copied, though he did not know why. She laughed at him silently, tossed her auburn hair back from her face and went out of the roofless house, holding the gold dress casually over her bare arm. Eudalia took him to the nursery. He was irritated now in another, angrier way. The infants, protected by cellophane-like coverlets, were asleep. "They never cry," the thin woman told him. "But they grow—God, how they grow!" "Good," said Tennant, fighting down his anger. He kissed her, held her close, although neither of them felt desire at the moment. Their captors had seen to that; it wasn't Eudalia's turn. Tennant said, "I wish I could do something about this. I hate seeing Dana so bitter and Olga so scared. It isn't their fault." "And it's not yours," insisted Eudalia. "Don't let them make you think it is." "I'll try not to," he said and stopped, realizing the family party was over. He had felt the inner tug of command, said good-by to the women and returned to his smaller compound within its own barrier dome. Then came the invisible aura of strain in the air, the shimmering illusion of heat that was not heat, that was prelude to his teleportation ... if that were the word. It was neither pleasant nor unpleasant; it was , that was all. He called it the training hall, not because it looked like a training hall but because that was its function. It didn't actually look like anything save some half-nourished dream a surrealist might have discarded as too nightmarish for belief. As in all of this strange universe, excepting the dome-cages in which the captives were held, the training hall followed no rules of three-dimensional space. One wall looked normal for perhaps a third of its length, then it simply wasn't for a bit. It came back farther on at an impossible angle. Yet, walking along it, touching it, it felt perfectly smooth and continuously straight. The opposite wall resembled a diagonal cross-section of an asymmetrical dumbbell—that was the closest Tennant could come to it in words. And it, too, felt straight. The floor looked like crystal smashed by some cosmic impact, yet it had reason. He knew this even though no reason was apparent to his three-dimensional vision. The ceiling, where he could see it, was beyond description. The captor Tennant called Opal came in through a far corner of the ceiling. He—if it was a he—was not large, although this, Tennant knew, meant nothing; Opal might extend thousands of yards in some unseen direction. He had no regular shape and much of him was iridescent and shot with constantly changing colors. Hence the name Opal. Communication was telepathic. Tennant could have yodeled or yelled or sung Mississippi Mud and Opal would have shown no reaction. Yet Tennant suspected that the captors could hear somewhere along the auditory scale, just as perhaps they could smell, although not in any human sense. You will approach without use of your appendages. The command was as clear as if it had been spoken aloud. Tennant took a deep breath. He thought of the space beside Opal. It took about three seconds and he was there, having spanned a distance of some ninety feet. He was getting good at it. Dog does trick, he thought. He went through the entire routine at Opal's bidding. When at last he was allowed to relax, he wondered, not for the first time, if he weren't mastering some of the alleged Guru arts. At once he felt probing investigation. Opal, like the rest of the captors, was as curious as a cat—or a human being. Tennant sat against a wall, drenched with sweat. There would be endless repetition before his workout was done. On Earth, dogs were said to be intellectually two-dimensional creatures. He wondered if they felt this helpless futility when their masters taught them to heel, to point, to retrieve. Some days later, the training routine was broken. He felt a sudden stir of near-sick excitement as he received the thought: Now you are ready. We are going through at last. Opal was nervous, so much so that he revealed more than he intended. Or perhaps that was his intent; Tennant could never be sure. They were going through to Tennant's own dimension. He wondered briefly just what his role was to be. He had little time to speculate before Opal seemed to envelop him. There was the blurring wrench of forced teleportation and they were in another room, a room which ended in a huge irregular passage that might have been the interior of a giant concertina—or an old-fashioned kodak. He stood before a kidney-shaped object over whose jagged surface colors played constantly. From Opal's thoughts it appeared to be some sort of ultradimensional television set, but to Tennant it was as incomprehensible as an oil painting to an animal. Opal was annoyed that Tennant could make nothing of it. Then came the thought: What cover must your body have not to be conspicuous? Tennant wondered, cynically, what would happen if he were to demand a costume of mediaeval motley, complete with Pied Piper's flute. He received quick reproof that made his head ring as from a blow. He asked Opal where and when they were going, was informed that he would soon emerge on Earth where he had left it. That told him everything but the date and season. Opal, like the rest of the captors, seemed to have no understanding of time in a human sense. Waiting, Tennant tried not to think of his wife, of the fact that he hadn't seen her in—was it more than a year and a half on Earth? He could have controlled his heartbeat with one of his new powers, but that might have made Opal suspicious. He should be somewhat excited. He allowed himself to be, though he obscured the reasons. He was going to see his wife again ... and maybe he could trick his way into not returning. The maid who opened the door for him was new, although her eyes were old. But she recognized him and stood aside to let him enter. There must, he thought, still be pictures of him around. He wondered how Agatha could afford a servant. "Is Mrs. Tennant in?" he asked. She shook her head and fright made twin stoplights of the rouge on her cheeks as she shut the door behind him. He went into the living room, directly to the long silver cigarette box on the coffee table. It was proof of homecoming to fill his lungs with smoke he could smell . He took another drag, saw the maid still in the doorway, staring. "There's no need for fright," he told her. "I believe I still own this house." Then, "When do you expect Mrs. Tennant?" "She just called. She's on her way home from the club." Still looking frightened, she departed for the rear of the house. Tennant stared after her puzzledly until the kitchen door swung shut behind her. The club? What club? He shrugged, returned to the feeling of comfort that came from being back here, about to see Agatha again, hold her close in no more than a few minutes. And stay, his mind began to add eagerly, but he pushed the thought down where Opal could not detect it. He took another deep, lung-filling drag on his cigarette, looked around the room that was so important a part of his life. The three women back there would be in a ghastly spot. He felt like a heel for wanting to leave them there, then knew that he would try somehow to get them out. Not, of course, anything that would endanger his remaining with Agatha; the only way his captors would get him back would be as a taxidermist's specimen. He realized, shocked and scared, that his thoughts of escape had slipped past his mental censor, and he waited apprehensively for Opal to strike. Nothing happened and he warily relaxed. Opal wasn't tapping his thoughts. Because he felt sure of his captive ... or because he couldn't on Earth? It was like being let out of a cage. Tennant grinned at the bookcase; the ebony-and-ivory elephants that Agatha had never liked were gone, but he'd get them back or another pair. The credenza had been replaced by a huge and ugly television console. That, he resolved, would go down in the cellar rumpus room, where its bleached modernity wouldn't clash with the casual antiquity of the living room. Agatha would complain, naturally, but his being back would make up for any amount of furniture shifting. He imagined her standing close to him, her lovely face lifted to be kissed, and his heart lurched like an adolescent's. This hunger was real, not implanted. Everything would be real ... his love for her, the food he ate, the things he touched, his house, his life.... Your wife and a man are approaching the house. The thought message from Opal crumbled his illusion of freedom. He sank down in a chair, trying to refuse to listen to the rest of the command: You are to bring the man through the gateway with you. We want another live male. Tennant shook his head, stiff and defiant in his chair. The punishment, when it came, was more humiliating than a slap across a dog's snout. Opal had been too interested in the next lab specimen to bother about his thoughts—that was why he had been free to think of escape. Tennant closed his eyes, willed himself to the front window. Now that he had mastered teleportation, it was incredible how much easier it was in his own world. He had covered the two miles from the gateway to the house in a mere seven jumps, the distance to the window in an instant. But there was no pleasure in it, only a confirmation of his captor's power over him. He was not free of them. He understood all too well what they wanted him to do; he was to play the Judas goat ... or rather the Judas ram, leading another victim to the fourth-dimensional pen. Grim, he watched the swoop of headlights in the driveway and returned to the coffee table, lit a fresh cigarette. The front door was flung open and his diaphragm tightened at the remembered sound of Agatha's throaty laugh ... and tightened further when it was followed by a deeper rumbling laugh. Sudden fear made the cigarette shake in his fingers. "... Don't be such a stuffed-shirt, darling." Agatha's mocking sweetness rang alarm-gongs in Tennant's memory. "Charley wasn't making a grab for me . He'd had one too many and only wanted a little fun. Really, darling, you seem to think that a girl...." Her voice faded out as she saw Tennant standing there. She was wearing a white strapless gown, had a blue-red-and-gold Mandarin jacket slung hussar-fashion over her left shoulder. She looked even sleeker, better groomed, more assured than his memory of her. "I'm no stuffed-shirt and you know it." Cass' tone was peevish. "But your idea of fun, Agatha, is pretty damn...." It was his turn to freeze. Unbelieving, Tennant studied his successor. Cass Gordon—the man , the ex-halfback whose bulk was beginning to get out of hand, but whose inherent aggressive grace had not yet deserted him. The man , that was all—unless one threw in the little black mustache and the smooth salesman's manner. "You know, Cass," Tennant said quietly, "I never for a moment dreamed it would be you." " Roger! " Agatha found her voice. "You're alive !" "Roger," repeated Tennant viciously. He felt sick with disgust. Maybe he should have expected a triangle, but somehow he hadn't. And here it was, with all of them going through their paces like a trio of tent-show actors. He said, "For God's sake, sit down." Agatha did so hesitantly. Her huge dark eyes, invariably clear and limpid no matter how much she had drunk, flickered toward him furtively. She said defensively, "I had detectives looking for you for six months. Where have you been, Rog? Smashing up the car like that and—disappearing! I've been out of my mind." "Sorry," said Tennant. "I've had my troubles, too." Agatha was scared stiff—of him. Probably with reason. He looked again at Cass Gordon and found that he suddenly didn't care. She couldn't say it was loneliness. Women have waited longer than eighteen months. He would have if his captors had let him. "Where in hell have you been, Rog?" Gordon's tone was almost parental. "I don't suppose it's news to you, but there was a lot of suspicion directed your way while that crazy killer was operating around here. Agatha and I managed to clear you." "Decent of you," said Tennant. He got up, crossed to the cabinet that served as a bar. It was fully equipped—with more expensive liquor, he noticed, than he had ever been able to afford. He poured a drink of brandy, waited for the others to fill their glasses. Agatha looked at him over the rim of hers. "Tell us, Rog. We have a right to know. I do, anyway." "One question first," he said. "What about those killings? Have there been any lately?" "Not for over a year," Cass told him. "They never did get the devil who skinned those bodies and removed the heads." So, Tennant thought, they hadn't used the gateway. Not since they had brought the four of them through, not since they had begun to train him for his Judas ram duties. Agatha was asking him if he had been abroad. "In a way," he replied unemotionally. "Sorry if I've worried you, Agatha, but my life has been rather—indefinite, since I—left." He was standing no more than four inches from this woman he had desired desperately for six years, and he no longer wanted her. He was acutely conscious of her perfume. It wrapped them both like an exotic blanket, and it repelled him. He studied the firm clear flesh of her cheek and chin, the arch of nostril, the carmine fullness of lower lip, the swell of bosom above low-cut gown. And he no longer wanted any of it or of her. Cass Gordon— It didn't have to be anybody at all. For it to be Cass Gordon was revolting. "Rog," she said and her voice trembled, "what are we going to do? What do you want to do?" Take her back? He smiled ironically; she wouldn't know what that meant. It would serve her right, but maybe there was another way. "I don't know about you," he said, "but I suspect we're in the same boat. I also have other interests." "You louse!" said Cass Gordon, arching rib cage and nostrils. "If you try to make trouble for Agatha, I can promise...." " What can you promise?" demanded Tennant. When Gordon's onset subsided in mumbles, he added, "Actually, I don't think I'm capable of making more than a fraction of the trouble for either of you that you both are qualified to make for yourselves." He lit a cigarette, inhaled. "Relax. I'm not planning revenge. After this evening, I plan to vanish for good. Of course, Agatha, that offers you a minor nuisance. You will have to wait six years to marry Cass—seven years if the maid who let me in tonight talks. That's the law, isn't it, Cass? You probably had it all figured out." "You bastard," said Cass. "You dirty bastard! You know what a wait like that could do to us." "Tristan and Isolde," said Tennant, grinning almost happily. "Well, I've had my little say. Now I'm off again. Cass, would you give me a lift? I have a conveyance of sorts a couple of miles down the road." He needed no telepathic powers to read the thoughts around him then. He heard Agatha's quick intake of breath, saw the split-second look she exchanged with Cass. He turned away, knowing that she was imploring her lover to do something, anything , as long as it was safe. Deliberately, Tennant poured himself a second drink. This might be easier and pleasanter than he had expected. They deserved some of the suffering he had had and there was a chance that they might get it. Tennant knew now why he was the only male human the captors had been able to take alive. Apparently, thanks to the rain-slick road, he had run the sedan into a tree at the foot of the hill beyond the river. He had been sitting there, unconscious, ripe fruit on their doorstep. They had simply picked him up. Otherwise, apparently, men were next to impossible for them to capture. All they could do was kill them and bring back their heads and hides as trophies. With women it was different—perhaps the captors' weapons, whatever they were, worked more efficiently on females. A difference in body chemistry or psychology, perhaps. More than once, during his long training with Opal, Tennant had sent questing thoughts toward his captor, asking why they didn't simply set up the gateway in some town or city and take as many humans as they wanted. Surprisingly there had been a definite fear reaction. As nearly as he could understand, it had been like asking an African pygmy, armed with a blowgun, to set up shop in the midst of a herd of wild elephants. It simply wasn't feasible—and furthermore he derived an impression of the tenuosity as well as the immovability of the gateway itself. They could be hurt, even killed by humans in a three-dimensional world. How? Tennant did not know. Perhaps as a man can cut finger or even throat on the edge of a near-two-dimensional piece of paper. It took valor for them to hunt men in the world of men. In that fact lay a key to their character—if such utterly alien creatures could be said to have character.
|
D. because Opal was unable to bring other men back
|
What is the significance of the title of the story?
A. It references the old technology that is disturbed
B. It is an image of the chase that Var and Neena are running from
C. It hints to the great power of the Watcher
D. It points to Var and Neena disrupting an area that is usually quiet
|
WHEN THE MOUNTAIN SHOOK By Robert Abernathy Illustrated by Kelly Freas [Transcriber Note: This etext was produced from IF Worlds of Science Fiction March 1954. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Dark was the Ryzga mountain and forbidding; steep were its cliffs and sheer its crevasses. But its outward perils could not compare with the Ryzgas themselves, who slept within, ready to wake and conquer.... At sunset they were in sight of the Ryzga mountain. Strangely it towered among the cliffs and snow-slopes of the surrounding ranges: an immense and repellently geometric cone, black, its sides blood-tinted by the dying sun. Neena shivered, even though the surrounding cold could not reach her. The ice-wind blew from the glacier, but Var's love was round her as a warming cloak, a cloak that glowed softly golden in the deepening twilight, even as her love was about him. Var said, "The Watcher's cave should be three miles beyond this pass." He stood rigid, trying to catch an echo of the Watcher's thoughts, but there was nothing. Perhaps the old man was resting. From the other direction, the long way that they two had come, it was not difficult to sense the thought of Groz. That thought was powerful, and heavy with vengeance. "Hurry," said Neena. "They're closer than they were an hour ago." She was beautiful and defiant, facing the red sunset and the black mountain. Var sensed her fear, and the love that had conquered it. He felt a wave of tenderness and bitterness. For him she had come to this. For the flame that had sprung between them at the Truce of New Grass, she had challenged the feud of their peoples and had left her home, to follow him. Now, if her father and his kinsmen overtook them, it would be death for Var, and for Neena living shame. Which of the two was worse was no longer a simple problem to Var, who had grown much older in the last days. "Wait," he commanded. While she waited he spun a dream, attaching it to the crags that loomed over the pass, and to the frozen ground underfoot. It was black night, as it would really be when Groz and his henchmen reached this place; lurid fire spewed from the Ryzga mountain, and strange lights dipped above it; and for good measure there was an avalanche in the dream, and hideous beasts rushed snapping and ravening from the crevices of the rock. "Oh!" cried Neena in involuntary alarm. Var sighed, shaking his head. "It won't hold them for long, but it's the best I can do now. Come on." There was no path. Now they were descending the steeper face of the sierra, and the way led over bottomless crevasses, sheer drops and sheer ascents, sheets of traitorous glare ice. Place after place had to be crossed on the air, and both grew weary with the effort such crossings cost. They hoarded their strength, helping one another; one alone might never have won through. It was starry night already when they saw the light from the Watcher's cave. The light shone watery and dim from beneath the hoary back of the glacier, and as they came nearer they saw why: the cave entrance was sealed by a sheet of ice, a frozen waterfall that fell motionless from the rocks above. They heard no sound. The two young people stared for a long minute, intrigued and fearful. Both had heard of this place, and the ancient who lived there to keep watch on the Ryzga mountain, as a part of the oldest legends of their childhood; but neither had been here before. But this was no time for shyness. Var eyed the ice-curtain closely to make sure that it was real, not dream-stuff; then he struck it boldly with his fist. It shattered and fell in a rain of splinters, sparkling in the light that poured from within. They felt the Watcher rouse, heard his footsteps, and finally saw him—a shrunken old man, white-haired, with a lined beardless face. The sight of him, more marred by age than anyone they had ever seen before, was disappointing. They had expected something more—an ancient giant, a tower of wisdom and strength. The Watcher was four hundred years old; beside him even Groz, who had always seemed so ancient, was like a boy. The Watcher peered at them in turn. "Welcome," he said in a cracked voice. He did not speak again; the rest of his conversation was in thought only. "Welcome indeed. I am too much alone here." "You were asleep!" said Var. Shock made his thought accusing, though he had not meant to be. The old man grinned toothlessly. "Never fear. Asleep or awake, I watch. Come in! You're letting in the wind." Inside the cave it was warm as summer. Var saw with some surprise that all the walls were sheathed in ice—warm to the touch, bound fast against melting by the Watcher's will. Light blazed in reflections from the ice walls, till there was no shadow in the place. Behind them began a tinkling of falling water, thawed from the glacial ridges above to descend sheet-wise over the cave mouth, freezing as it fell into lengthening icicles. The old man gazed at his work for a moment, then turned questioningly to the young pair. "We need a little rest out of the cold," said Var. "And food, if you can spare it. We're pursued." "Yes, yes. You shall have what I can give you. Make yourselves comfortable, and in one minute.... Pursued, eh? A pity. I see the world is as bad as it was when I was last in it." Hot food and drink were before them almost at once. The Watcher regarded them with compassion as their eyes brightened and some of the shadow of weariness lifted from them. "You have stolen your enemy's daughter, no doubt, young man? Such things happened when I was young." Warming to the old man now, Var sketched his and Neena's history briefly. "We should have been safe among my people by now. And before very long, I'm sure, I would have performed some deed which Groz would recognize as a worthy exploit, and would thus have healed the feud between our families. But our flight was found out too soon. They cut us off and forced us into the mountains, and now they are only a few hours behind us." "A pity, indeed. I would like to help you—but, you understand, I am the Mountain Watcher. I must be above feuds and families." Var nodded somberly, thinking that an old recluse would in any case be able to do little for them against Groz and his violent kinsfolk. "And what will you do now?" Var grinned mirthlessly. "We haven't much choice, since they're overtaking us. I have only one idea left: we can go where Groz may fear to follow us." "To the mountain, you mean." "And into it, if need be." The Watcher was broodingly silent; his eyes shifted to Neena, where she nestled by Var's side. He asked, "And you—are you willing to follow your lover in this?" Neena returned his gaze without flinching; then she looked sidelong at Var, and her lips curled with a proud and tender mockery. "Follow? Why, I will lead, if his courage should fail him." The old man said, "It is no part of my duty to dissuade you from this thing. You are free persons. But I must be sure that you know what you are doing. That is the second part of the law the First Watcher made: to guard lest the unwary and the ignorant should bring harm on themselves and on all men." "We know the stories," Var said brusquely. "In the hollow heart of their mountain the Ryzgas sleep, as they chose to do when their world crumbled. But if they are wakened, the mountain will tremble, and the Ryzgas will come forth." "Do you believe that?" "As one believes stories." "It is true," said the Watcher heavily. "In my youth I penetrated farther into the mountain than anyone before, farther even than did the First Watcher. I did not see the sleepers, nor will any man until they come again, but I met their sentries, the sentinel machines that guard them now as they have for two thousand years. When I had gone that far, the mountain began to shake, the force that is in the Earth rumbled below, and I returned in time." Now for the first time Var sensed the power in the old man's look, the power of four hundred years' wisdom. Var stared down at his hands. "The Ryzgas also were men," said the Watcher. "But they were such a race as the world has not seen before or since. There were tyrannies before the Ryzgas, there was lust for power, and atrocious cruelty; but such tyranny, power, and cruelty as theirs, had never been known. They ruled the Earth for four generations, and the Earth was too little for them. They laid the world waste, stripped it of metals and fuels and bored to its heart for energy, poisoned its seas and its air with the fume of their works, wrung its peoples dry for their labor ... and in each of those four generations they launched a ship of space. They were great and evil as no other people has been, because they wanted the stars. "Because of them we must build with dreams instead of iron, and our only fire is that of the Sun, and even now, two thousand years later, the Earth is still slowly recovering from the pangs and poison of that age. If you turn up the sod in the plain where the wild herds graze, you will find numberless fragments of rusted or corroded metal, bits of glass and strange plastic substances, debris of artifacts still showing the marks of their shaping—the scattered wreckage of the things they made. And we—we too are a remnant, the descendants of the few out of all humanity that survived when the Ryzgas' world went down in flame and thunder. "In the last generation of their power the Ryzgas knew by their science that the race of man would endure them no longer. They made ready their weapons, they mined the cities and the factories for destruction, making sure that their works and their knowledge would perish with them. Meanwhile they redoubled the yoke and the punishments, hastening the completion of the last of the starships. "From the memories that the old Watchers have left here, and from the memories of dead men that still echo in the air, I have gathered a picture of that world's end. I will show it to you...." Var and Neena stared, unstirring, with wide vacant eyes, while the old man wove a dream around them, and the bright ice-cave faded from their vision, and they saw— Black starless night, a sky of rolling smoke above the greatest city that was ever built. Only the angry light of fires relieved the city's darkness—that, and the blue-white lightning flashes that silhouetted the naked skeletons of buildings and were followed by thunder and a shaking of the earth. Along lightless streets, half choked with rubble and with the dead, poured a mad, hating horde. The recurrent flashes lit scarred faces, naked bodies blackened and maimed from the hell of the workshops where the Ryzgas' might had been forged, eyes that stared white and half sightless from the glare of the furnaces, gnarled hands that now at long last clutched the weapons of the last rebellion—a rebellion without hope of new life on a world gutted and smoldering from the fulfilment of the Ryzgas' dream, without slogans other than a cry for blood. Before them death waited around the citadel where the masters still fought. All round, from the lowest and most poisonous levels of the shattered city, the slaves swarmed up in their millions. And the lightning blazed, and the city howled and screamed and burned. Then, unbelievably, the thunder fell silent, and the silence swept outward like a wave, from ruined street to street. The mouths that had shouted their wrath were speechless, and the rage-blinded eyes were lifted in sudden awe. From the center, over the citadel, an immense white globe soared upward, rising swiftly without sound. They had never seen its like, but they knew. It was the last starship, and it was leaving. It poised motionless. For an instant the burning city lay mute; then the millions found voice. Some roared ferocious threats and curses; others cried desolately— wait! Then the whole city, the dark tumuli of its buildings and its leaping fires and tormented faces, and the black sky over it, seemed to twist and swim, like a scene under water when a great fish sweeps past, and the ship was gone. The stunned paralysis fell apart in fury. Flame towered over the citadel. The hordes ran and shrieked again toward the central inferno, and the city burned and burned.... Var blinked dazedly in the shadowless glow of the ice-cave. His arm tightened about Neena till she gasped. He was momentarily uncertain that he and she were real and here, such had been the force of the dream, a vision of such scope and reality as Var had never seen—no, lived through—before. With deep respect now he gazed upon the bent old man who was the Mountain Watcher. "Some of the Ryzgas took flight to the stars, and some perished on Earth. But there was a group of them who believed that their time to rule would come again. These raised a black mountain from the Earth's heart, and in hollows within it cast themselves into deathless sleep, their deathless and lifeless sentinels round them, to wait till someone dare arouse them, or until their chosen time—no one knows surely. "I have told you the story you know, and have shown you a glimpse of the old time, because I must make sure that you do not approach the mountain in ignorance. Our world is unwise and sometimes evil, full of arrogance, folly, and passion that are in the nature of man. Yet it is a happy world, compared to that the Ryzgas made and will make again." The Watcher eyed them speculatively. "Before all," he said finally, "this is a world where you are free to risk wakening the old tyrants, if in your own judgment your great need renders the chance worth taking." Neena pressed her face against Var's shoulder, hiding her eyes. In her mind as it groped for his there was a confusion of horror and pity. Var looked grimly at the Watcher, and would have spoken; but the Watcher seemed suddenly a very long way off, and Var could no longer feel his own limbs, his face was a numb mask. Dully he heard the old man say, "You are tired. Best sleep until morning." Var strove to cry out that there was no time, that Groz was near and that sleep was for infants and the aged, but his intention sank and drowned under wave upon wave of unconquerable languor. The bright cave swam and dissolved; his eyelids closed. Var woke. Daylight glimmered through the ice of the cave mouth. He had been unconscious, helpless, for hours! At the thought of that, panic gripped him. He had not slept since childhood, and he had forgotten how it was. He came to his feet in one quick movement, realizing in that action that sleep had refreshed his mind and body—realizing also that a footstep had wakened him. Across the cave he faced a young man who watched him coolly with dark piercing eyes that were familiar though he did not know the face. Neena sat up and stifled a cry of fright. Var growled, "Who are you? Where's the Watcher?" The other flashed white teeth in a smile. "I'm the Watcher," he answered. "Often I become a youth at morning, and relax into age as the day passes. A foolish amusement, no doubt, but amusements are few here." "You made us fall asleep. Groz will be on us—" "Groz and his people could not detect your thoughts as you slept. They were all night chasing elusive dreams on the high ridges, miles away." Var passed a hand across bewildered eyes. Neena said softly, "Thank you, Watcher." "Don't thank me. I take no sides in your valley feuds. But now you are rested, your minds are clear. Do you still mean to go on to the Ryzga mountain?" Not looking at the Watcher, Var muttered unsteadily, "We have no alternative." There was a liquid tinkling as the ice-curtain collapsed; the fresh breeze of morning swept into the cave. The youth beckoned to them, and they followed him outside. The glacial slope on which the cavern opened faced toward the mountain. It rose black and forbidding in the dawn as it had by sunset. To right and left of it, the grand cliffs, ocher and red, were lit splendidly by the morning sun, but the mountain of the Ryzgas drank in the light and gave nothing back. Below their feet the slope fell away into an opaque sea of fog, filling a mile-wide gorge. There was a sound of turbulent water, of a river dashed from rock to rock in its struggle toward the plain, but the curling fog hid everything. "You have an alternative," said the Watcher crisply. The two took their eyes from the black mountain and gazed at him in sudden hope, but his face was unsmiling. "It is this. You, Var, can flee up the canyon to the north, by a way I will show you, disguising your thoughts and masking your presence as well as you are able, while the girl goes in the other direction, southward, without seeking to conceal herself. Your pursuers will be deceived and follow her, and by the time they catch her it will be too late for them to overtake Var." That possibility had not occurred to them at all. Var and Neena looked at one another. Then by common consent they blended their minds into one. They thought, in the warm intimacy of unreserved understanding: " It would work: I-you would make the sacrifice of shame and mockery—yet these can be borne—that I-you might be saved from death—which is alone irreparable.... But to become I and you again—that cannot be borne. " They said in unison, "No. Not that." The Watcher's face did not change. He said gravely, "Very well. I will give you what knowledge I have that may help you when you enter the Ryzga mountain." Quickly, he impressed on them what he had learned of the structure of the mountain and of its guardian machines. Var closed his eyes, a little dizzied by the rapid flood of detail. "You are ready to go," said the Watcher. He spoke aloud, and his voice was cracked and harsh. Var opened his eyes in surprise, and saw that the Watcher had become again the hoary ancient of last night. Var felt a twinge of unfamiliar emotion; only by its echo in Neena's mind did he recognize it as a sense of guilt. He said stiffly, "You don't blame us?" "You have taken life in your own hands," rasped the Watcher. "Who does that needs no blessing and feels no curse. Go!" They groped through the fog above blank abysses that hid the snarling river, crept hand in hand, sharing their strength, across unstable dream bridges from crag to crag. Groz and his pack, in their numbers, would cross the gorge more surely and swiftly. When Var and Neena set foot at last on the cindery slope of the great volcanic cone, they sensed that the pursuit already halved their lead. They stood high on the side of the Ryzga mountain, and gazed at the doorway. It was an opaque yet penetrable well of darkness, opening into the face of a lava cliff, closed only by an intangible curtain—so little had the Ryzgas feared those who might assail them in their sleep. Var sent his thoughts probing beyond the curtain, listened intently, head thrown back, to their echoes that returned. The tunnel beyond slanted steeply downward. Var's hands moved, molding a radiant globe from the feeble sunshine that straggled through the fog-bank. With an abrupt motion he hurled it. The sun-globe vanished, as if the darkness had drunk it up, but though sight did not serve they both sensed that it had passed through to light up the depths beyond. For within the mountain something snapped suddenly alert—something alive yet not living, seeing yet blind. They felt light-sensitive cells tingle in response, felt electric currents sting along buried, long-idle circuits.... The two stood shivering together. The morning wind stirred, freshening, the fog lifted a little, and they heard a great voice crying, "There they are!" Var and Neena turned. Far out in the sea of fog, on a dream bridge that they could not see, stood Groz. He shook the staff he carried. It was too far to discern the rage that must contort his features, but the thought he hurled at them was a soundless bellow: "Young fools! I've caught you now!" Behind Groz the figures of his followers loomed up as striding shadows. Neena's hand tightened on Var's. Var sent a thought of defiance: "Go back! Or you'll drive us to enter the mountain!" Groz seemed to hesitate. Then he swung his staff up like a weapon, and for the two on the mountainside the world turned upside down, the mountain's black shoulder hung inverted above them and the dizzy gulf of sky was beneath. Var fought for footing with his balance gone, feeling Neena reel against him until, summoning all his strength, he broke the grip of the illusion and the world seemed to right itself. The mist billowed again and Groz was out of sight, but they could hear him exhorting his men to haste. Neena's face was deadly pale and her lips trembled, but her urgent whisper said, "Come on!" Together they plunged into the curtain of darkness. At Var's thought command Neena froze instantly. "Feel that!" he muttered, and she, listening, sensed it too: the infinitesimal trickle of currents behind what appeared to be a blank tunnel wall, a rising potential that seemed to whisper Ready ... ready.... The sun-globe floated behind them, casting light before them down the featureless tunnel that sloped always toward the mountain's heart. Var summoned it, and it drifted ahead, a dozen feet, a little more— Between wall and wall a blinding spindle of flame sprang into being, pulsed briefly with radiant energy that pained the eyes, and went out. The immaterial globe of light danced on before them. "Forward, before the charge builds up again!" said Var. A few feet further on, they stumbled over a pile of charred bones. Someone else had made it only this far. It was farther than the Watcher had gone into these uncharted regions, and only the utmost alertness of mind and sense had saved them from death in traps like this. But as yet the way was not blocked.... Then they felt the mountain begin to tremble. A very faint and remote vibration at first, then an increasingly potent shuddering of the floor under their feet and the walls around them. Somewhere far below immense energies were stirring for the first time in centuries. The power that was in the Earth was rising; great wheels commenced to turn, the mechanical servitors of the Ryzgas woke one by one and began to make ready, while their masters yet slept, for the moment of rebirth that might be near at hand. From behind, up the tunnel, came a clear involuntary thought of dismay, then a directed thought, echoing and ghostly in the confinement of the dark burrow: " Stop! —before you go too far!" Var faced that way and thought coldly: "Only if you return and let us go free." In the black reaches of the shaft his will groped for and locked with that of Groz, like the grip of two strong wrestlers. In that grip each knew with finality that the other's stubbornness matched his own—that neither would yield, though the mountain above them and the world outside should crumble to ruin around them. "Follow us, then!" They plunged deeper into the mountain. And the shaking of the mountain increased with every step, its vibrations became sound, and its sound was like that of the terrible city which they had seen in the dream. Through the slow-rolling thunder of the hidden machines seemed to echo the death-cries of a billion slaves, the despair of all flesh and blood before their monstrous and inhuman power. Without warning, lights went on. Blinking in their glare, Var and Neena saw that fifty paces before them the way opened out into a great rounded room that was likewise ablaze with light. Cautiously they crept forward to the threshold of that chamber at the mountain's heart. Its roof was vaulted; its circular walls were lined with panels studded with gleaming control buttons, levers, colored lights. As they watched light flicked on and off in changing patterns, registering the progressive changes in the vast complex of mechanisms for which this must be the central control station. Behind those boards circuits opened and closed in bewildering confusion; the two invaders felt the rapid shifting of magnetic fields, the fury of electrons boiling in vacuum.... For long moments they forgot the pursuit, forgot everything in wonder at this place whose remotest like they had never seen in the simplicity of their machineless culture. In all the brilliant space there was no life. They looked at one another, the same thought coming to both at once: perhaps, after two thousand years, the masters were dead after all, and only the machines remained? As if irresistibly drawn, they stepped over the threshold. There was a clang of metal like a signal. Halfway up the wall opposite, above a narrow ramp that descended between the instrument panels, a massive doorway swung wide, and in its opening a figure stood. Var and Neena huddled frozenly, half expecting each instant to be their last. And the Ryzga too stood motionless, looking down at them. He was a man of middle height and stocky build, clad in a garment of changing colors, of fabric delicate as dream-stuff. In his right hand, with the care one uses with a weapon, he grasped a gleaming metal tube; his other hand rested as for support against the frame of the doorway. That, and his movements when he came slowly down the ramp toward them, conveyed a queer suggestion of weariness or weakness, as if he were yet not wholly roused from his two millenia of slumber. But the Ryzga's manner and his mind radiated a consciousness of power, a pride and assurance of self that smote them like a numbing blow. With a new shock, Var realized that the Ryzga's thoughts were quite open. They had a terse, disconnected quality that was strange and unsettling, and in part they were couched in alien and unintelligible symbols. But there was no block. Apparently the Ryzga felt no need to close his mind in the presence of inferior creatures.... He paused with his back to the central control panel, and studied the interlopers with the dispassionate gaze of a scientist examining a new, but not novel, species of insect. His thoughts seemed to click, like metal parts of a mechanism falling into places prepared for them. The image occurred oddly to Var, to whom such a comparison would ordinarily have been totally strange. "Culture: late barbarism. Handwork of high quality—good. Physically excellent stock...." There was a complicated and incomprehensible schemata of numbers and abstract forms. "The time: two thousand years—more progress might have been expected, if any survivors at all initially postulated; but this will do. The pessimists were mistaken. We can begin again." Then, startlingly super-imposed on the cool progression of logical thought, came a wave of raw emotion, devastating in its force. It was a lustful image of a world once more obedient, crawling, laboring to do the Ryzgas' will— toward the stars, the stars! The icy calculation resumed: "Immobilize these and the ones indicated in the passage above. Then wake the rest...." Var was staring in fascination at the Ryzga's face. It was a face formed by the custom of unquestioned command; yet it was lined by a deeply ingrained weariness, the signs of premature age—denied, overridden by the driving will they had sensed a moment earlier. It was a sick man's face. The Ryzga's final thought clicked into place: Decision! He turned toward the switchboard behind him, reaching with practised certainty for one spot upon it. Neena screamed. Between the Ryzga and the control panel a nightmare shape reared up seven feet tall, flapping black amorphous limbs and flashing red eyes and white fangs. The Ryzga recoiled, and the weapon in his hand came up. There was an instantaneous glare like heat lightning, and the monster crumpled in on itself, twitched briefly and vanished. But in that moment a light of inspiration had flashed upon Var, and it remained. As the Ryzga stretched out his hand again, Var acted. The Ryzga froze, teetering off balance and almost falling, as a numbing grip closed down on all his motor nerves. Holding that grip, Var strode across the floor and looked straight into the Ryzga's frantic eyes. They glared back at him with such hatred and such evil that for an instant he almost faltered. But the Ryzga's efforts, as he strove to free himself from the neural hold, were as misdirected and unavailing as those of a child who has not learned to wrestle with the mind. Var had guessed right. When Neena in her terror had flung a dream monster into the Ryzga's way—a mere child's bogey out of a fairy tale—the Ryzga had not recognized it as such, but had taken it for a real being. Var laughed aloud, and with great care, as one communicates with an infant, he projected his thoughts into the other's mind. "There will be no new beginning for you in our world, Ryzga! In two thousand years, we've learned some new things. Now at last I understand why you built so many machines, such complicated arrangements of matter and energy to do simple tasks—it was because you knew no other way." Behind the hate-filled eyes the cold brain tried to reason still. "Barbarians...? Our party was wrong after all. After us the machine civilization could never rise again, because it was a fire that consumed its fuel. After us man could not survive on the Earth, because the conditions that made him great were gone. The survivors must be something else—capacities undeveloped by our science—after us the end of man, the beginning.... But those of us who chose to die were right." The tide of hate and sick desire rose up to drown all coherence. The Ryzga made a savage, wholly futile effort to lift the weapon in his paralyzed hand. Then his eyes rolled upward, and abruptly he went limp and fell in a heap, like a mechanical doll whose motive power has failed. Var felt Neena beside him, and drew her close. As she sobbed her relief, he continued to look down absently at the dead man. When at last he raised his head, he saw that the drama's end had had a further audience. In the outer doorway, backed by his clansmen, stood Groz, gazing first in stupefaction at the fallen Ryzga, then with something like awe at Var. Var eyed him for a long moment; then he smiled, and asked, "Well, Groz? Is our feud finished, or does your ambition for a worthy son-in-law go beyond the conqueror of the Ryzgas?"
|
A. It references the old technology that is disturbed
|
The story implies that ____ is responsible for fueling capitalism and colonialism?
A. knowledge
B. industrialism
C. greediness
D. globalization
|
A Gift From Earth By MANLY BANISTER Illustrated by KOSSIN [Transcriber's Note: This etext was produced from Galaxy Science Fiction August 1955. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Except for transportation, it was absolutely free ... but how much would the freight cost? "It is an outrage," said Koltan of the House of Masur, "that the Earthmen land among the Thorabians!" Zotul, youngest of the Masur brothers, stirred uneasily. Personally, he was in favor of the coming of the Earthmen to the world of Zur. At the head of the long, shining table sat old Kalrab Masur, in his dotage, but still giving what he could of aid and comfort to the Pottery of Masur, even though nobody listened to him any more and he knew it. Around the table sat the six brothers—Koltan, eldest and Director of the Pottery; Morvan, his vice-chief; Singula, their treasurer; Thendro, sales manager; Lubiosa, export chief; and last in the rank of age, Zotul, who was responsible for affairs of design. "Behold, my sons," said Kalrab, stroking his scanty beard. "What are these Earthmen to worry about? Remember the clay. It is our strength and our fortune. It is the muscle and bone of our trade. Earthmen may come and Earthmen may go, but clay goes on forever ... and with it, the fame and fortune of the House of Masur." "It is a damned imposition," agreed Morvan, ignoring his father's philosophical attitude. "They could have landed just as easily here in Lor." "The Thorabians will lick up the gravy," said Singula, whose mind ran rather to matters of financial aspect, "and leave us the grease." By this, he seemed to imply that the Thorabians would rob the Earthmen, which the Lorians would not. The truth was that all on Zur were panting to get their hands on that marvelous ship, which was all of metal, a very scarce commodity on Zur, worth billions of ken. Lubiosa, who had interests in Thorabia, and many agents there, kept his own counsel. His people were active in the matter and that was enough for him. He would report when the time was ripe. "Doubtless," said Zotul unexpectedly, for the youngest at a conference was expected to keep his mouth shut and applaud the decisions of his elders, "the Earthmen used all the metal on their planet in building that ship. We cannot possibly bilk them of it; it is their only means of transport." Such frank expression of motive was unheard of, even in the secret conclave of conference. Only the speaker's youth could account for it. The speech drew scowls from the brothers and stern rebuke from Koltan. "When your opinion is wanted, we will ask you for it. Meantime, remember your position in the family." Zotul bowed his head meekly, but he burned with resentment. "Listen to the boy," said the aged father. "There is more wisdom in his head than in all the rest of you. Forget the Earthmen and think only of the clay." Zotul did not appreciate his father's approval, for it only earned him a beating as soon as the old man went to bed. It was a common enough thing among the brothers Masur, as among everybody, to be frustrated in their desires. However, they had Zotul to take it out upon, and they did. Still smarting, Zotul went back to his designing quarters and thought about the Earthmen. If it was impossible to hope for much in the way of metal from the Earthmen, what could one get from them? If he could figure this problem out, he might rise somewhat in the estimation of his brothers. That wouldn't take him out of the rank of scapegoat, of course, but the beatings might become fewer and less severe. By and by, the Earthmen came to Lor, flying through the air in strange metal contraptions. They paraded through the tile-paved streets of the city, marveled here, as they had in Thorabia, at the buildings all of tile inside and out, and made a great show of themselves for all the people to see. Speeches were made through interpreters, who had much too quickly learned the tongue of the aliens; hence these left much to be desired in the way of clarity, though their sincerity was evident. The Earthmen were going to do great things for the whole world of Zur. It required but the cooperation—an excellent word, that—of all Zurians, and many blessings would rain down from the skies. This, in effect, was what the Earthmen had to say. Zotul felt greatly cheered, for it refuted the attitude of his brothers without earning him a whaling for it. There was also some talk going around about agreements made between the Earthmen and officials of the Lorian government, but you heard one thing one day and another the next. Accurate reporting, much less a newspaper, was unknown on Zur. Finally, the Earthmen took off in their great, shining ship. Obviously, none had succeeded in chiseling them out of it, if, indeed, any had tried. The anti-Earthmen Faction—in any culture complex, there is always an "anti" faction to protest any movement of endeavor—crowed happily that the Earthmen were gone for good, and a good thing, too. Such jubilation proved premature, however. One day, a fleet of ships arrived and after they had landed all over the planet, Zur was practically acrawl with Earthmen. Immediately, the Earthmen established what they called "corporations"—Zurian trading companies under terrestrial control. The object of the visit was trade. In spite of the fact that a terrestrial ship had landed at every Zurian city of major and minor importance, and all in a single day, it took some time for the news to spread. The first awareness Zotul had was that, upon coming home from the pottery one evening, he found his wife Lania proudly brandishing an aluminum pot at him. "What is that thing?" he asked curiously. "A pot. I bought it at the market." "Did you now? Well, take it back. Am I made of money that you spend my substance for some fool's product of precious metal? Take it back, I say!" The pretty young wife laughed at him. "Up to your ears in clay, no wonder you hear nothing of news! The pot is very cheap. The Earthmen are selling them everywhere. They're much better than our old clay pots; they're light and easy to handle and they don't break when dropped." "What good is it?" asked Zotul, interested. "How will it hold heat, being so light?" "The Earthmen don't cook as we do," she explained patiently. "There is a paper with each pot that explains how it is used. And you will have to design a new ceramic stove for me to use the pots on." "Don't be idiotic! Do you suppose Koltan would agree to produce a new type of stove when the old has sold well for centuries? Besides, why do you need a whole new stove for one little pot?" "A dozen pots. They come in sets and are cheaper that way. And Koltan will have to produce the new stove because all the housewives are buying these pots and there will be a big demand for it. The Earthman said so." "He did, did he? These pots are only a fad. You will soon enough go back to cooking with your old ones." "The Earthman took them in trade—one reason why the new ones are so cheap. There isn't a pot in the house but these metal ones, and you will have to design and produce a new stove if you expect me to use them." After he had beaten his wife thoroughly for her foolishness, Zotul stamped off in a rage and designed a new ceramic stove, one that would accommodate the terrestrial pots very well. And Koltan put the model into production. "Orders already are pouring in like mad," he said the next day. "It was wise of you to foresee it and have the design ready. Already, I am sorry for thinking as I did about the Earthmen. They really intend to do well by us." The kilns of the Pottery of Masur fired day and night to keep up with the demand for the new porcelain stoves. In three years, more than a million had been made and sold by the Masurs alone, not counting the hundreds of thousands of copies turned out by competitors in every land. In the meantime, however, more things than pots came from Earth. One was a printing press, the like of which none on Zur had ever dreamed. This, for some unknown reason and much to the disgust of the Lorians, was set up in Thorabia. Books and magazines poured from it in a fantastic stream. The populace fervidly brushed up on its scanty reading ability and bought everything available, overcome by the novelty of it. Even Zotul bought a book—a primer in the Lorian language—and learned how to read and write. The remainder of the brothers Masur, on the other hand, preferred to remain in ignorance. Moreover, the Earthmen brought miles of copper wire—more than enough in value to buy out the governorship of any country on Zur—and set up telegraph lines from country to country and continent to continent. Within five years of the first landing of the Earthmen, every major city on the globe had a printing press, a daily newspaper, and enjoyed the instantaneous transmission of news via telegraph. And the business of the House of Masur continued to look up. "As I have always said from the beginning," chortled Director Koltan, "this coming of the Earthmen had been a great thing for us, and especially for the House of Masur." "You didn't think so at first," Zotul pointed out, and was immediately sorry, for Koltan turned and gave him a hiding, single-handed, for his unthinkable impertinence. It would do no good, Zotul realized, to bring up the fact that their production of ceramic cooking pots had dropped off to about two per cent of its former volume. Of course, profits on the line of new stoves greatly overbalanced the loss, so that actually they were ahead; but their business was now dependent upon the supply of the metal pots from Earth. About this time, plastic utensils—dishes, cups, knives, forks—made their appearance on Zur. It became very stylish to eat with the newfangled paraphernalia ... and very cheap, too, because for everything they sold, the Earthmen always took the old ware in trade. What they did with the stuff had been hard to believe at first. They destroyed it, which proved how valueless it really was. The result of the new flood was that in the following year, the sale of Masur ceramic table service dropped to less than a tenth. Trembling with excitement at this news from their book-keeper, Koltan called an emergency meeting. He even routed old Kalrab out of his senile stupor for the occasion, on the off chance that the old man might still have a little wit left that could be helpful. "Note," Koltan announced in a shaky voice, "that the Earthmen undermine our business," and he read off the figures. "Perhaps," said Zotul, "it is a good thing also, as you said before, and will result in something even better for us." Koltan frowned, and Zotul, in fear of another beating, instantly subsided. "They are replacing our high-quality ceramic ware with inferior terrestrial junk," Koltan went on bitterly. "It is only the glamor that sells it, of course, but before the people get the shine out of their eyes, we can be ruined." The brothers discussed the situation for an hour, and all the while Father Kalrab sat and pulled his scanty whiskers. Seeing that they got nowhere with their wrangle, he cleared his throat and spoke up. "My sons, you forget it is not the Earthmen themselves at the bottom of your trouble, but the things of Earth. Think of the telegraph and the newspaper, how these spread news of every shipment from Earth. The merchandise of the Earthmen is put up for sale by means of these newspapers, which also are the property of the Earthmen. The people are intrigued by these advertisements, as they are called, and flock to buy. Now, if you would pull a tooth from the kwi that bites you, you might also have advertisements of your own." Alas for that suggestion, no newspaper would accept advertising from the House of Masur; all available space was occupied by the advertisements of the Earthmen. In their dozenth conference since that first and fateful one, the brothers Masur decided upon drastic steps. In the meantime, several things had happened. For one, old Kalrab had passed on to his immortal rest, but this made no real difference. For another, the Earthmen had procured legal authority to prospect the planet for metals, of which they found a good deal, but they told no one on Zur of this. What they did mention was the crude oil and natural gas they discovered in the underlayers of the planet's crust. Crews of Zurians, working under supervision of the Earthmen, laid pipelines from the gas and oil regions to every major and minor city on Zur. By the time ten years had passed since the landing of the first terrestrial ship, the Earthmen were conducting a brisk business in gas-fired ranges, furnaces and heaters ... and the Masur stove business was gone. Moreover, the Earthmen sold the Zurians their own natural gas at a nice profit and everybody was happy with the situation except the brothers Masur. The drastic steps of the brothers applied, therefore, to making an energetic protest to the governor of Lor. At one edge of the city, an area had been turned over to the Earthmen for a spaceport, and the great terrestrial spaceships came to it and departed from it at regular intervals. As the heirs of the House of Masur walked by on their way to see the governor, Zotul observed that much new building was taking place and wondered what it was. "Some new devilment of the Earthmen, you can be sure," said Koltan blackly. In fact, the Earthmen were building an assembly plant for radio receiving sets. The ship now standing on its fins upon the apron was loaded with printed circuits, resistors, variable condensers and other radio parts. This was Earth's first step toward flooding Zur with the natural follow-up in its campaign of advertising—radio programs—with commercials. Happily for the brothers, they did not understand this at the time or they would surely have gone back to be buried in their own clay. "I think," the governor told them, "that you gentlemen have not paused to consider the affair from all angles. You must learn to be modern—keep up with the times! We heads of government on Zur are doing all in our power to aid the Earthmen and facilitate their bringing a great, new culture that can only benefit us. See how Zur has changed in ten short years! Imagine the world of tomorrow! Why, do you know they are even bringing autos to Zur!" The brothers were fascinated with the governor's description of these hitherto unheard-of vehicles. "It only remains," concluded the governor, "to build highways, and the Earthmen are taking care of that." At any rate, the brothers Masur were still able to console themselves that they had their tile business. Tile served well enough for houses and street surfacing; what better material could be devised for the new highways the governor spoke of? There was a lot of money to be made yet. Radio stations went up all over Zur and began broadcasting. The people bought receiving sets like mad. The automobiles arrived and highways were constructed. The last hope of the brothers was dashed. The Earthmen set up plants and began to manufacture Portland cement. You could build a house of concrete much cheaper than with tile. Of course, since wood was scarce on Zur, it was no competition for either tile or concrete. Concrete floors were smoother, too, and the stuff made far better road surfacing. The demand for Masur tile hit rock bottom. The next time the brothers went to see the governor, he said, "I cannot handle such complaints as yours. I must refer you to the Merchandising Council." "What is that?" asked Koltan. "It is an Earthman association that deals with complaints such as yours. In the matter of material progress, we must expect some strain in the fabric of our culture. Machinery has been set up to deal with it. Here is their address; go air your troubles to them." The business of a formal complaint was turned over by the brothers to Zotul. It took three weeks for the Earthmen to get around to calling him in, as a representative of the Pottery of Masur, for an interview. All the brothers could no longer be spared from the plant, even for the purpose of pressing a complaint. Their days of idle wealth over, they had to get in and work with the clay with the rest of the help. Zotul found the headquarters of the Merchandising Council as indicated on their message. He had not been this way in some time, but was not surprised to find that a number of old buildings had been torn down to make room for the concrete Council House and a roomy parking lot, paved with something called "blacktop" and jammed with an array of glittering new automobiles. An automobile was an expense none of the brothers could afford, now that they barely eked a living from the pottery. Still, Zotul ached with desire at sight of so many shiny cars. Only a few had them and they were the envied ones of Zur. Kent Broderick, the Earthman in charge of the Council, shook hands jovially with Zotul. That alien custom conformed with, Zotul took a better look at his host. Broderick was an affable, smiling individual with genial laugh wrinkles at his eyes. A man of middle age, dressed in the baggy costume of Zur, he looked almost like a Zurian, except for an indefinite sense of alienness about him. "Glad to have you call on us, Mr. Masur," boomed the Earthman, clapping Zotul on the back. "Just tell us your troubles and we'll have you straightened out in no time." All the chill recriminations and arguments Zotul had stored for this occasion were dissipated in the warmth of the Earthman's manner. Almost apologetically, Zotul told of the encroachment that had been made upon the business of the Pottery of Masur. "Once," he said formally, "the Masur fortune was the greatest in the world of Zur. That was before my father, the famous Kalrab Masur—Divinity protect him—departed this life to collect his greater reward. He often told us, my father did, that the clay is the flesh and bones of our culture and our fortune. Now it has been shown how prone is the flesh to corruption and how feeble the bones. We are ruined, and all because of new things coming from Earth." Broderick stroked his shaven chin and looked sad. "Why didn't you come to me sooner? This would never have happened. But now that it has, we're going to do right by you. That is the policy of Earth—always to do right by the customer." "Divinity witness," Zorin said, "that we ask only compensation for damages." Broderick shook his head. "It is not possible to replace an immense fortune at this late date. As I said, you should have reported your trouble sooner. However, we can give you an opportunity to rebuild. Do you own an automobile?" "No." "A gas range? A gas-fired furnace? A radio?" Zotul had to answer no to all except the radio. "My wife Lania likes the music," he explained. "I cannot afford the other things." Broderick clucked sympathetically. One who could not afford the bargain-priced merchandise of Earth must be poor indeed. "To begin with," he said, "I am going to make you a gift of all these luxuries you do not have." As Zotul made to protest, he cut him off with a wave of his hand. "It is the least we can do for you. Pick a car from the lot outside. I will arrange to have the other things delivered and installed in your home." "To receive gifts," said Zotul, "incurs an obligation." "None at all," beamed the Earthman cheerily. "Every item is given to you absolutely free—a gift from the people of Earth. All we ask is that you pay the freight charges on the items. Our purpose is not to make profit, but to spread technology and prosperity throughout the Galaxy. We have already done well on numerous worlds, but working out the full program takes time." He chuckled deeply. "We of Earth have a saying about one of our extremely slow-moving native animals. We say, 'Slow is the tortoise, but sure.' And so with us. Our goal is a long-range one, with the motto, 'Better times with better merchandise.'" The engaging manner of the man won Zotul's confidence. After all, it was no more than fair to pay transportation. He said, "How much does the freight cost?" Broderick told him. "It may seem high," said the Earthman, "but remember that Earth is sixty-odd light-years away. After all, we are absorbing the cost of the merchandise. All you pay is the freight, which is cheap, considering the cost of operating an interstellar spaceship." "Impossible," said Zotul drably. "Not I and all my brothers together have so much money any more." "You don't know us of Earth very well yet, but you will. I offer you credit!" "What is that?" asked Zotul skeptically. "It is how the poor are enabled to enjoy all the luxuries of the rich," said Broderick, and went on to give a thumbnail sketch of the involutions and devolutions of credit, leaving out some angles that might have had a discouraging effect. On a world where credit was a totally new concept, it was enchanting. Zotul grasped at the glittering promise with avidity. "What must I do to get credit?" "Just sign this paper," said Broderick, "and you become part of our Easy Payment Plan." Zotul drew back. "I have five brothers. If I took all these things for myself and nothing for them, they would beat me black and blue." "Here." Broderick handed him a sheaf of chattel mortgages. "Have each of your brothers sign one of these, then bring them back to me. That is all there is to it." It sounded wonderful. But how would the brothers take it? Zotul wrestled with his misgivings and the misgivings won. "I will talk it over with them," he said. "Give me the total so I will have the figures." The total was more than it ought to be by simple addition. Zotul pointed this out politely. "Interest," Broderick explained. "A mere fifteen per cent. After all, you get the merchandise free. The transportation company has to be paid, so another company loans you the money to pay for the freight. This small extra sum pays the lending company for its trouble." "I see." Zotul puzzled over it sadly. "It is too much," he said. "Our plant doesn't make enough money for us to meet the payments." "I have a surprise for you," smiled Broderick. "Here is a contract. You will start making ceramic parts for automobile spark plugs and certain parts for radios and gas ranges. It is our policy to encourage local manufacture to help bring prices down." "We haven't the equipment." "We will equip your plant," beamed Broderick. "It will require only a quarter interest in your plant itself, assigned to our terrestrial company." Zotul, anxious to possess the treasures promised by the Earthman, won over his brothers. They signed with marks and gave up a quarter interest in the Pottery of Masur. They rolled in the luxuries of Earth. These, who had never known debt before, were in it up to their ears. The retooled plant forged ahead and profits began to look up, but the Earthmen took a fourth of them as their share in the industry. For a year, the brothers drove their shiny new cars about on the new concrete highways the Earthmen had built. From pumps owned by a terrestrial company, they bought gas and oil that had been drawn from the crust of Zur and was sold to the Zurians at a magnificent profit. The food they ate was cooked in Earthly pots on Earth-type gas ranges, served up on metal plates that had been stamped out on Earth. In the winter, they toasted their shins before handsome gas grates, though they had gas-fired central heating. About this time, the ships from Earth brought steam-powered electric generators. Lines went up, power was generated, and a flood of electrical gadgets and appliances hit the market. For some reason, batteries for the radios were no longer available and everybody had to buy the new radios. And who could do without a radio in this modern age? The homes of the brothers Masur blossomed on the Easy Payment Plan. They had refrigerators, washers, driers, toasters, grills, electric fans, air-conditioning equipment and everything else Earth could possibly sell them. "We will be forty years paying it all off," exulted Zotul, "but meantime we have the things and aren't they worth it?" But at the end of three years, the Earthmen dropped their option. The Pottery of Masur had no more contracts. Business languished. The Earthmen, explained Broderick, had built a plant of their own because it was so much more efficient—and to lower prices, which was Earth's unswerving policy, greater and greater efficiency was demanded. Broderick was very sympathetic, but there was nothing he could do. The introduction of television provided a further calamity. The sets were delicate and needed frequent repairs, hence were costly to own and maintain. But all Zurians who had to keep up with the latest from Earth had them. Now it was possible not only to hear about things of Earth, but to see them as they were broadcast from the video tapes. The printing plants that turned out mortgage contracts did a lush business. For the common people of Zur, times were good everywhere. In a decade and a half, the Earthmen had wrought magnificent changes on this backward world. As Broderick had said, the progress of the tortoise was slow, but it was extremely sure. The brothers Masur got along in spite of dropped options. They had less money and felt the pinch of their debts more keenly, but television kept their wives and children amused and furnished an anodyne for the pangs of impoverishment. The pottery income dropped to an impossible low, no matter how Zotul designed and the brothers produced. Their figurines and religious ikons were a drug on the market. The Earthmen made them of plastic and sold them for less. The brothers, unable to meet the Payments that were not so Easy any more, looked up Zotul and cuffed him around reproachfully. "You got us into this," they said, emphasizing their bitterness with fists. "Go see Broderick. Tell him we are undone and must have some contracts to continue operating." Nursing bruises, Zotul unhappily went to the Council House again. Mr. Broderick was no longer with them, a suave assistant informed him. Would he like to see Mr. Siwicki instead? Zotul would. Siwicki was tall, thin, dark and somber-looking. There was even a hint of toughness about the set of his jaw and the hardness of his glance. "So you can't pay," he said, tapping his teeth with a pencil. He looked at Zotul coldly. "It is well you have come to us instead of making it necessary for us to approach you through the courts." "I don't know what you mean," said Zotul. "If we have to sue, we take back the merchandise and everything attached to them. That means you would lose your houses, for they are attached to the furnaces. However, it is not as bad as that—yet. We will only require you to assign the remaining three-quarters of your pottery to us." The brothers, when they heard of this, were too stunned to think of beating Zotul, by which he assumed he had progressed a little and was somewhat comforted. "To fail," said Koltan soberly, "is not a Masur attribute. Go to the governor and tell him what we think of this business. The House of Masur has long supported the government with heavy taxes. Now it is time for the government to do something for us." The governor's palace was jammed with hurrying people, a scene of confusion that upset Zotul. The clerk who took his application for an interview was, he noticed only vaguely, a young Earthwoman. It was remarkable that he paid so little attention, for the female terrestrials were picked for physical assets that made Zurian men covetous and Zurian women envious. "The governor will see you," she said sweetly. "He has been expecting you." "Me?" marveled Zotul. She ushered him into the magnificent private office of the governor of Lor. The man behind the desk stood up, extended his hand with a friendly smile. "Come in, come in! I'm glad to see you again." Zotul stared blankly. This was not the governor. This was Broderick, the Earthman. "I—I came to see the governor," he said in confusion. Broderick nodded agreeably. "I am the governor and I am well acquainted with your case, Mr. Masur. Shall we talk it over? Please sit down." "I don't understand. The Earthmen...." Zotul paused, coloring. "We are about to lose our plant." "You were about to say that the Earthmen are taking your plant away from you. That is true. Since the House of Masur was the largest and richest on Zur, it has taken a long time—the longest of all, in fact." "What do you mean?" "Yours is the last business on Zur to be taken over by us. We have bought you out." "Our government...." "Your governments belong to us, too," said Broderick. "When they could not pay for the roads, the telegraphs, the civic improvements, we took them over, just as we are taking you over." "You mean," exclaimed Zotul, aghast, "that you Earthmen own everything on Zur?" "Even your armies." "But why ?" Broderick clasped his hands behind back, went to the window and stared down moodily into the street. "You don't know what an overcrowded world is like," he said. "A street like this, with so few people and vehicles on it, would be impossible on Earth." "But it's mobbed," protested Zotul. "It gave me a headache." "And to us it's almost empty. The pressure of population on Earth has made us range the Galaxy for places to put our extra people. The only habitable planets, unfortunately, are populated ones. We take the least populous worlds and—well, buy them out and move in." "And after that?" Broderick smiled gently. "Zur will grow. Our people will intermarry with yours. The future population of Zur will be neither true Zurians nor true Earthmen, but a mixture of both." Zotul sat in silent thought. "But you did not have to buy us out. You had the power to conquer us, even to destroy us. The whole planet could have been yours alone." He stopped in alarm. "Or am I suggesting an idea that didn't occur to you?" "No," said Broderick, his usually smiling face almost pained with memory. "We know the history of conquest all too well. Our method causes more distress than we like to inflict, but it's better—and more sure—than war and invasion by force. Now that the unpleasant job is finished, we can repair the dislocations." "At last I understand what you said about the tortoise." "Slow but sure." Broderick beamed again and clapped Zotul on the shoulder. "Don't worry. You'll have your job back, the same as always, but you'll be working for us ... until the children of Earth and Zur are equal in knowledge and therefore equal partners. That's why we had to break down your caste system." Zotul's eyes widened. "And that is why my brothers did not beat me when I failed!" "Of course. Are you ready now to take the assignment papers for you and your brothers to sign?" "Yes," said Zotul. "I am ready."
|
C. greediness
|
How many characters are accepted as input of the language model?
|
### Introduction
There has been a recent surge of improvements in language modeling, powered by the introduction of the transformer architecture BIBREF0. These gains stem from the ability of the transformer self-attention mechanism to better model long context (as compared to RNN networks), spanning hundreds of characters BIBREF1 or words BIBREF2, BIBREF3. These approaches consider language modeling as a classification problem with the aim of predicting the next token given a fixed-size preceding context. To support variable-length context, BIBREF4 adds recurrence to a transformer model, improving the state-of-the-art further. Current word-based language models (LMs) depend on a series of preprocessing steps that include lowercasing, tokenization, normalization, and out-of-vocabulary handling. This preprocessing stage is language dependent and can add significant complexity to real applications. As such, it is appealing to shift to more general LMs that process raw text at the character level. Processing language at the character level allows us to model morphological variants of a word, assign reasonable likelihood to out-of-vocabulary words, and learn subword-level language abstractions. This open vocabulary modeling is quite important for languages with complex morphology such as Arabic, Turkish, or Finnish BIBREF5, BIBREF6, BIBREF7. While character- and word-based LMs have both improved in their performance over time, purely character-based LMs have continued to lag in performance compared to models that leverage a tokenizer. BIBREF1 report inferior performance from character-level modeling on a large scale word-level benchmark, lm1b BIBREF8. Similarly, BIBREF3 observe that a character-level LM is harder to train to competitive performance on their huge WebText corpus, as compared with subword segmentation using byte pair encoding (BPE) BIBREF9, BIBREF10. Sub-word tokenization approaches like BPE represent a middle ground for text segmentation. On one hand, they can help with better modeling open vocabulary. On the other hand, they still depend on a tokenizer, adding complexity to the final system. Moreover, the preprocessing stage is not jointly optimized with learning the task objective. This last point is especially relevant given that LMs are increasingly used for their ability to produce pretrained representations that will be fine-tuned for a downstream task BIBREF11, BIBREF12, BIBREF13, BIBREF14. Since word-based LMs use closed vocabulary and sub-word models adopt a segmentation that targets the pretraining corpus, there is little space to adapt the vocabulary or optimize the segmentation to fit the final task data distribution. The rest of this paper is organized as follows. In Section SECREF2, we describe our model architecture, which is a vanilla deep transformer byte-level LM. Section SECREF3 describes the lm1b dataset and our evaluation methodology. Section SECREF4 presents our results and how our model compares to the previous work. In Section SECREF5 we analyze the representations learned by the network at different depths using word-similarity benchmarks. For this analysis to be feasible we propose a strategy to extract word representations from a character model. To summarize our contributions: We develop a competitive tokenizer-free language model on a large scalable dataset. We probe the performance of our model's learned intermediate representations on word similarity tasks. ### Modeling
Language models (LMs) assign a probability distribution over a sequence $x_{0:t}$ by factoring out the joint probability from left to right as follows Instead of reading in the tokenized input text, our model reads raw utf-8 bytes. For English text in the ASCII range, this is equivalent to processing characters as individual tokens. Non-ASCII characters (e.g. accented characters, or non-Latin scripts) are typically two or three utf-8 bytes. We use a standard “transformer decoder” (a stack of transformer layers with a causal attention mask) to process the sequence $x_{0:i-1}$ and predict the following byte $x_i$. The model's prediction is an estimate of the probability distribution over all possible 256 byte values. Our input byte embedding matrix has dimensionality 256. Our byte-level transformer model has 40 standard transformer layers with hidden size 1024, filter size 8192, and 16 heads. The model has around 836M parameters, of which only 66K are byte embeddings. ### Modeling ::: Training
We sample random byte sequences of length 512. This sampling process does not respect the sentence boundary. Therefore, one example might span complete and partial sentences. We dropout both timesteps of self-attention layers and features of relu activations across timesteps with a probability of 0.3. We use the Adam optimizer BIBREF15 with initial learning rate $10^{-4}$ and batch size 1024. The training runs for two million steps, and at every 10,000 steps we decay the learning rate geometrically by 0.99. ### Modeling ::: Windowed Prediction
To score each byte prediction, we need to process an entire 512-byte context from scratch, which is computationally intensive. To speed up development, for each window of context size $c$, we score $(\text{stride}=c/2)$ characters in parallel (the second half of the window). This leads to a tractable running time for our development evaluation process. While this setup is sub-optimal for our model, we did not observe any significant regression in our metrics. For example, the final bits/byte value of 0.874055 ($\text{stride}=1$) only grows to 0.87413 with $\text{stride}=256$. Our final test evaluation is reported with $\text{stride} = 1$. ### Experimental Setup
There are no large scale datasets that are heavily studied for both word and character language modeling. Typically, a specific dataset will be considered under just one level of segmentation. For our efforts to be comparable with the literature, we use a word LM dataset. This puts our model at a disadvantage; the dataset is tokenized and our model will not utilize the given word boundary information. Our approach is able to model rare words and estimate their appropriate likelihoods, however, they have been replaced with a special token to produce closed vocabulary text that is appropriate for word-level modeling. Hence, the metrics we report are meant to provide a lower bound on the utility of our approach in realistic settings. ### Experimental Setup ::: LM1B
We use the One Billion Word benchmark BIBREF8 to compare LM performance. The dataset consists of shuffled short sentences, and doesn't require modeling long contexts (95% of the training sentences are under 256 bytes and over 99.78% are under 512 bytes). The corpus is tokenized, and a small percentage of rare words are replaced with UNK tokens. The data gets split into 100 shards, and the first one (00) is held out while the rest (01-99) are used for training. The holdout set is split again into 50 shards, and historically shard 00 of the holdout has been used as the test set. There is no standard dev set, so we use shard 01 of the holdout as dev. See the corpus statistics in Table TABREF6 for details. ### Experimental Setup ::: Metrics
Word LMs typically report their results in terms of perplexity per word $(ppl)$ while byte LMs report their results in bits per byte $(bpb)$. We report both metrics to make our results more accessible. Conversion between those metrics are based on the following observation: The amount of information in the test dataset is the same independent of segmentation. where $I(x)$ is the information contained in $x$, which is $- \log _2 P(x; model)$. Equation DISPLAY_FORM10 allows us to convert bits/word to bits/byte. Then straightforwardly, using Equation DISPLAY_FORM11 we can convert $bpb$ to $ppl$: We train our model to minimize $bpb$ over the training set and convert $bpb$ on the test set to $ppl$ for comparison. For the test dataset, we use the $|words|$ and $|bytes|$ values reported in Table TABREF6. ### Results and Discussion
Table TABREF7 shows the perplexity of several models on lm1b. We observe that tokenizer-free LM performance improves significantly (40.6 to 23.0) when the model capacity is increased from 0.2B to 0.8B parameters. With sufficient capacity our byte-level LM is competitive with word based models (ranging from 21.8 to 28.0). Note, our model is able to achieve comparable performance without any explicit signal of word boundaries. Because of the large symbol space that word-based LMs address, they rely on sparse operations running on heterogeneous devices to run efficiently (e.g. running sparse embedding lookups on CPU as opposed to GPU/TPU). By contrast, byte LMs are dense, and all operations can be executed on specialized accelerators efficiently. We expect that with advances in accelerated hardware, byte-level text processing will become a popular choice. Of all the baseline models we reference, only BIBREF4 uses recurrence to model arbitrary length history. This technique could be added to tokenizer-free models as well. Indeed, we expect this approach to be particularly well-suited to byte and character models where text gets mapped onto longer token sequences, as BIBREF4 show that adding recurrence increases the length of context their model can effectively use. ### Extracting Word Representations
In this section, we test our model's ability to produce meaningful word-level representations. We investigate this by feeding the model single words, and evaluating its intermediate activations on word similarity tasks. Since our model is trained to predict each individual character, activations within a word only have partial information about that word. To get a word representation, we append an empty space character at the end of the input word. The activation at the space position from the transformer's feed-forward layer takes all characters into account, given the causal attention. To predict what follows the space, the model must have a good understanding of the preceding word, so this activation can be used as a proxy for a word representation. To evaluate our extracted word representations, we use the word similarity tasks described in Swivel BIBREF16. Following their evaluation methodology, we score word pairs using cosine similarity, and then measure the correlation with human ratings using Spearman's $\rho $. We do not expect these results to be competitive, given that our model is never trained to represent words. Moreover, the Swivel model is trained on a combination of Wikipedia and the Gigaword5 corpus BIBREF17 which is composed of 3.3 billion lowercased words with discarded punctuation. They discard out-of-vocabulary words for evaluation, while we use all word pairs in the benchmark. Nevertheless, this evaluation is valuable for comparing the relative quality of representation across different layers. Figure FIGREF12 shows Spearman's $\rho $ across different layers of the model. We observe two main phases of performance. In the first phrase (layers 1-10), all task metrics improve with depth. In the second phase (layers 11-40), performance either plateaus or degrades slightly with depth. We suspect that the earlier layers learn general-purpose features which are linguistically relevant, while the final layers fine-tune specifically to the task of next character prediction. Interestingly, the Rare Word and SimLex999 datasets do not follow this paradigm. Their performance drops between layers 4-6, but picks up again and improves with depth (layers 6-40). We hypothesize that the model may be storing words at different depths according to their frequency. It would be interesting to investigate to what degree the improved performance of deeper LMs is due to better modeling of rare words/phrases. Table TABREF13 shows the best performance of our model across all layers compared to the state-of-the-art model on word similarity. The gap here is a reminder that work remains to be done on improving methods for extracting word representations from character models. ### Conclusion
We show that a tokenizer-free language model with sufficient capacity can achieve results that are competitive with word-based LMs. Our model reads raw byte-level input without the use of any text preprocessing. As such, the model has no direct access to word boundary information. Finally, we show that our model's intermediate representations capture word-level semantic similarity and relatedness across layers. Table 1: Word and byte counts in lm1b. The word count includes end of sentence tokens, and byte count includes newline characters. Table 2: Comparing recent language model results on lm1b. Figure 1: Performance on word similarity tasks described in Shazeer et al. (2016): Spearman’s ρ measuring correlation between human annotation and cosine similarities on word representations generated from activations on different transformer layers. Table 3: Spearman’s ρ for different datasets using our model activations. We report the best value achieved across all layers versus Swivel (Shazeer et al., 2016).
|
input byte embedding matrix has dimensionality 256
|
What is likely to happen next?
A. the girls will be arrested
B. the girls will get back in their car and drive to Judy's house
C. the girls will locate the fountain and make wishes
D. the girls will meet the people living in the Brandt estate
|
The Haunted Fountain CHAPTER I An Unsolved Mystery “Tell Judy about it,” begged Lois. “Please, Lorraine, it can’t be as bad as it appears. There isn’t anything that Judy can’t solve.” Lorraine tilted her head disdainfully. “We’re sisters now. We’re both Farringdon-Petts and should be loyal to each other. But you always did take Judy’s part. She was the one who nearly spoiled our double wedding trying to solve a mystery. I don’t believe she’d understand—understand any better than I do. Everyone has problems, and I’m sure Judy is no exception.” “You’re right, Lorraine,” announced Judy, coming in to serve dessert to the two friends she had invited for lunch at Peter’s suggestion. “I do have problems, and there are plenty of mysteries I can’t solve.” “Name one,” charged Lois. “Just mention one single spooky thing you couldn’t explain, and I’ll believe you. I’ve seen you in action, Judy Bolton—” “Judy Dobbs, remember?” “Well, you were Judy Bolton when you solved all those mysteries. I met you when the whole valley below the big Roulsville dam was threatened by flood and you solved that—” “That,” declared Judy, “was my brother Horace, not me. He was the hero without even meaning to be. He was the one who rode through town and warned people that the flood was coming. I was off chasing a shadow.” “A vanishing shadow,” Lois said with a sigh. “What you did wasn’t easy, Judy.” “It didn’t need to be as hard as it was,” Judy confessed. “I know now that keeping that promise not to talk about the dam was a great big mistake and could have cost lives. I should have told Arthur.” “Please,” Lorraine said, a pained expression clouding her pretty face, “let’s not talk about him now.” “Very well,” Judy agreed. “What shall we talk about?” “You,” Lois said, “and all the mysteries you’ve solved. Maybe you were mistaken about a thing or two before the flood, but what about the haunted house you moved into? You were the one who tracked down the ghosts in the attic and the cellar and goodness knows where all. You’ve been chasing ghosts ever since I met you, and not one of them did you fail to explain in some sensible, logical fashion.” “Before I met you,” Judy said, thinking back, “there were plenty of them I couldn’t explain. There was one I used to call the spirit of the fountain, but what she was or how she spoke to me is more than I know. If my grandparents knew, they weren’t telling. And now they’re both dead and I can’t ask them. They left me a lot of unsolved mysteries along with this house. Maybe I’ll find the answers to some of them when I finish sorting Grandma’s things. They’re stored in one end of the attic.” “Another haunted attic? How thrilling!” exclaimed Lois. “Why don’t you have another ghost party and show up the spooks?” “I didn’t say the attic was haunted.” Judy was almost sorry she had mentioned it. She wasn’t in the mood for digging up old mysteries, but Lois and Lorraine insisted. It all began, she finally told them, the summer before they met. Horace had just started working on the paper. Judy remembered that it was Lorraine’s father, Richard Thornton Lee, who gave him his job with the Farringdon Daily Herald . He had turned in some interesting church news, convincing Mr. Lee that he had in him the makings of a good reporter. And so it was that he spent the summer Judy was remembering in Farringdon where the Farringdon-Petts had their turreted mansion, while she had to suffer the heat and loneliness of Dry Brook Hollow. Her thoughts were what had made it so hard, she confessed now as she reviewed everything that had happened. She just couldn’t help resenting the fact that her parents left her every summer while they went off on a vacation by themselves. What did they think she would do? “You’ll have plenty to read,” her father had told her. “I bought you six new books in that mystery series you like. When they’re finished there are plenty of short stories around. Your grandmother never throws anything away. She has magazines she’s saved since your mother was a girl. If you ask for them she’ll let you have the whole stack. I know how you love to read.” “I do, Dad, but if the magazines are that old—” Judy had stopped. She had seen her father’s tired eyes and had realized that a busy doctor needed a vacation much more than a schoolgirl who had too little to do. He and Judy’s mother usually went to the beach hotel where they had honeymooned. It was a precious memory. Every summer Dr. Bolton and his wife relived it. And every summer Judy went to stay with her grandmother Smeed, who scolded and fussed and tried to pretend she wasn’t glad to have her. “You here again?” she had greeted her that summer, and Judy hadn’t noticed her old eyes twinkling behind her glasses. “What do you propose to do with yourself this time?” “Read,” Judy had told her. “Mom and Dad say you have a whole stack of old magazines—” “In the attic. Go up and look them over if you can stand the heat.” Judy went, not to look over the old magazines so much as to escape to a place where she could have a good cry. It was the summer before her fifteenth birthday. In another year she would have outgrown her childish resentment of her parents’ vacation or be grown up enough to ask them to let her have a vacation of her own. In another year she would be summering among the beautiful Thousand Islands and solving a mystery to be known as the Ghost Parade . “A whole parade of ghosts,” Lois would be telling her, “and you solved everything.” But then she didn’t even know Lois. She had no idea so many thrilling adventures awaited her. There seemed to be nothing—nothing—and so the tears came and spilled over on one of the magazines. As Judy wiped it away she noticed that it had fallen on a picture of a fountain. “A fountain with tears for water. How strange!” she remembered saying aloud. Judy had never seen a real fountain. The thrill of walking up to the door of the palatial Farringdon-Pett mansion was still ahead of her. On the lawn a fountain still caught and held rainbows like those she was to see on her honeymoon at Niagara Falls. But all that was in the future. If anyone had told the freckled-faced, pigtailed girl that she would one day marry Peter Dobbs, she would have laughed in their faces. “That tease!” For then she knew Peter only as an older boy who used to tease her and call her carrot-top until one day she yelled back at him, “Carrot-tops are green and so are you!” Peter was to win Judy’s heart when he gave her a kitten and suggested the name Blackberry for him. The kitten was now a dignified family cat. But the summer Judy found the picture of a fountain and spilled tears on it she had no kitten. She had nothing, she confessed, not even a friend. It had helped to pretend the fountain in the picture was filled with all the tears lonely girls like herself had ever cried. “But that would make it enchanted!” she had suddenly exclaimed. “If I could find it I’d wish—” A step had sounded on the stairs. Judy remembered it distinctly. She had turned to see her grandmother and to hear her say in her usual abrupt fashion, “Enchanted fountain, indeed! If you let people know your wishes instead of muttering them to yourself, most of them aren’t so impossible.” “Were they?” asked Lois. She and Lorraine had listened to this much of what Judy was telling them without interruption. “That’s the unsolved mystery,” Judy replied. “There weren’t any of them impossible.” And she went on to tell them how, the very next day, her grandparents had taken her to a fountain exactly like the one in the picture. It was in the center of a deep, circular pool with steps leading up to it. Beside the steps were smaller fountains with the water spurting from the mouths of stone lions. Judy had stared at them a moment and then climbed the steps to the pool. “Am I dreaming?” she remembered saying aloud. “Is this beautiful fountain real?” A voice had answered, although she could see no one. “Make your wishes, Judy. Wish wisely. If you shed a tear in the fountain your wishes will surely come true.” “A tear?” Judy had asked. “How can I shed a tear when I’m happy? This is a wonderful place.” “Shed a tear in the fountain and your wishes will surely come true,” the voice had repeated. “But what is there to cry about?” “You found plenty to cry about back at your grandmother’s house,” the mysterious voice had reminded her. “Weren’t you crying on my picture up there in the attic?” “Then you—you are the fountain!” Judy remembered exclaiming. “But a fountain doesn’t speak. It doesn’t have a voice.” “Wish wisely,” the voice from the fountain had said in a mysterious whisper. CHAPTER II If Wishes Came True “Did you?” Lois interrupted the story to ask excitedly. “Oh, Judy! Don’t keep us in suspense any longer. What did you wish?” “Patience,” Judy said with a smile. “I’m coming to that.” First, she told her friends, she had to think of a wise wish. There had been so much she wanted in those early days before the flood. Dora Scott had been her best friend in Roulsville, but she had moved away. “You see,” she explained, “I made the mistake of having just one best friend. There wasn’t anybody in Dry Brook Hollow. I remember thinking of how lonely I was and how I wished for a friend or a sister, and suddenly a tear splashed in the water. It made little ripples. I thought I had to wish quickly before they vanished, and so I began naming the things I wanted as fast as I could. I’m not sure they were wise wishes. They seem rather selfish to me, now. I wasn’t thinking of anybody but me, Judy Bolton, and what I wanted. It wasn’t until after I began to think of others that my wishes started to come true.” “But what were they?” Lois insisted. Lorraine seemed unusually quiet and thoughtful. Judy did not notice the fear in her eyes as she replied airily, “Oh, didn’t I tell you? I wished for lots of friends and a sister, and I wished I could marry a G-man and solve a lot of mysteries and that’s as far as I got when the ripples vanished. I thought the spell was broken and so I didn’t wish for anything more.” “Wasn’t there anything more you wanted?” Lois asked. “Of course,” replied Judy. “There were lots more things. I wanted to go places, of course, and keep pets, and have a nice home, and—” “And your wishes all came true!” “Every one of them,” Judy agreed, “even the one about the sister. You see, it wasn’t a baby sister I wanted. It was a sister near my own age. That seemed impossible at the time, but the future did hold a sister for me.” “It held one for me, too,” Lois said, squeezing Lorraine’s hand under the table. “Don’t you think sisters should tell each other their problems, Judy?” “Honey and I always do,” she replied “but then it was different. I didn’t know I would marry Peter or that he would become a G-man, and he didn’t know he had a sister. It is strange, isn’t it? But the strangest thing of all was the fountain itself.” “Why?” asked Lorraine. “Do you still think it was enchanted?” Lois laughed at this, but Judy was serious as she answered, “I was still little girl enough to think so at the time. I wandered around, growing very drowsy. Then I found a hammock and climbed into it. I must have gone to sleep, because I remember waking up and wondering if the voice in the fountain had been a dream.” “A hammock?” Lois questioned. “Are you sure it wasn’t a flying carpet?” “No, it was a hammock all right,” Judy assured her, laughing. “It was hung between two trees in a beautiful garden all enclosed in rose trellises thick with roses. Did I tell you it was June?” “All the year around?” Again Lois laughed. But Lorraine said abruptly, “Let’s not talk about rose gardens in June. It’s a long way from June to December.” “Do you mean a garden changes? I know,” Judy said, “but I think this one would be beautiful at any time of the year. There were rhododendrons, too, and I don’t know how many different kinds of evergreens. I explored the garden all around the fountain.” “And then what happened?” Lorraine urged her. “Yes, yes. Go on,” entreated Lois. “I didn’t dream you’d kept anything that exciting a secret. Why didn’t you try to solve the mystery?” “I think I would have tried,” Judy admitted, “if I had been older or more experienced. I really should have investigated it more thoroughly and learned the secret of the fountain. But after the ripples went away it didn’t speak to me any more, and I didn’t really think it had heard my wishes. I was still wishing for a friend when I met you, Lois. It did seem impossible for us to be friends at first, didn’t it? Lorraine was your friend.” “I did make trouble for you,” Lorraine remembered. “It was all because of my foolish jealousy.” “It was nothing compared to the trouble caused by the Roulsville flood,” declared Judy. “After that things started happening so fast that I completely forgot about the fountain. Honestly, Lois, I don’t believe I thought about it again until after we moved to Farringdon and I walked up to your door and saw the fountain on your lawn.” “The Farringdon-Pett puddle, I always called it,” Lois said with a giggle. “I’ve seen lots nicer fountains.” “You have?” asked Judy. “Then maybe you’ve seen the one I’ve been telling you about. I think the picture of it is still in the attic. Come on up and I’ll show you.” Lois and Lorraine had finished their dessert while Judy was telling them the story of the fountain. Somehow, she wasn’t hungry for hers. She had tasted it too often while she was making it. “I’ll leave it for Blackberry,” she decided. Lois watched in amusement as the cat lapped up the chocolate pudding after Judy had mixed it generously with cream. “Sometimes,” Judy said fondly, “Blackberry thinks he’s a person. He eats everything we eat, including lettuce. Do you mind if he comes with us, Lorraine? He wants to explore the attic, too.” “He’ll remember he’s a cat fast enough if there are any mice up there,” Lois said with a giggle. Leaving the table, they all started upstairs with the cat bounding ahead of them. In modernizing her grandparents’ house to suit her own and Peter’s tastes, Judy had seen to it that the old stair door was removed. But there was still a door closing off the narrower stairs that led to the attic. Blackberry reached it first and yowled for Judy to open it. “He can read my mind. He always knows where I’m going,” Judy said as the door creaked open and the cat shot through it. A moment later a weird rolling noise came from the floor above. “Come on. There’s nothing up here to be afraid of,” Judy urged her friends. “Maybe not, but I’m beginning to get the shivers,” confessed Lois as she followed Judy to the sewing room at the top of the last flight of stairs. “So am I,” Lorraine admitted. “I’m not superstitious about black cats, but they are creepy. Does Blackberry have to roll spools across the floor?” “Now he thinks he’s a kitten,” laughed Judy. Pausing at still another door that led to the darker part of the attic, she turned and said mysteriously, “Up here we can all turn back the clock. Does anybody care to explore the past?” The exploration began enthusiastically with Judy relating still more of what she remembered about the fountain. “When I told Grandma about it she laughed and said I must have dreamed it. She said if wishes came true that easily she’d be living in a castle. But would she?” Judy wondered. “When I first remember this house she was still burning kerosene lamps like those you see on that high shelf by the window. I think she and Grandpa like the way they lived without any modern conveniences or anything.” “I think so, too,” Lois agreed, looking around the old attic with a shiver. “It is strange they both died the same winter, isn’t it?” “Maybe they wanted it that way. Maybe they wished neither of them would outlive the other. If they did wish in the fountain,” Judy went on more thoughtfully, “I’m sure that was one of their wishes. Another could have been to keep the good old days, as Grandma used to call them. That one came true in a way. They did manage to keep a little of the past when they kept all these old things. That’s what I meant about turning back the clock.” “If wishes came true I’d like to turn it back a little myself,” Lorraine began. “It would be nice if things were the way they used to be when I trusted Arthur—” “Don’t you trust him now?” Judy asked. Afterwards she was sorry for the interruption. Lois and Judy both questioned Lorraine, but that was all she would say. Judy wondered, as they searched through the old magazines, what was wrong. Lorraine was of a jealous disposition. Was the green-eyed monster coming between her and her handsome husband, Arthur Farringdon-Pett? Until now they had seemed blissfully happy. But there was no happiness in Lorraine’s face as she gazed at a picture of one of the fountains and then said in a tight little voice, “It is. It’s the very same one.” “But that’s the picture I’ve been searching for!” Judy said eagerly. “Do you know where it is?” “I can’t be sure. But if it ever was enchanted, I’m sure it isn’t now. Let’s go,” Lorraine said suddenly to Lois. Judy knew she was suggesting a fast trip home. But, apparently, Lois did not understand it that way. If she did, she pretended not to. “Where?” she asked. “To the fountain? I’d love to, wouldn’t you, Judy?” “I certainly would,” Judy replied enthusiastically. “Do you recognize it, too?” “I think so,” Lois answered after studying a little more closely the picture they had found. “It looks like the fountain on the Brandt estate.” “The department store Brandts?” Judy questioned. “Then my grandparents must have driven old Fanny all the way to Farringdon.” “Not quite all the way,” Lorraine objected. “The Brandts own that stretch of woods just before you come into the city. You’ve passed it lots of times.” “Of course,” agreed Judy. She put the magazine back in its place under the eaves and turned eagerly to her friends. “I do remember a road turning off into the woods and going on uphill,” she told them. “I never thought it led to a house, though. There isn’t even a gate. Could that be the road my grandparents took?” “Why don’t we take it ourselves and find out?” Lois suggested. CHAPTER III A Strange Encounter Lorraine was not too enthusiastic about the proposed trip to the Brandt estate. Finally she agreed to it under one condition. They were not to drive all the way to the house which, she said, was just over the hilltop. They were to park the car where no one would see it and follow the path to the fountain. “But suppose we can’t find the path?” asked Judy. “You’ll remember it, won’t you?” Judy thought she would, but she wasn’t too sure. She and Lois both argued that it would be better to inquire at the house. Lois knew Helen Brandt slightly. “She’d be glad to show us around. This way it looks as if we’re planning a crime,” Lois said as they started off in the blue car she was driving. It was a neat little car, not too conspicuous, and easy to park in out-of-the-way places. Judy laughed and said if they did find the fountain she thought she’d wish for one exactly like it. “Well, you know what your grandmother said about wishes, don’t you?” Lorraine asked. “If you let people know about them instead of muttering them to yourself most of them aren’t so impossible.” “Quite true,” Judy agreed. “I’ll let Peter know about this one. He’s my Santa Claus, and it will soon be Christmas. Maybe I should have worn the fur coat he gave me last year.” “Your reversible’s better in case it rains. It’s too warm for snow. We picked a perfect day for this trip,” Lois continued, guiding the car around curves as it climbed the steep hill beyond Dry Brook Hollow. The trip was a short one. In twenty minutes they had covered the distance that had seemed such a long way to Judy when she was riding in her grandfather’s wagon. “I’ve been thinking about it,” she said, “and I’ve just about figured out how it happened. I didn’t think my grandparents knew the Brandts well enough to pay them a visit, though. We must have looked queer driving up to a beautiful estate in Grandpa’s old farm wagon. I do remember that Grandma had some hooked rugs to deliver. But that still doesn’t explain what happened afterwards. When I woke up in the hammock I was alone in the garden. Horse, wagon, grandparents—all had disappeared.” “How could they?” asked Lois. “Anyway,” Lorraine began, “you had a chance to see how beautiful everything was before—” Again she broke off as if there were something she wanted to tell but didn’t quite dare. “Before what?” questioned Judy. “Oh, nothing. Forget I said anything about it. You were telling us how you woke up in the hammock, but you never did explain how you got back home,” Lorraine reminded her. “Didn’t I?” asked Judy. “I’d forgotten a lot of it, but it’s beginning to come back now. I do remember driving home along this road. You see, I thought my grandparents had left me in the garden for a surprise and would return for me. I told you I was all alone. There wasn’t a house in sight.” “The Brandt house is just over the top of this next hill,” Lois put in. “I know. You told me that. Now I know why I couldn’t see it. All I could see was a windowless old tower and a path leading in that direction. Naturally, I followed it. There’s something about a path in the woods that always tempts me.” “We know that, Judy. Honey told us all about your latest mystery. You followed a trail or something.” “Well, this trail led out of the rose garden where the hammock was and then through an archway,” Judy continued. “All sorts of little cupids and gnomes peered out at me from unexpected places. I was actually scared by the time I reached the old tower. There wasn’t time to explore it. Just then I heard the rumble of my grandfather’s wagon and knew he was driving off without me.” “He was!” Judy’s friends both chorused in surprise, and Lois asked, “Why would he do a thing like that?” “I think now it was just to tease me. He did stop and wait for me after a while,” Judy remembered. “The rugs were gone. Grandma must have delivered them, but I didn’t ask where. If she made them for Mrs. Brandt they may still be there.” “I wouldn’t depend on it,” Lorraine said as they turned up the narrow road to the Brandt estate. “Watch out!” Judy suddenly exclaimed. “There’s another car coming.” As Lois swerved to avoid the oncoming car, Lorraine ducked her head. She kept herself hidden behind Judy until the car had passed. The man driving it was a stranger to Judy, but she would remember his hypnotic, dark eyes and swarthy complexion for a long time. The soft brown hat he was wearing covered most of his hair. “What’s the matter with you two?” asked Lois when the car had passed. “Aren’t you a little old for playing hide and seek?” “I wasn’t—playing. Let’s not go up there,” Lorraine begged. “I don’t think the Brandts live there any more.” “Maybe not, but we can pretend we think they do, can’t we?” Judy replied a little uncertainly. She was beginning to suspect that Lorraine knew more about the Brandt estate than she was telling. Lois kept on driving along the narrow, gravelly road. Soon there were more evergreens and a hedge of rhododendrons to be seen. They looked very green next to the leafless trees in the woods beyond. The sky was gray with white clouds being driven across it by the wind. “There’s the tower!” Lorraine exclaimed. “I can see it over to the left. It looks like something out of Grimm’s Fairy Tales, doesn’t it?” “It looks grim all right,” agreed Judy. “I wonder what it is.” “I suppose it’s nothing but an old water tower. It would be fun to explore it, though,” Lois said. “But if there are new people living here they’ll never give us permission.” “We might explore it without permission,” Judy suggested daringly. “Come on!” she urged her friends as Lois parked the car in a cleared place beside the road. “Who’s going to stop us? And who wants to explore a gloomy old tower, anyway? Let’s look for the fountain.” “Do you think we should?” Lorraine asked. “It won’t be enchanted. I told you—” “You told us very little,” Lois reminded her. “If you know anything about the people who live here now, I think you ought to let us know. Otherwise, I’m afraid we won’t be very welcome.” “I don’t think they’ll welcome us, anyway. I do know who they are,” Lorraine admitted. “You remember Roger Banning from school, don’t you? I’ve seen him around here. His family must have acquired sudden wealth, or else he’s just working on the estate.” “Then you’ve been here lately? Why didn’t you tell me?” asked Lois. “We always used to go places together.” “It wasn’t important,” Lorraine replied evasively. “I was just out for a drive.” “You plutocrats!” laughed Judy. “Each with a car of your own. You’re not interested in Roger Banning, are you, Lois? I’m sure you can do better than that. I did know him slightly, but not from school. The boys and girls were separated and went to different high schools by the time we moved to Farringdon. I remember his pal, Dick Hartwell, a lot better. He was in our young people’s group at church.” “Sh!” Lois cautioned her. “Nice people no longer mention Dick Hartwell’s name. He’s doing time.” “For what?” asked Judy. Like Peter, her FBI husband, she preferred facts to gossip. “Forgery, I guess. He stole some checkbooks from his father’s desk and forged the names of a lot of important business people. I think he forged some legal documents, too. Anyway, he went to the Federal Penitentiary. It was all in the papers,” Lorraine told her. Now Judy did remember. It was something she would have preferred to forget. She liked to think she was a good judge of character, and she had taken Dick Hartwell for a quiet, refined boy who would never stoop to crime. “I don’t see what all this has to do with the fountain,” Lois said impatiently. “Are we going to look for it, or aren’t we?” “Of course we are. That’s what we came for. I just like to know what a tiger looks like before he springs at me,” Judy explained. “You seem to think there’s danger in this expedition of ours, don’t you?” asked Lorraine. “I don’t know what to think. You’re the one who seems to know the answers, but you’re not telling. Hiding your face back there gave you away. You’ve seen that character who drove down this road and, for some reason, you were afraid he would see you. Why, Lorraine? Why didn’t you want to be recognized?” Lorraine hesitated a moment and then replied evasively, “People don’t generally enter private estates without an invitation. That’s all.” “I’d better turn the car around,” Lois decided, “in case we have to leave in a hurry. I don’t expect we’ll encounter any tigers, but we may be accused of trespassing.” “I’m sure we will be,” announced Judy as two dark-coated figures strode down the road toward them. “You drove right by a NO TRESPASSING sign, and this isn’t a welcoming committee coming to meet us!”
|
D. the girls will meet the people living in the Brandt estate
|
How many subjects have been used to create the annotations?
|
### Motivation
A script is “a standardized sequence of events that describes some stereotypical human activity such as going to a restaurant or visiting a doctor” BIBREF0 . Script events describe an action/activity along with the involved participants. For example, in the script describing a visit to a restaurant, typical events are entering the restaurant, ordering food or eating. Participants in this scenario can include animate objects like the waiter and the customer, as well as inanimate objects such as cutlery or food. Script knowledge has been shown to play an important role in text understanding (cullingford1978script, miikkulainen1995script, mueller2004understanding, Chambers2008, Chambers2009, modi2014inducing, rudinger2015learning). It guides the expectation of the reader, supports coreference resolution as well as common-sense knowledge inference and enables the appropriate embedding of the current sentence into the larger context. Figure 1 shows the first few sentences of a story describing the scenario taking a bath. Once the taking a bath scenario is evoked by the noun phrase (NP) “a bath”, the reader can effortlessly interpret the definite NP “the faucet” as an implicitly present standard participant of the taking a bath script. Although in this story, “entering the bath room”, “turning on the water” and “filling the tub” are explicitly mentioned, a reader could nevertheless have inferred the “turning on the water” event, even if it was not explicitly mentioned in the text. Table 1 gives an example of typical events and participants for the script describing the scenario taking a bath. A systematic study of the influence of script knowledge in texts is far from trivial. Typically, text documents (e.g. narrative texts) describing various scenarios evoke many different scripts, making it difficult to study the effect of a single script. Efforts have been made to collect scenario-specific script knowledge via crowdsourcing, for example the OMICS and SMILE corpora (singh2002open, Regneri:2010, Regneri2013), but these corpora describe script events in a pointwise telegram style rather than in full texts. This paper presents the InScript corpus (Narrative Texts Instantiating Script structure). It is a corpus of simple narrative texts in the form of stories, wherein each story is centered around a specific scenario. The stories have been collected via Amazon Mechanical Turk (M-Turk). In this experiment, turkers were asked to write down a concrete experience about a bus ride, a grocery shopping event etc. We concentrated on 10 scenarios and collected 100 stories per scenario, giving a total of 1,000 stories with about 200,000 words. Relevant verbs and noun phrases in all stories are annotated with event types and participant types respectively. Additionally, the texts have been annotated with coreference information in order to facilitate the study of the interdependence between script structure and coreference. The InScript corpus is a unique resource that provides a basis for studying various aspects of the role of script knowledge in language processing by humans. The acquisition of this corpus is part of a larger research effort that aims at using script knowledge to model the surprisal and information density in written text. Besides InScript, this project also released a corpus of generic descriptions of script activities called DeScript (for Describing Script Structure, Wanzare2016). DeScript contains a range of short and textually simple phrases that describe script events in the style of OMICS or SMILE (singh2002open, Regneri:2010). These generic telegram-style descriptions are called Event Descriptions (EDs); a sequence of such descriptions that cover a complete script is called an Event Sequence Description (ESD). Figure 2 shows an excerpt of a script in the baking a cake scenario. The figure shows event descriptions for 3 different events in the DeScript corpus (left) and fragments of a story in the InScript corpus (right) that instantiate the same event type. ### Collection via Amazon M-Turk
We selected 10 scenarios from different available scenario lists (e.g. Regneri:2010 , VanDerMeer2009, and the OMICS corpus BIBREF1 ), including scripts of different complexity (Taking a bath vs. Flying in an airplane) and specificity (Riding a public bus vs. Repairing a flat bicycle tire). For the full scenario list see Table 2 . Texts were collected via the Amazon Mechanical Turk platform, which provides an opportunity to present an online task to humans (a.k.a. turkers). In order to gauge the effect of different M-Turk instructions on our task, we first conducted pilot experiments with different variants of instructions explaining the task. We finalized the instructions for the full data collection, asking the turkers to describe a scenario in form of a story as if explaining it to a child and to use a minimum of 150 words. The selected instruction variant resulted in comparably simple and explicit scenario-related stories. In the future we plan to collect more complex stories using different instructions. In total 190 turkers participated. All turkers were living in the USA and native speakers of English. We paid USD $0.50 per story to each turker. On average, the turkers took 9.37 minutes per story with a maximum duration of 17.38 minutes. ### Data Statistics
Statistics for the corpus are given in Table 2 . On average, each story has a length of 12 sentences and 217 words with 98 word types on average. Stories are coherent and concentrate mainly on the corresponding scenario. Neglecting auxiliaries, modals and copulas, on average each story has 32 verbs, out of which 58% denote events related to the respective scenario. As can be seen in Table 2 , there is some variation in stories across scenarios: The flying in an airplane scenario, for example, is most complex in terms of the number of sentences, tokens and word types that are used. This is probably due to the inherent complexity of the scenario: Taking a flight, for example, is more complicated and takes more steps than taking a bath. The average count of sentences, tokens and types is also very high for the baking a cake scenario. Stories from the scenario often resemble cake recipes, which usually contain very detailed steps, so people tend to give more detailed descriptions in the stories. For both flying in an airplane and baking a cake, the standard deviation is higher in comparison to other scenarios. This indicates that different turkers described the scenario with a varying degree of detail and can also be seen as an indicator for the complexity of both scenarios. In general, different people tend to describe situations subjectively, with a varying degree of detail. In contrast, texts from the taking a bath and planting a tree scenarios contain a relatively smaller number of sentences and fewer word types and tokens. Both planting a tree and taking a bath are simpler activities, which results in generally less complex texts. The average pairwise word type overlap can be seen as a measure of lexical variety among stories: If it is high, the stories resemble each other more. We can see that stories in the flying in an airplane and baking a cake scenarios have the highest values here, indicating that most turkers used a similar vocabulary in their stories. In general, the response quality was good. We had to discard 9% of the stories as these lacked the quality we were expecting. In total, we selected 910 stories for annotation. ### Annotation
This section deals with the annotation of the data. We first describe the final annotation schema. Then, we describe the iterative process of corpus annotation and the refinement of the schema. This refinement was necessary due to the complexity of the annotation. ### Annotation Schema
For each of the scenarios, we designed a specific annotation template. A script template consists of scenario-specific event and participant labels. An example of a template is shown in Table 1 . All NP heads in the corpus were annotated with a participant label; all verbs were annotated with an event label. For both participants and events, we also offered the label unclear if the annotator could not assign another label. We additionally annotated coreference chains between NPs. Thus, the process resulted in three layers of annotation: event types, participant types and coreference annotation. These are described in detail below. As a first layer, we annotated event types. There are two kinds of event type labels, scenario-specific event type labels and general labels. The general labels are used across every scenario and mark general features, for example whether an event belongs to the scenario at all. For the scenario-specific labels, we designed an unique template for every scenario, with a list of script-relevant event types that were used as labels. Such labels include for example ScrEv_close_drain in taking a bath as in Example UID10 (see Figure 1 for a complete list for the taking a bath scenario) I start by closing $_{\textsc {\scriptsize ScrEv\_close\_drain}}$ the drain at the bottom of the tub. The general labels that were used in addition to the script-specific labels in every scenario are listed below: ScrEv_other. An event that belongs to the scenario, but its event type occurs too infrequently (for details, see below, Section "Modification of the Schema" ). We used the label “other" because event classification would become too finegrained otherwise. Example: After I am dried I put my new clothes on and clean up $_{\textsc {\scriptsize ScrEv\_other}}$ the bathroom. RelNScrEv. Related non-script event. An event that can plausibly happen during the execution of the script and is related to it, but that is not part of the script. Example: After finding on what I wanted to wear, I went into the bathroom and shut $_{\textsc {\scriptsize RelNScrEv}}$ the door. UnrelEv. An event that is unrelated to the script. Example: I sank into the bubbles and took $_{\textsc {\scriptsize UnrelEv}}$ a deep breath. Additionally, the annotators were asked to annotate verbs and phrases that evoke the script without explicitly referring to a script event with the label Evoking, as shown in Example UID10 . Today I took a bath $_{\textsc {\scriptsize Evoking}}$ in my new apartment. As in the case of the event type labels, there are two kinds of participant labels: general labels and scenario-specific labels. The latter are part of the scenario-specific templates, e.g. ScrPart_drain in the taking a bath scenario, as can be seen in Example UID15 . I start by closing the drain $_{\textsc {\scriptsize ScrPart\_drain}}$ at the bottom of the tub. The general labels that are used across all scenarios mark noun phrases with scenario-independent features. There are the following general labels: ScrPart_other. A participant that belongs to the scenario, but its participant type occurs only infrequently. Example: I find my bath mat $_{\textsc {\scriptsize ScrPart\_other}}$ and lay it on the floor to keep the floor dry. NPart. Non-participant. A referential NP that does not belong to the scenario. Example: I washed myself carefully because I did not want to spill water onto the floor $_{\textsc {\scriptsize NPart}}$ .labeled SuppVComp. A support verb complement. For further discussion of this label, see Section "Special Cases" Example: I sank into the bubbles and took a deep breath $_{\textsc {\scriptsize SuppVComp}}$ . Head_of_Partitive. The head of a partitive or a partitive-like construction. For a further discussion of this label cf. Section "Special Cases" Example: I grabbed a bar $_{\textsc {\scriptsize Head\_of\_Partitive}}$ of soap and lathered my body. No_label. A non-referential noun phrase that cannot be labeled with another label. Example: I sat for a moment $_{\textsc {\scriptsize No\_label}}$ , relaxing, allowing the warm water to sooth my skin. All NPs labeled with one of the labels SuppVComp, Head_of_Partitive or No_label are considered to be non-referential. No_label is used mainly in four cases in our data: non-referential time expressions (in a while, a million times better), idioms (no matter what), the non-referential “it” (it felt amazing, it is better) and other abstracta (a lot better, a little bit). In the first annotation phase, annotators were asked to mark verbs and noun phrases that have an event or participant type, that is not listed in the template, as MissScrEv/ MissScrPart (missing script event or participant, resp.). These annotations were used as a basis for extending the templates (see Section "Modification of the Schema" ) and replaced later by newly introduced labels or ScrEv_other and ScrPart_other respectively. All noun phrases were annotated with coreference information indicating which entities denote the same discourse referent. The annotation was done by linking heads of NPs (see Example UID21 , where the links are indicated by coindexing). As a rule, we assume that each element of a coreference chain is marked with the same participant type label. I $ _{\textsc {\scriptsize Coref1}}$ washed my $ _{\textsc {\scriptsize Coref1}}$ entire body $ _{\textsc {\scriptsize Coref2}}$ , starting with my $ _{\textsc {\scriptsize Coref1}}$ face $ _{\textsc {\scriptsize Coref3}} $ and ending with the toes $ _{\textsc {\scriptsize Coref4}} $ . I $ _{\textsc {\scriptsize Coref1}}$ always wash my $ _{\textsc {\scriptsize Coref1}}$ toes $_{\textsc {\scriptsize Coref4}}$ very thoroughly ... The assignment of an entity to a referent is not always trivial, as is shown in Example UID21 . There are some cases in which two discourse referents are grouped in a plural NP. In the example, those things refers to the group made up of shampoo, soap and sponge. In this case, we asked annotators to introduce a new coreference label, the name of which indicates which referents are grouped together (Coref_group_washing_tools). All NPs are then connected to the group phrase, resulting in an additional coreference chain. I $ _{\textsc {\scriptsize Coref1}}$ made sure that I $ _{\textsc {\scriptsize Coref1}}$ have my $ _{\textsc {\scriptsize Coref1}}$ shampoo $ _{\textsc {\scriptsize Coref2 + Coref\_group\_washing\_tools}}$ , soap $_{\textsc {\scriptsize Coref3 + Coref\_group\_washing\_tools}}$ and sponge $ _{\textsc {\scriptsize Coref4 + Coref\_group\_washing\_tools}}$ ready to get in. Once I $ _{\textsc {\scriptsize Coref1}}$ have those things $ _{\textsc {\scriptsize Coref\_group\_washing\_tools}}$ I $ _{\textsc {\scriptsize Coref1}}$ sink into the bath. ... I $ _{\textsc {\scriptsize Coref1}}$ applied some soap $ _{\textsc {\scriptsize Coref1}}$0 on my $ _{\textsc {\scriptsize Coref1}}$1 body and used the sponge $ _{\textsc {\scriptsize Coref1}}$2 to scrub a bit. ... I $ _{\textsc {\scriptsize Coref1}}$3 rinsed the shampoo $ _{\textsc {\scriptsize Coref1}}$4 . Example UID21 thus contains the following coreference chains: Coref1: I $ _{\textsc {\scriptsize Coref1}}$5 I $ _{\textsc {\scriptsize Coref1}}$6 my $ _{\textsc {\scriptsize Coref1}}$7 I $ _{\textsc {\scriptsize Coref1}}$8 I $ _{\textsc {\scriptsize Coref1}}$9 I $ _{\textsc {\scriptsize Coref1}}$0 my $ _{\textsc {\scriptsize Coref1}}$1 I Coref2: shampoo $\rightarrow $ shampoo Coref3: soap $\rightarrow $ soap Coref4: sponge $\rightarrow $ sponge Coref_group_washing_ tools: shampoo $\rightarrow $ soap $\rightarrow $ sponge $\rightarrow $ things ### Development of the Schema
The templates were carefully designed in an iterated process. For each scenario, one of the authors of this paper provided a preliminary version of the template based on the inspection of some of the stories. For a subset of the scenarios, preliminary templates developed at our department for a psycholinguistic experiment on script knowledge were used as a starting point. Subsequently, the authors manually annotated 5 randomly selected texts for each of the scenarios based on the preliminary template. Necessary extensions and changes in the templates were discussed and agreed upon. Most of the cases of disagreement were related to the granularity of the event and participant types. We agreed on the script-specific functional equivalence as a guiding principle. For example, reading a book, listening to music and having a conversation are subsumed under the same event label in the flight scenario, because they have the common function of in-flight entertainment in the scenario. In contrast, we assumed different labels for the cake tin and other utensils (bowls etc.), since they have different functions in the baking a cake scenario and accordingly occur with different script events. Note that scripts and templates as such are not meant to describe an activity as exhaustively as possible and to mention all steps that are logically necessary. Instead, scripts describe cognitively prominent events in an activity. An example can be found in the flight scenario. While more than a third of the turkers mentioned the event of fastening the seat belts in the plane (buckle_seat_belt), no person wrote about undoing their seat belts again, although in reality both events appear equally often. Consequently, we added an event type label for buckling up, but no label for undoing the seat belts. ### First Annotation Phase
We used the WebAnno annotation tool BIBREF2 for our project. The stories from each scenario were distributed among four different annotators. In a calibration phase, annotators were presented with some sample texts for test annotations; the results were discussed with the authors. Throughout the whole annotation phase, annotators could discuss any emerging issues with the authors. All annotations were done by undergraduate students of computational linguistics. The annotation was rather time-consuming due to the complexity of the task, and thus we decided for single annotation mode. To assess annotation quality, a small sample of texts was annotated by all four annotators and their inter-annotator agreement was measured (see Section "Inter-Annotator Agreement" ). It was found to be sufficiently high. Annotation of the corpus together with some pre- and post-processing of the data required about 500 hours of work. All stories were annotated with event and participant types (a total of 12,188 and 43,946 instances, respectively). On average there were 7 coreference chains per story with an average length of 6 tokens. ### Modification of the Schema
After the first annotation round, we extended and changed the templates based on the results. As mentioned before, we used MissScrEv and MissScrPart labels to mark verbs and noun phrases instantiating events and participants for which no appropriate labels were available in the templates. Based on the instances with these labels (a total of 941 and 1717 instances, respectively), we extended the guidelines to cover the sufficiently frequent cases. In order to include new labels for event and participant types, we tried to estimate the number of instances that would fall under a certain label. We added new labels according to the following conditions: For the participant annotations, we added new labels for types that we expected to appear at least 10 times in total in at least 5 different stories (i.e. in approximately 5% of the stories). For the event annotations, we chose those new labels for event types that would appear in at least 5 different stories. In order to avoid too fine a granularity of the templates, all other instances of MissScrEv and MissScrPart were re-labeled with ScrEv_other and ScrPart_other. We also relabeled participants and events from the first annotation phase with ScrEv_other and ScrPart_other, if they did not meet the frequency requirements. The event label air_bathroom (the event of letting fresh air into the room after the bath), for example, was only used once in the stories, so we relabeled that instance to ScrEv_other. Additionally, we looked at the DeScript corpus BIBREF3 , which contains manually clustered event paraphrase sets for the 10 scenarios that are also covered by InScript (see Section "Comparison to the DeScript Corpus" ). Every such set contains event descriptions that describe a certain event type. We extended our templates with additional labels for these events, if they were not yet part of the template. ### Special Cases
Noun-noun compounds were annotated twice with the same label (whole span plus the head noun), as indicated by Example UID31 . This redundant double annotation is motivated by potential processing requirements. I get my (wash (cloth $ _{\textsc {\scriptsize ScrPart\_washing\_tools}} ))$ , $_{\textsc {\scriptsize ScrPart\_washing\_tools}} $ and put it under the water. A special treatment was given to support verb constructions such as take time, get home or take a seat in Example UID32 . The semantics of the verb itself is highly underspecified in such constructions; the event type is largely dependent on the object NP. As shown in Example UID32 , we annotate the head verb with the event type described by the whole construction and label its object with SuppVComp (support verb complement), indicating that it does not have a proper reference. I step into the tub and take $ _{\textsc {\scriptsize ScrEv\_sink\_water}} $ a seat $ _{\textsc {\scriptsize SuppVComp}} $ . We used the Head_of_Partitive label for the heads in partitive constructions, assuming that the only referential part of the construction is the complement. This is not completely correct, since different partitive heads vary in their degree of concreteness (cf. Examples UID33 and UID33 ), but we did not see a way to make the distinction sufficiently transparent to the annotators. Our seats were at the back $ _{\textsc {\scriptsize Head\_of\_Partitive}} $ of the train $ _{\textsc {\scriptsize ScrPart\_train}} $ . In the library you can always find a couple $ _{\textsc {\scriptsize Head\_of\_Partitive}} $ of interesting books $ _{\textsc {\scriptsize ScrPart\_book}} $ . Group denoting NPs sometimes refer to groups whose members are instances of different participant types. In Example UID34 , the first-person plural pronoun refers to the group consisting of the passenger (I) and a non-participant (my friend). To avoid a proliferation of event type labels, we labeled these cases with Unclear. I $ _{\textsc {\scriptsize {ScrPart\_passenger}}}$ wanted to visit my $_{\textsc {\scriptsize {ScrPart\_passenger}}}$ friend $ _{\textsc {\scriptsize {NPart}}}$ in New York. ... We $_{\textsc {\scriptsize Unclear}}$ met at the train station. We made an exception for the Getting a Haircut scenario, where the mixed participant group consisting of the hairdresser and the customer occurs very often, as in Example UID34 . Here, we introduced the additional ad-hoc participant label Scr_Part_hairdresser_customer. While Susan $_{\textsc {\scriptsize {ScrPart\_hairdresser}}}$ is cutting my $_{\textsc {\scriptsize {ScrPart\_customer}}}$ hair we $_{\textsc {\scriptsize Scr\_Part\_hairdresser\_customer}}$ usually talk a bit. ### Inter-Annotator Agreement
In order to calculate inter-annotator agreement, a total of 30 stories from 6 scenarios were randomly chosen for parallel annotation by all 4 annotators after the first annotation phase. We checked the agreement on these data using Fleiss' Kappa BIBREF4 . The results are shown in Figure 4 and indicate moderate to substantial agreement BIBREF5 . Interestingly, if we calculated the Kappa only on the subset of cases that were annotated with script-specific event and participant labels by all annotators, results were better than those of the evaluation on all labeled instances (including also unrelated and related non-script events). This indicates one of the challenges of the annotation task: In many cases it is difficult to decide whether a particular event should be considered a central script event, or an event loosely related or unrelated to the script. For coreference chain annotation, we calculated the percentage of pairs which were annotated by at least 3 annotators (qualified majority vote) compared to the set of those pairs annotated by at least one person (see Figure 4 ). We take the result of 90.5% between annotators to be a good agreement. ### Annotated Corpus Statistics
Figure 5 gives an overview of the number of event and participant types provided in the templates. Taking a flight and getting a haircut stand out with a large number of both event and participant types, which is due to the inherent complexity of the scenarios. In contrast, planting a tree and going on a train contain the fewest labels. There are 19 event and participant types on average. Figure 6 presents overview statistics about the usage of event labels, participant labels and coreference chain annotations. As can be seen, there are usually many more mentions of participants than events. For coreference chains, there are some chains that are really long (which also results in a large scenario-wise standard deviation). Usually, these chains describe the protagonist. We also found again that the flying in an airplane scenario stands out in terms of participant mentions, event mentions and average number of coreference chains. Figure 7 shows for every participant label in the baking a cake scenario the number of stories which they occurred in. This indicates how relevant a participant is for the script. As can be seen, a small number of participants are highly prominent: cook, ingredients and cake are mentioned in every story. The fact that the protagonist appears most often consistently holds for all other scenarios, where the acting person appears in every story, and is mentioned most frequently. Figure 8 shows the distribution of participant/event type labels over all appearances over all scenarios on average. The groups stand for the most frequently appearing label, the top 2 to 5 labels in terms of frequency and the top 6 to 10. ScrEv_other and ScrPart_other are shown separately. As can be seen, the most frequently used participant label (the protagonist) makes up about 40% of overall participant instances. The four labels that follow the protagonist in terms of frequency together appear in 37% of the cases. More than 2 out of 3 participants in total belong to one of only 5 labels. In contrast, the distribution for events is more balanced. 14% of all event instances have the most prominent event type. ScrEv_other and ScrPart_other both appear as labels in at most 5% of all event and participant instantiations: The specific event and participant type labels in our templates cover by far most of the instances. In Figure 9 , we grouped participants similarly into the first, the top 2-5 and top 6-10 most frequently appearing participant types. The figure shows for each of these groups the average frequency per story, and in the rightmost column the overall average. The results correspond to the findings from the last paragraph. ### Comparison to the DeScript Corpus
As mentioned previously, the InScript corpus is part of a larger research project, in which also a corpus of a different kind, the DeScript corpus, was created. DeScript covers 40 scenarios, and also contains the 10 scenarios from InScript. This corpus contains texts that describe scripts on an abstract and generic level, while InScript contains instantiations of scripts in narrative texts. Script events in DeScript are described in a very simple, telegram-style language (see Figure 2 ). Since one of the long-term goals of the project is to align the InScript texts with the script structure given from DeScript, it is interesting to compare both resources. The InScript corpus exhibits much more lexical variation than DeScript. Many approaches use the type-token ratio to measure this variance. However, this measure is known to be sensitive to text length (see e.g. Tweedie1998), which would result in very small values for InScript and relatively large ones for DeScript, given the large average difference of text lengths between the corpora. Instead, we decided to use the Measure of Textual Lexical Diversity (MTLD) (McCarthy2010, McCarthy2005), which is familiar in corpus linguistics. This metric measures the average number of tokens in a text that are needed to retain a type-token ratio above a certain threshold. If the MTLD for a text is high, many tokens are needed to lower the type-token ratio under the threshold, so the text is lexically diverse. In contrast, a low MTLD indicates that only a few words are needed to make the type-token ratio drop, so the lexical diversity is smaller. We use the threshold of 0.71, which is proposed by the authors as a well-proven value. Figure 10 compares the lexical diversity of both resources. As can be seen, the InScript corpus with its narrative texts is generally much more diverse than the DeScript corpus with its short event descriptions, across all scenarios. For both resources, the flying in an airplane scenario is most diverse (as was also indicated above by the mean word type overlap). However, the difference in the variation of lexical variance of scenarios is larger for DeScript than for InScript. Thus, the properties of a scenario apparently influence the lexical variance of the event descriptions more than the variance of the narrative texts. We used entropy BIBREF6 over lemmas to measure the variance of lexical realizations for events. We excluded events for which there were less than 10 occurrences in DeScript or InScript. Since there is only an event annotation for 50 ESDs per scenario in DeScript, we randomly sampled 50 texts from InScript for computing the entropy to make the numbers more comparable. Figure 11 shows as an example the entropy values for the event types in the going on a train scenario. As can be seen in the graph, the entropy for InScript is in general higher than for DeScript. In the stories, a wider variety of verbs is used to describe events. There are also large differences between events: While wait has a really low entropy, spend_time_train has an extremely high entropy value. This event type covers many different activities such as reading, sleeping etc. ### Conclusion
In this paper we described the InScript corpus of 1,000 narrative texts annotated with script structure and coreference information. We described the annotation process, various difficulties encountered during annotation and different remedies that were taken to overcome these. One of the future research goals of our project is also concerned with finding automatic methods for text-to-script mapping, i.e. for the alignment of text segments with script states. We consider InScript and DeScript together as a resource for studying this alignment. The corpus shows rich lexical variation and will serve as a unique resource for the study of the role of script knowledge in natural language processing. ### Acknowledgements
This research was funded by the German Research Foundation (DFG) as part of SFB 1102 'Information Density and Linguistic Encoding'. Figure 1: An excerpt from a story on the TAKING A BATH script. Figure 2: Connecting DeScript and InScript: an example from the BAKING A CAKE scenario (InScript participant annotation is omitted for better readability). Table 1: Bath scenario template (labels added in the second phase of annotation are marked in bold). Table 2: Corpus statistics for different scenarios (standard deviation given in parentheses). The maximum per column is highlighted in boldface, the minimum in boldface italics. Figure 3: Sample event and participant annotation for the TAKING A BATH script. Figure 4: Inter-annotator agreement statistics. Figure 5: The number of participants and events in the templates. Figure 6: Annotation statistics over all scenarios. Figure 8: Distribution of participants (left) and events (right) for the 1, the top 2-5, top 6-10 most frequently appearing events/participants, SCREV/SCRPART OTHER and the rest. Figure 9: Average number of participant mentions for a story, for the first, the top 2-5, top 6-10 most frequently appearing events/participants, and the overall average. Figure 7: The number of stories in the BAKING A CAKE scenario that contain a certain participant label. Figure 10: MTLD values for DeScript and InScript, per scenario. Figure 11: Entropy over verb lemmas for events (left y-axis, H(x)) in the GOING ON A TRAIN SCENARIO. Bars in the background indicate the absolute number of occurrence of instances (right y-axis, N(x)).
|
four different annotators
|
what sentiment sources do they compare with?
|
### Introduction
Sentiment classification is an important task which requires either word level or document level sentiment annotations. Such resources are available for at most 136 languages BIBREF0 , preventing accurate sentiment classification in a low resource setup. Recent research efforts on cross-lingual transfer learning enable to train models in high resource languages and transfer this information into other, low resource languages using minimal bilingual supervision BIBREF1 , BIBREF2 , BIBREF3 . Besides that, little effort has been spent on the creation of sentiment lexica for low resource languages (e.g., BIBREF0 , BIBREF4 , BIBREF5 ). We create and release Unisent, the first massively cross-lingual sentiment lexicon in more than 1000 languages. An extensive evaluation across several languages shows that the quality of Unisent is close to manually created resources. Our method is inspired by BIBREF6 with a novel combination of vocabulary expansion and domain adaptation using embedding spaces. Similar to our work, BIBREF7 also use massively parallel corpora to project POS tags and dependency relations across languages. However, their approach is based on assignment of the most probable label according to the alignment model from the source to the target language and does not include any vocabulary expansion or domain adaptation and do not use the embedding graphs. ### Method
Our method, Adapted Sentiment Pivot requires a sentiment lexicon in one language (e.g. English) as well as a massively parallel corpus. Following steps are performed on this input. ### Experimental Setup
Our goal is to evaluate the quality of UniSent against several manually created sentiment lexica in different domains to ensure its quality for the low resource languages. We do this in several steps. As the gold standard sentiment lexica, we chose manually created lexicon in Czech BIBREF11 , German BIBREF12 , French BIBREF13 , Macedonian BIBREF14 , and Spanish BIBREF15 . These lexica contain general domain words (as opposed to Twitter or Bible). As gold standard for twitter domain we use emoticon dataset and perform emoticon sentiment prediction BIBREF16 , BIBREF17 . We use the (manually created) English sentiment lexicon (WKWSCI) in BIBREF18 as a resource to be projected over languages. For the projection step (Section SECREF1 ) we use the massively parallel Bible corpus in BIBREF8 . We then propagate the projected sentiment polarities to all words in the Wikipedia corpus. We chose Wikipedia here because its domain is closest to the manually annotated sentiment lexica we use to evaluate UniSent. In the adaptation step, we compute the shift between the vocabularies in the Bible and Wikipedia corpora. To show that our adaptation method also works well on domains like Twitter, we propose a second evaluation in which we use Adapted Sentiment Pivot to predict the sentiment of emoticons in Twitter. To create our test sets, we first split UniSent and our gold standard lexica as illustrated in Figure FIGREF11 . We then form our training and test sets as follows: (i) UniSent-Lexicon: we use words in UniSent for the sentiment learning in the target domain; for this purpose, we use words INLINEFORM0 . (ii) Baseline-Lexicon: we use words in the gold standard lexicon for the sentiment learning in the target domain; for this purpose we use words INLINEFORM0 . (iii) Evaluation-Lexicon: we randomly exclude a set of words the baseline-lexicon INLINEFORM0 . In selection of the sampling size we make sure that INLINEFORM1 and INLINEFORM2 would contain a comparable number of words. ### Results
In Table TABREF13 we compare the quality of UniSent with the Baseline-Lexicon as well as with the gold standard lexicon for general domain data. The results show that (i) UniSent clearly outperforms the baseline for all languages (ii) the quality of UniSent is close to manually annotated data (iii) the domain adaptation method brings small improvements for morphologically poor languages. The modest gains could be because our drift weighting method (Section SECREF3 ) mainly models a sense shift between words which is not always equivalent to a polarity shift. In Table TABREF14 we compare the quality of UniSent with the gold standard emoticon lexicon in the Twitter domain. The results show that (i) UniSent clearly outperforms the baseline and (ii) our domain adaptation technique brings small improvements for French and Spanish. ### Conclusion
Using our novel Adapted Sentiment Pivot method, we created UniSent, a sentiment lexicon covering over 1000 (including many low-resource) languages in several domains. The only necessary resources to create UniSent are a sentiment lexicon in any language and a massively parallel corpus that can be small and domain specific. Our evaluation showed that the quality of UniSent is closed to manually annotated resources. Figure 1: Neighbors of word ’sensual’ in Spanish, in bible embedding graph (a) and twitter embedding graph (b). Our unsupervised drift weighting method found this word in Spanish to be the most changing word from bible context to the twitter context. Looking more closely at the neighbors, the word sensual in the biblical context has been associated with a negative sentiment of sins. However, in the twitter domain, it has a positive sentiment. This example shows how our unsupervised method can improve the quality of sentiment lexicon. Figure 2: Data split used in the experimental setup of UniSent evaluation: Set (C) is the intersection of the target embedding space words (Wikipedia/Emoticon) and the UniSent lexicon as well as the manually created lexicon. Set (A) is the intersection of the target embedding space words and the UniSent lexicon, excluding set (C). Set (B) is the intersection of the target embedding space words and the manually created lexicon, excluding set (C). Table 1: Comparison of manually created lexicon performance with UniSent in Czech, German, French, Macedonians, and Spanish. We report accuracy and the macro-F1 (averaged F1 over positive and negative classes). The baseline is constantly considering the majority label. The last two columns indicate the performance of UniSent after drift weighting. Table 2: Comparison of domain adapted and vanilla UniSent for Emoticon sentiment prediction using monlingual twitter embeddings in German, Italian, French, and Spanish.
|
manually created lexicon in Czech BIBREF11 , German BIBREF12 , French BIBREF13 , Macedonian BIBREF14 , and Spanish BIBREF15
|
In the review of "Fight Club," lines from Tyler Durden cited by the reviewer illustrate the following literary device:
A. allusion
B. personification
C. metaphor
D. irony
|
Boys Do Bleed Fight Club is silly stuff, sensationalism that mistakes itself for satire, but it's also a brash and transporting piece of moviemaking, like Raging Bull on acid. The film opens with--literally--a surge of adrenalin, which travels through the bloodstream and into the brain of its protagonist, Jack (Edward Norton), who's viewed, as the camera pulls out of his insides, with a gun stuck in his mouth. How'd he get into this pickle? He's going to tell you, breezily, and the director, David Fincher, is going to illustrate his narrative--violently. Fincher ( Seven , 1995; The Game , 1997) is out to bombard you with so much feverish imagery that you have no choice but to succumb to the movie's reeling, punch-drunk worldview. By the end, you might feel as if you, too, have a mouthful of blood. Not to mention a hole in your head. Fight Club careers from one resonant satirical idea to the next without quite deciding whether its characters are full of crap or are Gen X prophets. It always gives you a rush, though. At first, it goofs on the absurd feminization of an absurdly macho culture. An increasingly desperate insomniac, Jack finds relief (and release) only at meetings for the terminally ill. At a testicular cancer group, he's enfolded in the ample arms of Bob (the singer Meat Loaf Aday), a former bodybuilder who ruined his health with steroids and now has "bitch tits." Jack and Bob subscribe to a new form of male bonding: They cling to each other and sob. But Jack's idyll is rudely disrupted by--wouldn't you know it?--a woman. A dark-eyed, sepulchral head case named Marla Singer (Helena Bonham Carter) begins showing up at all the same disparate meetings for essentially the same voyeuristic ends, and the presence of this "tourist" makes it impossible for Jack to emote. Jack finds another outlet, though. On a plane, he meets Tyler Durden (Brad Pitt), a cryptic hipster with a penchant for subversive acts both large (he makes high-priced soaps from liposuctioned human fat) and small (he splices frames from porn flicks into kiddie movies). When Jack's apartment mysteriously explodes--along with his carefully chosen IKEA furniture--he moves into Tyler's squalid warehouse and helps to found a new religion: Fight Club, in which young males gather after hours in the basement of a nightclub to pound one another (and be pounded) to a bloody pulp. That last parenthesis isn't so parenthetical. In some ways, it's the longing to be beaten into oblivion that's the strongest. "Self-improvement," explains Tyler, "is masturbation"; self-destruction is the new way. Tyler's manifesto calls for an end to consumerism ("Things you own end up owning you"), and since society is going down ("Martha Stewart is polishing brass on the Titanic "), the only creative outlet left is annihilation. "It's only after we've lost everything that we're free to do anything," he says. Fincher and his screenwriter, Jim Uhls, seem to think they've broken new ground in Fight Club , that their metaphor for our discontents hits harder than anyone else's. Certainly it produces more bloody splatter. But 20 years ago, the same impulse was called punk and, as Greil Marcus documents in Lipstick Traces , it was other things before that. Yes, the mixture of Johnny Rotten, Jake La Motta, and Jesus is unique; and the Faludi-esque emasculation themes are more explicit. But there's something deeply movie-ish about the whole conceit, as if the novelist and director were weaned on Martin Scorsese pictures and never stopped dreaming of recapturing that first masochistic rush. The novel, the first by Chuck Palahniuk (the surname sounds like Eskimo for "palooka"--which somehow fits), walks a line between the straight and ironic--it isn't always clear if its glib sociological pronouncements are meant to be taken straight or as the ravings of a delusional mama's boy. But onscreen, when Pitt announces to the assembled fighters that they are the "middle children of history" with "no purpose and no place"--emasculated on one hand by the lack of a unifying crisis (a world war or depression) and on the other by lack of material wealth as promised by television--he seems meant to be intoning gospel. "We are a generation of men raised by women," Tyler announces, and adds, "If our fathers bail, what does that tell you about God?" (I give up: What?) F ight Club could use a few different perspectives: a woman's, obviously, but also an African-American's--someone who'd have a different take on the "healing" properties of violence. It's also unclear just what has emasculated Jack: Is it that he's a materialist or that the materials themselves (i.e., IKEA's lacquered particle boards) don't measure up to his fantasies of opulence? Is he motivated by spiritual hunger or envy? Tyler's subsequent idea of confining his group's mayhem to franchise coffee bars and corporate-subsidized art is a witty one--it's like a parody of neo-Nazism as re-enacted by yuppies. It might have been a howl if performed by, say, the troupe of artsy German nihilists in Joel and Ethan Coen's The Big Lebowski (1998). Somehow Brad Pitt doesn't have the same piquancy. Actually, Pitt isn't as terrible as usual: He's playing not a character but a conceit, and he can bask in his movie-idol arrogance, which seems to be the most authentic emotion he has. But the film belongs to Norton. As a ferocious skinhead in last year's American History X , Norton was taut and ropy, his long torso curled into a sneer; here, he's skinny and wilting, a quivering pansy. Even when he fights he doesn't transform--he's a raging wimp. The performance is marvelous, and it makes poetic sense in light of the movie's climactic twist. But that twist will annoy more people than it will delight, if only because it shifts the drama from the realm of the sociological to that of the psychoanalytic. The finale, scored with the Pixies' great "Where Is My Mind?" comes off facetiously--as if Fincher is throwing the movie away. Until then, however, he has done a fabulous job of keeping it spinning. The most thrilling thing about Fight Club isn't what it says but how Uhls and Fincher pull you into its narrator's head and simulate his adrenalin rushes. A veteran of rock videos, Fincher is one of those filmmakers who helps make the case that MTV--along with digital editing--has transformed cinema for better as well as worse. The syntax has become more intricate. Voice-over narration, once considered uncinematic, is back in style, along with novelistic asides, digressions, fantasies, and flashbacks. To make a point, you can jazzily interject anything--even, as in Three Kings , a shot of a bullet slicing through internal organs. Films like Fight Club might not gel, but they have a breathless, free-associational quality that points to new possibilities in storytelling. Or maybe old possibilities: The language of movies hasn't seemed this unfettered since the pre-sound days of Sergei Eisenstein and Abel Gance. An actress named Hilary Swank gives one of the most rapturous performances I've ever seen as the cross-dressing Brandon Teena (a k a Teena Brandon) in Kimberly Peirce's stark and astonishingly beautiful debut feature, Boys Don't Cry . The movie opens with Teena being shorn of her hated female tresses and becoming "Brandon," who swaggers around in tight jeans and leather jackets. The joy is in watching the actor transform, and I don't just mean Swank: I mean Teena Brandon playing Brandon Teena--the role she has been longing for her whole life. In a redneck Nebraska bar, Brandon throws back a shot of whiskey and the gesture--a macho cliché--becomes an act of self-discovery. Every gesture does. "You're gonna have a shiner in the morning," someone tells Brandon after a barroom brawl, and he takes the news with a glee that's almost mystical: "I am????? Oh, shit!!!" he cries, grinning. That might be my favorite moment in the picture, because Swank's ecstatic expression carries us through the next hour, as Brandon acts out his urban-cowboy fantasies--"surfing" from the bumper of a pickup truck, rolling in the mud, and straddling a barstool with one hand on a brewski and the other on the shoulder of a gorgeous babe. That the people with whom Brandon feels most at home would kill him if they knew his true gender is the movie's most tragic irony--and the one that lifts it out of the realm of gay-martyr hagiography and into something more complex and irreducible: a meditation on the irrelevance of gender. Peirce's triumph is to make these scenes at once exuberant (occasionally hilarious) and foreboding, so that all the seeds of Brandon's killing are right there on the screen. John (Peter Sarsgaard), one of his future rapists and murderers, calls him "little buddy" and seems almost attracted to him; Sarsgaard's performance is a finely chiseled study of how unresolved emotion can suddenly resolve itself into violence. Though harrowing, the second half of Boys Don't Cry isn't as great as the first. The early scenes evoke elation and dread simultaneously, the later ones just dread; and the last half-hour is unrelieved torture. What keeps the movie tantalizing is Chloë Sevigny's Lana, who might or might not know that Brandon is a girl but who's entranced by him anyway. With her lank hair, hooded eyes, and air of sleepy sensuality, Sevigny--maybe even more than Swank--embodies the mystery of sex that's at the core of Boys Don't Cry . Everything she does is deliberate, ironic, slightly unreadable--and unyielding. She's could be saying, "I'm in this world but not of it. ... You'd never dream what's underneath." I n brief: If a friend tells you you'll love Happy Texas , rethink the friendship. This clunky mistaken-identity comedy about escaped cons who impersonate gay pageant directors doesn't even make sense on its own low farcical terms; it's mostly one lame homo joke after another. The only bright spot is Steve Zahn, who could be the offspring of Michael J. Fox and Crispin Glover if they'd mated on the set of Back to the Future (1985). It's hard to make a serious case for Lawrence Kasdan's Mumford , which has apparently flopped but which you can still catch at second- and third-tier theaters. It looks peculiar--a Norman Rockwell painting with noir shadows. And its tale of a small town healed by a depressive (Loren Dean) posing as a psychologist is full of doddering misconceptions about psychotherapy. I almost don't know why I loved it, but the relaxed pacing and the witty turns by Martin Short, Ted Danson, David Paymer, and Mary McDonnell surely helped. I can't decide if the weirdly affectless Dean is inspired or inept, but my indecision suggests why he works in the role. There's no doubt, however, about his even more depressive love object, Hope Davis, who posseses the cinema's most expressive honking-nasal voice and who slumps through the movie like the world's most lyrical anti-ballerina. Even her puffy cheeks are eloquent: They made me think of Mumford as the home of the psychological mumps.
|
C. metaphor
|
What would the author say about the impact of swearing on our current society?
A. it is important for our culture to continue to grow accustomed to using swear words
B. our feeling about swearing now shows a more educated society
C. we have more rebels than we used to
D. it is unhealthy for our society to have powerless swear words
|
Maledict oratory The high costs of low language. Sunday, Jan. 14, 1996: A day that will live in--well, not infamy, exactly. Blasphemy would be closer to it. Early that afternoon, the Pittsburgh Steelers defeated the Indianapolis Colts to win the American Football Conference championship. Linebacker Greg Lloyd, accepting the trophy in front of a national television audience, responded with enthusiasm. "Let's see if we can bring this damn thing back here next year," he said, "along with the [expletive] Super Bowl." A few hours later, Michael Irvin of the Dallas Cowboys offered this spirited defense of his coach on TV after his team won the National Football Conference title: "Nobody deserves it more than Barry Switzer. He took all of this [expletive] ." Iwatched those episodes, and, incongruous as it may sound, I thought of Kenneth Tynan. Britain's great postwar drama critic was no fan of American football, but he was a fan of swearing. Thirty years earlier, almost to the week, Tynan was interviewed on BBC television in his capacity as literary director of Britain's National Theater and asked if he would allow the theater to present a play in which sex took place on stage. "Certainly," he replied. "I think there are very few rational people in this world to whom the word '[expletive]' is particularly diabolical or revolting or totally forbidden." It turned out there were a few more than Tynan thought. Within 24 hours, resolutions had been introduced in the House of Commons calling for his prosecution on charges of obscenity, for his removal as a theater official, and for censure of the network for allowing an obscene word to go out on the airwaves. Tynan escaped punishment, but he acquired a public reputation for tastelessness that he carried for the rest his life. To much of ordinary Britain, he became the man who had said "[expletive]" on the BBC. Neither Greg Lloyd nor Michael Irvin was so stigmatized. "It's live television," NBC Vice President Ed Markey said, rationalizing the outbursts. "It's an emotional moment. These things happen." Irvin wasn't about to let that stand. "I knew exactly what I was saying," he insisted later. "Those of you who can't believe I said it--believe it." Swearing isn't the only public act that Western civilization condones today but didn't 30 years ago. But it is one of the most interesting. It is everywhere, impossible to avoid or tune out. I am sitting in a meeting at the office, talking with a colleague about a business circumstance that may possibly go against us. "In that case, we're [expletive] ," he says. Five years ago, he would have said "screwed." Twenty years ago, he would have said, "We're in big trouble." Societal tolerance of profanity requires us to increase our dosage as time goes on. I am walking along a suburban street, trailing a class of pre-schoolers who are linked to each other by a rope. A pair of teen-agers passes us in the other direction. By the time they have reached the end of the line of children, they have tossed off a whole catalog of obscenities I did not even hear until I was well into adolescence, let alone use in casual conversation on a public street. I am talking to a distinguished professor of public policy about a foundation grant. I tell her something she wasn't aware of before. In 1965, the appropriate response was "no kidding." In 1996, you do not say "no kidding." It is limp and ineffectual. If you are surprised at all, you say what she says: "No shit." What word is taboo in middle-class America in 1996? There are a couple of credible candidates: The four-letter word for "vagina" remains off-limits in polite conversation (although that has more to do with feminism than with profanity), and the slang expression for those who engage in oral sex with males is not yet acceptable by the standards of office-meeting etiquette. But aside from a few exceptions, the supply of genuinely offensive language has dwindled almost to nothing as the 20th century comes to an end; the currency of swearing has been inflated to the brink of worthlessness. When almost anything can be said in public, profanity ceases to exist in any meaningful way at all. That most of the forbidden words of the 1950s are no longer forbidden will come as news to nobody: The steady debasement of the common language is only one of many social strictures that have loosened from the previous generation to the current. What is important is that profanity served a variety of purposes for a long time in Western culture. It does not serve those purposes any more. What purposes? There are a couple of plausible answers. One of them is emotional release. Robert Graves, who wrote a book in the 1920s called The Future of Swearing , thought that profanity was the adult replacement for childhood tears. There comes a point in life, he wrote, when "wailing is rightly discouraged, and groans are also considered a signal of extreme weakness. Silence under suffering is usually impossible." So one reaches back for a word one does not normally use, and utters it without undue embarrassment or guilt. And one feels better--even stimulated. The anthropologist Ashley Montagu, whose Anatomy of Swearing , published in 1967, is the definitive modern take on the subject, saw profanity as a safety valve rather than a stimulant, a verbal substitute for physical aggression. When someone swears, Montagu wrote, "potentially noxious energy is converted into a form that renders it comparatively innocuous." One could point out, in arguing against the safety-valve theory, that as America has grown more profane in the past 30 years, it has also grown more violent, not less. But this is too simple. It isn't just the supply of dirty words that matters, it's their emotive power. If they have lost that power through overuse, it's perfectly plausible to say that their capacity to deter aggressive behavior has weakened as well. But there is something else important to say about swearing--that it represents the invocation of those ideas a society considers powerful, awesome, and a little scary. I'm not sure there is an easy way to convey to anybody under 30, for example, the sheer emotive force that the word "[expletive]" possessed in the urban childhood culture of 40 years ago. It was the verbal link to a secret act none of us understood but that was known to carry enormous consequences in the adult world. It was the embodiment of both pleasure and danger. It was not a word or an idea to mess with. When it was used, it was used, as Ashley Montagu said, "sotto voce , like a smuggler cautiously making his way across a forbidden frontier." In that culture, the word "[expletive]" was not only obscene, it was profane, in the original sense: It took an important idea in vain. Profanity can be an act of religious defiance, but it doesn't have to be. The Greeks tempted fate by invoking the names of their superiors on Mount Olympus; they also swore upon everyday objects whose properties they respected but did not fully understand. "By the Cabbage!" Socrates is supposed to have said in moments of stress, and that was for good reason. He believed that cabbage cured hangovers, and as such, carried sufficient power and mystery to invest any moment with the requisite emotional charge. These days, none of us believes in cabbage in the way Socrates did, or in the gods in the way most Athenians did. Most Americans tell poll-takers that they believe in God, but few of them in a way that would make it impossible to take His name in vain: That requires an Old Testament piety that disappeared from American middle-class life a long time ago. Nor do we believe in sex any more the way most American children and millions of adults believed in it a generation ago: as an act of profound mystery and importance that one did not engage in, or discuss, or even invoke, without a certain amount of excitement and risk. We have trivialized and routinized sex to the point where it just doesn't carry the emotional freight it carried in the schoolyards and bedrooms of the 1950s. Many enlightened people consider this to be a great improvement over a society in which sex generated not only emotion and power, but fear. For the moment, I wish to insist only on this one point: When sexuality loses its power to awe, it loses its power to create genuine swearing. When we convert it into a casual form of recreation, we shouldn't be surprised to hear linebackers using the word "[expletive]" on national television. To profane something, in other words, one must believe in it. The cheapening of profanity in modern America represents, more than anything else, the crumbling of belief. There are very few ideas left at this point that are awesome or frightening enough for us to enforce a taboo against them. The instinctive response of most educated people to the disappearance of any taboo is to applaud it, but this is wrong. Healthy societies need a decent supply of verbal taboos and prohibitions, if only as yardsticks by which ordinary people can measure and define themselves. By violating these taboos over and over, some succeed in defining themselves as rebels. Others violate them on special occasions to derive an emotional release. Forbidden language is one of the ways we remind children that there are rules to everyday life, and consequences for breaking them. When we forget this principle, or cease to accept it, it is not just our language that begins to fray at the edges. What do we do about it? Well, we could pass a law against swearing. Mussolini actually did that. He decreed that trains and buses, in addition to running on time, had to carry signs that read "Non bestemmiare per l'onore d'Italia." ("Do not swear for the honor of Italy.") The commuters of Rome reacted to those signs exactly as you would expect: They cursed them. What Mussolini could not do, I am reasonably sure that American governments of the 1990s cannot do, nor would I wish it. I merely predict that sometime in the coming generation, profanity will return in a meaningful way. It served too many purposes for too many years of American life to disappear on a permanent basis. We need it. And so I am reasonably sure that when my children have children, there will once again be words so awesome that they cannot be uttered without important consequences. This will not only represent a new stage of linguistic evolution, it will be a token of moral revival. What the dirty words will be, God only knows.
|
D. it is unhealthy for our society to have powerless swear words
|
How are citizens organized into different classes in society?
A. Through random assignment at birth
B. According to their socioeconomic status
C. After a lengthy interview with Anthropos upon reaching a specific age-set
D. By an analysis of their genes and heredity
|
Conditionally Human By WALTER M. MILLER, JR. Illustrated by DAVID STONE [Transcriber's Note: This etext was produced from Galaxy Science Fiction February 1952. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] They were such cute synthetic creatures, it was impossible not to love them. Of course, that was precisely why they were dangerous! There was no use hanging around after breakfast. His wife was in a hurt mood, and he could neither endure the hurt nor remove it. He put on his coat in the kitchen and stood for a moment with his hat in his hands. His wife was still at the table, absently fingering the handle of her cup and staring fixedly out the window at the kennels behind the house. He moved quietly up behind her and touched her silk-clad shoulder. The shoulder shivered away from him, and her dark hair swung shiningly as she shuddered. He drew his hand back and his bewildered face went slack and miserable. "Honeymoon's over, huh?" She said nothing, but shrugged faintly. "You knew I worked for the F.B.A.," he said. "You knew I'd have charge of a district pound. You knew it before we got married." "I didn't know you killed them," she said venomously. "I won't have to kill many. Besides, they're only animals." " Intelligent animals!" "Intelligent as a human imbecile, maybe." "A small child is an imbecile. Would you kill a small child?" "You're taking intelligence as the only criterion of humanity," he protested hopelessly, knowing that a logical defense was useless against sentimentality. "Baby—" "Don't call me baby! Call them baby!" Norris backed a few steps toward the door. Against his better judgment, he spoke again. "Anne honey, look! Think of the good things about the job. Sure, everything has its ugly angles. But think—we get this house rent-free; I've got my own district with no bosses around; I make my own hours; you'll meet lots of people that stop in at the pound. It's a fine job, honey!" She sipped her coffee and appeared to be listening, so he went on. "And what can I do? You know how the Federation handles employment. They looked over my aptitude tests and sent me to Bio-Administration. If I don't want to follow my aptitudes, the only choice is common labor. That's the law ." "I suppose you have an aptitude for killing babies?" she said sweetly. Norris withered. His voice went desperate. "They assigned me to it because I liked babies. And because I have a B.S. in biology and an aptitude for dealing with people. Can't you understand? Destroying unclaimed units is the smallest part of it. Honey, before the evolvotron, before Anthropos went into the mutant-animal business, people used to elect dogcatchers. Think of it that way—I'm just a dogcatcher." Her cool green eyes turned slowly to meet his gaze. Her face was delicately cut from cold marble. She was a small woman, slender and fragile, but her quiet contempt made her loom. He backed closer to the door. "Well, I've got to get on the job." He put on his hat and picked at a splinter on the door. He frowned studiously at the splinter. "I—I'll see you tonight." He ripped the splinter loose when it became obvious that she didn't want to be kissed. He grunted a nervous good-by and stumbled down the hall and out of the house. The honeymoon was over, all right. He climbed in the kennel-truck and drove east toward the highway. The suburban street wound among the pastel plasticoid cottages that were set approximately two to an acre on the lightly wooded land. With its population legally fixed at three hundred million, most of the country had become one big suburb, dotted with community centers and lined with narrow belts of industrial development. Norris wished there were someplace where he could be completely alone. As he approached an intersection, he saw a small animal sitting on the curb, wrapped in its own bushy tail. Its oversized head was bald on top, but the rest of its body was covered with blue-gray fur. Its tiny pink tongue was licking daintily at small forepaws with prehensile thumbs. It was a cat-Q-5. It glanced curiously at the truck as Norris pulled to a halt. He smiled at it from the window and called, "What's your name, kitten?" The cat-Q-5 stared at him impassively for a moment, let out a stuttering high-pitched wail, then: "Kiyi Rorry." "Whose child are you, Rorry?" he asked. "Where do you live?" The cat-Q-5 took its time about answering. There were no houses near the intersection, and Norris feared that the animal might be lost. It blinked at him, sleepily bored, and resumed its paw-washing. He repeated the questions. "Mama kiyi," said the cat-Q-5 disgustedly. "That's right, Mama's kitty. But where is Mama? Do you suppose she ran away?" The cat-Q-5 looked startled. It stuttered for a moment, and its fur crept slowly erect. It glanced around hurriedly, then shot off down the street at a fast scamper. He followed it in the truck until it darted onto a porch and began wailing through the screen, "Mama no run ray! Mama no run ray!" Norris grinned and drove on. A class-C couple, allowed no children of their own, could get quite attached to a cat-Q-5. The felines were emotionally safer than the quasi-human chimp-K series called "neutroids." When a pet neutroid died, a family was broken with grief; but most couples could endure the death of a cat-Q or a dog-F. Class-C couples were allowed two lesser units or one neutroid. His grin faded as he wondered which Anne would choose. The Norrises were class-C—defective heredity. He found himself in Sherman III Community Center—eight blocks of commercial buildings, serving the surrounding suburbs. He stopped at the message office to pick up his mail. There was a memo from Chief Franklin. He tore it open nervously and read it in the truck. It was something he had been expecting for several days. Attention All District Inspectors: Subject: Deviant Neutroid. You will immediately begin a systematic and thorough survey of all animals whose serial numbers fall in the Bermuda-K-99 series for birth dates during July 2234. This is in connection with the Delmont Negligency Case. Seize all animals in this category, impound, and run proper sections of normalcy tests. Watch for mental and glandular deviation. Delmont has confessed to passing only one non-standard unit, but there may be others. He disclaims memory of deviant's serial number. This could be a ruse to bring a stop to investigations when one animal is found. Be thorough. If allowed to reach age-set or adulthood, such a deviant could be dangerous to its owner or to others. Hold all seized K-99s who show the slightest abnormality in the normalcy tests. Forward to central lab. Return standard units to their owners. Accomplish entire survey project within seven days. C. Franklin Norris frowned at the last sentence. His district covered about two hundred square miles. Its replacement-quota of new neutroids was around three hundred animals a month. He tried to estimate how many of July's influx had been K-99s from Bermuda Factory. Forty, at least. Could he do it in a week? And there were only eleven empty neutroid cages in his kennel. The other forty-nine were occupied by the previous inspector's "unclaimed" inventory—awaiting destruction. He wadded the memo in his pocket, then nosed the truck onto the highway and headed toward Wylo City and the district wholesale offices of Anthropos, Inc. They should be able to give him a list of all July's Bermuda K-99 serial numbers that had entered his territory, together with the retailers to whom the animals had been sold. A week's deadline for finding and testing forty neutroids would put him in a tight squeeze. He was halfway to Wylo City when the radiophone buzzed on his dashboard. He pulled into the slow lane and answered quickly, hoping for Anne's voice. A polite professional purr came instead. "Inspector Norris? This is Doctor Georges. We haven't met, but I imagine we will. Are you extremely busy at the moment?" Norris hesitated. "Extremely," he said. "Well, this won't take long. One of my patients—a Mrs. Sarah Glubbes—called a while ago and said her baby was sick. I must be getting absent-minded, because I forgot she was class C until I got there." He hesitated. "The baby turned out to be a neutroid. It's dying. Eighteenth order virus." "So?" "Well, she's—uh—rather a peculiar woman, Inspector. Keeps telling me how much trouble she had in childbirth, and how she can't ever have another one. It's pathetic. She believes it's her own. Do you understand?" "I think so," Norris replied slowly. "But what do you want me to do? Can't you send the neutroid to a vet?" "She insists it's going to a hospital. Worst part is that she's heard of the disease. Knows it can be cured with the proper treatment—in humans. Of course, no hospital would play along with her fantasy and take a neutroid, especially since she couldn't pay for its treatment." "I still don't see—" "I thought perhaps you could help me fake a substitution. It's a K-48 series, five-year-old, three-year set. Do you have one in the pound that's not claimed?" Norris thought for a moment. "I think I have one . You're welcome to it, Doctor, but you can't fake a serial number. She'll know it. And even though they look exactly alike, the new one won't recognize her. It'll be spooky." There was a long pause, followed by a sigh. "I'll try it anyway. Can I come get the animal now?" "I'm on the highway—" "Please, Norris! This is urgent. That woman will lose her mind completely if—" "All right, I'll call my wife and tell her to open the pound for you. Pick out the K-48 and sign for it. And listen—" "Yes?" "Don't let me catch you falsifying a serial number." Doctor Georges laughed faintly. "I won't, Norris. Thanks a million." He hung up quickly. Norris immediately regretted his consent. It bordered on being illegal. But he saw it as a quick way to get rid of an animal that might later have to be killed. He called Anne. Her voice was dull. She seemed depressed, but not angry. When he finished talking, she said, "All right, Terry," and hung up. By noon, he had finished checking the shipping lists at the wholesale house in Wylo City. Only thirty-five of July's Bermuda-K-99s had entered his territory, and they were about equally divided among five pet shops, three of which were in Wylo City. After lunch, he called each of the retail dealers, read them the serial numbers, and asked them to check the sales records for names and addresses of individual buyers. By three o'clock, he had the entire list filled out, and the task began to look easier. All that remained was to pick up the thirty-five animals. And that , he thought, was like trying to take a year-old baby away from its doting mother. He sighed and drove to the Wylo suburbs to begin his rounds. Anne met him at the door when he came home at six. He stood on the porch for a moment, smiling at her weakly. The smile was not returned. "Doctor Georges came," she told him. "He signed for the—" She stopped to stare at him. "Darling, your face! What happened?" Gingerly he touch the livid welts down the side of his cheek. "Just scratched a little," he muttered. He pushed past her and went to the phone in the hall. He sat eying it distastefully for a moment, not liking what he had to do. Anne came to stand beside him and examine the scratches. Finally he lifted the phone and dialed the Wylo exchange. A grating mechanical voice answered, "Locator center. Your party, please." "Sheriff Yates," Norris grunted. The robot operator, which had on tape the working habits of each Wylo City citizen, began calling numbers. It found the off-duty sheriff on its third try, in a Wylo pool hall. "I'm getting so I hate that infernal gadget," Yates grumbled. "I think it's got me psyched. What do you want, Norris?" "Cooperation. I'm mailing you three letters charging three Wylo citizens with resisting a Federal official—namely me —and charging one of them with assault. I tried to pick up their neutroids for a pound inspection—" Yates bellowed lusty laughter into the phone. "It's not funny. I've got to get those neutroids. It's in connection with the Delmont case." Yates stopped laughing. "Oh. Well, I'll take care of it." "It's a rush-order, Sheriff. Can you get the warrants tonight and pick up the animals in the morning?" "Easy on those warrants, boy. Judge Charleman can't be disturbed just any time. I can get the newts to you by noon, I guess, provided we don't have to get a helicopter posse to chase down the mothers." "That'll be all right. And listen, Yates—fix it so the charges will be dropped if they cooperate. Don't shake those warrants around unless they just won't listen to reason. But get those neutroids." "Okay, boy. Gotcha." Norris gave him the names and addresses of the three unwilling mothers. As soon as he hung up, Anne touched his shoulders and said, "Sit still." She began smoothing a chilly ointment over his burning cheek. "Hard day?" she asked. "Not too hard. Those were just three out of fifteen. I got the other twelve. They're in the truck." "That's good," she said. "You've got only twelve empty cages." He neglected to tell her that he had stopped at twelve for just this reason. "Guess I better get them unloaded," he said, standing up. "Can I help you?" He stared at her for a moment, saying nothing. She smiled a little and looked aside. "Terry, I'm sorry—about this morning. I—I know you've got a job that has to be—" Her lip quivered slightly. Norris grinned, caught her shoulders, and pulled her close. "Honeymoon's on again, huh?" she whispered against his neck. "Come on," he grunted. "Let's unload some neutroids, before I forget all about work." They went out to the kennels together. The cages were inside a sprawling concrete barn, which was divided into three large rooms—one for the fragile neuter humanoid creatures, and another for the lesser mutants, such as cat-Qs, dog-Fs, dwarf bears, and foot-high lambs that never matured into sheep. The third room contained a small gas chamber with a conveyor belt leading from it to a crematory-incinerator. Norris kept the third locked lest his wife see its furnishings. The doll-like neutroids began their mindless chatter as soon as their keepers entered the building. Dozens of blazing blond heads began dancing about their cages. Their bodies thwacked against the wire mesh as they leaped about their compartments with monkey grace. Their human appearance was broken by only two distinct features: short beaverlike tails decorated with fluffy curls of fur, and an erect thatch of scalp-hair that grew up into a bright candleflame. Otherwise, they appeared completely human, with baby-pink skin, quick little smiles, and cherubic faces. They were sexually neuter and never grew beyond a predetermined age-set which varied for each series. Age-sets were available from one to ten years human equivalent. Once a neutroid reached its age-set, it remained at the set's child-development level until death. "They must be getting to know you pretty well," Anne said, glancing around at the cages. Norris was wearing a slight frown as he inspected the room. "They've never gotten this excited before." He walked along a row of cages, then stopped by a K-76 to stare. " Apple cores! " He turned to face his wife. "How did apples get in there?" She reddened. "I felt sorry for them, eating that goo from the mechanical feeder. I drove down to Sherman III and bought six dozen cooking apples." "That was a mistake." She frowned irritably. "We can afford it." "That's not the point. There's a reason for the mechanical feeders." He paused, wondering how he could tell her the truth. He blundered on: "They get to love whoever feeds them." "I can't see—" "How would you feel about disposing of something that loved you?" Anne folded her arms and stared at him. "Planning to dispose of any soon?" she asked acidly. "Honeymoon's off again, eh?" She turned away. "I'm sorry, Terry. I'll try not to mention it again." He began unloading the truck, pulling the frightened and squirming doll-things forth one at a time with a snare-pole. They were one-man pets, always frightened of strangers. "What's the Delmont case, Terry?" Anne asked while he worked. "Huh?" "I heard you mention it on the phone. Anything to do with why you got your face scratched?" He nodded sourly. "Indirectly, yes. It's a long story." "Tell me." "Well, Delmont was a green-horn evolvotron operator at the Bermuda plant. His job was taking the unfertilized chimpanzee ova out of the egg-multiplier, mounting them in his machine, and bombarding the gene structure with sub-atomic particles. It's tricky business. He flashes a huge enlargement of the ovum on the electron microscope screen—large enough so he can see the individual protein molecules. He has an artificial gene pattern to compare it with. It's like shooting sub-atomic billiards. He's got to fire alpha-particles into the gene structure and displace certain links by just the right amount. And he's got to be quick about it before the ovum dies from an overdose of radiation from the enlarger. A good operator can get one success out of seven tries. "Well, Delmont worked a week and spoiled over a hundred ova without a single success. They threatened to fire him. I guess he got hysterical. Anyway, he reported one success the next day. It was faked. The ovum had a couple of flaws—something wrong in the central nervous system's determinants, and in the glandular makeup. Not a standard neutroid ovum. He passed it on to the incubators to get a credit, knowing it wouldn't be caught until after birth." "It wasn't caught at all?" Anne asked. "Funny thing, he was afraid it wouldn't be. He got to worrying about it, thought maybe a mental-deviant would pass, and that it might be dangerous. So he went back to its incubator and cut off the hormone flow into its compartment." "Why that?" "So it would develop sexuality. A neutroid would be born a female if they didn't give it suppressive doses of male hormone prenatally. That keeps ovaries from developing and it comes out neuter. But Delmont figured a female would be caught and stopped before the final inspection. They'd dispose of her without even bothering to examine for the other defects. And he could blame the sexuality on an equipment malfunction. He thought it was pretty smart. Trouble was they didn't catch the female. She went on through; they all look female." "How did they find out about it now?" "He got caught last month, trying it again. And he confessed to doing it once before. No telling how many times he really did it." Norris held up the final kicking, squealing, tassel-haired doll from the back of the kennel-truck. He grinned at his wife. "This little fellow, for instance. It might be a potential she. It might also be a potential murderer. All these kiddos are from the machines in the section where Delmont worked." Anne snorted and caught the baby-creature in her arms. It struggled and tried to bite, but subsided a little when she disentangled it from the snare. "Kkr-r-reee," it cooed nervously. "Kkr-r-reee!" "You tell him you're no murderer," Anne purred to it. Norris watched disapprovingly while she fondled it. One thing he had learned: to steer clear of emotional attachments. It was eight months old and looked like a child of two years—a year short of its age-set. And it was designed to be as affectionate as a human child. "Put it in the cage, Anne," he said quietly. She looked up and shook her head. "It belongs to somebody else. If it fixes a libido attachment on you, you're actually robbing its owner. They can't love many people at once." She snorted, but installed the thing in its cage. "Anne—" Norris hesitated, hating to approach the subject. "Do you—want one—for yourself? I can sign an unclaimed one over to you to keep in the house. It won't cost us anything." Slowly she shook her head, and her pale eyes went moody and luminous. "I'm going to have one of my own," she said. He stood in the back of the truck, staring down at her. "Do you realize what—" "I know what I'm saying. We're class-C on account of heart-trouble in both our families. Well, I don't care, Terry. I'm not going to waste a heart over one of these pathetic little artificial animals. We're going to have a baby." "You know what they'd do to us?" "If they catch us, yes—compulsory divorce, sterilization. But they won't catch us. I'll have it at home, Terry. Not even a doctor. We'll hide it." "I won't let you do such a thing." She faced him angrily. "Oh, this whole rotten world !" she choked. Suddenly she turned and fled out of the building. She was sobbing. Norris climbed slowly down from the truck and wandered on into the house. She was not in the kitchen nor the living room. The bedroom door was locked. He shrugged and went to sit on the sofa. The television set was on, and a newscast was coming from a local station. "... we were unable to get shots of the body," the announcer was saying. "But here is a view of the Georges residence. I'll switch you to our mobile unit in Sherman II, James Duncan reporting." Norris frowned with bewilderment as the scene shifted to a two-story plasticoid house among the elm trees. It was after dark, but the mobile unit's powerful floodlights made daylight of the house and its yard and the police 'copters sitting in a side lot. An ambulance was parked in the street. A new voice came on the audio. "This is James Duncan, ladies and gentlemen, speaking to you from our mobile unit in front of the late Doctor Hiram Georges' residence just west of Sherman II. We are waiting for the stretcher to be brought out, and Police Chief Erskine Miler is standing here beside me to give us a word about the case. Doctor Georges' death has shocked the community deeply. Most of you local listeners have known him for many years—some of you have depended upon his services as a family physician. He was a man well known, well loved. But now let's listen to Chief Miler." Norris sat breathing quickly. There could scarcely be two Doctor Georges in the community, but only this morning.... A growling drawl came from the audio. "This's Chief Miler speaking, folks. I just want to say that if any of you know the whereabouts of a Mrs. Sarah Glubbes, call me immediately. She's wanted for questioning." "Thank you, Chief. This is James Duncan again. I'll review the facts for you briefly again, ladies and gentlemen. At seven o'clock, less than an hour ago, a woman—allegedly Mrs. Glubbes—burst into Doctor Georges' dining room while the family was at dinner. She was brandishing a pistol and screaming, 'You stole my baby! You gave me the wrong baby! Where's my baby?' "When the doctor assured her that there was no other baby, she fired, shattering his salad plate. Glancing off it, the bullet pierced his heart. The woman fled. A peculiar feature of the case is that Mrs. Glubbes, the alleged intruder, has no baby . Just a minute—just a minute—here comes the stretcher now." Norris turned the set off and went to call the police. He told them what he knew and promised to make himself available for questioning if it became necessary. When he turned from the phone, Anne was standing in the bedroom doorway. She might have been crying a little, but she concealed it well. "What was all that?" she asked. "Woman killed a man. I happened to know the motive." "What was it?" "Neutroid trouble." "You meet up with a lot of unpleasantness in this business, don't you?" "Lot of unpleasant emotions tangled up in it," he admitted. "I know. Well, supper's been keeping hot for two hours. Shall we eat?" They went to bed at midnight, but it was after one when he became certain that his wife was asleep. He lay in darkness for a time, listening to her even breathing. Then he cautiously eased himself out of bed and tiptoed quietly through the door, carrying his shoes and trousers. He put them on in the kitchen and stole silently out to the kennels. A half moon hung low in a misty sky, and the wind was chilly out of the north. He went into the neutroid room and flicked a switch. A few sleepy chatters greeted the light. One at a time, he awoke twenty-three of the older doll-things and carried them to a large glass-walled compartment. These were the long-time residents; they knew him well, and they came with him willingly—like children after the Piper of Hamlin. When he had gotten them in the glass chamber, he sealed the door and turned on the gas. The conveyor would automatically carry them on to the incinerator. Now he had enough cages for the Bermuda-K-99s. He hurriedly quit the kennels and went to sit on the back steps. His eyes were burning, but the thought of tears made him sicker. It was like an assassin crying while he stabbed his victim. It was more honest just to retch. When he tiptoed back inside, he got as far as the hall. Then he saw Anne's small figure framed in the bedroom window, silhouetted against the moonlit yard. She had slipped into her negligee and was sitting on the narrow windowstool, staring silently out at the dull red tongue of exhaust gases from the crematory's chimney. Norris backed away. He went to the parlor and lay down on the couch. After a while he heard her come into the room. She paused in the center of the rug, a fragile mist in the darkness. He turned his face away and waited for the rasping accusation. But soon she came to sit on the edge of the sofa. She said nothing. Her hand crept out and touched his cheek lightly. He felt her cool finger-tips trace a soft line up his temple. "It's all right, Terry," she whispered. He kept his face averted. Her fingers traced a last stroke. Then she padded quietly back to the bedroom. He lay awake until dawn, knowing that it would never be all right, neither the creating nor the killing, until he—and the whole world—completely lost sanity. And then everything would be all right, only it still wouldn't make sense. Anne was asleep when he left the house. The night mist had gathered into clouds that made a gloomy morning of it. He drove on out in the kennel-truck, meaning to get the rest of the Bermuda-K-99s so that he could begin his testing. Still he felt the night's guilt, like a sticky dew that refused to depart with morning. Why should he have to kill the things? The answer was obvious. Society manufactured them because killing them was permissible. Human babies could not be disposed of when the market became glutted. The neutroids offered solace to childless women, kept them satisfied with a restricted birth rate. And why a restricted birth rate? Because by keeping the population at five billions, the Federation could insure a decent living standard for everybody. Where there was giving, Norris thought glumly, there was also taking away. Man had always deluded himself by thinking that he "created," but he created nothing. He thought that he had created—with his medical science and his end to wars—a longer life for the individual. But he found that he had only taken the lives of the unborn and added them to the years of the aged. Man now had a life expectancy of eighty, except that he had damn little chance of being born to enjoy it. A neutroid filled the cradle in his stead. A neutroid that never ate as much, or grew up to be unemployed. A neutroid could be killed if things got tough, but could still satisfy a woman's craving to mother something small. Norris gave up thinking about it. Eventually he would have to adjust to it. He was already adjusted to a world that loved the artificial mutants as children. He had been brought up in it. Emotion came in conflict with the grim necessities of his job. Somehow he would have to love them in the parlor and kill them in the kennel. It was only a matter of adjustment. At noon, he brought back another dozen K-99s and installed them in his cages. There had been two highly reluctant mothers, but he skipped them and left the seizure to the local authorities. Yates had already brought in the three from yesterday. "No more scratches?" Anne asked him while they ate lunch. They did not speak of the night's mass-disposal. Norris smiled mechanically. "I learned my lesson yesterday. If they bare their fangs, I get out without another word. Funny thing though—I've got a feeling one mother pulled a fast one." "What happened?" "Well, I told her what I wanted and why. She didn't like it, but she let me in. I started out with her newt, but she wanted a receipt. So I gave her one; took the serial number off my checklist. She looked at it and said, 'Why, that's not Chichi's number!' I looked at the newt's foot, and sure enough it wasn't. I had to leave it. It was a K-99, but not even from Bermuda." "I thought they were all registered," Anne said. "They are. I told her she had the wrong neutroid, but she got mad. Went and got the sales receipt. It checked with her newt, and it was from O'Reilley's pet shop—right place, wrong number. I just don't get it." "Nothing to worry about, is it Terry?" He looked at her peculiarly. "Ever think what might happen if someone started a black market in neutroids?" They finished the meal in silence. After lunch he went out again to gather up the rest of the group. By four o'clock, he had gotten all that were to be had without the threat of a warrant. The screams and pleas and tears of the owners left him gloomily despising himself. If Delmont's falsification had been widespread, he might have to turn several of the thirty-five over to central lab for dissection and ultimate destruction. That would bring the murderous wrath of their owners down upon him. He began to understand why bio-inspectors were frequently shifted from one territory to another. On the way home, he stopped in Sherman II to check on the missing number. It was the largest of the Sherman communities, covering fifty blocks of commercial buildings. He parked in the outskirts and took a sidewalk escalator toward O'Reilley's address. It was on a dingy sidestreet, reminiscent of past centuries, a street of small bars and bowling alleys and cigar stores. There was even a shop with three gold balls above the entrance, but the place was now an antique store. A light mist was falling when he stepped off the escalator and stood in front of the pet shop. A sign hung out over the sidewalk, announcing: J. "DOGGY" O'REILLEY PETS FOR SALE DUMB BLONDES AND GOLDFISH MUTANTS FOR THE CHILDLESS BUY A BUNDLE OF JOY Norris frowned at the sign and wandered inside. The place was warm and gloomy. He wrinkled his nose at the strong musk of animal odors. O'Reilley's was not a shining example of cleanliness. Somewhere a puppy was yapping, and a parrot croaked the lyrics of A Chimp to Call My Own , which Norris recognized as the theme song of a popular soap-opera about a lady evolvotron operator. He paused briefly by a tank of silk-draped goldfish. The shop had a customer. An elderly lady was haggling with a wizened manager over the price of a half grown second-hand dog-F. She was shaking her last dog's death certificate under his nose and demanding a guarantee of the dog's alleged F-5 intelligence. The old man offered to swear on a Bible, but he demurred when it came to swearing on a ledger. The dog was saying, "Don' sell me, Dada. Don' sell me." Norris smiled sardonically to himself. The non-human pets were smarter than the neutroids. A K-108 could speak a dozen words, and a K-99 never got farther than "mamma," "pappa," and "cookie." Anthropos was afraid to make the quasi-humans too intelligent, lest sentimentalists proclaim them really human. He wandered on toward the back of the building, pausing briefly by the cash register to inspect O'Reilley's license, which hung in a dusty frame on the wall behind the counter. "James Fallon O'Reilley ... authorized dealer in mutant animals ... all non-predatory mammals including chimpanzee-K series ... license expires June 1, 2235." It seemed in order, although the expiration date was approaching. He started toward a bank of neutroid cages along the opposite wall, but O'Reilley was mincing across the floor to meet him. The customer had gone. The little manager wore an elfin professional smile, and his bald head bobbled in a welcoming nod. "Good day, sir, good day! May I show you a dwarf kangaroo, or a—" He stopped and adjusted his spectacles. He blinked and peered as Norris flashed his badge. His smile waned. "I'm Agent Norris, Mr. O'Reilley. Called you yesterday for that rundown on K-99 sales." O'Reilley looked suddenly nervous. "Oh, yes. Find 'em all?" Norris shook his head. "No. That's why I stopped by. There's some mistake on—" he glanced at his list—"on K-99-LJZ-351. Let's check it again." O'Reilley seemed to cringe. "No mistake. I gave you the buyer's name." "She has a different number." "Can I help it if she traded with somebody?" "She didn't. She bought it here. I saw the receipt." "Then she traded with one of my other customers!" snapped the old man. "Two of your customers have the same name—Adelia Schultz? Not likely. Let's see your duplicate receipt book." O'Reilley's wrinkled face set itself into a stubborn mask. "Doubt if it's still around." Norris frowned. "Look, pop, I've had a rough day. I could start naming some things around here that need fixing—sanitary violations and such. Not to mention that sign—'dumb blondes.' They outlawed that one when they executed that shyster doctor for shooting K-108s full of growth hormones, trying to raise himself a harem to sell. Besides, you're required to keep sales records until they've been micro-filmed. There hasn't been a microfilming since July." The wrinkled face twitched with frustrated anger. O'Reilley shuffled to the counter while Norris followed. He got a fat binder from under the register and started toward a wooden stairway. "Where you going?" Norris called. "Get my old glasses," the manager grumbled. "Can't see through these new things." "Leave the book here and I'll check it," Norris offered. But O'Reilley was already limping quickly up the stairs. He seemed not to hear. He shut the door behind him, and Norris heard the lock click. The bio-agent waited. Again the thought of a black market troubled him. Unauthorized neutroids could mean lots of trouble.
|
D. By an analysis of their genes and heredity
|
Why is the narrator the only one who notices a flight of volplas soaring slowly across the full Moon?
A. Because volplas are fictional creatures and people do not believe they exist.
B. Because other witness believe this was ET with a little boy riding his bicycle over the moon.
C. Because people generally only notice what they look for and would dismiss the phenomenon as something else.
D. Because it is nighttime and everyone is indoors.
|
Volpla By WYMAN GUIN Illustrated by DICK FRANCIS [Transcriber's Note: This etext was produced from Galaxy Science Fiction May 1956. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] The only kind of gag worth pulling, I always maintained, was a cosmic one—till I learned the Cosmos has a really nasty sense of humor! There were three of them. Dozens of limp little mutants that would have sent an academic zoologist into hysterics lay there in the metabolic accelerator. But there were three of them . My heart took a great bound. I heard my daughter's running feet in the animal rooms and her rollerskates banging at her side. I closed the accelerator and walked across to the laboratory door. She twisted the knob violently, trying to hit a combination that would work. I unlocked the door, held it against her pushing and slipped out so that, for all her peering, she could see nothing. I looked down on her tolerantly. "Can't adjust your skates?" I asked again. "Daddy, I've tried and tried and I just can't turn this old key tight enough." I continued to look down on her. "Well, Dad-dee, I can't!" "Tightly enough." "What?" "You can't turn this old key tightly enough." "That's what I say -yud." "All right, wench. Sit on this chair." I got down and shoved one saddle shoe into a skate. It fitted perfectly. I strapped her ankle and pretended to use the key to tighten the clamp. Volplas at last. Three of them. Yet I had always been so sure I could create them that I had been calling them volplas for ten years. No, twelve. I glanced across the animal room to where old Nijinsky thrust his graying head from a cage. I had called them volplas since the day old Nijinsky's elongated arms and his cousin's lateral skin folds had given me the idea of a flying mutant. When Nijinsky saw me looking at him, he started a little tarantella about his cage. I smiled with nostalgia when the fifth fingers of his hands, four times as long as the others, uncurled as he spun about the cage. I turned to the fitting of my daughter's other skate. "Daddy?" "Yes?" "Mother says you are eccentric. Is that true?" "I'll speak to her about it." "Don't you know ?" "Do you understand the word?" "No." I lifted her out of the chair and stood her on her skates. "Tell your mother that I retaliate. I say she is beautiful." She skated awkwardly between the rows of cages from which mutants with brown fur and blue fur, too much and too little fur, enormously long and ridiculously short arms, stared at her with simian, canine or rodent faces. At the door to the outside, she turned perilously and waved. Again in the laboratory, I entered the metabolic accelerator and withdrew the intravenous needles from my first volplas. I carried their limp little forms out to a mattress in the lab, two girls and a boy. The accelerator had forced them almost to adulthood in less than a month. It would be several hours before they would begin to move, to learn to feed and play, perhaps to learn to fly. Meanwhile, it was clear that here was no war of dominant mutations. Modulating alleles had smoothed the freakish into a beautiful pattern. These were no monsters blasted by the dosage of radiation into crippled structures. They were lovely, perfect little creatures. My wife tried the door, too, but more subtly, as if casually touching the knob while calling. "Lunch, dear." "Be right there." She peeked too, as she had for fifteen years, but I blocked her view when I slipped out. "Come on, you old hermit. I have a buffet on the terrace." "Our daughter says I'm eccentric. Wonder how the devil she found out." "From me, of course." "But you love me just the same." "I adore you." She stretched on tiptoe and put her arms over my shoulders and kissed me. My wife did indeed have a delicious-looking buffet ready on the terrace. The maid was just setting down a warmer filled with hot hamburgers. I gave the maid a pinch and said, "Hello, baby." My wife looked at me with a puzzled smile. "What on Earth's got into you?" The maid beat it into the house. I flipped a hamburger and a slice of onion onto a plate and picked up the ketchup and said, "I've reached the dangerous age." "Oh, good heavens!" I dowsed ketchup over the hamburger, threw the onion on and closed it. I opened a bottle of beer and guzzled from it, blew out my breath and looked across the rolling hills and oak woods of our ranch to where the Pacific shimmered. I thought, "All this and three volplas, too." I wiped the back of my hand across my mouth and said aloud, "Yes, sir, the dangerous age. And, lady, I'm going to have fun." My wife sighed patiently. I walked over and put the arm that held the beer bottle around her shoulder and chucked her chin up with my other hand. The golden sun danced in her blue eyes. I watched that light in her beautiful eyes and said, "But you're the only one I'm dangerous about." I kissed her until I heard rollerskates coming across the terrace from one direction and a horse galloping toward the terrace from the other direction. "You have lovely lips," I whispered. "Thanks. Yours deserve the Good Housekeeping Seal of Approval, too." Our son reared the new palomino I had just bought him for his fourteenth birthday and yelled down, "Unhand that maiden, Burrhead, or I'll give you lead poisoning." I laughed and picked up my plate and sat down in a chair. My wife brought me a bowl of salad and I munched the hamburger and watched the boy unsaddle the horse and slap it away to the pasture. I thought, "By God, wouldn't he have a fit if he knew what I have back there in that lab! Wouldn't they all!" The boy carried the saddle up onto the terrace and dropped it. "Mom, I'd like a swim before I eat." He started undressing. "You look as though a little water might help," she agreed, sitting down next to me with her plate. The girl was yanking off her skates. "And I want one." "All right. But go in the house and put on your swim suit." "Oh, Mother . Why?" "Because, dear, I said so." The boy had already raced across the terrace and jack-knifed into the pool. The cool sound of the dive sent the girl scurrying for her suit. I looked at my wife. "What's the idea?" "She's going to be a young woman soon." "Is that any reason for wearing clothes? Look at him. He's a young man sooner than already." "Well, if you feel that way about it, they'll both have to start wearing clothes." I gulped the last of my hamburger and washed it down with the beer. "This place is going to hell," I complained. "The old man isn't allowed to pinch the maid and the kids can't go naked." I leaned toward her and smacked her cheek. "But the food and the old woman are still the best." "Say, what goes with you? You've been grinning like a happy ape ever since you came out of the lab." "I told you—" "Oh, not that again! You were dangerous at any age." I stood up and put my plate aside and bent over her. "Just the same, I'm going to have a new kind of fun." She reached up and grabbed my ear. She narrowed her eyes and put a mock grimness on her lips. "It's a joke," I assured her. "I'm going to play a tremendous joke on the whole world. I've only had the feeling once before in a small way, but I've always...." She twisted my ear and narrowed her eyes even more. "Like?" "Well, when my old man was pumping his first fortune out of some oil wells in Oklahoma, we lived down there. Outside this little town, I found a litter of flat stones that had young black-snakes under each slab. I filled a pail with them and took them into town and dumped them on the walk in front of the movie just as Theda Bara's matinee let out. The best part was that no one had seen me do it. They just couldn't understand how so many snakes got there. I learned how great it can be to stand around quietly and watch people encounter the surprise that you have prepared for them." She let go of my ear. "Is that the kind of fun you're going to have?" "Yep." She shook her head. "Did I say you are eccentric ?" I grinned. "Forgive me if I eat and run, dear. Something in the lab can't wait." The fact was that I had something more in the lab than I had bargained for. I had aimed only at a gliding mammal a little more efficient than the Dusky Glider of Australia, a marsupial. Even in the basically mutating colony, there had been a decidedly simian appearance in recent years, a long shift from the garbage-dump rats I had started with. But my first volplas were shockingly humanoid. They were also much faster than had been their predecessors in organizing their nervous activity after the slumbrous explosion of growth in the metabolic accelerator. When I returned to the lab, they were already moving about on the mattress and the male was trying to stand. He was a little the larger and stood twenty-eight inches high. Except for the face, chest and belly, they were covered with a soft, almost golden down. Where it was bare of this golden fur, the skin was pink. On their heads and across the shoulders of the male stood a shock of fur as soft as chinchilla. The faces were appealingly humanoid, except that the eyes were large and nocturnal. The cranium was in the same proportion to the body as it is in the human. When the male spread his arms, the span was forty-eight inches. I held his arms out and tried to tease the spars open. They were not new. The spars had been common to the basic colony for years and were the result of serial mutations effecting those greatly elongated fifth fingers that had first appeared in Nijinsky. No longer jointed like a finger, the spar turned backward sharply and ran alongside the wrist almost to the elbow. Powerful wrist muscles could snap it outward and forward. Suddenly, as I teased the male volpla, this happened. The spars added nine inches on each side to his span. As they swept out and forward, the lateral skin that had, till now, hung in resting folds was tightened in a golden plane that stretched from the tip of the spar to his waist and continued four inches wide down his legs to where it anchored at the little toe. This was by far the most impressive plane that had appeared till now. It was a true gliding plane, perhaps even a soaring one. I felt a thrill run along my back. By four o'clock that afternoon, I was feeding them solid food and, with the spars closed, they were holding little cups and drinking water from them in a most humanlike way. They were active, curious, playful and decidedly amorous. Their humanoid qualities were increasingly apparent. There was a lumbar curvature and buttocks. The shoulder girdle and pectoral muscles were heavy and out of proportion, of course, yet the females had only one pair of breasts. The chin and jaw were humanlike instead of simian and the dental equipment was appropriate to this structure. What this portended was brought home to me with a shock. I was kneeling on the mattress, cuffing and roughing the male as one might a puppy dog, when one of the females playfully climbed up my back. I reached around and brought her over my shoulder and sat her down. I stroked the soft fur on her head and said, "Hello, pretty one. Hello." The male watched me, grinning. He said, "'Ello, 'ello." As I walked into the kitchen, giddy with this enormous joke, my wife said, "Guy and Em are flying up for dinner. That rocket of Guy's they launched in the desert yesterday was a success. It pulled Guy up to Cloud Nine and he wants to celebrate." I danced a little jig the way old Nijinsky might do it. "Oh, great! Oh, wonderful! Good old Guy! Everybody's a success. It's great. It's wonderful. Success on success!" I danced into the kitchen table and tipped over a basket of green corn. The maid promptly left the kitchen for some other place. My wife just stared at me. "Have you been drinking the lab alcohol?" "I've been drinking the nectar of the gods. My Hera, you're properly married to Zeus. I've my own little Greeks descended from Icarus." She pretended a hopeless sag of her pretty shoulders. "Wouldn't you just settle for a worldly martini?" "I will, yes. But first a divine kiss." I sipped at my martini and lounged in a terrace chair watching the golden evening slant across the beautiful hills of our ranch. I dreamed. I would invent a euphonious set of words to match the Basic English vocabulary and teach it to them as their language. They would have their own crafts and live in small tree houses. I would teach them legends: that they had come from the stars, that they had subsequently watched the first red men and then the first white men enter these hills. When they were able to take care of themselves, I would turn them loose. There would be volpla colonies all up and down the Coast before anyone suspected. One day, somebody would see a volpla. The newspapers would laugh. Then someone authoritative would find a colony and observe them. He would conclude, "I am convinced that they have a language and speak it intelligently." The government would issue denials. Reporters would "expose the truth" and ask, "Where have these aliens come from?" The government would reluctantly admit the facts. Linguists would observe at close quarters and learn the simple volpla language. Then would come the legends. Volpla wisdom would become a cult—and of all forms of comedy, cults, I think, are the funniest. "Darling, are you listening to me?" my wife asked with impatient patience. "What? Sure. Certainly." "You didn't hear a word. You just sit there and grin into space." She got up and poured me another martini. "Here, maybe this will sober you up." I pointed. "That's probably Guy and Em." A 'copter sidled over the ridge, then came just above the oak woods toward us. Guy set it gently on the landing square and we walked down to meet them. I helped Em out and hugged her. Guy jumped out, asking, "Do you have your TV set on?" "No," I answered. "Should I?" "It's almost time for the broadcast. I was afraid we would miss it." "What broadcast?" "From the rocket." "Rocket?" "For heaven's sake, darling," my wife complained, "I told you about Guy's rocket being a success. The papers are full of it. So are the broadcasts." As we stepped up on the terrace, she turned to Guy and Em. "He's out of contact today. Thinks he's Zeus." I asked our son to wheel a TV set out onto the terrace while I made martinis for our friends. Then we sat down and drank the cocktails and the kids had fruit juice and we watched the broadcast Guy had tuned in. Some joker from Cal Tech was explaining diagrams of a multi-stage rocket. After a bit, I got up and said, "I have something out in the lab I want to check on." "Hey, wait a minute," Guy objected. "They're about to show the shots of the launching." My wife gave me a look; you know the kind. I sat down. Then I got up and poured myself another martini and freshened Em's up, too. I sat down again. The scene had changed to a desert launching site. There was old Guy himself explaining that when he pressed the button before him, the hatch on the third stage of the great rocket in the background would close and, five minutes later, the ship would fire itself. Guy, on the screen, pushed the button, and I heard Guy, beside me, give a sort of little sigh. We watched the hatch slowly close. "You look real good," I said. "A regular Space Ranger. What are you shooting at?" "Darling, will you please—be— quiet ?" "Yeah, Dad. Can it, will you? You're always gagging around." On the screen, Guy's big dead-earnest face was explaining more about the project and suddenly I realized that this was an instrument-bearing rocket they hoped to land on the Moon. It would broadcast from there. Well, now—say, that would be something! I began to feel a little ashamed of the way I had been acting and I reached out and slapped old Guy on the shoulder. For just a moment, I thought of telling him about my volplas. But only for a moment. A ball of flame appeared at the base of the rocket. Miraculously, the massive tower lifted, seemed for a moment merely to stand there on a flaming pillar, then was gone. The screen returned to a studio, where an announcer explained that the film just shown had been taken day before yesterday. Since then, the rocket's third stage was known to have landed successfully at the south shore of Mare Serenitatis. He indicated the location on a large lunar map behind him. "From this position, the telemeter known as Rocket Charlie will be broadcasting scientific data for several months. But now, ladies and gentlemen, we will clear the air for Rocket Charlie's only general broadcast. Stand by for Rocket Charlie." A chronometer appeared on the screen and, for several seconds, there was silence. I heard my boy whisper, "Uncle Guy, this is the biggest!" My wife said, "Em, I think I'll just faint." Suddenly there was a lunar landscape on the screen, looking just as it's always been pictured. A mechanical voice cut in. "This is Rocket Charlie saying, 'Hello, Earth,' from my position in Mare Serenitatis. First I will pan the Menelaus Mountains for fifteen seconds. Then I will focus my camera on Earth for five seconds." The camera began to move and the mountains marched by, stark and awesomely wild. Toward the end of the movement, the shadow of the upright third stage appeared in the foreground. Abruptly the camera made a giddy swing, focused a moment, and we were looking at Earth. At that time, there was no Moon over California. It was Africa and Europe we were looking at. "This is Rocket Charlie saying, 'Good-by, Earth.'" Well, when that screen went dead, there was pandemonium around our terrace. Big old Guy was so happy, he was wiping tears from his eyes. The women were kissing him and hugging him. Everybody was yelling at once. I used the metabolic accelerator to cut the volplas' gestation down to one week. Then I used it to bring the infants to maturity in one month. I had luck right off. Quite by accident, the majority of the early infants were females, which sped things up considerably. By the next spring, I had a colony of over a hundred volplas and I shut down the accelerator. From now on, they could have babies in their own way. I had devised the language for them, using Basic English as my model, and during the months while every female was busy in the metabolic accelerator, I taught the language to the males. They spoke it softly in high voices and the eight hundred words didn't seem to tax their little skulls a bit. My wife and the kids went down to Santa Barbara for a week and I took the opportunity to slip the oldest of the males and his two females out of the lab. I put them in the jeep beside me and drove to a secluded little valley about a mile back in the ranch. They were all three wide-eyed at the world and jabbered continuously. They kept me busy relating their words for "tree," "rock," "sky" to the objects. They had a little trouble with "sky." Until I had them out in the open country, it had been impossible to appreciate fully what lovely little creatures they were. They blended perfectly with the California landscape. Occasionally, when they raised their arms, the spars would open and spread those glorious planes. Almost two hours went by before the male made it into the air. His playful curiosity about the world had been abandoned momentarily and he was chasing one of the girls. As usual, she was anxious to be caught and stopped abruptly at the bottom of a little knoll. He probably meant to dive for her. But when he spread his arms, the spars snapped out and those golden planes sheared into the air. He sailed over her in a stunning sweep. Then he rose up and up until he hung in the breeze for a long moment, thirty feet above the ground. He turned a plaintive face back to me, dipped worriedly and skimmed straight for a thorn bush. He banked instinctively, whirled toward us in a golden flash and crashed with a bounce to the grass. The two girls reached him before I did and stroked and fussed over him so that I could not get near. Suddenly he laughed with a shrill little whoop. After that, it was a carnival. They learned quickly and brilliantly. They were not fliers; they were gliders and soarers. Before long, they took agilely to the trees and launched themselves in beautiful glides for hundreds of feet, banking, turning and spiraling to a gentle halt. I laughed out loud with anticipation. Wait till the first pair of these was brought before a sheriff! Wait till reporters from the Chronicle motored out into the hills to witness this! Of course, the volplas didn't want to return to the lab. There was a tiny stream through there and at one point it formed a sizable pool. They got into this and splashed their long arms about and they scrubbed each other. Then they got out and lay on their backs with the planes stretched to dry. I watched them affectionately and wondered about the advisability of leaving them out here. Well, it had to be done sometime. Nothing I could tell them about surviving would help them as much as a little actual surviving. I called the male over to me. He came and squatted, conference fashion, the elbows resting on the ground, the wrists crossed at his chest. He spoke first. "Before the red men came, did we live here?" "You lived in places like this all along these mountains. Now there are very few of you left. Since you have been staying at my place, you naturally have forgotten the ways of living outdoors." "We can learn again. We want to stay here." His little face was so solemn and thoughtful that I reached out and stroked the fur on his head reassuringly. We both heard the whir of wings overhead. Two mourning doves flew across the stream and landed in an oak on the opposite hillside. I pointed. "There's your food, if you can kill it." He looked at me. "How?" "I don't think you can get at them in the tree. You'll have to soar up above and catch one of them on the wing when they fly away. Think you can get up that high?" He looked around slowly at the breeze playing in the branches and dancing along the hillside grass. It was as if he had been flying a thousand years and was bringing antique wisdom to bear. "I can get up there. I can stay for a while. How long will they be in the tree?" "Chances are they won't stay long. Keep your eye on the tree in case they leave while you are climbing." He ran to a nearby oak and clambered aloft. Presently he launched himself, streaked down-valley a way and caught a warm updraft on a hillside. In no time, he was up about two hundred feet. He began criss-crossing the ridge, working his way back to us. The two girls were watching him intently. They came over to me wonderingly, stopping now and then to watch him. When they were standing beside me, they said nothing. They shaded their eyes with tiny hands and watched him as he passed directly above us at about two hundred and fifty feet. One of the girls, with her eyes fast on his soaring planes, reached out and grasped my sleeve tightly. He flashed high above the stream and hung behind the crest of the hill where the doves rested. I heard their mourning from the oak tree. It occurred to me they would not leave that safety while the hawklike silhouette of the volpla marred the sky so near. I took the girl's hand from my sleeve and spoke to her, pointing as I did so. "He is going to catch a bird. The bird is in that tree. You can make the bird fly so that he can catch it. Look here." I got up and found a stick. "Can you do this?" I threw the stick up into a tree near us. Then I found her a stick. She threw it better than I had expected. "Good, pretty one. Now run across the stream and up to that tree and throw a stick into it." She climbed skillfully into the tree beside us and launched herself across the stream. She swooped up the opposite hillside and landed neatly in the tree where the doves rested. The birds came out of the tree, climbing hard with their graceful strokes. I looked back, as did the girl remaining beside me. The soaring volpla half closed his planes and started dropping. He became a golden flash across the sky. The doves abruptly gave up their hard climbing and fell away with swiftly beating wings. I saw one of the male volpla's planes open a little. He veered giddily in the new direction and again dropped like a molten arrow. The doves separated and began to zigzag down the valley. The volpla did something I would not have anticipated—he opened his planes and shot lower than the bird he was after, then swept up and intercepted the bird's crossward flight. I saw the planes close momentarily. Then they opened again and the bird plummeted to a hillside. The volpla landed gently atop the hill and stood looking back at us. The volpla beside me danced up and down shrieking in a language all her own. The girl who had raised the birds from the tree volplaned back to us, yammering like a bluejay. It was a hero's welcome. He had to walk back, of course—he had no way to carry such a load in flight. The girls glided out to meet him. Their lavish affection held him up for a time, but eventually he strutted in like every human hunter. They were raptly curious about the bird. They poked at it, marveled at its feathers and danced about it in an embryonic rite of the hunt. But presently the male turned to me. "We eat this?" I laughed and took his tiny, four-fingered hand. In a sandy spot beneath a great tree that overhung the creek, I built a small fire for them. This was another marvel, but first I wanted to teach them how to clean the bird. I showed them how to spit it and turn it over their fire. Later, I shared a small piece of the meat in their feast. They were gleeful and greasily amorous during the meal. When I had to leave, it was dark. I warned them to stand watches, keep the fire burning low and take to the tree above if anything approached. The male walked a little away with me when I left the fire. I said again, "Promise me you won't leave here until we've made you ready for it." "We like it here. We will stay. Tomorrow you bring more of us?" "Yes. I will bring many more of you, if you promise to keep them all here in this woods until they're ready to leave." "I promise." He looked up at the night sky and, in the firelight, I saw his wonder. "You say we came from there?" "The old ones of your kind told me so. Didn't they tell you?" "I can't remember any old ones. You tell me." "The old ones told me you came long before the red men in a ship from the stars." Standing there in the dark, I had to grin, visioning the Sunday supplements that would be written in about a year, maybe even less. He looked into the sky for a long time. "Those little lights are the stars?" "That's right." "Which star?" I glanced about and presently pointed over a tree. "From Venus." Then I realized I had blundered by passing him an English name. "In your language, Pohtah." He looked at the planet a long time and murmured, "Venus. Pohtah." That next week, I transported all of the volplas out to the oak woods. There were a hundred and seven men, women and children. With no design on my part, they tended to segregate into groups consisting of four to eight couples together with the current children of the women. Within these groups, the adults were promiscuous, but apparently not outside the group. The group thus had the appearance of a super-family and the males indulged and cared for all the children without reference to actual parenthood. By the end of the week, these super-families were scattered over about four square miles of the ranch. They had found a new delicacy, sparrows, and hunted them easily as they roosted at night. I had taught the volplas to use the fire drill and they were already utilizing the local grasses, vines and brush to build marvelously contrived tree houses in which the young, and sometimes the adults, slept through midday and midnight. The afternoon my family returned home, I had a crew of workmen out tearing down the animal rooms and lab building. The caretakers had anesthetized all the experimental mutants, and the metabolic accelerator and other lab equipment was being dismantled. I wanted nothing around that might connect the sudden appearance of the volplas with my property. It was already apparent that it would take the volplas only a few more weeks to learn their means of survival and develop an embryonic culture of their own. Then they could leave my ranch and the fun would be on. My wife got out of the car and looked around at the workmen hurrying about the disemboweled buildings and she said, "What on Earth is going on here?" "I've finished my work and we no longer need the buildings. I'm going to write a paper about my results." My wife looked at me appraisingly and shook her head. "I thought you meant it. But you really ought to. It would be your first." My son asked, "What happened to the animals?" "Turned them over to the university for further study," I lied. "Well," he said to her, "you can't say our pop isn't a man of decision." Twenty-four hours later, there wasn't a sign of animal experimentation on the ranch. Except, of course, that the woods were full of volplas. At night, I could hear them faintly when I sat out on the terrace. As they passed through the dark overhead, they chattered and laughed and sometimes moaned in winged love. One night a flight of them soared slowly across the face of the full Moon, but I was the only one who noticed.
|
C. Because people generally only notice what they look for and would dismiss the phenomenon as something else.
|
What is the meaning of the title?
A. When Mr. and Mrs. Graham are apart, a major imbalance persists
B. McGill is manipulating Alec as part of a social experiment
C. Alec is at the center of all the coincidental behavior
D. Alec possesses supernatural abilities that will eventually destroy him
|
I am a Nucleus By STEPHEN BARR Illustrated by GAUGHAN [Transcriber's Note: This etext was produced from Galaxy Science Fiction February 1957. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] No doubt whatever about it, I had the Indian sign on me ... my comfortably untidy world had suddenly turned into a monstrosity of order! When I got home from the office, I was not so much tired as beaten down, but the effect is similar. I let myself into the apartment, which had an absentee-wife look, and took a cold shower. The present downtown temperature, according to the radio, was eighty-seven degrees, but according to my Greenwich Village thermometer, it was ninety-six. I got dressed and went into the living room, and wished ardently that my wife Molly were here to tell me why the whole place looked so woebegone. What do they do, I asked myself, that I have left undone? I've vacuumed the carpet, I've dusted and I've straightened the cushions.... Ah! The ashtrays. I emptied them, washed them and put them back, but still the place looked wife-deserted. It had been a bad day; I had forgotten to wind the alarm clock, so I'd had to hurry to make a story conference at one of the TV studios I write for. I didn't notice the impending rain storm and had no umbrella when I reached the sidewalk, to find myself confronted with an almost tropical downpour. I would have turned back, but a taxi came up and a woman got out, so I dashed through the rain and got in. "Madison and Fifty-fourth," I said. "Right," said the driver, and I heard the starter grind, and then go on grinding. After some futile efforts, he turned to me. "Sorry, Mac. You'll have to find another cab. Good hunting." If possible, it was raining still harder. I opened my newspaper over my hat and ran for the subway: three blocks. Whizzing traffic held me up at each crossing and I was soaked when I reached the platform, just in time to miss the local. After an abnormal delay, I got one which exactly missed the express at Fourteenth Street. The same thing happened at both ends of the crosstown shuttle, but I found the rain had stopped when I got out at Fifty-first and Lexington. As I walked across to Madison Avenue, I passed a big excavation where they were getting ready to put up a new office building. There was the usual crowd of buffs watching the digging machines and, in particular, a man with a pneumatic drill who was breaking up some hard-packed clay. While I looked, a big lump of it fell away, and for an instant I was able to see something that looked like a chunk of dirty glass, the size of an old-fashioned hatbox. It glittered brilliantly in the sunlight, and then his chattering drill hit it. There was a faint bang and the thing disintegrated. It knocked him on his back, but he got right up and I realized he was not hurt. At the moment of the explosion—if so feeble a thing can be called one—I felt something sting my face and, on touching it, found blood on my hand. I mopped at it with my handkerchief but, though slight, the bleeding would not stop, so I went into a drugstore and bought some pink adhesive which I put on the tiny cut. When I got to the studio, I found that I had missed the story conference. During the day, by actual count, I heard the phrase "I'm just spitballing" eight times, and another Madison Avenue favorite, "The whole ball of wax," twelve times. However, my story had been accepted without change because nobody had noticed my absence from the conference room. There you have what is known as the Advertising World, the Advertising game or the advertising racket, depending upon which rung of the ladder you have achieved. The subway gave a repeat performance going home, and as I got to the apartment house we live in, the cop on the afternoon beat was standing there talking to the doorman. He said, "Hello, Mr. Graham. I guess you must have just have missed it at your office building." I looked blank and he explained, "We just heard it a little while ago: all six elevators in your building jammed at the same time. Sounds crazy. I guess you just missed it." Anything can happen in advertising, I thought. "That's right, Danny, I just missed it," I said, and went on in. Psychiatry tells us that some people are accident-prone; I, on the other hand, seemed recently to be coincidence-prone, fluke-happy, and except for the alarm clock, I'd had no control over what had been going on. I went into our little kitchen to make a drink and reread the directions Molly had left, telling me how to get along by myself until she got back from her mother's in Oyster Bay, a matter of ten days. How to make coffee, how to open a can, whom to call if I took sick and such. My wife used to be a trained nurse and she is quite convinced that I cannot take a breath without her. She is right, but not for the reasons she supposes. I opened the refrigerator to get some ice and saw another notice: "When you take out the Milk or Butter, Put it Right Back. And Close the Door, too." Intimidated, I took my drink into the living room and sat down in front of the typewriter. As I stared at the novel that was to liberate me from Madison Avenue, I noticed a mistake and picked up a pencil. When I put it down, it rolled off the desk, and with my eyes on the manuscript, I groped under the chair for it. Then I looked down. The pencil was standing on its end. There, I thought to myself, is that one chance in a million we hear about, and picked up the pencil. I turned back to my novel and drank some of the highball in hopes of inspiration and surcease from the muggy heat, but nothing came. I went back and read the whole chapter to try to get a forward momentum, but came to a dead stop at the last sentence. Damn the heat, damn the pencil, damn Madison Avenue and advertising. My drink was gone and I went back to the kitchen and read Molly's notes again to see if they would be like a letter from her. I noticed one that I had missed, pinned to the door of the dumbwaiter: "Garbage picked up at 6:30 AM so the idea is to Put it Here the Night Before. I love you." What can you do when the girl loves you? I made another drink and went and stared out of the living room window at the roof opposite. The Sun was out again and a man with a stick was exercising his flock of pigeons. They wheeled in a circle, hoping to be allowed to perch, but were not allowed to. Pigeons fly as a rule in formation and turn simultaneously, so that their wings all catch the sunlight at the same time. I was thinking about this decorative fact when I saw that as they were making a turn, they seemed to bunch up together. By some curious chance, they all wanted the same place in the sky to turn in, and several collided and fell. The man was as surprised as I and went to one of the dazed birds and picked it up. He stood there shaking his head from side to side, stroking its feathers. My speculations about this peculiar aerial traffic accident were interrupted by loud voices in the hallway. Since our building is usually very well behaved, I was astonished to hear what sounded like an incipient free-for-all, and among the angry voices I recognized that of my neighbor, Nat, a very quiet guy who works on a newspaper and has never, to my knowledge, given wild parties, particularly in the late afternoon. "You can't say a thing like that to me!" I heard him shout. "I tell you I got that deck this afternoon and they weren't opened till we started to play!" Several other loud voices started at the same time. "Nobody gets five straight-flushes in a row!" "Yeah, and only when you were dealer!" The tone of the argument was beginning to get ugly, and I opened the door to offer Nat help if he needed it. There were four men confronting him, evidently torn between the desire to make an angry exit and the impulse to stay and beat him up. His face was furiously red and he looked stunned. "Here!" he said, holding out a deck of cards, "For Pete's sake, look at 'em yourselves if you think they're marked!" The nearest man struck them up from his hand. "Okay, Houdini! So they're not marked! All I know is five straight...." His voice trailed away. He and the others stared at the scattered cards on the floor. About half were face down, as might be expected, and the rest face up—all red. Someone must have rung, because at that moment the elevator arrived and the four men, with half frightened, incredulous looks, and in silence, got in and were taken down. My friend stood looking at the neatly arranged cards. "Judas!" he said, and started to pick them up. "Will you look at that! My God, what a session...." I helped him and said to come in for a drink and tell me all about it, but I had an idea what I would hear. After a while, he calmed down, but he still seemed dazed. "Never seen anything to equal it," he said. "Wouldn't have believed it. Those guys didn't believe it. Every round normal, nothing unusual about the hands—three of a kind, a low straight, that sort of thing and one guy got queens over tens, until it gets to be my deal. Brother! Straight flush to the king—every time! And each time, somebody else has four aces...." He started to sweat again, so I got up to fix him another drink. There was one quart of club soda left, but when I tried to open it, the top broke and glass chips got into the bottle. "I'll have to go down for more soda," I said. "I'll come, too. I need air." At the delicatessen on the corner, the man gave me three bottles in what must have been a wet bag, because as he handed them to me over the top of the cold-meat display, the bottom gave and they fell onto the tile floor. None of them broke, although the fall must have been from at least five feet. Nat was too wound up in his thoughts to notice and I was getting used to miracles. We left the proprietor with his mouth open and met Danny, the cop, looking in at the door, also with his mouth open. On the sidewalk, a man walking in front of Nat stooped suddenly to tie his shoe and Nat, to avoid bumping him, stepped off the curb and a taxi swerved to avoid Nat. The street was still wet and the taxi skidded, its rear end lightly flipping the front of one of those small foreign cars, which was going rather fast. It turned sideways and, without any side-slip, went right up the stoop of a brownstone opposite, coming to rest with its nose inside the front door, which a man opened at that moment. The sight of this threw another driver into a skid, and when he and the taxi had stopped sliding around, they were face to face, arranged crosswise to the street. This gave them exactly no room to move either forward or backward, for the car had its back to a hydrant and the taxi to a lamp. Although rather narrow, this is a two-way street, and in no time at all, traffic was stacked up from both directions as far as the avenues. Everyone was honking his horn. Danny was furious—more so when he tried to put through a call to his station house from the box opposite. It was out of order. Upstairs, the wind was blowing into the apartment and I closed the windows, mainly to shut out the tumult and the shouting. Nat had brightened up considerably. "I'll stay for one more drink and then I'm due at the office," he said. "You know, I think this would make an item for the paper." He grinned and nodded toward the pandemonium. When he was gone, I noticed it was getting dark and turned on the desk lamp. Then I saw the curtains. They were all tied in knots, except one. That was tied in three knots. All right , I told myself, it was the wind. But I felt the time had come for me to get expert advice, so I went to the phone to call McGill. McGill is an assistant professor of mathematics at a university uptown and lives near us. He is highly imaginative, but we believe he knows everything. When I picked up the receiver, the line sounded dead and I thought, more trouble. Then I heard a man cough and I said hello. McGill's voice said, "Alec? You must have picked up the receiver just as we were connected. That's a damn funny coincidence." "Not in the least," I said. "Come on over here. I've got something for you to work on." "Well, as a matter of fact, I was calling up to ask you and Molly—" "Molly's away for the week. Can you get over here quick? It's urgent." "At once," he said, and hung up. While I waited, I thought I might try getting down a few paragraphs of my novel—perhaps something would come now. It did, but as I came to a point where I was about to put down the word "agurgling," I decided it was too reminiscent of Gilbert and Sullivan, and stopped at the letter "R." Then I saw that I had unaccountably hit all four keys one step to the side of the correct ones, and tore out the page, with my face red. This was absolutely not my day. "Well," McGill said, "nothing you've told me is impossible or supernatural. Just very, very improbable. In fact, the odds against that poker game alone would lead me to suspect Nat, well as I know him. It's all those other things...." He got up and walked over to the window and looked at the hot twilight while I waited. Then he turned around; he had a look of concern. "Alec, you're a reasonable guy, so I don't think you'll take offense at what I'm going to say. What you have told me is so impossibly unlikely, and the odds against it so astronomical, that I must take the view that you're either stringing me or you're subject to a delusion." I started to get up and expostulate, but he motioned me back. "I know, but don't you see that that is far more likely than...." He stopped and shook his head. Then he brightened. "I have an idea. Maybe we can have a demonstration." He thought for a tense minute and snapped his fingers. "Have you any change on you?" "Why, yes," I said. "Quite a bit." I reached into my pocket. There must have been nearly two dollars in silver and pennies. "Do you think they'll each have the same date, perhaps?" "Did you accumulate all that change today?" "No. During the week." He shook his head. "In that case, no. Discounting the fact that you could have prearranged it, if my dim provisional theory is right, that would be actually impossible. It would involve time-reversal. I'll tell you about it later. No, just throw down the change. Let's see if they all come up heads." I moved away from the carpet and tossed the handful of coins onto the floor. They clattered and bounced—and bounced together—and stacked themselves into a neat pile. I looked at McGill. His eyes were narrowed. Without a word, he took a handful of coins from his own pocket and threw them. These coins didn't stack. They just fell into an exactly straight line, the adjacent ones touching. "Well," I said, "what more do you want?" "Great Scott," he said, and sat down. "I suppose you know that there are two great apparently opposite principles governing the Universe—random and design. The sands on the beach are an example of random distribution and life is an example of design. The motions of the particles of a gas are what we call random, but there are so many of them, we treat them statistically and derive the Second Law of Thermodynamics—quite reliable. It isn't theoretically hard-and-fast; it's just a matter of extreme probability. Now life, on the other hand, seems not to depend on probability at all; actually, it goes against it. Or you might say it is certainly not an accidental manifestation." "Do you mean," I asked in some confusion, "that some form of life is controlling the coins and—the other things?" He shook his head. "No. All I mean is that improbable things usually have improbable explanations. When I see a natural law being broken, I don't say to myself, 'Here's a miracle.' I revise my version of the book of rules. Something—I don't know what—is going on, and it seems to involve probability, and it seems to center around you. Were you still in that building when the elevators stuck? Or near it?" "I guess I must have been. It happened just after I left." "Hm. You're the center, all right. But why?" "Center of what?" I asked. "I feel as though I were the center of an electrical storm. Something has it in for me!" McGill grinned. "Don't be superstitious. And especially don't be anthropomorphic." "Well, if it's the opposite of random, it's got to be a form of life." "On what basis? All we know for certain is that random motions are being rearranged. A crystal, for example, is not life, but it's a non-random arrangement of particles.... I wonder." He had a faraway, frowning look. I was beginning to feel hungry and the drinks had worn off. "Let's go out and eat," I said, "There's not a damn thing in the kitchen and I'm not allowed to cook. Only eggs and coffee." We put on our hats and went down to the street. From either end, we could hear wrecking trucks towing away the stalled cars. There were, by this time, a number of harassed cops directing the maneuver and we heard one of them say to Danny, "I don't know what the hell's going on around here. Every goddam car's got something the matter with it. They can't none of them back out for one reason or another. Never seen anything like it." Near us, two pedestrians were doing a curious little two-step as they tried to pass one another; as soon as one of them moved aside to let the other pass, the other would move to the same side. They both had embarrassed grins on their faces, but before long their grins were replaced by looks of suspicion and then determination. "All right, smart guy!" they shouted in unison, and barged ahead, only to collide. They backed off and threw simultaneous punches which met in mid-air. Then began one of the most remarkable bouts ever witnessed—a fight in which fist hit fist but never anything else, until both champions backed away undefeated, muttering identical excuses and threats. Danny appeared at that moment. His face was dripping. "You all right, Mr. Graham?" he asked. "I don't know what's going on around here, but ever since I came on this afternoon, things are going crazy. Bartley!" he shouted—he could succeed as a hog-caller. "Bring those dames over here!" Three women in a confused wrangle, with their half-open umbrellas intertwined, were brought across the street, which meant climbing over fenders. Bartley, a fine young patrolman, seemed self-conscious; the ladies seemed not to be. "All right, now, Mrs. Mac-Philip!" one of them said. "Leave go of my umbrella and we'll say no more about it!" "And so now it's Missus Mac-Philip, is it?" said her adversary. The third, a younger one with her back turned to us, her umbrella also caught in the tangle, pulled at it in a tentative way, at which the other two glared at her. She turned her head away and tried to let go, but the handle was caught in her glove. She looked up and I saw it was Molly. My nurse-wife. "Oh, Alec!" she said, and managed to detach herself. "Are you all right?" Was I all right! "Molly! What are you doing here?" "I was so worried, and when I saw all this, I didn't know what to think." She pointed to the stalled cars. "Are you really all right?" "Of course I'm all right. But why...." "The Oyster Bay operator said someone kept dialing and dialing Mother's number and there wasn't anyone on the line, so then she had it traced and it came from our phone here. I kept calling up, but I only got a busy signal. Oh, dear, are you sure you're all right?" I put my arm around her and glanced at McGill. He had an inward look. Then I caught Danny's eye. It had a thoughtful, almost suspicious cast to it. "Trouble does seem to follow you, Mr. Graham," was all he said. When we got upstairs, I turned to McGill. "Explain to Molly," I said. "And incidentally to me. I'm not properly briefed yet." He did so, and when he got to the summing up, I had the feeling she was a jump ahead of him. "In other words, you think it's something organic?" "Well," McGill said, "I'm trying to think of anything else it might be. I'm not doing so well," he confessed. "But so far as I can see," Molly answered, "it's mere probability, and without any over-all pattern." "Not quite. It has a center. Alec is the center." Molly looked at me with a curious expression for a moment. "Do you feel all right, darling?" she asked me. I nodded brightly. "You'll think this silly of me," she went on to McGill, "but why isn't it something like an overactive poltergeist?" "Pure concept," he said. "No genuine evidence." "Magnetism?" "Absolutely not. For one thing, most of the objects affected weren't magnetic—and don't forget magnetism is a force, not a form of energy, and a great deal of energy has been involved. I admit the energy has mainly been supplied by the things themselves, but in a magnetic field, all you'd get would be stored kinetic energy, such as when a piece of iron moves to a magnet or a line of force. Then it would just stay there, like a rundown clock weight. These things do a lot more than that—they go on moving." "Why did you mention a crystal before? Why not a life-form?" "Only an analogy," said McGill. "A crystal resembles life in that it has a definite shape and exhibits growth, but that's all. I'll agree this—thing—has no discernible shape and motion is involved, but plants don't move and amebas have no shape. Then a crystal feeds, but it does not convert what it feeds on; it merely rearranges it into a non-random pattern. In this case, it's rearranging random motions and it has a nucleus and it seems to be growing—at least in what you might call improbability." Molly frowned. "Then what is it? What's it made of?" "I should say it was made of the motions. There's a similar idea about the atom. Another thing that's like a crystal is that it appears to be forming around a nucleus not of its own material—the way a speck of sand thrown into a supersaturated solution becomes the nucleus of crystallization." "Sounds like the pearl in an oyster," Molly said, and gave me an impertinent look. "Why," I asked McGill, "did you say the coins couldn't have the same date? I mean apart from the off chance I got them that way." "Because I don't think this thing got going before today and everything that's happened can all be described as improbable motions here and now. The dates were already there, and to change them would require retroactive action, reversing time. That's out, in my book. That telephone now—" The doorbell rang. We were not surprised to find it was the telephone repairman. He took the set apart and clucked like a hen. "I guess you dropped it on the floor, mister," he said with strong disapproval. "Certainly not," I said. "Is it broken?" "Not exactly broken , but—" He shook his head and took it apart some more. McGill went over and they discussed the problem in undertones. Finally the man left and Molly called her mother to reassure her. McGill tried to explain to me what had happened with the phone. "You must have joggled something loose. And then you replaced the receiver in such a way that the contact wasn't quite open." "But for Pete's sake, Molly says the calls were going on for a long time! I phoned you only a short time ago and it must have taken her nearly two hours to get here from Oyster Bay." "Then you must have done it twice and the vibrations in the floor—something like that—just happened to cause the right induction impulses. Yes, I know how you feel," he said, seeing my expression. "It's beginning to bear down." Molly was through telephoning and suggested going out for dinner. I was so pleased to see her that I'd forgotten all about being hungry. "I'm in no mood to cook," she said. "Let's get away from all this." McGill raised an eyebrow. "If all this, as you call it, will let us." In the lobby, we ran into Nat, looking smug in a journalistic way. "I've been put on the story—who could be better?—I live here. So far, I don't quite get what's been happening. I've been talking to Danny, but he didn't say much. I got the feeling he thinks you're involved in some mystical, Hibernian way. Hello, McGill, what's with you?" "He's got a theory," said Molly. "Come and eat with us and he'll tell you all about it." Since we decided on an air-conditioned restaurant nearby on Sixth Avenue, we walked. The jam of cars didn't seem to be any less than before and we saw Danny again. He was talking to a police lieutenant, and when he caught sight of us, he said something that made the lieutenant look at us with interest. Particularly at me. "If you want your umbrella, Mrs. Graham," Danny said, "it's at the station house. What there's left of it, that is." Molly thanked him and there was a short pause, during which I felt the speculative regard of the lieutenant. I pulled out a packet of cigarettes, which I had opened, as always, by tearing off the top. I happened to have it upside down and all the cigarettes fell out. Before I could move my foot to obliterate what they had spelled out on the sidewalk, the two cops saw it. The lieutenant gave me a hard look, but said nothing. I quickly kicked the insulting cigarettes into the gutter. When we got to the restaurant, it was crowded but cool—although it didn't stay cool for long. We sat down at a side table near the door and ordered Tom Collinses as we looked at the menu. Sitting at the next table were a fat lady, wearing a very long, brilliant green evening gown, and a dried-up sour-looking man in a tux. When the waiter returned, they preempted him and began ordering dinner fussily: cold cuts for the man, and vichyssoise, lobster salad and strawberry parfait for the fat lady. I tasted my drink. It was most peculiar; salt seemed to have been used instead of sugar. I mentioned this and my companions tried theirs, and made faces. The waiter was concerned and apologetic, and took the drinks back to the bar across the room. The bartender looked over at us and tasted one of the drinks. Then he dumped them in his sink with a puzzled expression and made a new batch. After shaking this up, he set out a row of glasses, put ice in them and began to pour. That is to say he tilted the shaker over the first one, but nothing came out. He bumped it against the side of the bar and tried again. Still nothing. Then he took off the top and pried into it with his pick, his face pink with exasperation. I had the impression that the shaker had frozen solid. Well, ice is a crystal, I thought to myself. The other bartender gave him a fresh shaker, but the same thing happened, and I saw no more because the customers sitting at the bar crowded around in front of him, offering advice. Our waiter came back, baffled, saying he'd have the drinks in a moment, and went to the kitchen. When he returned, he had madame's vichyssoise and some rolls, which he put down, and then went to the bar, where the audience had grown larger. Molly lit a cigarette and said, "I suppose this is all part of it, Alec. Incidentally, it seems to be getting warmer in here." It was, and I had the feeling the place was quieter—a background noise had stopped. It dawned on me that I no longer heard the faint hum of the air-conditioner over the door, and as I started to say so, I made a gesture toward it. My hand collided with Molly's when she tapped her cigarette over the ashtray, and the cigarette landed in the neighboring vichyssoise. "Hey! What's the idea?" snarled the sour-looking man. "I'm terribly sorry," I said. "It was an accident. I—" "Throwing cigarettes at people!" the fat lady said. "I really didn't mean to," I began again, getting up. There must have been a hole in the edge of their tablecloth which one of my cuff buttons caught in, because as I stepped out from between the closely set tables, I pulled everything—tablecloth, silver, water glasses, ashtrays and the vichyssoise-à-la-nicotine—onto the floor. The fat lady surged from the banquette and slapped me meatily. The man licked his thumb and danced as boxers are popularly supposed to do. The owner of the place, a man with thick black eyebrows, hustled toward us with a determined manner. I tried to explain what had happened, but I was outshouted, and the owner frowned darkly.
|
C. Alec is at the center of all the coincidental behavior
|
what word embedding techniques did they experiment with?
|
### Introduction
Music is part of the day-to-day life of a huge number of people, and many works try to understand the best way to classify, recommend, and identify similarities between songs. Among the tasks that involve music classification, genre classification has been studied widely in recent years BIBREF0 since musical genres are the main top-level descriptors used by music dealers and librarians to organize their music collections BIBREF1. Automatic music genre classification based only on the lyrics is considered a challenging task in the field of Natural Language Processing (NLP). Music genres remain a poorly defined concept, and boundaries between genres still remain fuzzy, which makes the automatic classification problem a nontrivial task BIBREF1. Traditional approaches in text classification have applied algorithms such as Support Vector Machine (SVM) and Naïve Bayes, combined with handcraft features (POS and chunk tags) and word count-based representations, like bag-of-words. More recently, the usage of Deep Learning methods such as Recurrent Neural Networks (RNNs) and Convolutional Neural Networks (CNNs) has produced great results in text classification tasks. Some works like BIBREF2, BIBREF3 BIBREF4 focus on classification of mood or sentiment of music based on its lyrics or audio content. Other works, like BIBREF1, and BIBREF5, on the other hand, try to automatically classify the music genre; and the work BIBREF6 tries to classify, besides the music genre, the best and the worst songs, and determine the approximate publication time of a song. In this work, we collected a set of about 130 thousand Brazilian songs distributed in 14 genres. We use a Bidirectional Long Short-Term Memory (BLSTM) network to make a lyrics-based music genre classification. We did not apply an elaborate set of handcraft textual features, instead, we represent the lyrics songs with a pre-trained word embeddings model, obtaining an F1 average score of $0.48$. Our experiments and results show some real aspects that exist among the Brazilian music genres and also show the usefulness of the dataset we have built for future works. This paper is organized as follows. In the next section, we cite and comment on some related works. Section SECREF3 describes our experiments from data collection to the proposed model, presenting some important concepts. Our experimental results are presented in Section SECREF4, and Section SECREF5 presents our concluding remarks and future work. ### Related Works
Several works have been carried out to add textual information to genre and mood classification. Fell and Sporleder BIBREF6 used several handcraft features, such as vocabulary, style, semantics, orientation towards the world, and song structure to obtain performance gains on three different classification tasks: detecting genre, distinguishing the best and the worst songs, and determining the approximate publication time of a song. The experiments in genre classification focused on eight genres: Blues, Rap, Metal, Folk, R&B, Reggae, Country, and Religious. Only lyrics in English were included and they used an SVM with the default settings for the classification. Ying et al. BIBREF0 used Part-of-Speech (POS) features extracted from lyrics and combined them with three different machine learning techniques – k-Nearest-Neighbor, Naïve Bayes, and Support Vector Machines – to classify a collection of 600 English songs by the genre and mood. Zaanen and Kanters BIBREF7 used the term frequency and inverse document frequency statistical metrics as features to solve music mood classification, obtaining an accuracy of more than 70%. In recent years, deep learning techniques have also been applied to music genre classification. This kind of approach typically does not rely on handcraft features or external data. In BIBREF5, the authors used a hierarchical attention network to perform the task in a large dataset of nearly half a million song lyrics, obtaining an accuracy of more than 45%. Some papers such as BIBREF8 used word embedding techniques to represent words from the lyrics and then classify them by the genre using a 3-layer Deep Learning model. ### Methods
In this chapter we present all the major steps we have taken, from obtaining the dataset to the proposed approach to address the automatic music genre classification problem. ### Methods ::: Data Acquisition
In order to obtain a large number of Brazilian music lyrics, we created a crawler to navigate into the Vagalume website, extracting, for each musical genre, all the songs by all the listed authors. The implementation of a crawler was necessary because, although the Vagalume site provides an API, it is only for consultation and does not allow obtaining large amounts of data. The crawler was implemented using Scrapy, an open-source and collaborative Python library to extract data from websites. From the Vagalume's music web page, we collect the song title and lyrics, and the artist name. The genre was collected from the page of styles, which lists all the musical genres and, for each one, all the artists. We selected only 14 genres that we consider as representative Brazilian music, shown in Table TABREF8. Figure FIGREF6 presents an example of the Vagalume's music Web page with the song “Como é grande o meu amor por você”, of the Brazilian singer Roberto Carlos. Green boxes indicate information about music that can be extracted directly from the web page. From this information, the language in which the lyrics are available can be obtained by looking at the icon indicating the flag of Brazil preceded by the “Original” word. After extracting data, we obtained a set of $138,368$ songs distributed across 14 genres. Table TABREF8 presents the number of songs and artists by genre. In order to use the data to learn how to automatically classify genre, we split the dataset into tree partitions: training ($96,857$ samples), validation ($27,673$ samples), and test ($13,838$ samples). The total dataset and splits are available for download. ### Methods ::: Word Embeddings
Word embeddings is a technique to represent words as real vectors, so that these vectors maintain some semantic aspects of the real words. Basically, vectors are computed by calculating probabilities of the context of words, with the intuition that semantically similar words have similar contexts, and must therefore have similar vectors. Word2Vec, by Mikolov et al. BIBREF9, is one of the first and most widely used algorithms to make word embeddings. It has two architectures to compute word vectors: Continuous Bag-Of-Words (CBOW) and Skip-gram. CBOW gets a context as input and predicts the current word, while Skip-gram gets the current word as input and predicts its context. In this work, we use the Python Word2Vec implementation provided by the Gensim library. The Portuguese pre-trained word embeddings created by BIBREF10 and available for download was used to represent words as vectors. We only used models of dimension 300 and, for Word2Vec, Wang2Vec, and FastText, skip-gram architectured models. ### Methods ::: Bidirectional Long Short-Term Memory
Long Short-Term Memory (LSTM) is a specification of Recurrent Neural Network (RNN) that was proposed by Hochreiter and Schmidhuber BIBREF11. This kind of network is widely used to solve classification of sequential data and is designed to capture time dynamics through graph cycles. Figure FIGREF14 presents an LSTM unity, which receives an input from the previous unit, processes it, and passes it to the next unit. The following equations are used to update $C_t$ and $h_t$ values. where $W_f$, $W_i$, $W_C$, $W_o$ are the weight matrices for $h_{t-1}$ input; $U_f$, $U_i$, $U_C$, $U_o$ are the weight matrices for $x_t$ input; and $b_f$, $b_i$, $b_C$, $b_o$ are the bias vectors. Basically, a Bidirectional LSTM network consists of using two LSTM networks: a forward LSTM and a backward LSTM. The intuition behind it is that, in some types of problems, past and future information captured by forward and backward LSTM layers are useful to predict the current data. ### Methods ::: Proposed Approach
Our proposed approach consists of three main steps. Firstly, we concatenate the title of the song with its lyrics, put all words in lower case and then we clean up the text by removing line breaks, multiple spaces, and some punctuation (,!.?). Secondly, we represent the text as a vector provided by a pre-trained word embeddings model. For classical learning algorithms like SVM and Random Forest, we generate, for each song, a vectorial representation by calculating the average of the vectors of each word in the song lyrics that can be can be expressed by the equation below: where $L$ is the song lyrics, $w$ is a word in $L$, and $n$ is the number of words in $L$. If a word does not have a vector representation in the word embeddings model, it is not considered in the equation. For the BLSTM algorithm, the representation was made in the format of a matrix, as shown in Figure FIGREF16, where each line is a vector representation of a word in the lyrics. In the third step, we use as features the generated representation for the genre classification tasks using SVM, Random Forests, and BLSTM. ### Experimental Results
In this section, we describe our experiments. We used the Linear SVM and Random Forest Scikit-learn implementations and Keras on top of TensorFlow for the BLSTM implementation. In this study, we did not focus on finding the best combination of parameters for the algorithms, so that for SVM we used the default parameters, and for Random Forest we used a number of 100 trees. Our BLSTM model was trained using 4 epochs, with Adam optimizer, and 256 as the size of the hidden layer. As we can see in Table TABREF20, our BLSTM approach outperforms the other models with an F1-score average of $0.48$. In addition, we can note that the use of Wang2Vec pre-trained word embeddings made it possible to obtain better F1-score results in BLSTM, which is not necessarily noticed in other cases, since for SVM and Random Forest, Glove and FastText, respectively, were the techniques that obtained better F1-scores. Table TABREF21 shows the BLSTM classification results for each genre. We can see that the genres gospel, funk-carioca and sertanejo have a greater distinction in relation to the other genres, since they were better classified by the model. In particular, funk-carioca obtained a good classification result although it did not have a large number of collected song lyrics. In gospel song lyrics, we can identify some typical words, such as “Deus” (God) , “Senhor” (Lord), and “Jesus” (Jesus); in funk-carioca, songs have the words “bonde” (tram), “chão” (floor) and “baile” (dance ball), all used as slang; in sertanejo, some of the most common words are “amor” (love), “coração” (heart) and “saudade” (longing). The occurrence of these typical words could contribute to the higher performance of F1-scores in these genres. The bossa-nova and jovem-guarda genres, which have few instances in the dataset, are among the most difficult ones to classify using the model. The pop genre, by contrast, has a small distribution between the number of songs and the number of artists, and could not be well classified by our model. This may indicate that our model was unable to identify a pattern due to the low number of songs per artist, or that the song lyrics of this genre cover several subjects that are confused with other genres. Figure FIGREF22 shows the confusion matrix of the results produced by our BLSTM model. We can notice that many instances of class forró are often confused with class sertanejo. Indeed, these two genres are very close. Both Forró and sertanejo have as theme the cultural and daily aspects of the Northeast region of Brazil. Instances of class infantil are often confused with class gospel: in infantil we have music for children for both entertainment and education. In some of the songs, songwriters try to address religious education, which could explain the confusion between those genres. The MPB (Brazilian Popular Music) genre was the most confused of all, which may indicate that song lyrics of this genre cover a wide range of subjects that intersect with other genres. ### Conclusion and Future Works
In this work we constructed a dataset of $138,368$ Brazilian song lyrics distributed in 14 genres. We applied SVM, Random Forest, and a Bidirectional Long Short-Term Memory (BLSTM) network combined with different word embeddings techniques to address the automatic genre classification task based only on the song lyrics. We compared the results between the different combinations of classifiers and word embedding techniques, concluding that our BLSTM combined with the Wang2Vec pre-trained model obtained the best F1-score classification result. Beside the dataset construction and the comparison of tools, this work also evidences the lack of an absolute superiority between the different techniques of word embeddings, since their use and efficiency in this specific task showed to be very closely related to the classification technique. As future work, it is possible to explore the dataset to identify genre or artist similarities, generating visualizations that may or may not confirm aspects pre-conceived by the consumers of Brazilian music. It is also possible to perform classification tasks by artists of a specific genre. Figure 1: An example of a Vagalume’s song web page Table 1: The number of songs and artists by genre Figure 2: The Long Short-Term Memory unit. Figure 3: Our BLSTM model architecture Table 2: Classification results for each classifier and word embeddings model combination Table 3: Detailed result of BLSTM Figure 4: Normalized confusion matrix
|
Word2Vec, Wang2Vec, and FastText
|
Which dataset do they train their models on?
|
### Introduction
One of the principal challenges in computational linguistics is to account for the word order of the document or utterance being processed BIBREF0 . Of course, the numbers of possible phrases grows exponentially with respect to a given phrase length, requiring an approximate approach to summarizing its content. rnn are such an approach, and they are used in various tasks in nlp, such as machine translation BIBREF1 , abstractive summarization BIBREF2 and question answering BIBREF3 . However, rnn, as approximations, suffer from numerical troubles that have been identified, such as that of recovering from past errors when generating phrases. We take interest in a model that mitigates this problem, mrnn, and how it has been and can be combined for new models. To evaluate these models, we use the task of recurrent language modeling, which consists in predicting the next token (character or word) in a document. This paper is organized as follows: rnn and mrnn are introduced respectively in Sections SECREF2 and SECREF3 . Section SECREF4 presents new and existing multiplicative models. Section SECREF5 describes the datasets and experiments performed, as well as results obtained. Sections SECREF6 discusses and concludes our findings. ### Recurrent neural networks
rnn are powerful tools of sequence modeling that can preserve the order of words or characters in a document. A document is therefore a sequence of words, INLINEFORM0 . Given the exponential growth of possible histories with respect to the sequence length, the probability of observing a given sequence needs to be approximated. rnn will make this approximation using the product rule, INLINEFORM1 and updating a hidden state at every time step. This state is first null, INLINEFORM0 Thereafter, it is computed as a function of the past hidden state as well as the input at the current time step, INLINEFORM0 known as the transition function. INLINEFORM0 is a learned function, often taking the form INLINEFORM1 This allows, in theory, for straightforward modeling of sequences of arbitrary length. In practice, rnn encounter some difficulties that need some clever engineering to be mitigated. For example, learning long-term dependencies such as those found in language is not without its share of woes arising from numerical considerations, such as the well-known vanishing gradient problem BIBREF4 . This can be addressed with gating mechanisms, such as lstm BIBREF5 and gru BIBREF6 . A problem that is more specific to generative rnn is their difficulty recovering from past errors BIBREF7 , which BIBREF8 argue arises from having hidden-state transitions that are highly correlated across possible inputs. One approach to adapting rnn to have more input-dependent transition functions is to use the multiplicative "trick" BIBREF9 . This approximates the idea of having the input at each time synthesize a dedicated kernel of parameters dictating the transition from the previous hidden state to the next. These two approaches can be combined, as in the mlstm BIBREF8 . We begin by contending that, in making rnn multiplicative, sharing what is known as the intermediate state does not significantly hinder performance when parameter counts are equal. We verify this with existing as well as new gated models on several well-known language modeling tasks. ### Multiplicative RNNs
Most recurrent neural network architectures, including lstm and gru share the following building block: DISPLAYFORM0 INLINEFORM0 is the candidate hidden state, computed from the previous hidden state, INLINEFORM1 , and the current input, INLINEFORM2 , weighted by the parameter matrices INLINEFORM3 and INLINEFORM4 , respectively. This candidate hidden state may then be passed through gating mechanisms and non-linearities depending on the specific recurrent model. Let us assume for simplicity that the input is a one-hot vector (one component is 1, the rest are 0 BIBREF10 [see p.45]), as it is often the case in nlp. Then, the term INLINEFORM0 is reduced to a single column of INLINEFORM1 and can therefore be thought of as an input-dependent bias in the hidden state transition. As the dependencies we wish to establish between the elements of the sequences under consideration become more distant, the term INLINEFORM2 will have to be significantly larger than this input-dependent bias, INLINEFORM3 , in order to remain unchanged across time-steps. This will mean that from one time-step to the next, the hidden-to-hidden transition will be highly correlated across possible inputs. This can be addressed by having more input-dependent hidden state transitions, making rnn more expressive. In order to remedy the aforementioned problem, each possible input INLINEFORM0 can be given its own matrix INLINEFORM1 parameterizing the contribution of INLINEFORM2 to INLINEFORM3 . DISPLAYFORM0 This is known as a trnn BIBREF9 , because all the matrices can be stacked to form a rank 3 tensor, INLINEFORM0 . The input INLINEFORM1 selects the relevant slice of the tensor in the one-hot case and a weighted sum over all slices in the dense case. The resulting matrix then acts as the appropriate INLINEFORM2 . However, such an approach is impractical because of the high parameter count such a tensor would entail. The tensor can nonetheless be approximated by factorizing it BIBREF11 as follows: DISPLAYFORM0 where INLINEFORM0 and INLINEFORM1 are weight matrices, and INLINEFORM2 is the operator turning a vector INLINEFORM3 into a diagonal matrix where the elements of INLINEFORM4 form the main diagonal of said matrix. Replacing INLINEFORM5 in Equation ( EQREF2 ) by this tensor factorization, we obtain DISPLAYFORM0 where INLINEFORM0 is known as the intermediate state, given by DISPLAYFORM0 Here, INLINEFORM0 refers to the Hadamard or element-wise product of vectors. The intermediate state is the result of having the input apply a learned filter via the new parameter kernel INLINEFORM1 to the factors of the hidden state. It should be noted that the dimensionality of INLINEFORM2 is free and, should it become sufficiently large, the factorization becomes as expressive as the tensor. The ensuing model is known as a mrnn BIBREF9 . ### Sharing intermediate states
While mrnn outperform simple rnn in character-level language modeling, they have been found wanting with respect to the popular lstm BIBREF5 . This prompted BIBREF8 to apply the multiplicative "trick" to lstm resulting in the mlstm, which achieved promising results in several language modeling tasks BIBREF8 . ### mLSTM
Gated rnn, such as lstm and gru, use gates to help signals move through the network. The value of these gates is computed in much the same way as the candidate hidden state, albeit with different parameters. For example, lstm uses two different gates, INLINEFORM0 and INLINEFORM1 in updating its memory cell, INLINEFORM2 , DISPLAYFORM0 It uses another gate, INLINEFORM0 , in mapping INLINEFORM1 to the new hidden state, INLINEFORM2 , DISPLAYFORM0 where INLINEFORM0 is the sigmoid function, squashing its input between 0 and 1. INLINEFORM1 and INLINEFORM2 are known as forget and input gates, respectively. The forget gates allows the network to ignore components of the value of the memory cell at the past state. The input gate filters out certain components of the new hidden state. Finally, the output gates separates the memory cell from the actual hidden state. The values of these gates are computed at each time step as follows: DISPLAYFORM0 DISPLAYFORM1 Each gate has its own set of parameters to infer. If we were to replace each INLINEFORM0 by a tensor factorization as in mrnn, we would obtain a mlstm model. However, in the original formulation of mlstm, there is no factorization of each would-be INLINEFORM1 individually. There is no separate intermediate state for each gate, as one would expect. Instead, a single intermediate state, INLINEFORM2 , is computed to replace INLINEFORM3 in all equations in the system, by Eq. EQREF5 . Furthermore, each gate has its own INLINEFORM4 weighting INLINEFORM5 . Their values are computed as follows: DISPLAYFORM0 DISPLAYFORM1 The model can therefore no longer be understood as as an approximation of the trnn. Nonetheless, it has achieved empirical success in nlp. We therefore try to explore the empirical merits of this shared parametrization and apply them to other rnn architectures. ### True mLSTM
We have presented the original mlstm model with its shared intermediate state. If we wish to remain true to the original multiplicative model, however, we have to factorize every would-be INLINEFORM0 tensor separately. We have: DISPLAYFORM0 DISPLAYFORM1 with each INLINEFORM0 being given by a separate set of parameters: DISPLAYFORM0 We henceforth refer to this model as tmlstm. We sought to apply the same modifications to the gru model, as lstm and gru are known to perform similarly BIBREF12 , BIBREF13 , BIBREF14 . That is, we build a tmgru model, as well as a mgru with a shared intermediate state. ### GRU
The gru was first proposed by BIBREF6 as a lighter, simpler variant of lstm. gru relies on two gates, called, respectively, the update and reset gates, and no additional memory cell. These gates intervene in the computation of the hidden state as follows: DISPLAYFORM0 where the candidate hidden state, INLINEFORM0 , is given by: DISPLAYFORM0 The update gate deletes specific components of the hidden state and replaces them with those of the candidate hidden state, thus updating its content. On the other hand, the reset gate allows the unit to start anew, as if it were reading the first symbol of the input sequence. They are computed much in the same way as the gates of lstm: DISPLAYFORM0 DISPLAYFORM0 ### True mGRU
We can now make gru multiplicative by using the tensor factorization for INLINEFORM0 and INLINEFORM1 : DISPLAYFORM0 DISPLAYFORM1 with each INLINEFORM0 given by Eq. EQREF19 . There is a subtlety to computing INLINEFORM1 , as we need to apply the reset gate to INLINEFORM2 . While INLINEFORM3 itself is given by Eq. EQREF4 , INLINEFORM4 is not computed the same way as in mlstm and mrnn. Instead, it is given by: DISPLAYFORM0 ### mGRU with shared intermediate state
Sharing an intermediate state is not as immediate for gru. This is due to the application of INLINEFORM0 , which we need in computing the intermediate state that we want to share. That is, INLINEFORM1 and INLINEFORM2 would both depend on each other. We modify the role of INLINEFORM3 to act as a filter on INLINEFORM4 , rather than a reset on individual components of INLINEFORM5 . Note that, when all components of INLINEFORM6 go to zero, it amounts to having all components of INLINEFORM7 at zero. We have DISPLAYFORM0 and DISPLAYFORM0 INLINEFORM0 is given by DISPLAYFORM0 with INLINEFORM0 the same as in mrnn and mlstm this time, i.e. Eq. EQREF5 . The final hidden state is computed the same way as in the original gru (Eq. EQREF21 ). ### Experiments in character-level language modeling
Character-level language modeling (or character prediction) consists in predicting the next character while reading a document one character at a time. It is a common benchmark for rnn because of the heightened need for shared parametrization when compared to word-level models. We test mgru on two well-known datasets, the Penn Treebank and Text8. ### Penn Treebank
The Penn Treebank dataset BIBREF15 comes from a series of Wall Street Journal articles written in English. Following BIBREF16 , sections 0-20 were used for training, 21-22 for validation and 23-24 for testing, respectively, which amounts to 5.1M, 400K and 450K characters, respectively. The vocabulary consists of 10K lowercase words. All punctuation is removed and numbers were substituted for a single capital N. All words out of vocabulary are replaced by the token <unk>. The training sequences were passed to the model in batches of 32 sequences. Following BIBREF8 , we built an initial mlstm model of 700 units. However, we set the dimensionality of the intermediate state to that of the input in order to keep the model small. We do the same for our mgru, tmlstm and tmgru, changing only the size of the hidden state so that all four models have roughly the same parameter count. We trained it using the Adam optimizer BIBREF17 , selecting the best model on validation over 10 epochs. We apply no regularization other than a checkpoint which keeps the best model over all epochs. The performance of the model is evaluated using cross entropy in bpc, which is INLINEFORM0 of perplexity. All models outperform previously reported results for mlstm BIBREF8 despite lower parameter counts. This is likely due to our relatively small batch size. However, they perform fairly similarly. Encouraged by these results, we built an mgru with both hidden and intermediate state sizes set to that of the original mlstm (700). This version highly surpasses the previous state of the art while still having fewer parameters than previous work. For the sake of comparison, results as well as parameter counts (where available) of our models (bold) and related approaches are presented in Table TABREF34 . mgru and larger mgru, our best models, achieved respectively an error of 1.07 and 0.98 bpc on the test data, setting a new state of the art for this task. ### Text8
The Text8 corpus BIBREF21 comprises the first 100M plain text characters in English from Wikipedia in 2006. As such, the alphabet consists of the 26 letters of the English alphabet as well as the space character. No vocabulary restrictions were put in place. As per BIBREF16 , the first 90M and 5M characters were used for training and validation, respectively, with the last 5M used for testing. Encouraged by our results on the Penn Treebank dataset, we opted to use similar configurations. However, as the data is one long sequence of characters, we divide it into sequences of 200 characters. We pass these sequences to the model in slightly larger batches of 50 to speed up computation. Again, the dimensionality of the hidden state for mlstm is set at 450 after the original model, and that of the intermediate state is set to the size of the alphabet. The size of the hidden state is adjusted for the other three models as it was for the PTB experiments. The model is also trained using the Adam optimizer over 10 epochs. The best model as per validation data over 10 epochs achieves 1.40 bpc on the test data, slightly surpassing an mlstm of smaller hidden-state dimensionality (450) but larger parameter count. Our results are more modest, as are those of the original mlstm. Once again, results do not vary greatly between models. As with the Penn Treebank, we proceed with building an mgru with both hidden and intermediate state sizes set to 450. This improves performance to 1.21 bpc, setting a new state of the art for this task and surpassing a large mlstm of 1900 units from BIBREF8 despite having far fewer parameters (45M to 5M). For the sake of comparison, results as well as parameter counts of our models and related approaches are presented in Table TABREF36 . It should be noted that some of these models employ dynamic evaluation BIBREF7 , which fits the model further during evaluation. We refer the reader to BIBREF22 . These models are indicated by a star. ### Conclusion
We have found that competitive results can be achieved with mrnn using small models. We have not found significant differences in the approaches presented, despite added non-intuitive parameter-sharing constraints when controlling for model size. Our results are restricted to character-level language modeling. Along this line of thought, previous work on mrnn demonstrated their increased potential when compared to their regular variants BIBREF9 , BIBREF8 , BIBREF23 . We therefore offer other variants as well as a first investigation into their differences. We hope to have evinced the impact of increased flexibility in hidden-state transitions on rnn sequence-modeling capabilities. Further work in this area is required to transpose these findings into applied tasks in nlp. Table 1: Test set error on Penn Treebank and parameter counts in character-level language modeling Table 2: Test set error on Text8 and parameter counts in character-level language modeling
|
Penn Treebank, Text8
|
What was NOT a metric test subjects were asked to use in these experiments?
A. Choosing their favorite of the samples
B. Guessing the most expensive of the samples
C. Personal opinion of the sample
D. Choosing their least favorite of the samples
|
More Booze You Can Use When we last heard from them, the members of the Slate beer-testing team were coping with lagers and trying to see if they could taste the 3-to-1 price difference between the most- and least-expensive brands. (Click for a wrap-up of the first round of beer tasting.) The answer was: They found one beer they really liked, Samuel Adams Boston Lager , and one they really hated, imported Grolsch from Holland. Both were expensive beers--Grolsch was the most expensive in the test--and otherwise the testers had a hard time telling beers apart. The members of the team, as noted in the original article, all hold day jobs at Microsoft, mainly as designers, managers, and coders for Microsoft Word. The point of the second test was not to find the difference between cheap and expensive beers but instead to compare a variety of top-of-the-line beers. Was there one kind the tasters preferred consistently? Could they detect any of the subtleties of brewing style and provenance that microbrew customers pay such attention to when choosing some Doppelbock over a cream ale? Since the tasting panel had left the first round grumbling that cheap lagers were not a fair test of their abilities, this second round of testing was advertised to the panel as a reward. Every beer in Round 2 would be a fancy beer. A microbrew. A "craft beer." A prestigious import. These were the kinds of beer the panel members said they liked--and the ones they said they were most familiar with. One aspect of the reward was that they would presumably enjoy the actual testing more--fewer rueful beer descriptions along the lines of "urine" or "get it away!" were expected than in the first round. The other aspect of anticipated reward was the panelists' unspoken but obvious assumption that this time they would "do better" on the test. Intellectual vanity being what it is, people who had fought for and won jobs at Microsoft and who still must fight every six months for primacy on the employee-ranking scale (which determines--gasp!--how many new stock options they receive) would assume that their skill as tasters was on trial, just as much as the beer was. Of course they were right, which is what made this round as amusing to administer as the first one had been. Here is what happened and what it meant: 1. Procedure. This was similar in most ways to the experimental approach of Round 1. The nine testers who showed up were a subset of the original 12. The missing three dropped out with excuses of "my wife is sick" (one person) and "meeting is running long" (two). As before, each tester found before him on a table 10 red plastic cups, labeled A through J. Each cup held 3 ounces of one of the beers. The A-to-J labeling scheme was the same for all testers. Instead of saltines for palate-cleansing, this time we had popcorn and nuts. As they began, the tasters were given these and only these clues: that the flight included one "holdover" beer from the previous round (Sam Adams); that it included at least one import (Bass); that it included at least one macrobrew , specifically, a member of the vast Anheuser-Busch family (Michelob Hefeweizen). After sampling all beers, the tasters rated them as follows: Overall quality points, from zero to 100, reflecting their personal, subjective fondness for the beer. Descriptions of and comments about each beer's taste--"smooth and nutty," "too strong," etc. If the first ranking was a measure of how good each beer was, this was an attempt to explain what made it good. Best and Worst , one of each from the group. Name that beer! The tasters were told that some of the drinks were Hefeweizens, some might be IPAs (India pale ales), some might be bitters, and so on. They were asked to put each beer in its proper category--and to name a specific brewery and brand if they could. The idea here was to test the veteran beer drinkers' claim to recognize the distinctive tastes of famous brands. (To see all the grids for all the beers, click .) 2. Philosophy. The first round of testing was All Lager. This second round was All Fancy, and Mainly Not Lager. As several correspondents (for instance, the of Best American Beers ) have helpfully pointed out, the definition of lager provided last time was not exactly "accurate." If you want to stay within the realm of textbook definitions, a lager is a beer brewed a particular way--slowly, at cool temperatures, with yeast that settles on the bottom of the vat. This is in contrast with an ale, which is brewed faster, warmer, and with the yeast on top. By this same reasoning, lagers don't have to be light-colored, weak-flavored, and watery, as mainstream American lagers are. In principle, lagers can be dark, fierce, manly. Therefore, the correspondents suggest, it was wrong to impugn Sam Adams or Pete's Wicked for deceptive labeling, in presenting their tawnier, more flavorful beers as lagers too. To this the beer scientist must say: Book-learning is fine in its place. But let's be realistic. Actual drinking experience teaches the American beer consumer that a) all cheap beers are lagers; and b) most lagers are light-colored and weak. The first test was designed to evaluate low-end beers and therefore had to be lager-centric. This one is designed to test fancy beers--but in the spirit of open-mindedness and technical accuracy, it includes a few "strong" lagers too. 3. Materials. The 10 test beers were chosen with several goals in mind: To cover at least a modest range of fancy beer types--extra special bitter, India pale ale, Hefeweizen, and so on. To include both imported and domestic beers. Among the domestic microbrews, there's an obvious skew toward beers from the Pacific Northwest. But as Microsoft would put it, that's a feature not a bug. These beers all came from the Safeway nearest the Redmond, Wash., "main campus" of Microsoft, and microbrews are supposed to be local. To include one holdover from the previous test, as a scientific control on our tasters' preferences. This was Sam Adams , runaway winner of Round 1. To include one fancy product from a monster-scale U.S. mass brewery, to see if the tasters liked it better or worse than the cute little microbrews. This was Michelob Hefeweizen , from the pride of St. Louis, Anheuser-Busch. Click for pricing information and pre-quaffing evaluations. The beers tasted were: 4. Data Analysis. a) Best and Worst. Compared to the lager test, we would expect the range of "best" choices to be more varied, since all the tested beers were supposed to be good. This expectation was most dramatically borne out in the "Best and Worst" rankings. The nine tasters cast a total of nine Worst votes and 11.5 Best votes. (Tester No. 1 turned in a sheet with three Best selections, or two more than his theoretical quota. Tester No. 4 listed a Best and a Best-minus, which counted as half a vote.) The results were clearest at the bottom: three Worsts for Pyramid Hefeweizen , even though most comments about the beer were more or less respectful. ("Bitter, drinkable.") But at the top and middle the situation was muddier: There were three Bests for Full Sail ESB , which most of the tasters later said they weren't familiar with, and 2.5 for Redhook IPA , which all the tasters knew. But each of these also got a Worst vote, and most of the other beers had a mixed reading. So far, the tasters are meeting expectations, finding something to like in nearly all these fancy beers. b) Overall preference points. Here the complications increase. The loser was again apparent: Pyramid Hefeweizen came in last on rating points, as it had in the Best/Worst derby. But the amazing dark horse winner was Michelob Hefeweizen . The three elements of surprise here, in ascending order of unexpectedness, are: This best-liked beer belonged to the same category, Hefeweizen, as the least-liked product, from Pyramid. This was also the only outright Anheuser-Busch product in the contest (the Redhooks are 75 percent A-B free). It is safe to say that all tasters would have said beforehand that they would rank an American macrobrew last, and Anheuser-Busch last of all. Although it clearly won on overall preference points, Michelob Hefeweizen was the only beer not to have received a single "Best" vote. The first two anomalies can be written off as testament to the power of a blind taste test. The third suggests an important difference in concepts of "bestness." Sometimes a product seems to be the best of a group simply because it's the most unusual or distinctive. This is why very high Wine Spectator ratings often go to wines that mainly taste odd. But another kind of bestness involves an unobtrusive, day-in day-out acceptability. That seems to be Michelob Hefe 's achievement here: no one's first choice, but high on everyone's list. Let's go to the charts: This table shows how the beers performed on "raw score"--that is, without the advanced statistical adjustment of throwing out the highest and lowest score each beer received. Next, we have "corrected average preference points," throwing out the high and low marks for each beer. The result is basically the same: It is worth noting the fate of Sam Adams on these charts. Here it ends up with a score of less than 61. These were the numbers awarded by the very same tasters who gave it a corrected preference rating of 83.33 the last time around--and 10 "Best" votes, vs. one Best (and one Worst) this time. The shift in Bests is understandable and demonstrates the importance of picking your competition. The severe drop in preference points illustrates more acutely the ancient principle of being a big fish in a small pond. These same tasters thought that Sam Adams was objectively much better when it was surrounded by Busch and Schmidt's. c) Value rankings. Last time this calculation led to what the colorful French would call a bouleversement. One of the cheapest beers, Busch, which had been in the lower ranks on overall preference points, came out at the top on value-for-money ratings, because it was so cheap. The big surprise now is that the highest-rated beer was also the cheapest one, Michelob Hefe , so the value calculation turned into a rout: Pyramid Hefeweizen was expensive on top of being unpopular, so its position at the bottom was hammered home--but not as painfully as that of Bass Ale . Bass had been in the respectable lower middle class of the preference rankings, so its disappointing Val-u-meter showing mainly reflects the fact that it was the only beer not on "sale" and therefore by far the costliest entry in the experiment. d) Taster skill. As members of the tasting panel began to suspect, they themselves were being judged while they judged the beer. One of the tasters, No. 7, decided to live dangerously and give specific brands and breweries for Samples A through J. This man was the only panel member whose job does not involve designing Microsoft Word--and the only one to identify two or more of the beers accurately and specifically. (He spotted Redhook IPA and Redhook ESB.) The fact that the beers correctly identified were the two most popular microbrews in the Seattle area suggests that familiarity is the main ingredient in knowing your beer. Many others were simply lost. Barely half the tasters, five of nine, recognized that Michelob Hefeweizen was a Hefeweizen. Before the test, nine of nine would have said that picking out a Hefe was easy, because of its cloudy look and wheaty flavor. Three tasters thought Sam Adams was an IPA ; two thought Redhook's IPA was a Hefeweizen. In fairness, six of nine testers identified Pyramid Hefeweizen as a Hefe, and six recognized Full Sail ESB as a bitter. Much in the fashion of blind men describing an elephant, here is a how the testers handled Sam Adams Boston Lager : 5. Implications and Directions for Future Research. Science does not always answer questions; often, it raises many new ones. This excursion into beer science mainly raises the question: What kind of people are we? If we are Gradgrind-like empiricists, living our life for "welfare maximization" as described in introductory econ. courses, the conclusion is obvious. We learned from the first experiment to buy either Sam Adams (when we wanted maximum lager enjoyment per bottle) or Busch (for maximum taste and snob appeal per dollar). From this second round we see an even more efficient possibility: Buy Michelob Hefeweizen and nothing else, since on the basis of this test it's the best liked and the cheapest beer. By the way, if there is a single company whose achievements the testing panel honored, it would be Anheuser-Busch . From its brewing tanks came two of the double-crown winners of the taste tests: plain old Busch , the Taste-o-meter and Snob-o-meter victor of Round 1, and Michelob Hefeweizen , the preference-point and Val-u-meter winner this time. But, of course, there is another possibility: that what is excluded in a blind taste test is in fact what we want, and are happy to pay for, when we sit down with a beer. The complicated label, the fancy bottle, the exotic concept that this beer has traveled from some far-off corner of Bohemia or even the Yakima Valley--all this may be cheap at the $1.25-per-pint cost difference between the cheapest and the most expensive beers. In elementary school, we all endured a standard science experiment: If you shut your eyes and pinch your nose closed, can you tell any difference in the taste of a slice of apple, of carrot, of pear? You can't--but that doesn't mean that from then on you should close your eyes, hold your nose, and chew a cheap carrot when you feel like having some fruit. There is a time and place for carrots, but also for juicy pears. There is a time for Busch, but also for Full Sail "Equinox." For scientists who want to continue this work at home, here are a few suggestions for further research: Tell the testers ahead of time what beers they will be drinking. Ask them to rank the beers, 1 through 10, based on how well they like them. Then compare the list with the "revealed preferences" that come from the blind test. As a variation, show them the list ahead of time and ask them to pick out the beer they know they love and the one they know they hate. Then compare this with the "after" list. If you're going to test imported lagers, try Foster's or Corona rather than Grolsch. Remember to stay strictly in the scientist's role. Don't take the test yourself.
|
B. Guessing the most expensive of the samples
|
What is the significance of the glass statue that Frank finds in the store?
A. It prompts a discussion of the worth of various materials in this town.
B. It is the first piece of evidence about the others who live on the planet.
C. It is proof that hedgehogs are held in high esteem in this society.
D. It shows him where he can find a craftsman to help them with the project.
|
THE PERFECTIONISTS By ARNOLD CASTLE ILLUSTRATED by SUMMERS Is there something wrong with you? Do you fail to fit in with your group? Nervous, anxious, ill-at-ease? Happy about it? Lucky you! Frank Pembroke sat behind the desk of his shabby little office over Lemark's Liquors in downtown Los Angeles and waited for his first customer. He had been in business for a week and as yet had had no callers. Therefore, it was with a mingled sense of excitement and satisfaction that he greeted the tall, dark, smooth-faced figure that came up the stairs and into the office shortly before noon. "Good day, sir," said Pembroke with an amiable smile. "I see my advertisement has interested you. Please stand in that corner for just a moment." Opening the desk drawer, which was almost empty, Pembroke removed an automatic pistol fitted with a silencer. Pointing it at the amazed customer, he fired four .22 caliber longs into the narrow chest. Then he made a telephone call and sat down to wait. He wondered how long it would be before his next client would arrive. The series of events leading up to Pembroke's present occupation had commenced on a dismal, overcast evening in the South Pacific a year earlier. Bound for Sydney, two days out of Valparaiso, the Colombian tramp steamer Elena Mia had encountered a dense greenish fog which seemed vaguely redolent of citrus trees. Standing on the forward deck, Pembroke was one of the first to perceive the peculiar odor and to spot the immense gray hulk wallowing in the murky distance. Then the explosion had come, from far below the waterline, and the decks were awash with frantic crewmen, officers, and the handful of passengers. Only two lifeboats were launched before the Elena Mia went down. Pembroke was in the second. The roar of the sinking ship was the last thing he heard for some time. Pembroke came as close to being a professional adventurer as one can in these days of regimented travel, organized peril, and political restriction. He had made for himself a substantial fortune through speculation in a great variety of properties, real and otherwise. Life had given him much and demanded little, which was perhaps the reason for his restiveness. Loyalty to person or to people was a trait Pembroke had never recognized in himself, nor had it ever been expected of him. And yet he greatly envied those staunch patriots and lovers who could find it in themselves to elevate the glory and safety of others above that of themselves. Lacking such loyalties, Pembroke adapted quickly to the situation in which he found himself when he regained consciousness. He awoke in a small room in what appeared to be a typical modern American hotel. The wallet in his pocket contained exactly what it should, approximately three hundred dollars. His next thought was of food. He left the room and descended via the elevator to the restaurant. Here he observed that it was early afternoon. Ordering a full dinner, for he was unusually hungry, he began to study the others in the restaurant. Many of the faces seemed familiar; the crew of the ship, probably. He also recognized several of the passengers. However, he made no attempt to speak to them. After his meal, he bought a good corona and went for a walk. His situation could have been any small western American seacoast city. He heard the hiss of the ocean in the direction the afternoon sun was taking. In his full-gaited walk, he was soon approaching the beach. On the sand he saw a number of sun bathers. One in particular, an attractive woman of about thirty, tossed back her long, chestnut locks and gazed up intently at Pembroke as he passed. Seldom had he enjoyed so ingenuous an invitation. He halted and stared down at her for a few moments. "You are looking for someone?" she inquired. "Much of the time," said the man. "Could it be me?" "It could be." "Yet you seem unsure," she said. Pembroke smiled, uneasily. There was something not entirely normal about her conversation. Though the rest of her compensated for that. "Tell me what's wrong with me," she went on urgently. "I'm not good enough, am I? I mean, there's something wrong with the way I look or act. Isn't there? Please help me, please!" "You're not casual enough, for one thing," said Pembroke, deciding to play along with her for the moment. "You're too tense. Also you're a bit knock-kneed, not that it matters. Is that what you wanted to hear?" "Yes, yes—I mean, I suppose so. I can try to be more casual. But I don't know what to do about my knees," she said wistfully, staring across at the smooth, tan limbs. "Do you think I'm okay otherwise? I mean, as a whole I'm not so bad, am I? Oh, please tell me." "How about talking it over at supper tonight?" Pembroke proposed. "Maybe with less distraction I'll have a better picture of you—as a whole." "Oh, that's very generous of you," the woman told him. She scribbled a name and an address on a small piece of paper and handed it to him. "Any time after six," she said. Pembroke left the beach and walked through several small specialty shops. He tried to get the woman off his mind, but the oddness of her conversation continued to bother him. She was right about being different, but it was her concern about being different that made her so. How to explain that to her? Then he saw the weird little glass statuette among the usual bric-a-brac. It rather resembled a ground hog, had seven fingers on each of its six limbs, and smiled up at him as he stared. "Can I help you, sir?" a middle-aged saleswoman inquired. "Oh, good heavens, whatever is that thing doing here?" Pembroke watched with lifted eyebrows as the clerk whisked the bizarre statuette underneath the counter. "What the hell was that?" Pembroke demanded. "Oh, you know—or don't you? Oh, my," she concluded, "are you one of the—strangers?" "And if I were?" "Well, I'd certainly appreciate it if you'd tell me how I walk." She came around in front of the counter and strutted back and forth a few times. "They tell me I lean too far forward," she confided. "But I should think you'd fall down if you didn't." "Don't try to go so fast and you won't fall down," suggested Pembroke. "You're in too much of a hurry. Also those fake flowers on your blouse make you look frumpy." "Well, I'm supposed to look frumpy," the woman retorted. "That's the type of person I am. But you can look frumpy and still walk natural, can't you? Everyone says you can." "Well, they've got a point," said Pembroke. "Incidentally, just where are we, anyway? What city is this?" "Puerto Pacifico," she told him. "Isn't that a lovely name? It means peaceful port. In Spanish." That was fine. At least he now knew where he was. But as he left the shop he began checking off every west coast state, city, town, and inlet. None, to the best of his knowledge, was called Puerto Pacifico. He headed for the nearest service station and asked for a map. The attendant gave him one which showed the city, but nothing beyond. "Which way is it to San Francisco?" asked Pembroke. "That all depends on where you are," the boy returned. "Okay, then where am I?" "Pardon me, there's a customer," the boy said. "This is Puerto Pacifico." Pembroke watched him hurry off to service a car with a sense of having been given the runaround. To his surprise, the boy came back a few minutes later after servicing the automobile. "Say, I've just figured out who you are," the youngster told him. "I'd sure appreciate it if you'd give me a little help on my lingo. Also, you gas up the car first, then try to sell 'em the oil—right?" "Right," said Pembroke wearily. "What's wrong with your lingo? Other than the fact that it's not colloquial enough." "Not enough slang, huh? Well, I guess I'll have to concentrate on that. How about the smile?" "Perfect," Pembroke told him. "Yeah?" said the boy delightedly. "Say, come back again, huh? I sure appreciate the help. Keep the map." "Thanks. One more thing," Pembroke said. "What's over that way—outside the city?" "Sand." "How about that way?" he asked, pointing north. "And that way?" pointing south. "More of the same." "Any railroads?" "That we ain't got." "Buses? Airlines?" The kid shook his head. "Some city." "Yeah, it's kinda isolated. A lot of ships dock here, though." "All cargo ships, I'll bet. No passengers," said Pembroke. "Right," said the attendant, giving with his perfect smile. "No getting out of here, is there?" "That's for sure," the boy said, walking away to wait on another customer. "If you don't like the place, you've had it." Pembroke returned to the hotel. Going to the bar, he recognized one of the Elena Mia's paying passengers. He was a short, rectangular little man in his fifties named Spencer. He sat in a booth with three young women, all lovely, all effusive. The topic of the conversation turned out to be precisely what Pembroke had predicted. "Well, Louisa, I'd say your only fault is the way you keep wigglin' your shoulders up 'n' down. Why'n'sha try holdin' 'em straight?" "I thought it made me look sexy," the redhead said petulantly. "Just be yourself, gal," Spencer drawled, jabbing her intimately with a fat elbow, "and you'll qualify." "Me, me," the blonde with a feather cut was insisting. "What is wrong with me?" "You're perfect, sweetheart," he told her, taking her hand. "Ah, come on," she pleaded. "Everyone tells me I chew gum with my mouth open. Don't you hate that?" "Naw, that's part of your charm," Spencer assured her. "How 'bout me, sugar," asked the girl with the coal black hair. "Ah, you're perfect, too. You are all perfect. I've never seen such a collection of dolls as parade around this here city. C'mon, kids—how 'bout another round?" But the dolls had apparently lost interest in him. They got up one by one and walked out of the bar. Pembroke took his rum and tonic and moved over to Spencer's booth. "Okay if I join you?" "Sure," said the fat man. "Wonder what the hell got into those babes?" "You said they were perfect. They know they're not. You've got to be rough with them in this town," said Pembroke. "That's all they want from us." "Mister, you've been doing some thinkin', I can see," said Spencer, peering at him suspiciously. "Maybe you've figured out where we are." "Your bet's as good as mine," said Pembroke. "It's not Wellington, and it's not Brisbane, and it's not Long Beach, and it's not Tahiti. There are a lot of places it's not. But where the hell it is, you tell me. "And, by the way," he added, "I hope you like it in Puerto Pacifico. Because there isn't any place to go from here and there isn't any way to get there if there were." "Pardon me, gentlemen, but I'm Joe Valencia, manager of the hotel. I would be very grateful if you would give me a few minutes of honest criticism." "Ah, no, not you, too," groaned Spencer. "Look, Joe, what's the gag?" "You are newcomers, Mr. Spencer," Valencia explained. "You are therefore in an excellent position to point out our faults as you see them." "Well, so what?" demanded Spencer. "I've got more important things to do than to worry about your troubles. You look okay to me." "Mr. Valencia," said Pembroke. "I've noticed that you walk with a very slight limp. If you have a bad leg, I should think you would do better to develop a more pronounced limp. Otherwise, you may appear to be self-conscious about it." Spencer opened his mouth to protest, but saw with amazement that it was exactly this that Valencia was seeking. Pembroke was amused at his companion's reaction but observed that Spencer still failed to see the point. "Also, there is a certain effeminateness in the way in which you speak," said Pembroke. "Try to be a little more direct, a little more brusque. Speak in a monotone. It will make you more acceptable." "Thank you so much," said the manager. "There is much food for thought in what you have said, Mr. Pembroke. However, Mr. Spencer, your value has failed to prove itself. You have only yourself to blame. Cooperation is all we require of you." Valencia left. Spencer ordered another martini. Neither he nor Pembroke spoke for several minutes. "Somebody's crazy around here," the fat man muttered after a few moments. "Is it me, Frank?" "No. You just don't belong here, in this particular place," said Pembroke thoughtfully. "You're the wrong type. But they couldn't know that ahead of time. The way they operate it's a pretty hit-or-miss operation. But they don't care one bit about us, Spencer. Consider the men who went down with the ship. That was just part of the game." "What the hell are you sayin'?" asked Spencer in disbelief. "You figure they sunk the ship? Valencia and the waitress and the three babes? Ah, come on." "It's what you think that will determine what you do, Spencer. I suggest you change your attitude; play along with them for a few days till the picture becomes a little clearer to you. We'll talk about it again then." Pembroke rose and started out of the bar. A policeman entered and walked directly to Spencer's table. Loitering at the juke box, Pembroke overheard the conversation. "You Spencer?" "That's right," said the fat man sullenly. "What don't you like about me? The truth , buddy." "Ah, hell! Nothin' wrong with you at all, and nothin'll make me say there is," said Spencer. "You're the guy, all right. Too bad, Mac," said the cop. Pembroke heard the shots as he strolled casually out into the brightness of the hotel lobby. While he waited for the elevator, he saw them carrying the body into the street. How many others, he wondered, had gone out on their backs during their first day in Puerto Pacifico? Pembroke shaved, showered, and put on the new suit and shirt he had bought. Then he took Mary Ann, the woman he had met on the beach, out to dinner. She would look magnificent even when fully clothed, he decided, and the pale chartreuse gown she wore hardly placed her in that category. Her conversation seemed considerably more normal after the other denizens of Puerto Pacifico Pembroke had listened to that afternoon. After eating they danced for an hour, had a few more drinks, then went to Pembroke's room. He still knew nothing about her and had almost exhausted his critical capabilities, but not once had she become annoyed with him. She seemed to devour every factual point of imperfection about herself that Pembroke brought to her attention. And, fantastically enough, she actually appeared to have overcome every little imperfection he had been able to communicate to her. It was in the privacy of his room that Pembroke became aware of just how perfect, physically, Mary Ann was. Too perfect. No freckles or moles anywhere on the visible surface of her brown skin, which was more than a mere sampling. Furthermore, her face and body were meticulously symmetrical. And she seemed to be wholly ambidextrous. "With so many beautiful women in Puerto Pacifico," said Pembroke probingly, "I find it hard to understand why there are so few children." "Yes, children are decorative, aren't they," said Mary Ann. "I do wish there were more of them." "Why not have a couple of your own?" he asked. "Oh, they're only given to maternal types. I'd never get one. Anyway, I won't ever marry," she said. "I'm the paramour type." It was obvious that the liquor had been having some effect. Either that, or she had a basic flaw of loquacity that no one else had discovered. Pembroke decided he would have to cover his tracks carefully. "What type am I?" he asked. "Silly, you're real. You're not a type at all." "Mary Ann, I love you very much," Pembroke murmured, gambling everything on this one throw. "When you go to Earth I'll miss you terribly." "Oh, but you'll be dead by then," she pouted. "So I mustn't fall in love with you. I don't want to be miserable." "If I pretended I was one of you, if I left on the boat with you, they'd let me go to Earth with you. Wouldn't they?" "Oh, yes, I'm sure they would." "Mary Ann, you have two other flaws I feel I should mention." "Yes? Please tell me." "In the first place," said Pembroke, "you should be willing to fall in love with me even if it will eventually make you unhappy. How can you be the paramour type if you refuse to fall in love foolishly? And when you have fallen in love, you should be very loyal." "I'll try," she said unsurely. "What else?" "The other thing is that, as my mistress, you must never mention me to anyone. It would place me in great danger." "I'll never tell anyone anything about you," she promised. "Now try to love me," Pembroke said, drawing her into his arms and kissing with little pleasure the smooth, warm perfection of her tanned cheeks. "Love me my sweet, beautiful, affectionate Mary Ann. My paramour." Making love to Mary Ann was something short of ecstasy. Not for any obvious reason, but because of subtle little factors that make a woman a woman. Mary Ann had no pulse. Mary Ann did not perspire. Mary Ann did not fatigue gradually but all at once. Mary Ann breathed regularly under all circumstances. Mary Ann talked and talked and talked. But then, Mary Ann was not a human being. When she left the hotel at midnight, Pembroke was quite sure that she understood his plan and that she was irrevocably in love with him. Tomorrow might bring his death, but it might also ensure his escape. After forty-two years of searching for a passion, for a cause, for a loyalty, Frank Pembroke had at last found his. Earth and the human race that peopled it. And Mary Ann would help him to save it. The next morning Pembroke talked to Valencia about hunting. He said that he planned to go shooting out on the desert which surrounded the city. Valencia told him that there were no living creatures anywhere but in the city. Pembroke said he was going out anyway. He picked up Mary Ann at her apartment and together they went to a sporting goods store. As he guessed there was a goodly selection of firearms, despite the fact that there was nothing to hunt and only a single target range within the city. Everything, of course, had to be just like Earth. That, after all, was the purpose of Puerto Pacifico. By noon they had rented a jeep and were well away from the city. Pembroke and Mary Ann took turns firing at the paper targets they had purchased. At twilight they headed back to the city. On the outskirts, where the sand and soil were mixed and no footprints would be left, Pembroke hopped off. Mary Ann would go straight to the police and report that Pembroke had attacked her and that she had shot him. If necessary, she would conduct the authorities to the place where they had been target shooting, but would be unable to locate the spot where she had buried the body. Why had she buried it? Because at first she was not going to report the incident. She was frightened. It was not airtight, but there would probably be no further investigation. And they certainly would not prosecute Mary Ann for killing an Earthman. Now Pembroke had himself to worry about. The first step was to enter smoothly into the new life he had planned. It wouldn't be so comfortable as the previous one, but should be considerably safer. He headed slowly for the "old" part of town, aging his clothes against buildings and fences as he walked. He had already torn the collar of the shirt and discarded his belt. By morning his beard would grow to blacken his face. And he would look weary and hungry and aimless. Only the last would be a deception. Two weeks later Pembroke phoned Mary Ann. The police had accepted her story without even checking. And when, when would she be seeing him again? He had aroused her passion and no amount of long-distance love could requite it. Soon, he assured her, soon. "Because, after all, you do owe me something," she added. And that was bad because it sounded as if she had been giving some womanly thought to the situation. A little more of that and she might go to the police again, this time for vengeance. Twice during his wanderings Pembroke had seen the corpses of Earthmen being carted out of buildings. They had to be Earthmen because they bled. Mary Ann had admitted that she did not. There would be very few Earthmen left in Puerto Pacifico, and it would be simple enough to locate him if he were reported as being on the loose. There was no out but to do away with Mary Ann. Pembroke headed for the beach. He knew she invariably went there in the afternoon. He loitered around the stalls where hot dogs and soft drinks were sold, leaning against a post in the hot sun, hat pulled down over his forehead. Then he noticed that people all about him were talking excitedly. They were discussing a ship. It was leaving that afternoon. Anyone who could pass the interview would be sent to Earth. Pembroke had visited the docks every day, without being able to learn when the great exodus would take place. Yet he was certain the first lap would be by water rather than by spaceship, since no one he had talked to in the city had ever heard of spaceships. In fact, they knew very little about their masters. Now the ship had arrived and was to leave shortly. If there was any but the most superficial examination, Pembroke would no doubt be discovered and exterminated. But since no one seemed concerned about anything but his own speech and behavior, he assumed that they had all qualified in every other respect. The reason for transporting Earth People to this planet was, of course, to apply a corrective to any of the Pacificos' aberrant mannerisms or articulation. This was the polishing up phase. Pembroke began hobbling toward the docks. Almost at once he found himself face to face with Mary Ann. She smiled happily when she recognized him. That was a good thing. "It is a sign of poor breeding to smile at tramps," Pembroke admonished her in a whisper. "Walk on ahead." She obeyed. He followed. The crowd grew thicker. They neared the docks and Pembroke saw that there were now set up on the roped-off wharves small interviewing booths. When it was their turn, he and Mary Ann each went into separate ones. Pembroke found himself alone in the little room. Then he saw that there was another entity in his presence confined beneath a glass dome. It looked rather like a groundhog and had seven fingers on each of its six limbs. But it was larger and hairier than the glass one he had seen at the gift store. With four of its limbs it tapped on an intricate keyboard in front of it. "What is your name?" queried a metallic voice from a speaker on the wall. "I'm Jerry Newton. Got no middle initial," Pembroke said in a surly voice. "Occupation?" "I work a lot o' trades. Fisherman, fruit picker, fightin' range fires, vineyards, car washer. Anything. You name it. Been out of work for a long time now, though. Goin' on five months. These here are hard times, no matter what they say." "What do you think of the Chinese situation?" the voice inquired. "Which situation's 'at?" "Where's Seattle?" "Seattle? State o' Washington." And so it went for about five minutes. Then he was told he had qualified as a satisfactory surrogate for a mid-twentieth century American male, itinerant type. "You understand your mission, Newton?" the voice asked. "You are to establish yourself on Earth. In time you will receive instructions. Then you will attack. You will not see us, your masters, again until the atmosphere has been sufficiently chlorinated. In the meantime, serve us well." He stumbled out toward the docks, then looked about for Mary Ann. He saw her at last behind the ropes, her lovely face in tears. Then she saw him. Waving frantically, she called his name several times. Pembroke mingled with the crowd moving toward the ship, ignoring her. But still the woman persisted in her shouting. Sidling up to a well-dressed man-about-town type, Pembroke winked at him and snickered. "You Frank?" he asked. "Hell, no. But some poor punk's sure red in the face, I'll bet," the man-about-town said with a chuckle. "Those high-strung paramour types always raising a ruckus. They never do pass the interview. Don't know why they even make 'em." Suddenly Mary Ann was quiet. "Ambulance squad," Pembroke's companion explained. "They'll take her off to the buggy house for a few days and bring her out fresh and ignorant as the day she was assembled. Don't know why they keep making 'em, as I say. But I guess there's a call for that type up there on Earth." "Yeah, I reckon there is at that," said Pembroke, snickering again as he moved away from the other. "And why not? Hey? Why not?" Pembroke went right on hating himself, however, till the night he was deposited in a field outside of Ensenada, broke but happy, with two other itinerant types. They separated in San Diego, and it was not long before Pembroke was explaining to the police how he had drifted far from the scene of the sinking of the Elena Mia on a piece of wreckage, and had been picked up by a Chilean trawler. How he had then made his way, with much suffering, up the coast to California. Two days later, his identity established and his circumstances again solvent, he was headed for Los Angeles to begin his save-Earth campaign. Now, seated at his battered desk in the shabby rented office over Lemark's Liquors, Pembroke gazed without emotion at the two demolished Pacificos that lay sprawled one atop the other in the corner. His watch said one-fifteen. The man from the FBI should arrive soon. There were footsteps on the stairs for the third time that day. Not the brisk, efficient steps of a federal official, but the hesitant, self-conscious steps of a junior clerk type. Pembroke rose as the young man appeared at the door. His face was smooth, unpimpled, clean-shaven, without sweat on a warm summer afternoon. "Are you Dr. Von Schubert?" the newcomer asked, peering into the room. "You see, I've got a problem—" The four shots from Pembroke's pistol solved his problem effectively. Pembroke tossed his third victim onto the pile, then opened a can of lager, quaffing it appreciatively. Seating himself once more, he leaned back in the chair, both feet upon the desk. He would be out of business soon, once the FBI agent had got there. Pembroke was only in it to get the proof he would need to convince people of the truth of his tale. But in the meantime he allowed himself to admire the clipping of the newspaper ad he had run in all the Los Angeles papers for the past week. The little ad that had saved mankind from God-knew-what insidious menace. It read: ARE YOU IMPERFECT? LET DR. VON SCHUBERT POINT OUT YOUR FLAWS IT IS HIS GOAL TO MAKE YOU THE AVERAGE FOR YOUR TYPE FEE—$3.75 MONEY BACK IF NOT SATISFIED! THE END Transcriber's Note: This etext was produced from Amazing Science Fiction Stories January 1960. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed. Minor spelling and typographical errors have been corrected without note.
|
B. It is the first piece of evidence about the others who live on the planet.
|
How is multi-tasking performed?
|
### Introduction
The emergence of social media sites with limited character constraint has ushered in a new style of communication. Twitter users within 280 characters per tweet share meaningful and informative messages. These short messages have a powerful impact on how we perceive and interact with other human beings. Their compact nature allows them to be transmitted efficiently and assimilated easily. These short messages can shape people's thought and opinion. This makes them an interesting and important area of study. Tweets are not only important for an individual but also for the companies, political parties or any organization. Companies can use tweets to gauge the performance of their products and predict market trends BIBREF0. The public opinion is particularly interesting for political parties as it gives them an idea of voter's inclination and their support. Sentiment and emotion analysis can help to gauge product perception, predict stock prices and model public opinions BIBREF1. Sentiment analysis BIBREF2 is an important area of research in natural language processing (NLP) where we automatically determine the sentiments (positive, negative, neutral). Emotion analysis focuses on the extraction of predefined emotion from documents. Discrete emotions BIBREF3, BIBREF4 are often classified into anger, anticipation, disgust, fear, joy, sadness, surprise and trust. Sentiments and emotions are subjective and hence they are understood similarly and often used interchangeably. This is also mostly because both emotions and sentiments refer to experiences that result from the combined influences of the biological, the cognitive, and the social BIBREF5. However, emotions are brief episodes and are shorter in length BIBREF6, whereas sentiments are formed and retained for a longer period. Moreover, emotions are not always target-centric whereas sentiments are directed. Another difference between emotion and sentiment is that a sentence or a document may contain multiple emotions but a single overall sentiment. Prior studies show that sentiment and emotion are generally tackled as two separate problems. Although sentiment and emotion are not exactly the same, they are closely related. Emotions, like joy and trust, intrinsically have an association with a positive sentiment. Similarly, anger, disgust, fear and sadness have a negative tone. Moreover, sentiment analysis alone is insufficient at times in imparting complete information. A negative sentiment can arise due to anger, disgust, fear, sadness or a combination of these. Information about emotion along with sentiment helps to better understand the state of the person or object. The close association of emotion with sentiment motivates us to build a system for sentiment analysis using the information obtained from emotion analysis. In this paper, we put forward a robust two-layered multi-task attention based neural network which performs sentiment analysis and emotion analysis simultaneously. The model uses two levels of attention - the first primary attention builds the best representation for each word using Distributional Thesaurus and the secondary attention mechanism creates the final sentence level representation. The system builds the representation hierarchically which gives it a good intuitive working insight. We perform several experiments to evaluate the usefulness of primary attention mechanism. Experimental results show that the two-layered multi-task system for sentiment analysis which uses emotion analysis as an auxiliary task improves over the existing state-of-the-art system of SemEval 2016 Task 6 BIBREF7. The main contributions of the current work are two-fold: a) We propose a novel two-layered multi-task attention based system for joint sentiment and emotion analysis. This system has two levels of attention which builds a hierarchical representation. This provides an intuitive explanation of its working; b) We empirically show that emotion analysis is relevant and useful in sentiment analysis. The multi-task system utilizing fine-grained information of emotion analysis performs better than the single task system of sentiment analysis. ### Related Work
A survey of related literature reveals the use of both classical and deep-learning approaches for sentiment and emotion analysis. The system proposed in BIBREF8 relied on supervised statistical text classification which leveraged a variety of surface form, semantic, and sentiment features for short informal texts. A Support Vector Machine (SVM) based system for sentiment analysis was used in BIBREF9, whereas an ensemble of four different sub-systems for sentiment analysis was proposed in BIBREF10. It comprised of Long Short-Term Memory (LSTM) BIBREF11, Gated Recurrent Unit (GRU) BIBREF12, Convolutional Neural Network (CNN) BIBREF13 and Support Vector Regression (SVR) BIBREF14. BIBREF15 reported the results for emotion analysis using SVR, LSTM, CNN and Bi-directional LSTM (Bi-LSTM) BIBREF16. BIBREF17 proposed a lexicon based feature extraction for emotion text classification. A rule-based approach was adopted by BIBREF18 to extract emotion-specific semantics. BIBREF19 used a high-order Hidden Markov Model (HMM) for emotion detection. BIBREF20 explored deep learning techniques for end-to-end trainable emotion recognition. BIBREF21 proposed a multi-task learning model for fine-grained sentiment analysis. They used ternary sentiment classification (negative, neutral, positive) as an auxiliary task for fine-grained sentiment analysis (very-negative, negative, neutral, positive, very-positive). A CNN based system was proposed by BIBREF22 for three phase joint multi-task training. BIBREF23 presented a multi-task learning based model for joint sentiment analysis and semantic embedding learning tasks. BIBREF24 proposed a multi-task setting for emotion analysis based on a vector-valued Gaussian Process (GP) approach known as coregionalisation BIBREF25. A hierarchical document classification system based on sentence and document representation was proposed by BIBREF26. An attention framework for sentiment regression is described in BIBREF27. BIBREF28 proposed a DeepEmoji system based on transfer learning for sentiment, emotion and sarcasm detection through emoji prediction. However, the DeepEmoji system treats these independently, one at a time. Our proposed system differs from the above works in the sense that none of these works addresses the problem of sentiment and emotion analysis concurrently. Our empirical analysis shows that performance of sentiment analysis is boosted significantly when this is jointly performed with emotion analysis. This may be because of the fine-grained characteristics of emotion analysis that provides useful evidences for sentiment analysis. ### Proposed Methodology
We propose a novel two-layered multi-task attention based neural network for sentiment analysis where emotion analysis is utilized to improve its efficiency. Figure FIGREF1 illustrates the overall architecture of the proposed multi-task system. The proposed system consists of a Bi-directional Long Short-Term Memory (BiLSTM) BIBREF16, a two-level attention mechanism BIBREF29, BIBREF30 and a shared representation for emotion and sentiment analysis tasks. The BiLSTM encodes the word representation of each word. This representation is shared between the subsystems of sentiment and emotion analysis. Each of the shared representations is then fed to the primary attention mechanism of both the subsystems. The primary attention mechanism finds the best representation for each word for each task. The secondary attention mechanism acts on top of the primary attention to extract the best sentence representation by focusing on the suitable context for each task. Finally, the representations of both the tasks are fed to two different feed-forward neural networks to produce two outputs - one for sentiment analysis and one for emotion analysis. Each component is explained in the subsequent subsections. ### Proposed Methodology ::: Two-Layered Multi-Task Attention Model ::: BiLSTM based word encoder
Recurrent Neural Networks (RNN) are a class of networks which take sequential input and computes a hidden state vector for each time step. The current hidden state vector depends on the current input and the previous hidden state vector. This makes them good for handling sequential data. However, they suffer from a vanishing or exploding gradient problem when presented with long sequences. The gradient for back-propagating error either reduces to a very small number or increases to a very high value which hinders the learning process. Long Short Term Memory (LSTM) BIBREF11, a variant of RNN solves this problem by the gating mechanisms. The input, forget and output gates control the information flow. BiLSTM is a special type of LSTM which takes into account the output of two LSTMs - one working in the forward direction and one working in the backward direction. The presence of contextual information for both past and future helps the BiLSTM to make an informed decision. The concatenation of a hidden state vectors $\overrightarrow{h_t}$ of the forward LSTM and $\overleftarrow{h_t}$ of the backward LSTM at any time step t provides the complete information. Therefore, the output of the BiLSTM at any time step t is $h_t$ = [$\overrightarrow{h_t}$, $\overleftarrow{h_t}$]. The output of the BiLSTM is shared between the main task (Sentiment Analysis) and the auxiliary task (Emotion Analysis). ### Proposed Methodology ::: Two-Layered Multi-Task Attention Model ::: Word Attention
The word level attention (primary attention) mechanism gives the model a flexibility to represent each word for each task differently. This improves the word representation as the model chooses the best representation for each word for each task. A Distributional Thesaurus (DT) identifies words that are semantically similar, based on whether they tend to occur in a similar context. It provides a word expansion list for words based on their contextual similarity. We use the top-4 words for each word as their candidate terms. We only use the top-4 words for each word as we observed that the expansion list with more words started to contain the antonyms of the current word which empirically reduced the system performance. Word embeddings of these four candidate terms and the hidden state vector $h_t$ of the input word are fed to the primary attention mechanism. The primary attention mechanism finds the best attention coefficient for each candidate term. At each time step $t$ we get V($x_t$) candidate terms for each input $x_t$ with $v_i$ being the embedding for each term (Distributional Thesaurus and word embeddings are described in the next section). The primary attention mechanism assigns an attention coefficient to each of the candidate terms having the index $i$ $\in $ V($x_t$): where $W_w$ and $b_{w}$ are jointly learned parameters. Each embedding of the candidate term is weighted with the attention score $\alpha _{ti}$ and then summed up. This produces $m_{t}$, the representation for the current input $x_{t}$ obtained from the Distributional Thesaurus using the candidate terms. Finally, $m_{t}$ and $h_{t}$ are concatenated to get $\widehat{h_{t}}$, the final output of the primary attention mechanism. ### Proposed Methodology ::: Two-Layered Multi-Task Attention Model ::: Sentence Attention
The sentence attention (secondary attention) part focuses on each word of the sentence and assigns the attention coefficients. The attention coefficients are assigned on the basis of words' importance and their contextual relevance. This helps the model to build the overall sentence representation by capturing the context while weighing different word representations individually. The final sentence representation is obtained by multiplying each word vector representation with their attention coefficient and summing them over. The attention coefficient $\alpha _t$ for each word vector representation and the sentence representation $\widehat{H}$ are calculated as: where $W_s$ and $b_{s}$ are parameters to be learned. $\widehat{H}$ denotes the sentence representation for sentiment analysis. Similarly, we calculate $\bar{H}$ which represents the sentence for emotion classification. The system has the flexibility to compute different representations for sentiment and emotion analysis both. ### Proposed Methodology ::: Two-Layered Multi-Task Attention Model ::: Final Output
The final outputs for both sentiment and emotion analysis are computed by feeding $\widehat{H}$ and $\bar{H}$ to two different one-layer feed forward neural networks. For our task, the feed forward network for sentiment analysis has two output units, whereas the feed forward network for emotion analysis has eight output nodes performing multi-label classification. ### Proposed Methodology ::: Distributional Thesaurus
Distributional Thesaurus (DT) BIBREF31 ranks words according to their semantic similarity. It is a resource which produces a list of words in decreasing order of their similarity for each word. We use the DT to expand each word of the sentence. The top-4 words serve as the candidate terms for each word. For example, the candidate terms for the word good are: great, nice awesome and superb. DT offers the primary attention mechanism external knowledge in the form of candidate terms. It assists the system to perform better when presented with unseen words during testing as the unseen words could have been a part of the DT expansion list. For example, the system may not come across the word superb during training but it can appear in the test set. Since the system has already seen the word superb in the DT expansion list of the word good, it can handle this case efficiently. This fact is established by our evaluation results as the model performs better when the DT expansion and primary attentions are a part of the final multi-task system. ### Proposed Methodology ::: Word Embeddings
Word embeddings represent words in a low-dimensional numerical form. They are useful for solving many NLP problems. We use the pre-trained 300 dimensional Google Word2Vec BIBREF32 embeddings. The word embedding for each word in the sentence is fed to the BiLSTM network to get the current hidden state. Moreover, the primary attention mechanism is also applied to the word embeddings of the candidate terms for the current word. ### Datasets, Experiments and Analysis
In this section we present the details of the datasets used for the experiments, results that we obtain and the necessary analysis. ### Datasets, Experiments and Analysis ::: Datasets
We evaluate our proposed approach for joint sentiment and emotion analysis on the benchmark dataset of SemEval 2016 Task 6 BIBREF7 and Stance Sentiment Emotion Corpus (SSEC) BIBREF15. The SSEC corpus is an annotation of the SemEval 2016 Task 6 corpus with emotion labels. The re-annotation of the SemEval 2016 Task 6 corpus helps to bridge the gap between the unavailability of a corpus with sentiment and emotion labels. The SemEval 2016 corpus contains tweets which are classified into positive, negative or other. It contains 2,914 training and 1,956 test instances. The SSEC corpus is annotated with anger, anticipation, disgust, fear, joy, sadness, surprise and trust labels. Each tweet could belong to one or more emotion classes and one sentiment class. Table TABREF15 shows the data statistics of SemEval 2016 task 6 and SSEC which are used for sentiment and emotion analysis, respectively. ### Datasets, Experiments and Analysis ::: Preprocessing
The SemEval 2016 task 6 corpus contains tweets from Twitter. Since the tweets are derived from an environment with the constraint on the number of characters, there is an inherent problem of word concatenation, contractions and use of hashtags. Example: #BeautifulDay, we've, etc. Usernames and URLs do not impart any sentiment and emotion information (e.g. @John). We use the Python package ekphrasis BIBREF33 for handling these situations. Ekphrasis helps to split the concatenated words into individual words and expand the contractions. For example, #BeautifulDay to # Beautiful Day and we've to we have. We replace usernames with $<$user$>$, number with $<number>$ and URLs with $<$url$>$ token. ### Datasets, Experiments and Analysis ::: Implementation Details
We implement our model in Python using Tensorflow on a single GPU. We experiment with six different BiLSTM based architectures. The three architectures correspond to BiLSTM based systems without primary attention i.e. only with secondary attention for sentiment analysis (S1), emotion analysis (E1) and the multi-task system (M1) for joint sentiment and emotion analysis. The remaining three architectures correspond to the systems for sentiment analysis (S2), emotion analysis (E2) and multi-task system (M2), with both primary and secondary attention. The weight matrices were initialized randomly using numbers form a truncated normal distribution. The batch size was 64 and the dropout BIBREF34 was 0.6 with the Adam optimizer BIBREF35. The hidden state vectors of both the forward and backward LSTM were 300-dimensional, whereas the context vector was 150-dimensional. Relu BIBREF36 was used as the activation for the hidden layers, whereas in the output layer we used sigmoid as the activation function. Sigmoid cross-entropy was used as the loss function. F1-score was reported for the sentiment analysis BIBREF7 and precision, recall and F1-score were used as the evaluation metric for emotion analysis BIBREF15. Therefore, we report the F1-score for sentiment and precision, recall and F1-score for emotion analysis. ### Datasets, Experiments and Analysis ::: Results and Analysis
We compare the performance of our proposed system with the state-of-the-art systems of SemEval 2016 Task 6 and the systems of BIBREF15. Experimental results show that the proposed system improves the existing state-of-the-art systems for sentiment and emotion analysis. We summarize the results of evaluation in Table TABREF18. The primary attention mechanism plays a key role in the overall system as it improves the score of both sentiment and emotion analysis in both single task as well as multi-task systems. The use of primary attention improves the performance of single task systems for sentiment and emotion analysis by 2.21 and 1.72 points, respectively.Similarly, when sentiment and emotion analysis are jointly performed the primary attention mechanism improves the score by 0.93 and 2.42 points for sentiment and emotion task, respectively. To further measure the usefulness of the primary attention mechanism and the Distributional Thesaurus, we remove it from the systems S2, E2, and M2 to get the systems S1, E1, and M1. In all the cases, with the removal of primary attention mechanism, the performance drops. This is clearly illustrated in Figure FIGREF21. These observations indicate that the primary attention mechanism is an important component of the two-layered multi-task attention based network for sentiment analysis. We also perform t-test BIBREF40 for computing statistical significance of the obtained results from the final two-layered multi-task system M2 for sentiment analysis by calculating the p-values and observe that the performance gain over M1 is significant with p-value = 0.001495. Similarly, we perform the statistical significance test for each emotion class. The p-values for anger, anticipation, fear, disgust, joy, sadness, surprise and trust are 0.000002, 0.000143, 0.00403, 0.000015, 0.004607, 0.069, 0.000001 and 0.000001, respectively. These results provide a good indication of statistical significance. Table TABREF19 shows the comparison of our proposed system with the existing state-of-the-art system of SemEval 2016 Task 6 for the sentiment dataset. BIBREF7 used feature-based SVM, BIBREF39 used keyword rules, LitisMind relied on hashtag rules on external data, BIBREF38 utilized a combination of sentiment classifiers and rules, whereas BIBREF37 used a maximum entropy classifier with domain-specific features. Our system comfortably surpasses the existing best system at SemEval. Our system manages to improve the existing best system of SemEval 2016 task 6 by 3.2 F-score points for sentiment analysis. We also compare our system with the state-of-the-art systems proposed by BIBREF15 on the emotion dataset. The comparison is demonstrated in Table TABREF22. Maximum entropy, SVM, LSTM, Bi-LSTM, and CNN were the five individual systems used by BIBREF15. Overall, our proposed system achieves an improvement of 5 F-Score points over the existing state-of-the-art system for emotion analysis. Individually, the proposed system improves the existing F-scores for all the emotions except surprise. The findings of BIBREF15 also support this behavior (i.e. worst result for the surprise class). This could be attributed to the data scarcity and a very low agreement between the annotators for the emotion surprise. Experimental results indicate that the multi-task system which uses fine-grained information of emotion analysis helps to boost the performance of sentiment analysis. The system M1 comprises of the system S1 performing the main task (sentiment analysis) with E1 undertaking the auxiliary task (emotion analysis). Similarly, the system M2 is made up of S2 and E2 where S2 performs the main task (sentiment analysis) and E2 commits to the auxiliary task (emotion analysis). We observe that in both the situations, the auxiliary task, i.e. emotional information increases the performance of the main task, i.e. sentiment analysis when these two are jointly performed. Experimental results help us to establish the fact that emotion analysis benefits sentiment analysis. The implicit sentiment attached to the emotion words assists the multi-task system. Emotion such as joy and trust are inherently associated with a positive sentiment whereas, anger, disgust, fear and sadness bear a negative sentiment. Figure FIGREF21 illustrates the performance of various models for sentiment analysis. As a concrete example which justifies the utility of emotion analysis in sentiment analysis is shown below. @realMessi he is a real sportsman and deserves to be the skipper. The gold labels for the example are anticipation, joy and trust emotion with a positive sentiment. Our system S2 (single task system for sentiment analysis with primary and secondary attention) had incorrectly labeled this example with a negative sentiment and the E2 system (single task system with both primary and secondary attention for emotion analysis) had tagged it with anticipation and joy only. However, M2 i.e. the multi-task system for joint sentiment and emotion analysis had correctly classified the sentiment as positive and assigned all the correct emotion tags. It predicted the trust emotion tag, in addition to anticipation and joy (which were predicted earlier by E2). This helped M2 to correctly identify the positive sentiment of the example. The presence of emotional information helped the system to alter its sentiment decision (negative by S2) as it had better understanding of the text. A sentiment directly does not invoke a particular emotion always and a sentiment can be associated with more than one emotion. However, emotions like joy and trust are associated with positive sentiment mostly whereas, anger, disgust and sadness are associated with negative sentiment particularly. This might be the reason of the extra sentiment information not helping the multi-task system for emotion analysis and hence, a decreased performance for emotion analysis in the multi-task setting. ### Datasets, Experiments and Analysis ::: Error Analysis
We perform quantitative error analysis for both sentiment and emotion for the M2 model. Table TABREF23 shows the confusion matrix for sentiment analysis. anger,anticipation,fear,disgust,joy,sadness,surprise,trust consist of the confusion matrices for anger, anticipation, fear, disgust, joy, sadness, surprise and trust. We observe from Table TABREF23 that the system fails to label many instances with the emotion surprise. This may be due to the reason that this particular class is the most underrepresented in the training set. A similar trend can also be observed for the emotion fear and trust in Table TABREF23 and Table TABREF23, respectively. These three emotions have the least share of training instances, making the system less confident towards these emotions. Moreover, we closely analyze the outputs to understand the kind of errors that our proposed model faces. We observe that the system faces difficulties at times and wrongly predicts the sentiment class in the following scenarios: $\bullet $ Often real-world phrases/sentences have emotions of conflicting nature. These conflicting nature of emotions are directly not evident from the surface form and are left unsaid as these are implicitly understood by humans. The system gets confused when presented with such instances. Text: When you become a father you realize that you are not the most important person in the room anymore... Your child is! Actual Sentiment: positive Actual Emotion: anticipation, joy, surprise, trust Predicted Sentiment: negative Predicted Emotion: anger, anticipation, sadness The realization of not being the most important person in a room invokes anger, anticipation and sadness emotions, and a negative sentiment. However, it is a natural feeling of overwhelmingly positive sentiment when you understand that your own child is the most significant part of your life. $\bullet $ Occasionally, the system focuses on the less significant part of the sentences. Due to this the system might miss crucial information which can influence and even change the final sentiment or emotion. This sometimes lead to the incorrect prediction of the overall sentiment and emotion. Text: I've been called many things, quitter is not one of them... Actual Sentiment: positive Actual Emotion: anticipation, joy, trust Predicted Sentiment: negative Predicted Emotion: anticipation, sadness Here, the system focuses on the first part of the sentence where the speaker was called many things which denotes a negative sentiment. Hence, the system predicts a negative sentiment and, anticipation and sadness emotions. However, the speaker in the second part uplifts the overall tone by justifying that s/he has never been called a quitter. This changes the negative sentiment to a positive sentiment and the overall emotion. ### Conclusion
In this paper, we have presented a novel two-layered multi-task attention based neural network which performs sentiment analysis through emotion analysis. The primary attention mechanism of the two-layered multi-task system relies on Distributional Thesaurus which acts as a source of external knowledge. The system hierarchically builds the final representation from the word level to the sentence level. This provides a working insight to the system and its ability to handle the unseen words. Evaluation on the benchmark dataset suggests an improvement of 3.2 F-score point for sentiment analysis and an overall performance boost of 5 F-score points for emotion analysis over the existing state-of-the-art systems. The system empirically establishes the fact that emotion analysis is both useful and relevant to sentiment analysis. The proposed system does not rely on any language dependent features or lexicons. This makes it extensible to other languages as well. In future, we would like to extend the two-layered multi-task attention based neural network to other languages. ### Acknowledgements
Asif Ekbal acknowledges the Young Faculty Research Fellowship (YFRF), supported by Visvesvaraya PhD scheme for Electronics and IT, Ministry of Electronics and Information Technology (MeitY), Government of India, being implemented by Digital India Corporation (formerly Media Lab Asia). Fig. 1. Two-layered multi-task attention based network TABLE I DATASET STATISTICS OF SEMEVAL 2016 TASK 6 AND SSEC USED FOR SENTIMENT AND EMOTION ANALYSIS, RESPECTIVELY. TABLE II F-SCORE OF VARIOUS MODELS ON SENTIMENT AND EMOTION TEST DATASET. TABLE III COMPARISON WITH THE STATE-OF-THE-ART SYSTEMS OF SEMEVAL 2016 TASK 6 ON SENTIMENT DATASET. Fig. 2. Comparison of various models (S1, S2, M1, M2) w.r.t different hidden state vector sizes of BiLSTM for sentiment analysis. Y-axis denotes the Fscores. TABLE IV COMPARISON WITH THE STATE-OF-THE-ART SYSTEMS PROPOSED BY [16] ON EMOTION DATASET. THE METRICS P, R AND F STAND FOR PRECISION, RECALL AND F1-SCORE. TABLE XI CONFUSION MATRIX FOR sadness
|
The proposed system consists of a Bi-directional Long Short-Term Memory (BiLSTM) BIBREF16, a two-level attention mechanism BIBREF29, BIBREF30 and a shared representation for emotion and sentiment analysis tasks., Each of the shared representations is then fed to the primary attention mechanism
|
What would likely happen if Harris begins legally selling women's eggs?
A. he would have an influx of buyers
B. he would have more egg donors than egg buyers
C. he would make millions off of commissions
D. no one would show interest in his website
|
eBabe This week, soft-porn entrepreneur Ron Harris began auctioning the eggs of fashion models on the Internet. His site, ronsangels.com (named after the 1970s' babe show Charlie's Angels ), invites visitors to "bid on eggs from beautiful, healthy and intelligent women." Like Dr. Richard Seed, who recently declared his intention to clone human beings, Harris has attracted the attention of the media and politicians who are "looking into" whether he can be stopped. Most people agree that Harris is a creep and that his site is an outrage. What they don't agree on is why. Here's what the critics have to say about the auction--and each other. 1. Egg auctions will produce designer babies. Harris cites his experience as a horse breeder and asks, "We bid for everything else in this society--why not eggs?" Alarmists, agreeing that Harris "can put you into your own designer baby by selling eggs," predict that his success will steer "the future of human breeding" toward "genetic engineering." 2. Egg auctions will fail to produce designer babies. While fretting about what will happen if Harris succeeds, fertility experts simultaneously debunk that scenario. "Not only is it ethically ludicrous, but the fact is, no kid's going to look like the model's picture," observes ethicist George Annas. The experts give four reasons. First, the child of an ugly man and a pretty woman is just as likely to be ugly as to be pretty. Second, everyone carries "recessive" genes, which are invisible in this generation but may become visible in the next. A model with a small nose can pass on genes for a big nose. Third, even if both parents are attractive, a child can combine their features unattractively. For example, a girl can inherit her mother's weak nose and her father's strong brow. 3. Egg auctions will promote the survival of the fittest. Doomsayers predict that once "beautiful eggs are available strictly to people who are willing to spend an ungodly sum for them," the rich will transform themselves into a "super-race" reminiscent of the Nazis. To this, Harris replies, "It is not our intention to suggest that we make a super society of only beautiful people. This site simply mirrors our current society, in that beauty usually goes to the highest bidder." But this reply only fuels concern that gradually, society will separate into "genetic haves and have nots." 4. Egg auctions will promote the survival of the unfittest. Harris writes that only men with "substantial financial resources" are fit to give his models' offspring "a financially secure and stable life." But skeptics wonder whether women who sell their eggs to the highest bidder--and men who buy these eggs for the sole purpose of spawning good-looking children--may produce children just as dysfunctional as themselves. As Calgary Sun columnist Sydney Sharpe put it, "Any woman ... who enters into this mephistophelian pact has a few screws loose. Maybe her kid will, too. Not to mention the buyers who sign her up." 5. Egg auctions will fail to promote the survival of the unfittest. Many models, if not most, have had cosmetic surgery. A model who is perfectly ruthless will conceal this fact when selling her eggs. (One of Harris' "angels" has already been caught lying about her age.) How does Harris know whether his models have had collagen injections and nose jobs? "There's no way to know that. You can ask the girl and hope she tells you the truth," he says. Annas concludes that since there's "no way to know how much of their beauty is a product of their genes, plastic surgery, a makeup artist, or exercise," only a "naive" person would buy their eggs on the basis of the photographs displayed on the site. "You don't want to see the models," he points out. "You want to see pictures of their parents." On this theory, children produced by the egg auction are likely to be the offspring of liars on one side and fools on the other. 6. Beauty doesn't convey health. Harris casually asserts that beauty "shows healthiness and longevity." On his site, he writes, " 'Natural Selection' is choosing genes that are healthy and beautiful." Skeptics question this assumed equivalence, noting that traits men find attractive in women these days--thinness, for example--are often unhealthy. When asked on the Today show how much "medical screening" he has given his egg donors, Harris answered, "None." 7. Beauty is less meaningful than intelligence. Harris says he's not the first person to market good genes. Others, he notes, have sold sperm and solicited eggs on the basis of the donor's intelligence. Harris' detractors reply that beauty is "superficial" and conveys a "harmful preoccupation with exterior appearances over intelligence and content of character." This critique is usually offered by a blow-dried TV interviewer who, after thanking Harris for his time, urges viewers to stay tuned for the movie starlet who will join the program after a brief commercial break. 8. Beauty is less useful than intelligence. Harris advertises beauty not as an end but as a means to "success," since people who are physically desirable get more attention, power, and favorable treatment. Having chided Harris for exalting social advantage over "character," critics turn around and adopt his ruthless logic. While conceding that beauty is useful, they argue that intelligence is a better weapon in today's meritocratic information economy--and that although Harris claims his models are "beautiful, healthy and intelligent," he offers no evidence of brains, such as IQ or SAT scores. London's Independent envisions "Bimbo births." A fertility expert shrugs, "If people want to spend $150,000 for the eggs of a gorgeous woman who has an IQ of 68, let them." 9. The auction exploits desperate buyers. Harris preaches pure capitalism, saying it's "unfair to put a limit on a girl's ability to make money" by auctioning her eggs. In turn, fertility clinic operators accuse Harris of "taking advantage of couples trying to conceive" and exploiting "desperate people ... susceptible to the dreams he is trying to sell." USA Today laments, "This is about human need. And human greed." 10. The auction exploits desperate sellers. By late Monday, Harris had only a handful of bids, and only one was verified as legitimate. On the other hand, 50 women had asked him to put their eggs up for auction. Gradually, the media concluded that the donors were the true victims. USA Today described the models as "struggling actresses," reported that they were unaware of the health risks of donating eggs, and quoted one as saying, "I'd rather do this than do Playboy or Penthouse ." Harris' sole verified bidder told the paper that selling eggs was "better than prostitution." Harris constantly refers to the donors as his "girls" and describes them like cattle--"We have a legitimate bid of $42,000 on one of the girls." He gets a 20 percent commission on each winning bid, though he takes no responsibility for executing financial transactions or medical procedures. "We have no control over the quality, safety or legality of the items advertised, the truth or accuracy of the listings, the ability of sellers to sell items or the ability of buyers to buy items," he stipulates. His role, he explains, is simply to "find beautiful girls, take beautiful photographs of them, [and] put them up on the Web." To some critics, the mystery isn't, as Harris suggests, how women throughout history have exploited their sexual power over men, but how pimps like him have come away with the profit. 11. The auction exploits voyeurs. The Washington Post thinks Harris isn't targeting either buyers or sellers. He's not serious about selling eggs, says the Post . He's just using the sex appeal of his models and the intriguing perversity of a human egg auction to drum up publicity and attract Internet traffic to his site, from which he can sell advertising and subscriptions ($24.95 a month to view profiles of the models), hawk his forthcoming book ( Naked Power ), and direct prurient visitors to his various porn sites. A spokesman for fertility doctors suspects that ronsangels.com is really aimed at "adolescent boys." 12. The Internet facilitates monstrous purchases. Technology watchdogs call the egg auction another chapter in the cultural slide marked by Jennycam (a Web site featuring live video of a young woman undressing and doing other normal activities in her apartment), the promised Webcast of a man and woman losing their virginity together (which turned out to be a hoax), and a human kidney auction that was conducted and aborted on eBay last month. "Ever since the Internet, it seems to snowball more rapidly, this depersonalization of people and selling of eggs," one fertility expert complains to the New York Times . USA Today says the egg auction "just might force an Internet-obsessed society to finally sit down and ask itself: Where is the Internet taking us?" 13. The Internet cheats people of their monstrous purchases. The only thing worse than buying human eggs on the Internet, according to the critics, is not getting the eggs you paid for. "When you have large transactions of this kind conducted over the Internet, there may be fraud," a computer crime expert warns USA Today . Lori Andrews, a reproductive technology lawyer, warns CNN viewers that "there's very little that you can do to prove that these eggs actually came from the donors that were expected," and "the Internet just adds ... a layer that it makes it even more difficult to scrutinize where the eggs are coming from." 14. Egg buyers will reap unintended consequences. Sophisticated skeptics point out that Harris' application of Darwin's theories to human professional success overlooks the interaction of genetics and human psychology. To begin with, if a child produced by Harris' auction fails to turn out as pretty as the buyer expected, the buyer may shun the child, or the child may grow to hate herself for disappointing her parents. (On the Today show, Harris said of this theory, "That's a pretty cynical view of human nature.") Second, if the child turns out pretty but doesn't want to be a beauty queen, her parents may force her in that direction anyway, thereby stifling her true talents and preventing her from becoming successful. Third, the child's good looks may attract too much attention of the wrong kind, eventually destroying her. Critics cite Elvis Presley and Marilyn Monroe as examples. 15. Other people's eggs don't pass on your genes. In defense of his auction, Harris quotes author Helen Fisher's statement that "having sex is the most important act of your life. This is how we get our genes to the next generation." But Harris seems to have overlooked the crucial words: "our genes." "The drive to send your own genes into tomorrow is much stronger than the [drive] to pick out of a sperm bank or egg site," Fisher observes. This consideration may not affect single men, but it can be a decisive turnoff for couples. On this view, Harris' mistake is not that he focuses too much on selfishness, but that he neglects it. He forgets that you don't care about reproducing unless what you're reproducing is yourself. 16. The power of beauty should be transcended, not exploited. Harris preaches that the world rewards beauty because it's human nature to favor those who are pleasant to look at, and therefore the way to have successful children is to make sure they're attractive. The most ambitious response is to attack the whole "prejudice" in favor of beauty. "The standards of beauty do vary with the culture. And they are social facts, not really genetics facts," says Hastings Center ethicist Bruce Jennings. Therefore, "we should think about" whether to "accept the existing prejudices and then try to eugenically manipulate them" or to transcend those prejudices. This critique challenges two precepts of Harris' worldview. First, while pretending to accept human nature as a given, he violates it by peddling strangers' eggs and encouraging the production of children who will probably never know their mothers. Family association, loyalty, and love are among the best parts of human nature. Slavish catering to physically attractive strangers is among the worst. If we're going to challenge human nature, the critics ask, why not start with the latter rather than the former? Second, Harris assumes that the perfection parents want in their children coincides with Darwinian perfection. "Every organism is trying to evolve to its most perfect state," he writes. What he doesn't seem to understand is that human beings aren't quite like other animals, just as the rest of the world isn't exactly like the modeling and soft-porn industries of Southern California. Humans have evolved to a stage at which our ideas about virtue, perfection, and success have become more than material. At least, most of us have.
|
B. he would have more egg donors than egg buyers
|
How often are the newspaper websites crawled daily?
|
### Introduction: New Words, NLP and the Logoscope
Like other areas of linguistics, the study of new words has benefited from the development of natural language processing techniques in the last twenty years. In this research area, the digital revolution has significantly changed the way to collect the data necessary for empirical research BIBREF0 , BIBREF1 : The traditional practice of collecting new words by reading texts (newspapers, literature, scientific and technical texts, etc.), has been supplemented by an automatisation of the collection process. In fact, today there are many computer tools capable of searching through large amounts of texts (often newspapers) in order to automatically detect the newly created words in various languages (German, Catalan, Spanish, English, French, etc.). ### General Description of the Logoscope Framework
The main building block of the Logoscope framework consists of a continuously updated lexical resource containing unknown words, their occurrences in French online press articles and further morpho-syntactic and contextual documentation. In addition our system features a query interface which allows an open access to this knowledge base. ### New Words are Collected in Three Stages
The Logoscope is built in three stages (see Figure FIGREF6 ). The first stage consists in the automatic detection of the unknown words. In the second stage the detected unknown words are manually validated, that is, a human expert decides which of them are genuine word creations. Finally, in the third stage these validated unknown words are documented. This is done firstly by manually adding morpho-syntactic features and information on the originating creation process. This information is automatically complemented by contextual information, typically e.g the journal and the paragraph the new words appeared in. But, in contrast to other similar systems (see Section SECREF32 ), the Logoscope also (automatically) gives a rough approximation of what the article containing the new word is about. In the next sections we will first give a more detailed description of each of these three stages before briefly addressing how the Logoscope might be used through its web interface in Section SECREF30 . A more detailed report of the arising NLP challenges and the methods we used to tackle them will be presented in Section SECREF5 . ### Stage 1: Detection of Unknown Words
The Logoscope retrieves newspaper articles from several RSS feeds in French on a daily basis. The newspaper articles are preprocessed such that only the journalistic content is kept. The articles are then segmented into paragraphs and word forms. The resulting forms are filtered based on an exclusion list (French words found in several lexicons and corpora). They are then reordered in such a way that those words which are the most likely new word candidates appear on top, using a supervised classification method which will be described more in detail in Section SECREF71 . Figure 1. Processing stages in the Logoscope. Figure 3. Sample csv (comma separated values) file showing the result of the validation process for the unknown words detected on 2015-01-02. Figure 4. Documentation of the new word lumbersexuel. Figure 5. Query page of the Logoscope browser-based application. Table 1. Lexical categories documented by The Logoscope. Figure 6. Contextual parameters for the description of new words. The parameters set in boldface are those documented in the Logoscope framework. Figure 7. Example of a thematic analysis on a Le Monde article (25-12-2015). According to this analysis, the text is principally about a societal topic, but it also employs many words related to the theme of defense in an international context. Within the main topic, the most important subject was found to be about “mythologies, religion and believes”. In our view, this analysis gives a reasonably good idea about the overall subject of the text, even if it is far from showing anything about the exact content. Table 3. Overview of features used in the classification task. Table 4. Classification results. In green (blue) best respectively worst F-measure and true positive results. Best balanced results highlighted in orange. Overall best precision, recall and Fmeasure results are set in bold face. Table 6. Top 5 predictions when applying the model. Figure 8. Words with highest probabilities in some topics acquired by applying Latent Dirichlet Allocation to the Le Monde corpus. Topic 0 and Topic 2 are examples of meaningful topics in our setting, which could be labeled easily. In contrast Topic 19 shows a topic which could hardly be used for representing the content of newspaper articles. Figure 9. Examples of resulting themes: Economie-Finance (economy and finance) and DroitJusticeLegislation (law, justice, legislation). Figure 10. Observing the thematic context in which word creation occurs. The figures are screenshots obtained from the online version of the Logoscope (http://logoscope.unistra. fr/topic/). Figure 11. Occurences of new words bitcoin and ethers in the Logoscope vs. lookups in the Wiktionary. Table 7. Examples of cultural specific and non-cultural specific new words added in dictionaries between 2014 and 2016.
|
RSS feeds in French on a daily basis
|
What wasn't an issue their bodies were going through?
A. dehydration
B. malnutrition
C. headaches
D. irritation
|
Brightside Crossing by Alan E. Nourse JAMES BARON was not pleased to hear that he had had a visitor when he reached the Red Lion that evening. He had no stomach for mysteries, vast or trifling, and there were pressing things to think about at this time. Yet the doorman had flagged him as he came in from the street: “A thousand pardons, Mr. Baron. The gentleman—he would leave no name. He said you’d want to see him. He will be back by eight.” Now Baron drummed his fingers on the table top, staring about the quiet lounge. Street trade was discouraged at the Red Lion, gently but persuasively; the patrons were few in number. Across to the right was a group that Baron knew vaguely—Andean climbers, or at least two of them were. Over near the door he recognized old Balmer, who had mapped the first passage to the core of Vulcan Crater on Venus. Baron returned his smile with a nod. Then he settled back and waited impatiently for the intruder who demanded his time without justifying it. Presently a small, grizzled man crossed the room and sat down at Baron’s table. He was short and wiry. His face held no key to his age—he might have been thirty or a thousand—but he looked weary and immensely ugly. His cheeks and forehead were twisted and brown, with scars that were still healing. The stranger said, “I’m glad you waited. I’ve heard you’re planning to attempt the Brightside.” Baron stared at the man for a moment. “I see you can read telecasts,” he said coldly. “The news was correct. We are going to make a Brightside Crossing.” “At perihelion?” “Of course. When else?” The grizzled man searched Baron’s face for a moment without expression. Then he said slowly, “No, I’m afraid you’re not going to make the Crossing.” “Say, who are you, if you don’t mind?” Baron demanded. “The name is Claney,” said the stranger. There was a silence. Then: “Claney? Peter Claney?” “That’s right.” Baron’s eyes were wide with excitement, all trace of anger gone. “Great balls of fire, man— where have you been hiding? We’ve been trying to contact you for months!” “I know. I was hoping you’d quit looking and chuck the whole idea.” “Quit looking!” Baron bent forward over the table. “My friend, we’d given up hope, but we’ve never quit looking. Here, have a drink. There’s so much you can tell us.” His fingers were trembling. Peter Claney shook his head. “I can’t tell you anything you want to hear.” “But you’ve got to. You’re the only man on Earth who’s attempted a Brightside Crossing and lived through it! And the story you cleared for the news—it was nothing. We need details . Where did your equipment fall down? Where did you miscalculate? What were the trouble spots?” Baron jabbed a finger at Claney’s face. “That, for instance—epithelioma? Why? What was wrong with your glass? Your filters? We’ve got to know those things. If you can tell us, we can make it across where your attempt failed—” “You want to know why we failed?” asked Claney. “Of course we want to know. We have to know.” “It’s simple. We failed because it can’t be done. We couldn’t do it and neither can you. No human beings will ever cross the Brightside alive, not if they try for centuries.” “Nonsense,” Baron declared. “We will.” Claney shrugged. “I was there. I know what I’m saying. You can blame the equipment or the men—there were flaws in both quarters—but we just didn’t know what we were fighting. It was the planet that whipped us, that and the Sun . They’ll whip you, too, if you try it.” “Never,” said Baron. “Let me tell you,” Peter Claney said. I’d been interested in the Brightside for almost as long as I can remember (Claney said). I guess I was about ten when Wyatt and Carpenter made the last attempt—that was in 2082, I think. I followed the news stories like a tri-V serial and then I was heartbroken when they just disappeared. I know now that they were a pair of idiots, starting off without proper equipment, with practically no knowledge of surface conditions, without any charts—they couldn’t have made a hundred miles—but I didn’t know that then and it was a terrible tragedy. After that, I followed Sanderson’s work in the Twilight Lab up there and began to get Brightside into my blood, sure as death. But it was Mikuta’s idea to attempt a Crossing. Did you ever know Tom Mikuta? I don’t suppose you did. No, not Japanese—Polish-American. He was a major in the Interplanetary Service for some years and hung onto the title after he gave up his commission. He was with Armstrong on Mars during his Service days, did a good deal of the original mapping and surveying for the Colony there. I first met him on Venus; we spent five years together up there doing some of the nastiest exploring since the Matto Grasso. Then he made the attempt on Vulcan Crater that paved the way for Balmer a few years later. I’d always liked the Major—he was big and quiet and cool, the sort of guy who always had things figured a little further ahead than anyone else and always knew what to do in a tight place. Too many men in this game are all nerve and luck, with no judgment. The Major had both. He also had the kind of personality that could take a crew of wild men and make them work like a well-oiled machine across a thousand miles of Venus jungle. I liked him and I trusted him. He contacted me in New York and he was very casual at first. We spent an evening here at the Red Lion, talking about old times; he told me about the Vulcan business, and how he’d been out to see Sanderson and the Twilight Lab on Mercury, and how he preferred a hot trek to a cold one any day of the year—and then he wanted to know what I’d been doing since Venus and what my plans were. “No particular plans,” I told him. “Why?” He looked me over. “How much do you weigh, Peter?” I told him one-thirty-five. “That much!” he said. “Well, there can’t be much fat on you, at any rate. How do you take heat?” “You should know,” I said. “Venus was no icebox.” “No, I mean real heat.” Then I began to get it. “You’re planning a trip.” “That’s right. A hot trip.” He grinned at me. “Might be dangerous, too.” “What trip?” “Brightside of Mercury,” the Major said. I whistled cautiously. “At aphelion?” He threw his head back. “Why try a Crossing at aphelion? What have you done then? Four thousand miles of butcherous heat, just to have some joker come along, use your data and drum you out of the glory by crossing at perihelion forty-four days later? No, thanks. I want the Brightside without any nonsense about it.” He leaned across me eagerly. “I want to make a Crossing at perihelion and I want to cross on the surface. If a man can do that, he’s got Mercury. Until then, nobody’s got Mercury. I want Mercury—but I’ll need help getting it.” I’d thought of it a thousand times and never dared consider it. Nobody had, since Wyatt and Carpenter disappeared. Mercury turns on its axis in the same time that it wheels around the Sun, which means that the Brightside is always facing in. That makes the Brightside of Mercury at perihelion the hottest place in the Solar System, with one single exception: the surface of the Sun itself. It would be a hellish trek. Only a few men had ever learned just how hellish and they never came back to tell about it. It was a real hell’s Crossing, but someday, I thought, somebody would cross it. I wanted to be along. The Twilight Lab, near the northern pole of Mercury, was the obvious jumping-off place. The setup there wasn’t very extensive—a rocket landing, the labs and quarters for Sanderson’s crew sunk deep into the crust, and the tower that housed the Solar ’scope that Sanderson had built up there ten years before. Twilight Lab wasn’t particularly interested in the Brightside, of course—the Sun was Sanderson’s baby and he’d picked Mercury as the closest chunk of rock to the Sun that could hold his observatory. He’d chosen a good location, too. On Mercury, the Brightside temperature hits 770° F. at perihelion and the Darkside runs pretty constant at -410° F. No permanent installation with a human crew could survive at either extreme. But with Mercury’s wobble, the twilight zone between Brightside and Darkside offers something closer to survival temperatures. Sanderson built the Lab up near the pole, where the zone is about five miles wide, so the temperature only varies 50 to 60 degrees with the libration. The Solar ’scope could take that much change and they’d get good clear observation of the Sun for about seventy out of the eighty-eight days it takes the planet to wheel around. The Major was counting on Sanderson knowing something about Mercury as well as the Sun when we camped at the Lab to make final preparations. Sanderson did. He thought we’d lost our minds and he said so, but he gave us all the help he could. He spent a week briefing Jack Stone, the third member of our party, who had arrived with the supplies and equipment a few days earlier. Poor Jack met us at the rocket landing almost bawling, Sanderson had given him such a gloomy picture of what Brightside was like. Stone was a youngster—hardly twenty-five, I’d say—but he’d been with the Major at Vulcan and had begged to join this trek. I had a funny feeling that Jack really didn’t care for exploring too much, but he thought Mikuta was God, followed him around like a puppy. It didn’t matter to me as long as he knew what he was getting in for. You don’t go asking people in this game why they do it—they’re liable to get awfully uneasy and none of them can ever give you an answer that makes sense. Anyway, Stone had borrowed three men from the Lab, and had the supplies and equipment all lined up when we got there, ready to check and test. We dug right in. With plenty of funds—tri-V money and some government cash the Major had talked his way around—our equipment was new and good. Mikuta had done the designing and testing himself, with a big assist from Sanderson. We had four Bugs, three of them the light pillow-tire models, with special lead-cooled cut-in engines when the heat set in, and one heavy-duty tractor model for pulling the sledges. The Major went over them like a kid at the circus. Then he said, “Have you heard anything from McIvers?” “Who’s he?” Stone wanted to know. “He’ll be joining us. He’s a good man—got quite a name for climbing, back home.” The Major turned to me. “You’ve probably heard of him.” I’d heard plenty of stories about Ted McIvers and I wasn’t too happy to hear that he was joining us. “Kind of a daredevil, isn’t he?” “Maybe. He’s lucky and skillful. Where do you draw the line? We’ll need plenty of both.” “Have you ever worked with him?” I asked. “No. Are you worried?” “Not exactly. But Brightside is no place to count on luck.” The Major laughed. “I don’t think we need to worry about McIvers. We understood each other when I talked up the trip to him and we’re going to need each other too much to do any fooling around.” He turned back to the supply list. “Meanwhile, let’s get this stuff listed and packed. We’ll need to cut weight sharply and our time is short. Sanderson says we should leave in three days.” Two days later, McIvers hadn’t arrived. The Major didn’t say much about it. Stone was getting edgy and so was I. We spent the second day studying charts of the Brightside, such as they were. The best available were pretty poor, taken from so far out that the detail dissolved into blurs on blow-up. They showed the biggest ranges of peaks and craters and faults, and that was all. Still, we could use them to plan a broad outline of our course. “This range here,” the Major said as we crowded around the board, “is largely inactive, according to Sanderson. But these to the south and west could be active. Seismograph tracings suggest a lot of activity in that region, getting worse down toward the equator—not only volcanic, but sub-surface shifting.” Stone nodded. “Sanderson told me there was probably constant surface activity.” The Major shrugged. “Well, it’s treacherous, there’s no doubt of it. But the only way to avoid it is to travel over the Pole, which would lose us days and offer us no guarantee of less activity to the west. Now we might avoid some if we could find a pass through this range and cut sharp east—” It seemed that the more we considered the problem, the further we got from a solution. We knew there were active volcanoes on the Brightside—even on the Darkside, though surface activity there was pretty much slowed down and localized. But there were problems of atmosphere on Brightside, as well. There was an atmosphere and a constant atmospheric flow from Brightside to Darkside. Not much—the lighter gases had reached escape velocity and disappeared from Brightside millennia ago—but there was CO 2 , and nitrogen, and traces of other heavier gases. There was also an abundance of sulfur vapor, as well as carbon disulfide and sulfur dioxide. The atmospheric tide moved toward the Darkside, where it condensed, carrying enough volcanic ash with it for Sanderson to estimate the depth and nature of the surface upheavals on Brightside from his samplings. The trick was to find a passage that avoided those upheavals as far as possible. But in the final analysis, we were barely scraping the surface. The only way we would find out what was happening where was to be there. Finally, on the third day, McIvers blew in on a freight rocket from Venus. He’d missed the ship that the Major and I had taken by a few hours, and had conned his way to Venus in hopes of getting a hop from there. He didn’t seem too upset about it, as though this were his usual way of doing things and he couldn’t see why everyone should get so excited. He was a tall, rangy man with long, wavy hair prematurely gray, and the sort of eyes that looked like a climber’s—half-closed, sleepy, almost indolent, but capable of abrupt alertness. And he never stood still; he was always moving, always doing something with his hands, or talking, or pacing about. Evidently the Major decided not to press the issue of his arrival. There was still work to do, and an hour later we were running the final tests on the pressure suits. That evening, Stone and McIvers were thick as thieves, and everything was set for an early departure after we got some rest. “And that,” said Baron, finishing his drink and signaling the waiter for another pair, “was your first big mistake.” Peter Claney raised his eyebrows. “McIvers?” “Of course.” Claney shrugged, glanced at the small quiet tables around them. “There are lots of bizarre personalities around a place like this, and some of the best wouldn’t seem to be the most reliable at first glance. Anyway, personality problems weren’t our big problem right then. Equipment worried us first and route next.” Baron nodded in agreement. “What kind of suits did you have?” “The best insulating suits ever made,” said Claney. “Each one had an inner lining of a fiberglass modification, to avoid the clumsiness of asbestos, and carried the refrigerating unit and oxygen storage which we recharged from the sledges every eight hours. Outer layer carried a monomolecular chrome reflecting surface that made us glitter like Christmas trees. And we had a half-inch dead-air space under positive pressure between the two layers. Warning thermocouples, of course—at 770 degrees, it wouldn’t take much time to fry us to cinders if the suits failed somewhere.” “How about the Bugs?” “They were insulated, too, but we weren’t counting on them too much for protection.” “You weren’t!” Baron exclaimed. “Why not?” “We’d be in and out of them too much. They gave us mobility and storage, but we knew we’d have to do a lot of forward work on foot.” Claney smiled bitterly. “Which meant that we had an inch of fiberglass and a half-inch of dead air between us and a surface temperature where lead flowed like water and zinc was almost at melting point and the pools of sulfur in the shadows were boiling like oatmeal over a campfire.” Baron licked his lips. His fingers stroked the cool, wet glass as he set it down on the tablecloth. “Go on,” he said tautly. “You started on schedule?” “Oh, yes,” said Claney, “we started on schedule, all right. We just didn’t quite end on schedule, that was all. But I’m getting to that.” He settled back in his chair and continued. We jumped off from Twilight on a course due southeast with thirty days to make it to the Center of Brightside. If we could cross an average of seventy miles a day, we could hit Center exactly at perihelion, the point of Mercury’s closest approach to the Sun—which made Center the hottest part of the planet at the hottest it ever gets. The Sun was already huge and yellow over the horizon when we started, twice the size it appears on Earth. Every day that Sun would grow bigger and whiter, and every day the surface would get hotter. But once we reached Center, the job was only half done—we would still have to travel another two thousand miles to the opposite twilight zone. Sanderson was to meet us on the other side in the Laboratory’s scout ship, approximately sixty days from the time we jumped off. That was the plan, in outline. It was up to us to cross those seventy miles a day, no matter how hot it became, no matter what terrain we had to cross. Detours would be dangerous and time-consuming. Delays could cost us our lives. We all knew that. The Major briefed us on details an hour before we left. “Peter, you’ll take the lead Bug, the small one we stripped down for you. Stone and I will flank you on either side, giving you a hundred-yard lead. McIvers, you’ll have the job of dragging the sledges, so we’ll have to direct your course pretty closely. Peter’s job is to pick the passage at any given point. If there’s any doubt of safe passage, we’ll all explore ahead on foot before we risk the Bugs. Got that?” McIvers and Stone exchanged glances. McIvers said: “Jack and I were planning to change around. We figured he could take the sledges. That would give me a little more mobility.” The Major looked up sharply at Stone. “Do you buy that, Jack?” Stone shrugged. “I don’t mind. Mac wanted—” McIvers made an impatient gesture with his hands. “It doesn’t matter. I just feel better when I’m on the move. Does it make any difference?” “I guess it doesn’t,” said the Major. “Then you’ll flank Peter along with me. Right?” “Sure, sure.” McIvers pulled at his lower lip. “Who’s going to do the advance scouting?” “It sounds like I am,” I cut in. “We want to keep the lead Bug light as possible.” Mikuta nodded. “That’s right. Peter’s Bug is stripped down to the frame and wheels.” McIvers shook his head. “No, I mean the advance work. You need somebody out ahead—four or five miles, at least—to pick up the big flaws and active surface changes, don’t you?” He stared at the Major. “I mean, how can we tell what sort of a hole we may be moving into, unless we have a scout up ahead?” “That’s what we have the charts for,” the Major said sharply. “Charts! I’m talking about detail work. We don’t need to worry about the major topography. It’s the little faults you can’t see on the pictures that can kill us.” He tossed the charts down excitedly. “Look, let me take a Bug out ahead and work reconnaissance, keep five, maybe ten miles ahead of the column. I can stay on good solid ground, of course, but scan the area closely and radio back to Peter where to avoid the flaws. Then—” “No dice,” the Major broke in. “But why not? We could save ourselves days!” “I don’t care what we could save. We stay together. When we get to the Center, I want live men along with me. That means we stay within easy sight of each other at all times. Any climber knows that everybody is safer in a party than one man alone—any time, any place.” McIvers stared at him, his cheeks an angry red. Finally he gave a sullen nod. “Okay. If you say so.” “Well, I say so and I mean it. I don’t want any fancy stuff. We’re going to hit Center together, and finish the Crossing together. Got that?” McIvers nodded. Mikuta then looked at Stone and me and we nodded, too. “All right,” he said slowly. “Now that we’ve got it straight, let’s go.” It was hot. If I forget everything else about that trek, I’ll never forget that huge yellow Sun glaring down, without a break, hotter and hotter with every mile. We knew that the first few days would be the easiest and we were rested and fresh when we started down the long ragged gorge southeast of the Twilight Lab. I moved out first; back over my shoulder, I could see the Major and McIvers crawling out behind me, their pillow tires taking the rugged floor of the gorge smoothly. Behind them, Stone dragged the sledges. Even at only 30 per cent Earth gravity they were a strain on the big tractor, until the ski-blades bit into the fluffy volcanic ash blanketing the valley. We even had a path to follow for the first twenty miles. I kept my eyes pasted to the big polaroid binocs, picking out the track the early research teams had made out into the edge of Brightside. But in a couple of hours we rumbled past Sanderson’s little outpost observatory and the tracks stopped. We were in virgin territory and already the Sun was beginning to bite. We didn’t feel the heat so much those first days out. We saw it. The refrig units kept our skins at a nice comfortable seventy-five degrees Fahrenheit inside our suits, but our eyes watched that glaring Sun and the baked yellow rocks going past, and some nerve pathways got twisted up, somehow. We poured sweat as if we were in a superheated furnace. We drove eight hours and slept five. When a sleep period came due, we pulled the Bugs together into a square, threw up a light aluminum sun-shield and lay out in the dust and rocks. The sun-shield cut the temperature down sixty or seventy degrees, for whatever help that was. And then we ate from the forward sledge—sucking through tubes—protein, carbohydrates, bulk gelatin, vitamins. The Major measured water out with an iron hand, because we’d have drunk ourselves into nephritis in a week otherwise. We were constantly, unceasingly thirsty. Ask the physiologists and psychiatrists why—they can give you have a dozen interesting reasons—but all we knew, or cared about, was that it happened to be so. We didn’t sleep the first few stops, as a consequence. Our eyes burned in spite of the filters and we had roaring headaches, but we couldn’t sleep them off. We sat around looking at each other. Then McIvers would say how good a beer would taste, and off we’d go. We’d have murdered our grandmothers for one ice-cold bottle of beer. After a few driving periods, I began to get my bearings at the wheel. We were moving down into desolation that made Earth’s old Death Valley look like a Japanese rose garden. Huge sun-baked cracks opened up in the floor of the gorge, with black cliffs jutting up on either side; the air was filled with a barely visible yellowish mist of sulfur and sulfurous gases. It was a hot, barren hole, no place for any man to go, but the challenge was so powerful you could almost feel it. No one had ever crossed this land before and escaped. Those who had tried it had been cruelly punished, but the land was still there, so it had to be crossed. Not the easy way. It had to be crossed the hardest way possible: overland, through anything the land could throw up to us, at the most difficult time possible. Yet we knew that even the land might have been conquered before, except for that Sun. We’d fought absolute cold before and won. We’d never fought heat like this and won. The only worse heat in the Solar System was the surface of the Sun itself. Brightside was worth trying for. We would get it or it would get us. That was the bargain. I learned a lot about Mercury those first few driving periods. The gorge petered out after a hundred miles and we moved onto the slope of a range of ragged craters that ran south and east. This range had shown no activity since the first landing on Mercury forty years before, but beyond it there were active cones. Yellow fumes rose from the craters constantly; their sides were shrouded with heavy ash. We couldn’t detect a wind, but we knew there was a hot, sulfurous breeze sweeping in great continental tides across the face of the planet. Not enough for erosion, though. The craters rose up out of jagged gorges, huge towering spears of rock and rubble. Below were the vast yellow flatlands, smoking and hissing from the gases beneath the crust. Over everything was gray dust—silicates and salts, pumice and limestone and granite ash, filling crevices and declivities—offering a soft, treacherous surface for the Bug’s pillow tires. I learned to read the ground, to tell a covered fault by the sag of the dust; I learned to spot a passable crack, and tell it from an impassable cut. Time after time the Bugs ground to a halt while we explored a passage on foot, tied together with light copper cable, digging, advancing, digging some more until we were sure the surface would carry the machines. It was cruel work; we slept in exhaustion. But it went smoothly, at first. Too smoothly, it seemed to me, and the others seemed to think so, too. McIvers’ restlessness was beginning to grate on our nerves. He talked too much, while we were resting or while we were driving; wisecracks, witticisms, unfunny jokes that wore thin with repetition. He took to making side trips from the route now and then, never far, but a little further each time. Jack Stone reacted quite the opposite; he grew quieter with each stop, more reserved and apprehensive. I didn’t like it, but I figured that it would pass off after a while. I was apprehensive enough myself; I just managed to hide it better. And every mile the Sun got bigger and whiter and higher in the sky and hotter. Without our ultra-violet screens and glare filters we would have been blinded; as it was our eyes ached constantly and the skin on our faces itched and tingled at the end of an eight-hour trek. But it took one of those side trips of McIvers’ to deliver the penultimate blow to our already fraying nerves. He had driven down a side-branch of a long canyon running off west of our route and was almost out of sight in a cloud of ash when we heard a sharp cry through our earphones. I wheeled my Bug around with my heart in my throat and spotted him through the binocs, waving frantically from the top of his machine. The Major and I took off, lumbering down the gulch after him as fast as the Bugs could go, with a thousand horrible pictures racing through our minds.... We found him standing stock-still, pointing down the gorge and, for once, he didn’t have anything to say. It was the wreck of a Bug; an old-fashioned half-track model of the sort that hadn’t been in use for years. It was wedged tight in a cut in the rock, an axle broken, its casing split wide open up the middle, half-buried in a rock slide. A dozen feet away were two insulated suits with white bones gleaming through the fiberglass helmets. This was as far as Wyatt and Carpenter had gotten on their Brightside Crossing. On the fifth driving period out, the terrain began to change. It looked the same, but every now and then it felt different. On two occasions I felt my wheels spin, with a howl of protest from my engine. Then, quite suddenly, the Bug gave a lurch; I gunned my motor and nothing happened. I could see the dull gray stuff seeping up around the hubs, thick and tenacious, splattering around in steaming gobs as the wheels spun. I knew what had happened the moment the wheels gave and, a few minutes later, they chained me to the tractor and dragged me back out of the mire. It looked for all the world like thick gray mud, but it was a pit of molten lead, steaming under a soft layer of concealing ash. I picked my way more cautiously then. We were getting into an area of recent surface activity; the surface was really treacherous. I caught myself wishing that the Major had okayed McIvers’ scheme for an advanced scout; more dangerous for the individual, maybe, but I was driving blind now and I didn’t like it. One error in judgment could sink us all, but I wasn’t thinking much about the others. I was worried about me , plenty worried. I kept thinking, better McIvers should go than me. It wasn’t healthy thinking and I knew it, but I couldn’t get the thought out of my mind. It was a grueling eight hours and we slept poorly. Back in the Bug again, we moved still more slowly—edging out on a broad flat plateau, dodging a network of gaping surface cracks—winding back and forth in an effort to keep the machines on solid rock. I couldn’t see far ahead, because of the yellow haze rising from the cracks, so I was almost on top of it when I saw a sharp cut ahead where the surface dropped six feet beyond a deep crack. I let out a shout to halt the others; then I edged my Bug forward, peering at the cleft. It was deep and wide. I moved fifty yards to the left, then back to the right. There was only one place that looked like a possible crossing; a long, narrow ledge of gray stuff that lay down across a section of the fault like a ramp. Even as I watched it, I could feel the surface crust under the Bug trembling and saw the ledge shift over a few feet.
|
B. malnutrition
|
What isn't the gambling industry willing to do?
A. regulate online gambling
B. donate money for gambling-addiction research
C. donate money to improve other areas of Las Vegas
D. change their term to "gaming"
|
Is <A NAME= Gambling's would-be federal regulators--the National Gambling Impact Study Commission--went to Las Vegas this week to hold hearings. In today's dispatch, we learn how gambling's foes seek to demonize wagering as a pernicious tobaccolike vice. In yesterday's dispatch, gambling's foes learn the folly of having brought their anti-sin crusade to an adult Disneyland. Tuesday's overpowering show of force by the Nevada gambling aristocracy has had at least one audible effect on the National Gambling Impact Study Commission. Wednesday, even commission Chair Kay Coles James, a gambling skeptic, succumbs to the hideous Vegas euphemism: She begins referring to the "gaming industry." After Tuesday's casino triumphalism, Wednesday is a comedown, eight hours of policy panels on teen gambling, compulsive gambling, gambling regulation, gambling marketing, and gambling credit practices. It is tough slogging, but for the first time I sense that this commission--though divided, underfunded, timid, and without any power beyond exhortation--isn't entirely useless. It may finally settle this question: Is gambling Hollywood or tobacco? Entertainment or vice? The sleek Vegas types, whose Strip palaces scramble casinos, theaters, restaurants, arcades, discos, cabarets, theme parks, concert halls, sports arenas, and museums into one giant orgy of amusement, have been selling the idea that gambling is just entertainment--Disney in the desert. This effort has largely succeeded, because Vegas is still the dominant image of American gambling, if not the dominant reality. The antis, meanwhile, cry that gambling is like cigarettes: unsafe for kids, viciously addictive, deceptively marketed, unhealthy, expensive, and unacceptable unless mightily regulated. Judging by today's hearings and by conversations with most of the commissioners, the tobacco model is winning. Today's panelists tell the commission that kids are starting to gamble too young and are getting addicted too easily, that compulsive gambling appears to be increasing as gambling spreads, that gambling marketing may be designed to addict customers, and that the industry exploits problem gamblers by allowing them to draw repeated credit card advances from ATMs on casino floors. The testimony clearly impresses the commissioners and seems especially to impress the three nonaligned commissioners who will be the swing votes on the June 1999 report. It is starting to become clear what that report will say. The commission won't (and can't) take any grand stand against gambling. Instead it will opt for small, targeted policies, concentrating on compulsive gambling. It will probably propose that casinos and state lotteries fund gambling-addiction research and that casinos take much stronger measures to bar problem gamblers from wagering. The commission may recommend that gaming taxes be used to underwrite treatment of pathological gamblers and that insurance companies be encouraged to cover gambling addiction. Similarly, the commission will try to reduce gamblers' access to cash by limiting the size of ATM advances and prodding casinos to remove the machines from their floors. The commission will also push the industry to do more to prevent kids from gambling. It will call for heavier regulation of Indian gambling and will probably try to ban or severely regulate Internet gambling, perhaps by forbidding gambling companies from running online casinos. It will rebuke state lotteries for their deceptive marketing and will try to force them to post odds and stop targeting the poor. In short, it will treat gambling as a tobaccolike vice. If the comments of the pro-industry commissioners can be believed, the industry will happily endorse such a report. Gamblers don't quite accept the cigarette analogy--though commission member Bill Bible, a former chief of the Nevada Gaming Commission, did concede that gambling was like alcohol--but they're happy to sign on to the specific measures. The casino industry is even trying to get ahead of the commission. It has already established a (mostly) independent center to fund research into pathological gambling. I suspect that the industry will not only agree to the commission's recommendations but will become their strongest advocate. Casino owners will avidly lobby Congress and state legislatures to enact the recommendations into law. Why should the pro-gamblers cooperate with a critical study? Because it provides superb cover for them. It medicalizes the problem of compulsive gambling, blaming it on psychological abnormality rather than industry machination. Likewise, cracking down on compulsives is also politically cost-effective. In exchange for losing a few compulsive gamblers, the casinos will (falsely) appear more concerned with the health of their customers than with profits. The cigarette agenda will also distract the commission and the public from the true reasons for worry. A few years ago, gambling was confined to Las Vegas and Atlantic City. It is now thriving in 48 states, and there is no sign that anyone can stop it. In this election, gambling interests dropped $100 million on a single California ballot initiative, toppled governors in two states, and bought senators and representatives by the crate. What the commission ought to be investigating is whether the gambling industry has become so powerful that it's politically untouchable. But it can't, because the gambling industry has become so powerful that it's politically untouchable. The antis can call gambling "tobacco." They can call it "vice." They can call it "a big red balloon" for all that the industry cares. As long as the commission just nibbles around the edges, the casino operators and state lotteries will be happy to indulge it. The pro-gambling folks will win credit for cooperating, without having to do anything that really hurts. The last national gambling commission was in the mid-1970s. If the gamblers play along with this commission's timid recommendations, they'll be safe for another 20 years. An Apology I owe an apology to Nevada Sen. Richard Bryan, whom I criticized yesterday for using the term "Indian country" during a speech critical of Indian casinos. As several readers pointed out to me, "Indian country" is a common phrase in the West and has no derogatory connotations. I'm sorry, Senator. Talk about quick defeats: The first sign I see outside the MGM Grand ballroom all but declares that the National Gambling Impact Study Commission has already lost. The sign reads: "National Gaming Impact Study Commission." "Gaming"? In Las Vegas, the euphemizers reign. Once upon a time, the casino owners decided that "gambling" was too crude, too avaricious, to describe their fair business. So "gambling" disappeared in Las Vegas, and "gaming" has risen in its place. He who controls language controls ideas, and at today's commission hearing, it is perfectly clear who controls the language. Video slot machines crammed into convenience stores--perhaps the most pernicious form of legal gambling there is--are called "retail gaming." People who own casinos are not "casino owners," they are "gaming visionaries." Pathological gamblers are "problem gamers"--as if they're having trouble mastering the rules of Monopoly. And the National Gambling Impact Study Commission is reborn as the National Gaming Impact Study Commission. The gambling industry did everything in its power to stop the establishment of this commission two years ago, but Congress and a fervent grassroots anti-gambling group eventually foisted it on the industry. The nine member blue-ribbon panel was charged with assessing the social and economic impact of gambling, and it will issue a final report to Congress and the president in June 1999. Even though the panel was carefully balanced between pro- and anti-gambling leaders, it was supposed to be Vegas' nemesis. The industry and Las Vegas' pro-gambling media quaked in anticipation of the onerous regulations and taxes the commission might recommend. But they quake no more. Whatever national momentum the anti-gamblers had dissolved in last week's elections. The industry routed opponents in state after state. Missouri voters passed a ballot initiative to allow boat casinos. Californians voted to expand Indian casinos. In South Carolina and Alabama, voters expelled anti-lottery, anti-gambling Republican governors and replaced them with pro-lottery Democrats. The gambling industry spent more than $100 million on political contributions and issue ads. It has never been fatter, happier, or more secure. "My goodness, no politician can withstand their resources," Focus on the Family's James Dobson, the commission's leading gambling opponent, tells me. The industry's political clout has emasculated the commission, Dobson continues: "Our report won't be acted on by the president or Congress. They are too heavily influenced by gambling money. Almost all the leaders of Congress are on the dole." It has also become obvious that the commission has too many pro-gambling members to produce a report that recommends taxes or other real penalties on the industry. So the commission's two day visit to Gomorrah has been transformed from a charged political event to a kind of victory lap for gaming. Nevada Gov. Bob Miller and the "gaming visionaries" have been planning for these hearings for months, hoping to use them to demonstrate the might and sanctity and goodness of the Nevada gambling industry. The MGM Grand, which is run by commission member Terrence Lanni, is itself the first exhibit of the Vegas triumphalists. It is gaudy testimony that consumers, at least, have no problem with this business. The MGM Grand, a k a "The City of Entertainment," has 5,000 rooms--the corridor outside my room is 200 yards long, so long I can't see its end--to feed the endless supply of slot machines, craps tables, and roulette wheels. David Cassidy performs here every night--twice! A few steps outside on the Strip is still more overwhelming evidence that Las Vegas has won the popular vote. New York, New York is just across the street, the $1.6 billion Bellagio is one door down, and a half-scale Eiffel Tower is going up next door. The setting has, as the pro-gambling folks no doubt hoped, stunned some of the gambling opponents. I asked one anti-gambling activist who had never before been to Vegas what she thinks of it. She could only blurt out "Wow." The hearings, too, reinforce the Glorious Las Vegas theme. Frank Fahrenkopf, the industry's top lobbyist (who is paid so much he can afford monogrammed shirt cuffs --I saw them), holds forth cheerfully outside the ballroom, celebrating the electoral triumph of freedom over religious moralist tyranny. Inside, the room is packed with more than 600 people in neon lime green T-shirts that read "Unions and Gaming: Together for a Better Life." They are members of the major casino union, here to cheer on their employers and their union. (Most of them, it must be said, are getting paid to do this.) Chairwoman Kay Coles James, a Christian conservative and skeptic of gambling, opens the hearing by assuring the crowd that the committee is toothless: "We're not here to take anyone's job. ... We have no power to do anything except make recommendations." This sets the mood for most of the day: Vegas is great, so you'd better leave it alone! The local government, by all appearances a wholly owned subsidiary of the casinos, puts on a bravura performance. Gov. Miller opens the show with a 15 minute hymn to Las Vegas. It is the first of many statistical barrages about Nevada's one-ders: No. 1 in job growth, No. 1 in population growth, and No. 1 on planet Earth in per capita Girl Scout troops--and Boy Scout troops! Later in the day, Nevada's senators and both its congressmen appear to chew out the commission for even thinking that Nevada might have a dark side. They pay tribute to Nevada's sophisticated gambling industry, especially its regulation (much stricter than other gambling states) and its use of gambling taxes to fund state services. It is one of the ironies of Nevada politics that its Republican congressmen (Jim Gibbons and John Ensign) end up crediting their state's success to government regulation and corporate taxation. There are also a fair share of gleeful gambling regulators, bookmakers, and casino employees among the panels of expert witnesses the commission hears from. Critics who gripe about the perils of sports gambling and the evils of convenience store slot machines leaven the pro-gambling folks. Everyone, including the gambling industry shills, agrees that Internet gambling is evil and should be destroyed. Everyone agrees to this because no one in Las Vegas is making any money off Internet gambling. If they were, you can be sure they would explain why it's as American as nickel slots and scratch-off games. Pro-Vegas forces are also perfectly happy to take shots at Indian gambling, the chief economic threat to Nevada's prosperity. The expansion of Indian casinos resulting from last week's California voter initiative will slam Las Vegas, cutting its gambling revenues by $400 million a year. So the Vegans repeatedly swing at casinos in "Indian country" (that's Nevada Sen. Richard Bryan's term--I'm not joking) for being insufficiently regulated and taxed. One tribal chief I spoke to calls this "red baiting." (Pause for an aesthetic observation: I am sitting right behind the witnesses, and after a while I begin to separate them into the Wides and the Narrows. The Wides are men in suits with enormous backs and enormous bellies, men who eat and eat and used to play football. They all testify to their love of gambling. The Narrows are thin and generally disapprove of it. I begin to wonder whether fondness for gambling correlates with general indulgence, and dislike correlates with asceticism, and decide that they probably do.) During the last hour of the day, the public comment period, the union sends a parade of casino employees to the microphone to hallelujah the gaming industry. Housekeepers, cooks, and slot change girls, almost all black or Latina, tell the same story: I was working a dead-end job in another state, "then I heard about Las Vegas, where there's opportunity!" I moved here, landed a job at a union casino with high pay, free medical insurance, a pension, and "now I am buying a house." The stories are intensely moving, by far the most persuasive tribute to the Strip that I've ever heard. Still, for all the Vegan triumphalism in the air, it's impossible not to be charmed by the chief gambling opponent, the Rev. Tom Grey. Grey is utterly irrepressible. A Vietnam rifleman turned Methodist minister, Grey has spent the last eight years evangelizing against gambling. He founded the National Coalition Against Legalized Gambling, the primary force behind the commission's creation. (Grey, in a rare acknowledgement of defeat, has just renamed it the National Coalition Against Gambling Expansion, tacitly recognizing that gambling is here to stay.) He is a genial motormouth and shameless promoter of the cause. He wears a gigantic "CasiNO" button in the casino. He posed for People in a shepherd's robe. He says "I would do anything short of lighting myself on fire in the Capitol rotunda to stop gambling." He is so excitable that I have to yank him out of the way of an oncoming car when he gets too wrapped up in one of his soliloquies. He and his Las Vegas allies, a former Las Vegas city councilman named Steve Miller and an inner city venture capitalist named Otis Harris, invite me on a tour of Las Vegas. "Behind the Mirage," they call it. For two hours, we cruise the streets behind the casinos. They show me all the evidence of gambling blight you'd never want to see, from a youth-center-turned-crack-house to pawn shops to sex shops to down at heels casinos to quickie motels. All the while, they keep up a patter about how terrible a neighbor the casino industry is and how superficial Las Vegas' prosperity is. It's very grim and mostly persuasive. Still, when we turn back on to the Strip, and pass the jaw-dropping Stratosphere and Circus Circus and Bellagio and the MGM Grand--a 30 story tower bathed in fabulous emerald light, I realize why Grey's task is hopeless here. He is committing the cardinal sin of Vegas. All he wants to do is talk about losers. In Las Vegas, under the thrilling lights of the Strip, no one wants to hear about losers. In the land of gaming, not gambling, everyone is sure he's a winner.
|
C. donate money to improve other areas of Las Vegas
|
What is the Red Lion?
A. A gentlemen's club
B. A restaurant
C. A club for explorers and adventurers
D. A bar
|
Brightside Crossing by Alan E. Nourse JAMES BARON was not pleased to hear that he had had a visitor when he reached the Red Lion that evening. He had no stomach for mysteries, vast or trifling, and there were pressing things to think about at this time. Yet the doorman had flagged him as he came in from the street: “A thousand pardons, Mr. Baron. The gentleman—he would leave no name. He said you’d want to see him. He will be back by eight.” Now Baron drummed his fingers on the table top, staring about the quiet lounge. Street trade was discouraged at the Red Lion, gently but persuasively; the patrons were few in number. Across to the right was a group that Baron knew vaguely—Andean climbers, or at least two of them were. Over near the door he recognized old Balmer, who had mapped the first passage to the core of Vulcan Crater on Venus. Baron returned his smile with a nod. Then he settled back and waited impatiently for the intruder who demanded his time without justifying it. Presently a small, grizzled man crossed the room and sat down at Baron’s table. He was short and wiry. His face held no key to his age—he might have been thirty or a thousand—but he looked weary and immensely ugly. His cheeks and forehead were twisted and brown, with scars that were still healing. The stranger said, “I’m glad you waited. I’ve heard you’re planning to attempt the Brightside.” Baron stared at the man for a moment. “I see you can read telecasts,” he said coldly. “The news was correct. We are going to make a Brightside Crossing.” “At perihelion?” “Of course. When else?” The grizzled man searched Baron’s face for a moment without expression. Then he said slowly, “No, I’m afraid you’re not going to make the Crossing.” “Say, who are you, if you don’t mind?” Baron demanded. “The name is Claney,” said the stranger. There was a silence. Then: “Claney? Peter Claney?” “That’s right.” Baron’s eyes were wide with excitement, all trace of anger gone. “Great balls of fire, man— where have you been hiding? We’ve been trying to contact you for months!” “I know. I was hoping you’d quit looking and chuck the whole idea.” “Quit looking!” Baron bent forward over the table. “My friend, we’d given up hope, but we’ve never quit looking. Here, have a drink. There’s so much you can tell us.” His fingers were trembling. Peter Claney shook his head. “I can’t tell you anything you want to hear.” “But you’ve got to. You’re the only man on Earth who’s attempted a Brightside Crossing and lived through it! And the story you cleared for the news—it was nothing. We need details . Where did your equipment fall down? Where did you miscalculate? What were the trouble spots?” Baron jabbed a finger at Claney’s face. “That, for instance—epithelioma? Why? What was wrong with your glass? Your filters? We’ve got to know those things. If you can tell us, we can make it across where your attempt failed—” “You want to know why we failed?” asked Claney. “Of course we want to know. We have to know.” “It’s simple. We failed because it can’t be done. We couldn’t do it and neither can you. No human beings will ever cross the Brightside alive, not if they try for centuries.” “Nonsense,” Baron declared. “We will.” Claney shrugged. “I was there. I know what I’m saying. You can blame the equipment or the men—there were flaws in both quarters—but we just didn’t know what we were fighting. It was the planet that whipped us, that and the Sun . They’ll whip you, too, if you try it.” “Never,” said Baron. “Let me tell you,” Peter Claney said. I’d been interested in the Brightside for almost as long as I can remember (Claney said). I guess I was about ten when Wyatt and Carpenter made the last attempt—that was in 2082, I think. I followed the news stories like a tri-V serial and then I was heartbroken when they just disappeared. I know now that they were a pair of idiots, starting off without proper equipment, with practically no knowledge of surface conditions, without any charts—they couldn’t have made a hundred miles—but I didn’t know that then and it was a terrible tragedy. After that, I followed Sanderson’s work in the Twilight Lab up there and began to get Brightside into my blood, sure as death. But it was Mikuta’s idea to attempt a Crossing. Did you ever know Tom Mikuta? I don’t suppose you did. No, not Japanese—Polish-American. He was a major in the Interplanetary Service for some years and hung onto the title after he gave up his commission. He was with Armstrong on Mars during his Service days, did a good deal of the original mapping and surveying for the Colony there. I first met him on Venus; we spent five years together up there doing some of the nastiest exploring since the Matto Grasso. Then he made the attempt on Vulcan Crater that paved the way for Balmer a few years later. I’d always liked the Major—he was big and quiet and cool, the sort of guy who always had things figured a little further ahead than anyone else and always knew what to do in a tight place. Too many men in this game are all nerve and luck, with no judgment. The Major had both. He also had the kind of personality that could take a crew of wild men and make them work like a well-oiled machine across a thousand miles of Venus jungle. I liked him and I trusted him. He contacted me in New York and he was very casual at first. We spent an evening here at the Red Lion, talking about old times; he told me about the Vulcan business, and how he’d been out to see Sanderson and the Twilight Lab on Mercury, and how he preferred a hot trek to a cold one any day of the year—and then he wanted to know what I’d been doing since Venus and what my plans were. “No particular plans,” I told him. “Why?” He looked me over. “How much do you weigh, Peter?” I told him one-thirty-five. “That much!” he said. “Well, there can’t be much fat on you, at any rate. How do you take heat?” “You should know,” I said. “Venus was no icebox.” “No, I mean real heat.” Then I began to get it. “You’re planning a trip.” “That’s right. A hot trip.” He grinned at me. “Might be dangerous, too.” “What trip?” “Brightside of Mercury,” the Major said. I whistled cautiously. “At aphelion?” He threw his head back. “Why try a Crossing at aphelion? What have you done then? Four thousand miles of butcherous heat, just to have some joker come along, use your data and drum you out of the glory by crossing at perihelion forty-four days later? No, thanks. I want the Brightside without any nonsense about it.” He leaned across me eagerly. “I want to make a Crossing at perihelion and I want to cross on the surface. If a man can do that, he’s got Mercury. Until then, nobody’s got Mercury. I want Mercury—but I’ll need help getting it.” I’d thought of it a thousand times and never dared consider it. Nobody had, since Wyatt and Carpenter disappeared. Mercury turns on its axis in the same time that it wheels around the Sun, which means that the Brightside is always facing in. That makes the Brightside of Mercury at perihelion the hottest place in the Solar System, with one single exception: the surface of the Sun itself. It would be a hellish trek. Only a few men had ever learned just how hellish and they never came back to tell about it. It was a real hell’s Crossing, but someday, I thought, somebody would cross it. I wanted to be along. The Twilight Lab, near the northern pole of Mercury, was the obvious jumping-off place. The setup there wasn’t very extensive—a rocket landing, the labs and quarters for Sanderson’s crew sunk deep into the crust, and the tower that housed the Solar ’scope that Sanderson had built up there ten years before. Twilight Lab wasn’t particularly interested in the Brightside, of course—the Sun was Sanderson’s baby and he’d picked Mercury as the closest chunk of rock to the Sun that could hold his observatory. He’d chosen a good location, too. On Mercury, the Brightside temperature hits 770° F. at perihelion and the Darkside runs pretty constant at -410° F. No permanent installation with a human crew could survive at either extreme. But with Mercury’s wobble, the twilight zone between Brightside and Darkside offers something closer to survival temperatures. Sanderson built the Lab up near the pole, where the zone is about five miles wide, so the temperature only varies 50 to 60 degrees with the libration. The Solar ’scope could take that much change and they’d get good clear observation of the Sun for about seventy out of the eighty-eight days it takes the planet to wheel around. The Major was counting on Sanderson knowing something about Mercury as well as the Sun when we camped at the Lab to make final preparations. Sanderson did. He thought we’d lost our minds and he said so, but he gave us all the help he could. He spent a week briefing Jack Stone, the third member of our party, who had arrived with the supplies and equipment a few days earlier. Poor Jack met us at the rocket landing almost bawling, Sanderson had given him such a gloomy picture of what Brightside was like. Stone was a youngster—hardly twenty-five, I’d say—but he’d been with the Major at Vulcan and had begged to join this trek. I had a funny feeling that Jack really didn’t care for exploring too much, but he thought Mikuta was God, followed him around like a puppy. It didn’t matter to me as long as he knew what he was getting in for. You don’t go asking people in this game why they do it—they’re liable to get awfully uneasy and none of them can ever give you an answer that makes sense. Anyway, Stone had borrowed three men from the Lab, and had the supplies and equipment all lined up when we got there, ready to check and test. We dug right in. With plenty of funds—tri-V money and some government cash the Major had talked his way around—our equipment was new and good. Mikuta had done the designing and testing himself, with a big assist from Sanderson. We had four Bugs, three of them the light pillow-tire models, with special lead-cooled cut-in engines when the heat set in, and one heavy-duty tractor model for pulling the sledges. The Major went over them like a kid at the circus. Then he said, “Have you heard anything from McIvers?” “Who’s he?” Stone wanted to know. “He’ll be joining us. He’s a good man—got quite a name for climbing, back home.” The Major turned to me. “You’ve probably heard of him.” I’d heard plenty of stories about Ted McIvers and I wasn’t too happy to hear that he was joining us. “Kind of a daredevil, isn’t he?” “Maybe. He’s lucky and skillful. Where do you draw the line? We’ll need plenty of both.” “Have you ever worked with him?” I asked. “No. Are you worried?” “Not exactly. But Brightside is no place to count on luck.” The Major laughed. “I don’t think we need to worry about McIvers. We understood each other when I talked up the trip to him and we’re going to need each other too much to do any fooling around.” He turned back to the supply list. “Meanwhile, let’s get this stuff listed and packed. We’ll need to cut weight sharply and our time is short. Sanderson says we should leave in three days.” Two days later, McIvers hadn’t arrived. The Major didn’t say much about it. Stone was getting edgy and so was I. We spent the second day studying charts of the Brightside, such as they were. The best available were pretty poor, taken from so far out that the detail dissolved into blurs on blow-up. They showed the biggest ranges of peaks and craters and faults, and that was all. Still, we could use them to plan a broad outline of our course. “This range here,” the Major said as we crowded around the board, “is largely inactive, according to Sanderson. But these to the south and west could be active. Seismograph tracings suggest a lot of activity in that region, getting worse down toward the equator—not only volcanic, but sub-surface shifting.” Stone nodded. “Sanderson told me there was probably constant surface activity.” The Major shrugged. “Well, it’s treacherous, there’s no doubt of it. But the only way to avoid it is to travel over the Pole, which would lose us days and offer us no guarantee of less activity to the west. Now we might avoid some if we could find a pass through this range and cut sharp east—” It seemed that the more we considered the problem, the further we got from a solution. We knew there were active volcanoes on the Brightside—even on the Darkside, though surface activity there was pretty much slowed down and localized. But there were problems of atmosphere on Brightside, as well. There was an atmosphere and a constant atmospheric flow from Brightside to Darkside. Not much—the lighter gases had reached escape velocity and disappeared from Brightside millennia ago—but there was CO 2 , and nitrogen, and traces of other heavier gases. There was also an abundance of sulfur vapor, as well as carbon disulfide and sulfur dioxide. The atmospheric tide moved toward the Darkside, where it condensed, carrying enough volcanic ash with it for Sanderson to estimate the depth and nature of the surface upheavals on Brightside from his samplings. The trick was to find a passage that avoided those upheavals as far as possible. But in the final analysis, we were barely scraping the surface. The only way we would find out what was happening where was to be there. Finally, on the third day, McIvers blew in on a freight rocket from Venus. He’d missed the ship that the Major and I had taken by a few hours, and had conned his way to Venus in hopes of getting a hop from there. He didn’t seem too upset about it, as though this were his usual way of doing things and he couldn’t see why everyone should get so excited. He was a tall, rangy man with long, wavy hair prematurely gray, and the sort of eyes that looked like a climber’s—half-closed, sleepy, almost indolent, but capable of abrupt alertness. And he never stood still; he was always moving, always doing something with his hands, or talking, or pacing about. Evidently the Major decided not to press the issue of his arrival. There was still work to do, and an hour later we were running the final tests on the pressure suits. That evening, Stone and McIvers were thick as thieves, and everything was set for an early departure after we got some rest. “And that,” said Baron, finishing his drink and signaling the waiter for another pair, “was your first big mistake.” Peter Claney raised his eyebrows. “McIvers?” “Of course.” Claney shrugged, glanced at the small quiet tables around them. “There are lots of bizarre personalities around a place like this, and some of the best wouldn’t seem to be the most reliable at first glance. Anyway, personality problems weren’t our big problem right then. Equipment worried us first and route next.” Baron nodded in agreement. “What kind of suits did you have?” “The best insulating suits ever made,” said Claney. “Each one had an inner lining of a fiberglass modification, to avoid the clumsiness of asbestos, and carried the refrigerating unit and oxygen storage which we recharged from the sledges every eight hours. Outer layer carried a monomolecular chrome reflecting surface that made us glitter like Christmas trees. And we had a half-inch dead-air space under positive pressure between the two layers. Warning thermocouples, of course—at 770 degrees, it wouldn’t take much time to fry us to cinders if the suits failed somewhere.” “How about the Bugs?” “They were insulated, too, but we weren’t counting on them too much for protection.” “You weren’t!” Baron exclaimed. “Why not?” “We’d be in and out of them too much. They gave us mobility and storage, but we knew we’d have to do a lot of forward work on foot.” Claney smiled bitterly. “Which meant that we had an inch of fiberglass and a half-inch of dead air between us and a surface temperature where lead flowed like water and zinc was almost at melting point and the pools of sulfur in the shadows were boiling like oatmeal over a campfire.” Baron licked his lips. His fingers stroked the cool, wet glass as he set it down on the tablecloth. “Go on,” he said tautly. “You started on schedule?” “Oh, yes,” said Claney, “we started on schedule, all right. We just didn’t quite end on schedule, that was all. But I’m getting to that.” He settled back in his chair and continued. We jumped off from Twilight on a course due southeast with thirty days to make it to the Center of Brightside. If we could cross an average of seventy miles a day, we could hit Center exactly at perihelion, the point of Mercury’s closest approach to the Sun—which made Center the hottest part of the planet at the hottest it ever gets. The Sun was already huge and yellow over the horizon when we started, twice the size it appears on Earth. Every day that Sun would grow bigger and whiter, and every day the surface would get hotter. But once we reached Center, the job was only half done—we would still have to travel another two thousand miles to the opposite twilight zone. Sanderson was to meet us on the other side in the Laboratory’s scout ship, approximately sixty days from the time we jumped off. That was the plan, in outline. It was up to us to cross those seventy miles a day, no matter how hot it became, no matter what terrain we had to cross. Detours would be dangerous and time-consuming. Delays could cost us our lives. We all knew that. The Major briefed us on details an hour before we left. “Peter, you’ll take the lead Bug, the small one we stripped down for you. Stone and I will flank you on either side, giving you a hundred-yard lead. McIvers, you’ll have the job of dragging the sledges, so we’ll have to direct your course pretty closely. Peter’s job is to pick the passage at any given point. If there’s any doubt of safe passage, we’ll all explore ahead on foot before we risk the Bugs. Got that?” McIvers and Stone exchanged glances. McIvers said: “Jack and I were planning to change around. We figured he could take the sledges. That would give me a little more mobility.” The Major looked up sharply at Stone. “Do you buy that, Jack?” Stone shrugged. “I don’t mind. Mac wanted—” McIvers made an impatient gesture with his hands. “It doesn’t matter. I just feel better when I’m on the move. Does it make any difference?” “I guess it doesn’t,” said the Major. “Then you’ll flank Peter along with me. Right?” “Sure, sure.” McIvers pulled at his lower lip. “Who’s going to do the advance scouting?” “It sounds like I am,” I cut in. “We want to keep the lead Bug light as possible.” Mikuta nodded. “That’s right. Peter’s Bug is stripped down to the frame and wheels.” McIvers shook his head. “No, I mean the advance work. You need somebody out ahead—four or five miles, at least—to pick up the big flaws and active surface changes, don’t you?” He stared at the Major. “I mean, how can we tell what sort of a hole we may be moving into, unless we have a scout up ahead?” “That’s what we have the charts for,” the Major said sharply. “Charts! I’m talking about detail work. We don’t need to worry about the major topography. It’s the little faults you can’t see on the pictures that can kill us.” He tossed the charts down excitedly. “Look, let me take a Bug out ahead and work reconnaissance, keep five, maybe ten miles ahead of the column. I can stay on good solid ground, of course, but scan the area closely and radio back to Peter where to avoid the flaws. Then—” “No dice,” the Major broke in. “But why not? We could save ourselves days!” “I don’t care what we could save. We stay together. When we get to the Center, I want live men along with me. That means we stay within easy sight of each other at all times. Any climber knows that everybody is safer in a party than one man alone—any time, any place.” McIvers stared at him, his cheeks an angry red. Finally he gave a sullen nod. “Okay. If you say so.” “Well, I say so and I mean it. I don’t want any fancy stuff. We’re going to hit Center together, and finish the Crossing together. Got that?” McIvers nodded. Mikuta then looked at Stone and me and we nodded, too. “All right,” he said slowly. “Now that we’ve got it straight, let’s go.” It was hot. If I forget everything else about that trek, I’ll never forget that huge yellow Sun glaring down, without a break, hotter and hotter with every mile. We knew that the first few days would be the easiest and we were rested and fresh when we started down the long ragged gorge southeast of the Twilight Lab. I moved out first; back over my shoulder, I could see the Major and McIvers crawling out behind me, their pillow tires taking the rugged floor of the gorge smoothly. Behind them, Stone dragged the sledges. Even at only 30 per cent Earth gravity they were a strain on the big tractor, until the ski-blades bit into the fluffy volcanic ash blanketing the valley. We even had a path to follow for the first twenty miles. I kept my eyes pasted to the big polaroid binocs, picking out the track the early research teams had made out into the edge of Brightside. But in a couple of hours we rumbled past Sanderson’s little outpost observatory and the tracks stopped. We were in virgin territory and already the Sun was beginning to bite. We didn’t feel the heat so much those first days out. We saw it. The refrig units kept our skins at a nice comfortable seventy-five degrees Fahrenheit inside our suits, but our eyes watched that glaring Sun and the baked yellow rocks going past, and some nerve pathways got twisted up, somehow. We poured sweat as if we were in a superheated furnace. We drove eight hours and slept five. When a sleep period came due, we pulled the Bugs together into a square, threw up a light aluminum sun-shield and lay out in the dust and rocks. The sun-shield cut the temperature down sixty or seventy degrees, for whatever help that was. And then we ate from the forward sledge—sucking through tubes—protein, carbohydrates, bulk gelatin, vitamins. The Major measured water out with an iron hand, because we’d have drunk ourselves into nephritis in a week otherwise. We were constantly, unceasingly thirsty. Ask the physiologists and psychiatrists why—they can give you have a dozen interesting reasons—but all we knew, or cared about, was that it happened to be so. We didn’t sleep the first few stops, as a consequence. Our eyes burned in spite of the filters and we had roaring headaches, but we couldn’t sleep them off. We sat around looking at each other. Then McIvers would say how good a beer would taste, and off we’d go. We’d have murdered our grandmothers for one ice-cold bottle of beer. After a few driving periods, I began to get my bearings at the wheel. We were moving down into desolation that made Earth’s old Death Valley look like a Japanese rose garden. Huge sun-baked cracks opened up in the floor of the gorge, with black cliffs jutting up on either side; the air was filled with a barely visible yellowish mist of sulfur and sulfurous gases. It was a hot, barren hole, no place for any man to go, but the challenge was so powerful you could almost feel it. No one had ever crossed this land before and escaped. Those who had tried it had been cruelly punished, but the land was still there, so it had to be crossed. Not the easy way. It had to be crossed the hardest way possible: overland, through anything the land could throw up to us, at the most difficult time possible. Yet we knew that even the land might have been conquered before, except for that Sun. We’d fought absolute cold before and won. We’d never fought heat like this and won. The only worse heat in the Solar System was the surface of the Sun itself. Brightside was worth trying for. We would get it or it would get us. That was the bargain. I learned a lot about Mercury those first few driving periods. The gorge petered out after a hundred miles and we moved onto the slope of a range of ragged craters that ran south and east. This range had shown no activity since the first landing on Mercury forty years before, but beyond it there were active cones. Yellow fumes rose from the craters constantly; their sides were shrouded with heavy ash. We couldn’t detect a wind, but we knew there was a hot, sulfurous breeze sweeping in great continental tides across the face of the planet. Not enough for erosion, though. The craters rose up out of jagged gorges, huge towering spears of rock and rubble. Below were the vast yellow flatlands, smoking and hissing from the gases beneath the crust. Over everything was gray dust—silicates and salts, pumice and limestone and granite ash, filling crevices and declivities—offering a soft, treacherous surface for the Bug’s pillow tires. I learned to read the ground, to tell a covered fault by the sag of the dust; I learned to spot a passable crack, and tell it from an impassable cut. Time after time the Bugs ground to a halt while we explored a passage on foot, tied together with light copper cable, digging, advancing, digging some more until we were sure the surface would carry the machines. It was cruel work; we slept in exhaustion. But it went smoothly, at first. Too smoothly, it seemed to me, and the others seemed to think so, too. McIvers’ restlessness was beginning to grate on our nerves. He talked too much, while we were resting or while we were driving; wisecracks, witticisms, unfunny jokes that wore thin with repetition. He took to making side trips from the route now and then, never far, but a little further each time. Jack Stone reacted quite the opposite; he grew quieter with each stop, more reserved and apprehensive. I didn’t like it, but I figured that it would pass off after a while. I was apprehensive enough myself; I just managed to hide it better. And every mile the Sun got bigger and whiter and higher in the sky and hotter. Without our ultra-violet screens and glare filters we would have been blinded; as it was our eyes ached constantly and the skin on our faces itched and tingled at the end of an eight-hour trek. But it took one of those side trips of McIvers’ to deliver the penultimate blow to our already fraying nerves. He had driven down a side-branch of a long canyon running off west of our route and was almost out of sight in a cloud of ash when we heard a sharp cry through our earphones. I wheeled my Bug around with my heart in my throat and spotted him through the binocs, waving frantically from the top of his machine. The Major and I took off, lumbering down the gulch after him as fast as the Bugs could go, with a thousand horrible pictures racing through our minds.... We found him standing stock-still, pointing down the gorge and, for once, he didn’t have anything to say. It was the wreck of a Bug; an old-fashioned half-track model of the sort that hadn’t been in use for years. It was wedged tight in a cut in the rock, an axle broken, its casing split wide open up the middle, half-buried in a rock slide. A dozen feet away were two insulated suits with white bones gleaming through the fiberglass helmets. This was as far as Wyatt and Carpenter had gotten on their Brightside Crossing. On the fifth driving period out, the terrain began to change. It looked the same, but every now and then it felt different. On two occasions I felt my wheels spin, with a howl of protest from my engine. Then, quite suddenly, the Bug gave a lurch; I gunned my motor and nothing happened. I could see the dull gray stuff seeping up around the hubs, thick and tenacious, splattering around in steaming gobs as the wheels spun. I knew what had happened the moment the wheels gave and, a few minutes later, they chained me to the tractor and dragged me back out of the mire. It looked for all the world like thick gray mud, but it was a pit of molten lead, steaming under a soft layer of concealing ash. I picked my way more cautiously then. We were getting into an area of recent surface activity; the surface was really treacherous. I caught myself wishing that the Major had okayed McIvers’ scheme for an advanced scout; more dangerous for the individual, maybe, but I was driving blind now and I didn’t like it. One error in judgment could sink us all, but I wasn’t thinking much about the others. I was worried about me , plenty worried. I kept thinking, better McIvers should go than me. It wasn’t healthy thinking and I knew it, but I couldn’t get the thought out of my mind. It was a grueling eight hours and we slept poorly. Back in the Bug again, we moved still more slowly—edging out on a broad flat plateau, dodging a network of gaping surface cracks—winding back and forth in an effort to keep the machines on solid rock. I couldn’t see far ahead, because of the yellow haze rising from the cracks, so I was almost on top of it when I saw a sharp cut ahead where the surface dropped six feet beyond a deep crack. I let out a shout to halt the others; then I edged my Bug forward, peering at the cleft. It was deep and wide. I moved fifty yards to the left, then back to the right. There was only one place that looked like a possible crossing; a long, narrow ledge of gray stuff that lay down across a section of the fault like a ramp. Even as I watched it, I could feel the surface crust under the Bug trembling and saw the ledge shift over a few feet.
|
C. A club for explorers and adventurers
|
What planet are the mysterious signals coming from?
A. Formia
B. Mars
C. Venus
D. Jupiter
|
THE RADIO PLANET Ralph Milne Farley I “It’s too bad that Myles Cabot can’t see this!” I exclaimed, as my eye fell on the following item: SIGNALS FROM MARS FAIL TO REACH HARVARD Cambridge, Massachusetts, Wednesday. The Harvard College Radio Station has for several weeks been in receipt of fragmentary signals of extraordinarily long wave-length, Professor Hammond announced yesterday. So far as it has been possible to test the direction of the source of these waves, it appears that the direction has a twenty-four hour cycle, thus indicating that the origin of these waves is some point outside the earth. The university authorities will express no opinion as to whether or not these messages come from Mars. Myles, alone of all the radio engineers of my acquaintance, was competent to surmount these difficulties, and thus enable the Cambridge savants to receive with clearness the message from another planet. 6 Twelve months ago he would have been available, for he was then quietly visiting at my farm, after five earth-years spent on the planet Venus, where, by the aid of radio, he had led the Cupians to victory over their oppressors, a human-brained race of gigantic black ants. He had driven the last ant from the face of continental Poros, and had won and wed the Princess Lilla, who had borne him a son to occupy the throne of Cupia. While at my farm Cabot had rigged up a huge radio set and a matter-transmitting apparatus, with which he had (presumably) shot himself back to Poros on the night of the big October storm which had wrecked his installation. I showed the newspaper item to Mrs. Farley, and lamented on Cabot’s absence. Her response opened up an entirely new line of thought. Said she: “Doesn’t the very fact that Mr. Cabot isn’t here suggest to you that this may be a message, not from Mars, but from him? Or perhaps from the Princess Lilla, inquiring about him in case he has failed in his attempted return?” That had never occurred to me! How stupid! “What had I better do about it, if anything?” I asked. “Drop Professor Hammond a line?” But Mrs. Farley was afraid that I would be taken for a crank. That evening, when I was over in town, the clerk in the drug store waylaid me to say that there had been a long-distance phone call for me, and would I please call a certain Cambridge number. So, after waiting an interminable time in the stuffy booth with my hands full of dimes, nickels, and quarters, I finally got my party. “Mr. Farley?” “Speaking.” “This is Professor Kellogg, O. D. Kellogg,” the voice replied. 7 It was my friend of the Harvard math faculty, the man who had analyzed the measurements of the streamline projectile in which Myles Cabot had shot to earth the account of the first part of his adventures on Venus. Some further adventures Myles had told me in person during his stay on my farm. “Professor Hammond thinks that he is getting Mars on the air,” the voice continued. “Yes,” I replied. “I judged as much from what I read in this morning’s paper. But what do you think?” Kellogg’s reply gave my sluggish mind the second jolt which it had received that day. “Well,” he said, “in view of the fact that I am one of the few people among your readers who take your radio stories seriously, I think that Hammond is getting Venus. Can you run up here and help me try and convince him?” And so it was that I took the early boat next morning for Boston, and had lunch with the two professors. As a result of our conference, a small committee of engineers returned with me to Edgartown that evening for the purpose of trying to repair the wrecked radio set which Myles Cabot had left on my farm. They utterly failed to comprehend the matter-transmitting apparatus, and so—after the fallen tower had been reerected and the rubbish cleared away—they had devoted their attention to the restoration of the conversational part of the set. To make a long story short, we finally restored it, with the aid of some old blue prints of Cabot’s which Mrs. Farley, like Swiss Family Robinson’s wife, produced from somewhere. I was the first to try the earphones, and was rewarded by a faint “bzt-bzt” like the song of a north woods blackfly. In conventional radioese, I repeated the sounds to the Harvard group: “Dah-dit-dah-dit dah-dah-dit-dah. Dah-dit-dah-dit dah-dah-dit-dah. Dah-dit-dah-dit dah-dah-dit-dah. Dah-dit-dit dit. Dah-dit-dah-dit dit-dah dah-dit dit dit dah-dah-dah dah. Dah-dit-dah-dit dit-dah dah-dit-dit-dit dah-dah-dah dah. Dah-dit-dah-dit dit-dah dah-dit-dit-dit-dah dah-dah-dah.” 8 A look of incredulity spread over their faces. Again came the same message, and again I repeated it. “You’re spoofing us!” one of them shouted. “Give me the earphones.” And he snatched them from my head. Adjusting them on his own head, he spelled out to us, “C-Q C-Q C-Q D-E C-A-B-O-T C-A-B-O-T C-A-B-O-T—” Seizing the big leaf-switch, he threw it over. The motor-generator began to hum. Grasping the key, the Harvard engineer ticked off into space: “Cabot Cabot Cabot D-E—” “Has this station a call letter?” he hurriedly asked me. “Yes,” I answered quickly, “One-X-X-B.” “One-X-X-B,” he continued the ticking “K.” Interplanetary communication was an established fact at last! And not with Mars after all these years of scientific speculations. But what meant more to me was that I was again in touch with my classmate Myles Standish Cabot, the radio man. The next day a party of prominent scientists, accompanied by a telegrapher and two stenographers, arrived at my farm. During the weeks that followed there was recorded Myles’s own account of the amazing adventures on the planet Venus (or Poros, as its own inhabitants call it,) which befell him upon his return there after his brief visit to the earth. I have edited those notes into the following coherent story. II TOO MUCH STATIC Myles Cabot had returned to the earth to study the latest developments of modern terrestrial science for the benefit of the Cupian nation. He was the regent of Cupia during the minority of his baby son, King Kew the Thirteenth. The loyal Prince Toron occupied the throne in his absence. The last of the ant-men and their ally, the renegade Cupian Prince Yuri, had presumably perished in an attempt to escape by flying through the steam-clouds which completely hem in continental Poros. What lay beyond the boiling seas no man knew. 9 During his stay on my farm, Cabot had built the matter-transmitting apparatus, with which he had shot himself off into space on that October night on which he had received the message from the skies: “S O S, Lilla.” A thunderstorm had been brewing all that evening, and just as Myles had placed himself between the coordinate axes of his machine and had gathered up the strings which ran from his control levers to within the apparatus, there had come a blinding flash. Lightning had struck his aerial. How long his unconsciousness lasted he knew not. He was some time in regaining his senses. But when he had finally and fully recovered, he found himself lying on a sandy beach beside a calm and placid lake beneath a silver sky. He fell to wondering, vaguely and pleasantly, where he was and how he had got here. Suddenly, however, his ears were jarred by a familiar sound. At once his senses cleared, and he listened intently to the distant purring of a motor. Yes, there could be no mistake; an airplane was approaching. Now he could see it, a speck in the sky, far down the beach. Nearer and nearer it came. Myles sprang to his feet. To his intense surprise, he found that the effort threw him quite a distance into the air. Instantly the idea flashed through his mind: “I must be on Mars! Or some other strange planet.” This idea was vaguely reminiscent of something. But while he was trying to catch this vaguely elusive train of thought, his attention was diverted by the fact that, for some unaccountable reason, his belt buckle and most of the buttons which had held his clothes together were missing, so that his clothing came to pieces as he rose, and that he had to shed it rapidly in order to avoid impeding his movements. He wondered at the cause of this. 10 But his speculations were cut short by the alighting of the plane a hundred yards down the beach. What was his horror when out of it clambered, not men but ants! Ants, six-footed, and six feet high. Huge ants, four of them, running toward him over the glistening sands. Gone was all his languor, as he seized a piece of driftwood and prepared to defend himself. As he stood thus expectant, Myles realized that his present position and condition, the surrounding scenery, and the advance of the ant-men were exactly, item for item, like the opening events of his first arrival on the planet Poros. He even recognized one of the ant-men as old Doggo, who had befriended him on his previous visit. Could it be that all his adventures in Cupia had been naught but a dream; a recurring dream, in fact? Were his dear wife Lilla and his little son Kew merely figments of his imagination? Horrible thought! And then events began to differ from those of the past; for the three other Formians halted, and Doggo advanced alone. By the agitation of the beast’s antennae the earth man could see that it was talking to him. But Myles no longer possessed the wonderful electrical headset which he had contrived and built during his previous visit to that planet, so as to talk with Cupians and Formians, both of which races are earless and converse by means of radiations from their antennae. So he picked up two sticks from the beach, and held them projecting from his forehead; then threw them to the ground with a grimace of disgust and pointed to his ears. Doggo understood, and scratched with his paw in Cupian shorthand on the silver sands the message: “Myles Cabot, you are our prisoner.” “What, again?” scratched Myles, then made a sign of submission. 11 He dreaded the paralyzing bite which Formians usually administer to their victims, and which he had twice experienced in the past; but, fortunately, it was not now forthcoming. The other three ants kept away from him as Doggo led him to the beached airplane, and soon they were scudding along beneath silver skies, northward as it later turned out. Far below them were silver-green fields and tangled tropical woods, interspersed with rivulets and little ponds. This was Cupia, his Cupia. He was home once more, back again upon the planet which held all that was dear to him in two worlds. His heart glowed with the warmth of homecoming. What mattered it that he was now a prisoner, in the hands (or, rather, claws) of his old enemies, the Formians? He had been their prisoner before, and had escaped. Once more he could escape, and rescue the Princess Lilla. Poor girl! How eager he was to reach her side, and save her from that peril, whatever it was, which had caused her to flash that “S O S” a hundred million miles across the solar system from Poros to the earth. He wondered what could have happened in Cupia since his departure, only a few sangths ago. How was it that the ant-men had survived their airplane journey across the boiling seas? What had led them to return? Or perhaps these ants were a group who had hidden somewhere and thus had escaped the general extermination of their race. In either event, how had they been able to reconquer Cupia? And where was their former leader, Yuri, the renegade Cupian prince? These and a hundred other similar questions flooded in upon the earth-man, as the Formian airship carried him, a captive, through the skies. He gazed again at the scene below, and now noted one difference from the accustomed Porovian landscape, for nowhere ran the smooth concrete roads which bear the swift two-wheeled kerkools of the Cupians to all parts of their continent. What uninhabited portion of Cupia could this be, over which they were now passing? 12 Turning to Doggo, Myles extended his left palm, and made a motion as though writing on it with the thumb and forefinger of his right hand. But the ant-man waved a negative with one of his forepaws. It was evident that there were no writing materials aboard the ship. Myles would have to wait until they reached their landing place; for doubtless they would soon hover down in some city or town, though just which one he could not guess, as the country below was wholly unfamiliar. Finally a small settlement loomed ahead. It was of the familiar style of toy-building-block architecture affected by the ant-men, and, from its appearance, was very new. On its outskirts further building operations were actively in progress. Apparently a few survivors of the accursed race of Formians were consolidating their position and attempting to build up a new empire in some out-of-the-way portion of the continent. As the earth-man was turning these thoughts over in his mind the plane softly settled down upon one of the flat roofs, and its occupants disembarked. Three of the ants advanced menacingly toward Myles, but Doggo held them off. Then all of the party descended down one of the ramps to the lower levels of the building. Narrow slitlike window openings gave onto courtyards, where fountains played and masses of blue and yellow flowers bloomed, amid gray-branched lichens with red and purple twig-knobs. It was in just such a garden, through just such a window, that he had first looked upon the lovely blue-eyed, golden-haired Lilla, Crown Princess of Cupia. The earth-man sighed. Where was his beloved wife now? That she needed his help was certain. He must therefore get busy. So once again he made motions of writing on the palm of his left hand with the thumb and forefinger of his right; and this time the sign language produced results, for Doggo halted the procession and led Cabot into a room. 13 It was a plain bare room, devoid of any furniture except a small table, for ant-men have no use for chairs and couches. The sky outside was already beginning to pinken with the unseen sun. With a sweep of his paw, Doggo indicated that this was to be Cabot’s quarters. Then, with another wave, he pointed to the table, where lay a pad of paper and stylus, not a pencil-like stylus as employed by the Cupians, but rather one equipped with straps for attaching it to the claw of a Formian. Even so, it was better than nothing. The earth-man seized it eagerly, but before he could begin writing an ant entered bearing a Cupian toga, short-sleeved and bordered with Grecian wave designs in blue. Myles put on this garment, and then quickly filled a sheet with questions: “How is my princess and my son, the baby king? Whence come all you Formians, whose race I thought had been exterminated? What part of Cupia is this? What is this city? Where is Prince Yuri? And what do you intend to do with me this time?” Then he passed the paper and stylus over to his old friend Doggo. They were alone together at last. The ant-man’s reply consumed sheet after sheet of paper; but, owning to the rapidity of Porovian shorthand, did not take so very much more time than speaking would have required. As he completed each sheet he passed it over to Myles, who read as follows: “As to your princess and your son, I know not, for this is not Cupia. Do you remember how, when your victorious army and air navy swept to the southern extremity of what had been Formia, a few of our survivors rose in planes from the ruins of our last stronghold and braved the dangers of the steam clouds which overhang the boiling seas? Our leader was Prince Yuri, erstwhile contender for the throne of Cupia, splendid even in defeat. “It was his brain that conceived our daring plan of escape. If there were other lands beyond the boiling seas, the lands which tradition taught were the origin of the Cupian race, then there we might prosper and raise up a new empire. At the worst we should merely meet death in another form, rather than at your hands. So we essayed. 14 “Your planes followed us, but turned back as we neared the area of terrific heat. Soon the vapor closed over us, blotting our enemies and our native land from view.” For page after page Doggo, the ant-man, related the harrowing details of that perilous flight across the boiling seas, ending with the words: “Here we are, and here are you, in Yuriana, capitol of New Formia. But how is it that you, Myles Cabot, have arrived here on this continent in exactly the same manner and condition in which I discovered you in old Formia eight years ago?” When Myles reached the end of reading this narrative, he in turn took the pad and stylus and related how he had gone to the planet Minos (which we call the Earth) to learn the latest discoveries and inventions there, and how his calculations for his return to Poros had been upset by some static conditions just as he had been about to transmit himself back. Oh, if only he had landed by chance upon the same beach as on his first journey through the skies! Wisely he refrained from mentioning the “S O S” message from Lilla. But his recollection of her predicament spurred him to be anxious about her rescue. His immediate problem was to learn what the ant-men planned for him; so the concluding words which he wrote upon the pad were: “And, now that you have me in your power, what shall you do with me?” “Old friend,” Doggo wrote in reply, “that depends entirely upon Yuri, our king, whose toga you now have on.” III YURI OR FORMIS? The earth-man grimaced, but then smiled. Perhaps, his succeeding to the toga of King Yuri might prove to be an omen. 15 “So Yuri is king of the ants?” he asked. “Yes,” his captor replied, “for Queen Formis did not survive the trip across the boiling seas.” “Then what of your empire?” Myles inquired. “No queen. No eggs. How can your race continue? For you Formians are like the ants on my own planet Minos.” Doggo’s reply astounded him. “Do you remember back at Wautoosa, I told you that some of us lesser Formians had occasionally laid eggs? So now behold before you Doggo, Admiral of the Formian Air Navy, and mother of a new Queen Formis.” This was truly a surprise! All along Cabot had always regarded the Formians as mannish. And rightly so, for they performed in their own country the duties assigned to men among the Cupians. Furthermore, all Formians, save only the reigning Formis herself, were called by the Porovian pronoun, which corresponds to “he” in English. When Myles had somewhat recovered from his astonishment, he warmly congratulated his friend by patting him on the side of the head, as is the Porovian custom. “Doggo,” he wrote, “this ought to constitute you a person of some importance among the Formians.” “It ought to,” the ant-man replied, “but as a matter of fact, it merely intensifies Yuri’s mistrust and hatred of me. Now that I am mother of the queen, he fears that I may turn against him and establish Formis in his place as the head of an empire of the Formians, by the Formians, and for the Formians exclusively.” “Why don’t you?” Myles wrote. It seemed to him to be a bully good idea, and incidentally a solution of his own difficulties. But Doggo wrote in horror, “It would be treason!” Then tore up all the correspondence. It is difficult to inculcate the thought of independence in the mind of one reared in an autocracy. The earth-man, however, persisted. “How many of the council can you count on, if the interests of Yuri should clash with those of Formis?” 16 “Only one—myself.” And again Doggo tore up the correspondence. Myles tactfully changed the subject. “Where is the arch-fiend now?” he asked. “We know not,” the Formian wrote in reply. “Six days ago he left us in his airship and flew westward. When he failed to return, we sent out scout planes to search for him, and we have been hunting ever since. When we sighted you on the beach this morning we thought that you might be our lost leader, and that is why we landed and approached you.” At about this point the conversation was interrupted by a worker ant who brought food: roast alta and green aphid milk. With what relish did the earth-man plunge into the feast, his first taste of Porovian delicacies in many months. During the meal conversation lagged, owing to the difficulty of writing and eating at the same time. But now Myles Cabot seized his pad and stylus and wrote: “Have you ever known me to fail in any undertaking on the planet Poros?” “No,” the ant-man wrote in reply. “Have you ever known me to be untrue to a principle, a cause, or a friend?” “No,” Doggo replied. “Then,” Myles wrote, “let us make your daughter queen in fact as well as in name.” “It is treason,” Doggo wrote in reply, but this time he did not tear up the correspondence. “Treason?” Myles asked. If he had spoken the word, he would have spoken it with scorn and derision. “Treason? Is it treason to support your own queen? What has become of the national pride of the once great Formians? Look! I pledge myself to the cause of Formis, rightful Queen of Formia. Formis, daughter of Doggo! What say you?” This time, as he tore up the correspondence, Doggo signified an affirmative. And thus there resulted further correspondence. 17 “Doggo,” Myles wrote, “can you get to the antenna of the queen?” The ant-man indicated that he could. “If she has inherited any of your character,” Myles continued, “she will assert herself, if given half a chance.” So the Pitmanesque conversation continued. Long since had the pink light of Porovian evening faded from the western sky. The ceiling vapor-lamps were lit. The night showed velvet-black through the slit-like windows. And still the two old friends wrote on, Myles Standish Cabot, the Bostonian, and Doggo, No. 334-2-18, the only really humanlike ant-man whom Myles had ever known among the once dominant race of Poros. Finally, as the dials indicated midnight, the two conspirators ceased their labors. All was arranged for the coup d’ etat . They tore into shreds every scrap of used paper, leaving extant merely the ant-man’s concluding words: “Meanwhile you are my prisoner.” Doggo then rang a soundless bell, which was answered by a worker ant, whom he inaudibly directed to bring sufficient draperies to form a bed for the earth-man. These brought, the two friends patted each other a fond good night, and the tired earth-man lay down for the first sleep which he had had in over forty earth hours. It hardly seemed possible! Night before last he had slept peacefully on a conventional feather-bed in a little New England farmhouse. Then had come the S O S message from the skies; and here he was now, millions of miles away through space retiring on matted silver felting on the concrete floor of a Porovian ant-house. Such are the mutations of fortune! With these thoughts the returned wanderer lapsed into a deep and dreamless sleep. When he awakened in the morning there was a guard posted at the door. 18 Doggo did not show up until nearly noon, when he rattled in, bristling with excitement. Seizing the pad he wrote: “A stormy session of the Council of Twelve! We are all agreed that you must be indicted for high crimes and misdemeanors. But the great question is as to just what we can charge you with.” “Sorry I can’t assist you,” the earth-man wrote. “How would it be if I were to slap your daughter’s face, or something? Or why not try me for general cussedness?” “That is just what we finally decided to do,” the ant-man wrote in reply. “We shall try you on general principles, and let the proper accusation develop from the evidence. “At some stage of the proceedings it will inevitably occur to some member of the council to suggest that you be charged with treason to Yuri, whereupon two members of the council, whom I have won over to the cause of my daughter, will raise the objection that Yuri is not our king. This will be the signal for the proclaiming of Queen Formis. If you will waive counsel the trial can take place to-morrow.” “I will waive anything,” Myles replied, “counsel, immunity, extradition, anything in order to speed up my return to Cupia, where Lilla awaits in some dire extremity.” “All right,” Doggo wrote, and the conference was at an end. The morrow would decide the ascendancy of Myles Cabot or the Prince Yuri over the new continent. IV THE COUP D’ETAT The next morning Myles Cabot was led under guard to the council chamber of the dread thirteen: Formis and her twelve advisers. The accused was placed in a wicker cage, from which he surveyed his surroundings as the proceedings opened. 19 On a raised platform stood the ant queen, surmounted by a scarlet canopy, which set off the perfect proportions of her jet-black body. On each side of her stood six refined and intelligent ant-men, her councillors. One of the twelve was Doggo. Messenger ants hurried hither and thither. First the accusation was read, Myles being furnished with a written copy. The witnesses were then called. They were veterans who had served in the wars in which Cabot had twice freed Cupia from the domination of its Formian oppressors. They spoke with bitterness of the downfall of their beloved Formia. Their testimony was brief. Then the accused was asked if he wished to say anything in his own behalf. Myles rose, then shrugged his shoulders, sat down again, and wrote: “I fully realize the futility of making an argument through the antennae of another.” Whereupon the queen and the council went into executive session. Their remarks were not intended for the eyes of the prisoner, but he soon observed that some kind of a dispute was on between Doggo, supported by two councillors named Emu and Fum on one side, and a councillor named Barth on the other. As this dispute reached its height, a messenger ant rushed in and held up one paw. Cabot’s interpreter, not deeming this a part of the executive session, obligingly translated the following into writing: The messenger: “Yuri lives and reigns over Cupia. It is his command that Cabot die.” Barth: “It is the radio. Know then, O Queen, and ye, members of the council, that when we fled across the boiling seas under the gallant leadership of Prince Yuri, the man with the heart of a Formian, he brought with him one of those powerful radio sets invented by the beast who is our prisoner here to-day. “Supporters of Yuri still remained among the Cupians, and he has been in constant communication with these ever since shortly after our arrival here. From them he learned of the return of Myles Cabot to the planet Minos. 20 “Then Yuri disappeared. Those of us who were closest to him suspected that he had gone back across the boiling seas to claim as his own the throne of Cupia. But we hesitated to announce this until we were sure, for we feared that some of our own people would regard his departure as desertion. Yet who can blame him for returning to his father-land and to the throne which is his by rights?” To which the messenger added: “And he offers to give us back our own old country, if we too will return across the boiling seas again.” “It is a lie!” Doggo shouted. “Yuri, usurper of the thrones of two continents. Bah!” shouted Emu. “Yuri, our rightful leader,” shouted Barth. “Give us a queen of our own race,” shouted Fum. “Release the prisoner,” shouted the Queen. And that is all that Myles learned of the conversation, for his interpreter at this juncture stopped writing and obeyed the queen. The earth-man was free! With one bound he gained the throne, where fighting was already in progress between the two factions. Barth and Doggo were rolling over and over on the floor in a death grapple, while the ant-queen had backed to the rear of the stage, closely guarded by Emu and Fum. Seizing one of the pikes which supported the scarlet canopy, Myles wrenched it loose and drove it into the thorax of Barth. In another instant the earth-man and Doggo stood beside the queen. Ant-men now came pouring into the chamber through all the entrances, taking sides as they entered and sized up the situation. If it had still been in vogue among the Formians to be known by numbers rather than names, and to have these identifying numbers painted on the backs of their abdomens followed by the numbers of those whom they had defeated in the duels so common among them, then many a Formian would have “got the number” of many another, that day.
|
C. Venus
|
What previous approaches are considered?
|
### Introduction
Keyword detection is like searching for a needle in a haystack: the detector must listen to continuously streaming audio, ignoring nearly all of it, yet still triggering correctly and instantly. In the last few years, with the advent of voice assistants, keyword spotting has become a common way to initiate a conversation with them (e.g. "Ok Google", "Alexa", or "Hey Siri"). As the assistant use cases spread through a variety of devices, from mobile phones to home appliances and further into the internet-of-things (IoT) –many of them battery powered or with restricted computational capacity, it is important for the keyword spotting system to be both high-quality as well as computationally efficient. Neural networks are core to the state of-the-art keyword spotting systems. These solutions, however, are not developed as a single deep neural network (DNN). Instead, they are traditionally comprised of different subsystems, independently trained, and/or manually designed. For example, a typical system is composed by three main components: 1) a signal processing frontend, 2) an acoustic encoder, and 3) a separate decoder. Of those components, it is the last two that make use of DNNs along with a wide variety of decoding implementations. They range from traditional approaches that make use of a Hidden Markov Model (HMM) to characterize acoustic features from a DNN into both "keyword" and "background" (i.e. non-keyword speech and noise) classes BIBREF0 , BIBREF1 , BIBREF2 , BIBREF3 , BIBREF4 . Simpler derivatives of that approach perform a temporal integration computation that verifies the outputs of the acoustic model are high in the right sequence for the target keyword in order to produce a single detection likelyhood score BIBREF5 , BIBREF6 , BIBREF7 , BIBREF8 , BIBREF9 . Other recent systems make use of CTC-trained DNNs –typically recurrent neural networks (RNNs) BIBREF10 , or even sequence-to-sequence trained models that rely on beam search decoding BIBREF11 . This last family of systems is the closest to be considered end-to-end, however they are generally too computationally complex for many embedded applications. Optimizing independent components, however, creates added complexities and is suboptimal in quality compared to doing it jointly. Deployment also suffers due to the extra complexity, making it harder to optimize resources (e.g. processing power and memory consumption). The system described in this paper addresses those concerns by learning both the encoder and decoder components into a single deep neural network, jointly optimizing to directly produce the detection likelyhood score. This system could be trained to subsume the signal processing frontend as well as in BIBREF2 , BIBREF12 , but it is computationally costlier to replace highly optimized fast fourier transform implementations with a neural network of equivalent quality. However, it is something we consider exploring in the future. Overall, we find this system provides state of the art quality across a number of audio and speech conditions compared to a traditional, non end-to-end baseline system described in BIBREF13 . Moreover, the proposed system significantly reduces the resource requirements for deployment by cutting computation and size over five times compared to the baseline system. The rest of the paper is organized as follows. In Section SECREF2 we present the architecture of the keyword spotting system; in particular the two main contributions of this work: the neural network topology, and the end-to-end training methodology. Next, in Section SECREF3 we describe the experimental setup, and the results of our evaluations in Section SECREF4 , where we compare against the baseline approach of BIBREF13 . Finally, we conclude with a discussion of our findings in Section SECREF5 . ### End-to-End system
This paper proposes a new end-to-end keyword spotting system that by subsuming both the encoding and decoding components into a single neural network can be trained to produce directly an estimation (i.e. score) of the presence of a keyword in streaming audio. The following two sections cover the efficient memoized neural network topology being utilized, as well as the method to train the end-to-end neural network to directly produce the keyword spotting score. ### Efficient memoized neural network topology
We make use of a type of neural network layer topology called SVDF (single value decomposition filter), originally introduced in BIBREF14 to approximate a fully connected layer with a low rank approximation. As proposed in BIBREF14 and depicted in equation EQREF2 , the activation INLINEFORM0 for each node INLINEFORM1 in the rank-1 SVDF layer at a given inference step INLINEFORM2 can be interpreted as performing a mix of selectivity in time ( INLINEFORM3 ) with selectivity in the feature space ( INLINEFORM4 ) over a sequence of input vectors INLINEFORM5 of size INLINEFORM6 . DISPLAYFORM0 This is equivalent to performing, on an SVDF layer of INLINEFORM0 nodes, INLINEFORM1 1-D convolutions of the feature filters INLINEFORM2 (by "sliding" each of the INLINEFORM3 filters on the input feature frames, with a stride of INLINEFORM4 ), and then filtering each of INLINEFORM5 output vectors (of size INLINEFORM6 ) with the time filters INLINEFORM7 . A more general and efficient interpretation, depicted in Figure FIGREF3 , is that the layer is just processing a single input vector INLINEFORM0 at a time. Thus for each node INLINEFORM1 , the input INLINEFORM2 goes through the feature filter INLINEFORM3 , and the resulting scalar output gets concatenated to those INLINEFORM4 computed in previous inference steps. The memory is either initialized to zeros during training for the first INLINEFORM5 inferences. Finally the time filter INLINEFORM6 is applied to them. This is how stateful networks work, where the layer is able to memorize the past within its state. Different from typical recurrent approaches though, and other types of stateful layers BIBREF15 , the SVDF does not recur the outputs into the state (memory), nor rewrites the entirety of the state with each iteration. Instead, the memory keeps each inference's state isolated from subsequent runs, just pushing new entries and popping old ones based on the memory size INLINEFORM7 configured for the layer. This also means that by stacking SVDF layers we are extending the receptive field of the network. For example, a DNN with INLINEFORM8 stacked layers, each with a memory of INLINEFORM9 , means that the DNN is taking into account inputs as old as INLINEFORM10 . This approach works very well for streaming execution, like in speech, text, and other sequential processing, where we constantly process new inputs from a large, possibly infinite sequence but do not want to attend to all of it. An implementation is available at BIBREF16 . This layer topology offers a number of benefits over other approaches. Compared with the convolutions use in BIBREF13 , it allows finer-grained control of the number of parameters and computation, given that the SVDF is composed by several relatively small filters. This is useful when selecting a tradeoff between quality, size and computation. Moreover, because of this characteristic, the SVDF allows creating very small networks that outperform other topologies which operate at larger granularity (e.g. our first stage, always-on network has about 13K parameters BIBREF7 ). The SVDF also pairs very well with linear “bottleneck” layers to significantly reduce the parameter count as in BIBREF17 , BIBREF18 , and more recently in BIBREF9 . And because it allows for creating evenly sized deep networks, we can insert them throughout the network as in Figure FIGREF8 . Another benefit is that due to the explicit sizing of the receptive field it allows for a fine grained control over how much to remember from the past. This has resulted in SVDF outperforming RNN-LSTMs, which do not benefit from, and are potentially hurt by, paying attention to theoretically infinite past. It also avoids having complex logic to reset the state every few seconds as in BIBREF11 . ### Method to train the end-to-end neural network
The goal of our end-to-end training is to optimize the network to produce the likelihood score, and to do so as precisely as possible. This means have a high score right at the place where the last bit of the keyword is present in the streaming audio, and not before and particularly not much after (i.e. a "spiky" behaviour is desirable). This is important since the system is bound to an operating point defined by a threshold (between 0 and 1) that is choosen to strike a balance between false-accepts and false-rejects, and a smooth likelyhood curve would add variability to the firing point. Moreover, any time between the true end of the keyword and the point where the score meets the threshold will become latency in the system (e.g. the "assistant" will be slow to respond). A common drawback of CTC-trained RNNs BIBREF19 we aim to avoid. We generate input sequences composed of pairs < INLINEFORM0 , INLINEFORM1 >. Where INLINEFORM2 is a 1D tensor corresponding to log-mel filter-bank energies produced by a front-end as in BIBREF5 , BIBREF14 , BIBREF13 , and INLINEFORM3 is the class label (one of INLINEFORM4 ). Each tensor INLINEFORM5 is first force-aligned from annotated audio utterances, using a large LVCSR system, to break up the components of the keyword BIBREF20 . For example, "ok google" is broken into: "ou", "k", "eI", "<silence>", "g", "u", "g", "@", "l". Then we assign labels of 1 to all sequence entries, part of a true keyword utterance, that correspond to the last component of the keyword ("l" in our "ok google" example). All other entries are assigned a label of 0, including those that are part of the keyword but that are not its last component. See Figure FIGREF6 . Additionally, we tweak the label generation by adding a fixed amount of entries with a label of 1, starting from the first vector INLINEFORM6 corresponding to the final keyword component. This is with the intetion of balancing the amount of negative and positive examples, in the same spirit as BIBREF0 . This proved important to make training stable, as otherwise the amount of negative examples overpowered the positive ones. The end-to-end training uses a simple frame-level cross-entropy (CE) loss that for the feature vector INLINEFORM0 is defined by INLINEFORM1 , where INLINEFORM2 are the parameters of the network, INLINEFORM3 the INLINEFORM4 th output of the final softmax. Our training recipe uses asynchronous stochastic gradient descent (ASGD) to produce a single neural network that can be fed streaming input features and produce a detection score. We propose two options to this recipe: Encoder+decoder. A two stage training procedure where we first train an acoustic encoder, as in BIBREF5 , BIBREF14 , BIBREF13 , and then a decoder from the outputs of the encoder (rather than filterbank energies) and the labels from SECREF5 . We do this in a single DNN by creating a final topology that is composed of the encoder and its pre-trained parameters (including the softmax), followed by the decoder. See Figure FIGREF8 . During the second stage of training the encoder parameters are frozen, such that only the decoder is trained. This recipe useful on models that tend to overfit to parts of the training set. End-to-end. In this option, we train the DNN end-to-end directly, with the sequences from SECREF5 . The DNN may use any topology, but we use that of the encoder+decoder, except for the intermediate encoder softmax. See Figure FIGREF8 . Similar to the encoder+decoder recipe, we can also initialize the encoder part with a pre-trained model, and use an adaptation rate INLINEFORM0 to tune how much the encoder part is being adjusted (e.g. a rate of 0 is equivalent to the encoder+decoder recipe). This end-to-end pipeline, where the entirety of the topology's parameters are adjusted, tends to outperform the encoder+decoder one, particularly in smaller sized models which do not tend to overfit. ### Experimental setup
In order to determine the effectiveness of our approach, we compare against a known keyword spotting system proposed in BIBREF13 . This section describes the setups used in the results section. ### Front-end
Both setups use the same front-end, which generates 40-dimensional log-mel filter-bank energies out of 30ms windows of streaming audio, with overlaps of 10ms. The front-end can be queried to produce a sequence of contiguous frames centered around the current frame INLINEFORM0 . Older frames are said to form the left context INLINEFORM1 , and newer frames form the right context INLINEFORM2 . Additionally, the sequences can be requested with a given stride INLINEFORM3 . ### Baseline model setup
Our baseline system (Baseline_1850K) is taken from BIBREF13 . It consists of a DNN trained to predict subword targets within the keywords. The input to the DNN consists of a sequence with INLINEFORM0 frames of left and INLINEFORM1 frames of right context; each with a stride of INLINEFORM2 . The topology consists of a 1-D convolutional layer with 92 filters (of shape 8x8 and stride 8x8), followed by 3 fully-connected layers with 512 nodes and a rectified linear unit activation each. A final softmax output predicts the 7 subword targets, obtained from the same forced alignment process described in SECREF5 . This results in the baseline DNN containing 1.7M parameters, and performing 1.8M multiply-accumulate operations per inference (every 30ms of streaming audio). A keyword spotting score between 0 and 1 is computed by first smoothing the posterior values, averaging them over a sliding window of the previous 100 frames with respect to the current INLINEFORM3 ; the score is then defined as the largest product of the smoothed posteriors in the sliding window as originally proposed in BIBREF6 . ### End-to-end model setup
The end-to-end system (prefix E2E) uses the DNN topology depicted in Figure FIGREF8 . We present results with 3 distinct size configurations (infixes 700K, 318K, and 40K) each representing the number of approximate parameters, and 2 types of training recipes (suffixes 1stage and 2stage) corresponding to end-to-end and encoder+decoder respectively, as described in UID7 . The input to all DNNs consist of a sequence with INLINEFORM0 frames of left and INLINEFORM1 frames of right context; each with a stride of INLINEFORM2 . More specifically, the E2E_700K model uses INLINEFORM3 nodes in the first 4 SVDF layers, each with a memory INLINEFORM4 , with intermediate bottleneck layers each of size 64; the following 3 SVDF layers have INLINEFORM5 nodes, each with a memory INLINEFORM6 . This model performs 350K multiply-accumulate operations per inference (every 20ms of streaming audio). The E2E_318K model uses INLINEFORM7 nodes in the first 4 SVDF layers, each with a memory INLINEFORM8 , with intermediate bottleneck layers each of size 64; the remainder layers are the same as E2E_700K. This model performs 159K multiply-accumulate operations per inference. Finally, the E2E_40K model uses INLINEFORM9 nodes in the first 4 SVDF layers, each with a memory INLINEFORM10 , with intermediate bottleneck layers each of size 32; the remainder layers are the same as the other two models. This model performs 20K multiply-accumulate operations per inference. ### Dataset
The training data for all experiments consists of 1 million anonymized hand-transcribed utterances of the keywords "Ok Google" and "Hey Google", with an even distribution. To improve robustness, we create "multi-style" training data by synthetically distorting the utterances, simulating the effect of background noise and reverberation. 8 distorted utterances are created for each original utterance; noise samples used in this process are extracted from environmental recordings of everyday events, music, and Youtube videos. Results are reported on four sets representative of various environmental conditions: Clean non-accented contains 170K non-accented english utterances of the keywords in "clean" conditions, plus 64K samples without the keywords (1K hours); Clean accented has 153K english utterances of the keywords with Australian, British, and Indian accents (also in "clean" conditions), plus 64K samples without the keywords (1K hours); High pitched has 1K high pitched utterances of the keywords, and 64K samples without them (1K hours); Query logs contains 110K keyword and 21K non-keyword utterances, collected from anonymized voice search queries. This last set contains background noises from real living conditions. ### Results
Our goal is to compare the efectiviness of the proposed approach against the baseline system described in BIBREF13 . We evaluate the false-reject (FR) and false-accept (FA) tradeoff across several end-to-end models of distinct sizes and computational complexities. As can be seen in the Receiver Operating Characteristic (ROC) curves in Figure FIGREF14 , the 2 largest end-to-end models, with 2-stage training, significantly outperform the recognition quality of the much larger and complex Baseline_1850K system. More specifically, E2E_318K_2stage and E2E_700K_2stage show up to 60% relative FR rate reduction over Baseline_1850K in most test conditions. Moreover, E2E_318K_2stage uses only about 26% of the computations that Baseline_1850K uses (once normalizing their execution rates over time), but still shows significant improvements. We also explore end-to-end models at a size that, as described in BIBREF7 , is small enough, in both size and computation, to be executed continuously with very little power consumption. These 2 models, E2E_40K_1stage and E2E_40K_2stage, also explore the capacity of end-to-end training (1stage) versus encoder+decoder training (2stage). As can be appreciated in the ROC curves, 1stage training outperforms 2stage training on all conditions, but particularly on both "clean" environments where it gets fairly close to the performance of the baseline setup. That is a significant achievement considering E2E_40K_1stage has 2.3% the parameters and performs 3.2% the computations of Baseline_1850K. Table TABREF13 compares the recognition quality of all setups by fixing on a very low false-accept rate of 0.1 FA per hour on a dataset containing only negative (i.e. non-keyword) utterances. Thus the table shows the false-reject rates at that operating point. Here we can appreciate similar trends as those described above: the 2 largest end-to-end models outperforms the baseline across all datasets, reducing FR rate about 40% on the clean conditions and 40%-20% on the other 2 sets depending on the model size. This table also shows how 1stage outperforms 2stage for small size models, and presents similar FR rates as Baseline_1850K on clean conditions. ### Conclusion
We presented a system for keyword spotting that by combining an efficient topology and two types of end-to-end training can significantly ourperform previous appraoches, at a much lower cost of size and computation. We specifically show how it beats the performance of a setup taken from BIBREF13 with models over 5 times smaller, and even get close to the same performance with a model over 40 times smaller. Our approach provides further benefits of not requiring anything other than a front-end and a neural network to perform the detection, and thus it is easier to extend to newer keywords and/or fine-tune with new training data. Future work includes exploring other loss-functions, as well as generalizing multi-channel support. Fig. 2. Input sequence generation for “Ok google”. Fig. 1. A single node (m) in the SVDF layer. Fig. 3. End-to-end topology trained to predict the keyword likelihood score. Bottleneck layers reduce parameters and computation. The intermediate softmax is used in encoder+decoder training only. Table 1. FR rate over 4 test conditions at 0.1 FAh level. Fig. 4. ROC curves under different conditions.
|
Our baseline system (Baseline_1850K) is taken from BIBREF13 .
|
What clustering algorithm is used on top of the VerbNet-specialized representations?
|
### Introduction
Playing a key role in conveying the meaning of a sentence, verbs are famously complex. They display a wide range of syntactic-semantic behaviour, expressing the semantics of an event as well as relational information among its participants BIBREF0 , BIBREF1 , BIBREF2 . Lexical resources which capture the variability of verbs are instrumental for many Natural Language Processing (NLP) applications. One of the richest verb resources currently available for English is VerbNet BIBREF3 , BIBREF4 . Based on the work of Levin Levin:1993book, this largely hand-crafted taxonomy organises verbs into classes on the basis of their shared syntactic-semantic behaviour. Providing a useful level of generalisation for many NLP tasks, VerbNet has been used to support semantic role labelling BIBREF5 , BIBREF6 , semantic parsing BIBREF7 , word sense disambiguation BIBREF8 , discourse parsing BIBREF9 , information extraction BIBREF10 , text mining applications BIBREF11 , BIBREF12 , research into human language acquisition BIBREF13 , and other tasks. This benefit for English NLP has motivated the development of VerbNets for languages such as Spanish and Catalan BIBREF14 , Czech BIBREF15 , and Mandarin BIBREF16 . However, end-to-end manual resource development using Levin's methodology is extremely time consuming, even when supported by translations of English VerbNet classes to other languages BIBREF17 , BIBREF18 . Approaches which aim to learn verb classes automatically offer an attractive alternative. However, existing methods rely on carefully engineered features that are extracted using sophisticated language-specific resources BIBREF19 , BIBREF17 , BIBREF20 , ranging from accurate parsers to pre-compiled subcategorisation frames BIBREF21 , BIBREF22 , BIBREF23 . Such methods are limited to a small set of resource-rich languages. It has been argued that VerbNet-style classification has a strong cross-lingual element BIBREF24 , BIBREF2 . In support of this argument, Majewska:2017lre have shown that English VerbNet has high translatability across different, even typologically diverse languages. Based on this finding, we propose an automatic approach which exploits readily available annotations for English to facilitate efficient, large-scale development of VerbNets for a wide set of target languages. Recently, unsupervised methods for inducing distributed word vector space representations or word embeddings BIBREF25 have been successfully applied to a plethora of NLP tasks BIBREF26 , BIBREF27 , BIBREF28 . These methods offer an elegant way to learn directly from large corpora, bypassing the feature engineering step and the dependence on mature NLP pipelines (e.g., POS taggers, parsers, extraction of subcategorisation frames). In this work, we demonstrate how these models can be used to support automatic verb class induction. Moreover, we show that these models offer the means to exploit inherent cross-lingual links in VerbNet-style classification in order to guide the development of new classifications for resource-lean languages. To the best of our knowledge, this proposition has not been investigated in previous work. There has been little work on assessing the suitability of embeddings for capturing rich syntactic-semantic phenomena. One challenge is their reliance on the distributional hypothesis BIBREF29 , which coalesces fine-grained syntactic-semantic relations between words into a broad relation of semantic relatedness (e.g., coffee:cup) BIBREF30 , BIBREF31 . This property has an adverse effect when word embeddings are used in downstream tasks such as spoken language understanding BIBREF32 , BIBREF33 or dialogue state tracking BIBREF34 , BIBREF35 . It could have a similar effect on verb classification, which relies on the similarity in syntactic-semantic properties of verbs within a class. In summary, we explore three important questions in this paper: (Q1) Given their fundamental dependence on the distributional hypothesis, to what extent can unsupervised methods for inducing vector spaces facilitate the automatic induction of VerbNet-style verb classes across different languages? (Q2) Can one boost verb classification for lower-resource languages by exploiting general-purpose cross-lingual resources such as BabelNet BIBREF36 , BIBREF37 or bilingual dictionaries such as PanLex BIBREF38 to construct better word vector spaces for these languages? (Q3) Based on the stipulated cross-linguistic validity of VerbNet-style classification, can one exploit rich sets of readily available annotations in one language (e.g., the full English VerbNet) to automatically bootstrap the creation of VerbNets for other languages? In other words, is it possible to exploit a cross-lingual vector space to transfer VerbNet knowledge from a resource-rich to a resource-lean language? To investigate Q1, we induce standard distributional vector spaces BIBREF39 , BIBREF40 from large monolingual corpora in English and six target languages. As expected, the results obtained with this straightforward approach show positive trends, but at the same time reveal its limitations for all the languages involved. Therefore, the focus of our work shifts to Q2 and Q3. The problem of inducing VerbNet-oriented embeddings is framed as vector space specialisation using the available external resources: BabelNet or PanLex, and (English) VerbNet. Formalised as an instance of post-processing semantic specialisation approaches BIBREF41 , BIBREF34 , our procedure is steered by two sets of linguistic constraints: 1) cross-lingual (translation) links between languages extracted from BabelNet (targeting Q2); and 2) the available VerbNet annotations for a resource-rich language. The two sets of constraints jointly target Q3. The main goal of vector space specialisation is to pull examples standing in desirable relations, as described by the constraints, closer together in the transformed vector space. The specialisation process can capitalise on the knowledge of VerbNet relations in the source language (English) by using translation pairs to transfer that knowledge to each of the target languages. By constructing shared bilingual vector spaces, our method facilitates the transfer of semantic relations derived from VerbNet to the vector spaces of resource-lean target languages. This idea is illustrated by Fig. FIGREF2 . Our results indicate that cross-lingual connections yield improved verb classes across all six target languages (thus answering Q2). Moreover, a consistent and significant boost in verb classification performance is achieved by propagating the VerbNet-style information from the source language (English) to any other target language (e.g., Italian, Croatian, Polish, Finnish) for which no VerbNet-style information is available during the fine-tuning process (thus answering Q3). We report state-of-the-art verb classification performance for all six languages in our experiments. For instance, we improve the state-of-the-art F-1 score from prior work from 0.55 to 0.79 for French, and from 0.43 to 0.74 for Brazilian Portuguese. ### Vector Space Specialisation
Our departure point is a state-of-the-art specialisation model for fine-tuning vector spaces termed Paragram BIBREF49 . The Paragram procedure injects similarity constraints between word pairs in order to make their vector space representations more similar; we term these the Attract constraints. Let INLINEFORM0 be the vocabulary consisting of the source language and target language vocabularies INLINEFORM1 and INLINEFORM2 , respectively. Let INLINEFORM3 be the set of word pairs standing in desirable lexical relations; these include: 1) verb pairs from the same VerbNet class (e.g. (en_transport, en_transfer) from verb class send-11.1); and 2) the cross-lingual synonymy pairs (e.g. (en_peace, fi_rauha)). Given the initial distributional space and collections of such Attract pairs INLINEFORM4 , the model gradually modifies the space to bring the designated word vectors closer together, working in mini-batches of size INLINEFORM5 . The method's cost function can be expressed as: DISPLAYFORM0 The first term of the method's cost function (i.e., INLINEFORM0 ) pulls the Attract examples INLINEFORM1 closer together (see Fig. FIGREF2 for an illustration). INLINEFORM2 refers to the current mini-batch of Attract constraints. This term is expressed as follows: DISPLAYFORM0 INLINEFORM0 is the standard rectified linear unit or the hinge loss function BIBREF50 , BIBREF51 . INLINEFORM1 is the “attract” margin: it determines how much vectors of words from Attract constraints should be closer to each other than to their negative examples. The negative example INLINEFORM2 for each word INLINEFORM3 in any Attract pair is always the vector closest to INLINEFORM4 taken from the pairs in the current mini-batch, distinct from the other word paired with INLINEFORM5 , and INLINEFORM6 itself. The second INLINEFORM0 term is the regularisation which aims to retain the semantic information encoded in the initial distributional space as long as this information does not contradict the used Attract constraints. Let INLINEFORM1 refer to the initial distributional vector of the word INLINEFORM2 and let INLINEFORM3 be the set of all word vectors present in the given mini-batch. If INLINEFORM4 denotes the L2 regularisation constant, this term can be expressed as: DISPLAYFORM0 The fine-tuning procedure effectively blends the knowledge from external resources (i.e., the input Attract set of constraints) with distributional information extracted directly from large corpora. We show how to propagate annotations from a knowledge source such as VerbNet from source to target by combining two types of constraints within the specialisation framework: a) cross-lingual (translation) links between languages, and b) available VerbNet annotations in a resource-rich language transformed into pairwise constraints. Cross-lingual constraints such as (pl_wojna, it_guerra) are extracted from BabelNet BIBREF36 , a large-scale resource which groups words into cross-lingual babel synsets (and is currently available for 271 languages). The wide and steadily growing coverage of languages in BabelNet means that our proposed framework promises to support the transfer of VerbNet-style information to numerous target languages (with increasingly high accuracy). To establish that the proposed transfer approach is in fact independent of the chosen cross-lingual information source, we also experiment with another cross-lingual dictionary: PanLex BIBREF38 , which was used in prior work on cross-lingual word vector spaces BIBREF52 , BIBREF53 . This dictionary currently covers around 1,300 language varieties with over 12 million expressions, thus offering support also for low-resource transfer settings. VerbNet constraints are extracted from the English VerbNet class structure in a straightforward manner. For each class INLINEFORM0 from the 273 VerbNet classes, we simply take the set of all INLINEFORM1 verbs INLINEFORM2 associated with that class, including its subclasses, and generate all unique pairs INLINEFORM3 so that INLINEFORM4 and INLINEFORM5 . Example VerbNet pairwise constraints are shown in Tab. TABREF15 . Note that VerbNet classes in practice contain verb instances standing in a variety of lexical relations, including synonyms, antonyms, troponyms, hypernyms, and the class membership is determined on the basis of connections between the syntactic patterns and the underlying semantic relations BIBREF54 , BIBREF55 . ### Clustering Algorithm
Given the initial distributional or specialised collection of target language vectors INLINEFORM0 , we apply an off-the-shelf clustering algorithm on top of these vectors in order to group verbs into classes. Following prior work BIBREF56 , BIBREF57 , BIBREF17 , we employ the MNCut spectral clustering algorithm BIBREF58 , which has wide applicability in similar NLP tasks which involve high-dimensional feature spaces BIBREF59 , BIBREF60 , BIBREF18 . Again, following prior work BIBREF17 , BIBREF61 , we estimate the number of clusters INLINEFORM1 using the self-tuning method of Zelnik:2004nips. This algorithm finds the optimal number by minimising a cost function based on the eigenvector structure of the word similarity matrix. We refer the reader to the relevant literature for further details. ### Results and Discussion
Cross-Lingual Transfer Model F-1 verb classification scores for the six target languages with different sets of constraints are summarised in Fig. FIGREF29 . We can draw several interesting conclusions. First, the strongest results on average are obtained with the model which transfers the VerbNet knowledge from English (as a resource-rich language) to the resource-lean target language (providing an answer to question Q3, Sect. SECREF1 ). These improvements are visible across all target languages, empirically demonstrating the cross-lingual nature of VerbNet-style classifications. Second, using cross-lingual constraints alone (XLing) yields strong gains over initial distributional spaces (answering Q1 and Q2). Fig. FIGREF29 also shows that cross-lingual similarity constraints are more beneficial than the monolingual ones, despite a larger total number of the monolingual constraints in each language (see Tab. TABREF18 ). This suggests that such cross-lingual similarity links are strong implicit indicators of class membership. Namely, target language words which map to the same source language word are likely to be synonyms and consequently end up in the same verb class in the target language. However, the cross-lingual links are even more useful as means for transferring the VerbNet knowledge, as evidenced by additional gains with XLing+VerbNet-EN. The absolute classification scores are the lowest for the two Slavic languages: pl and hr. This may be partially explained by the lowest number of cross-lingual constraints for the two languages covering only a subset of their entire vocabularies (see Tab. TABREF18 and compare the total number of constraints for hr and pl to the numbers for e.g. fi or fr). Another reason for weaker performance of these two languages could be their rich morphology, which induces data sparsity both in the initial vector space estimation and in the coverage of constraints. ### Further Discussion and Future Work
This work has proven the potential of transferring lexical resources from resource-rich to resource-poor languages using general-purpose cross-lingual dictionaries and bilingual vector spaces as means of transfer within a semantic specialisation framework. However, we believe that the proposed basic framework may be upgraded and extended across several research paths in future work. First, in the current work we have operated with standard single-sense/single-prototype representations, thus effectively disregarding the problem of verb polysemy. While several polysemy-aware verb classification models for English were developed recently BIBREF79 , BIBREF80 , the current lack of polysemy-aware evaluation sets in other languages impedes this line of research. Evaluation issues aside, one idea for future work is to use the Attract-Repel specialisation framework for sense-aware cross-lingual transfer relying on recently developed multi-sense/prototype word representations BIBREF81 , BIBREF82 . Another challenge is to apply the idea from this work to enable cross-lingual transfer of other structured lexical resources available in English such as FrameNet BIBREF44 , PropBank BIBREF45 , and VerbKB BIBREF83 . Other potential research avenues include porting the approach to other typologically diverse languages and truly low-resource settings (e.g., with only limited amounts of parallel data), as well as experiments with other distributional spaces, e.g. BIBREF84 . Further refinements of the specialisation and clustering algorithms may also result in improved verb class induction. ### Conclusion
We have presented a novel cross-lingual transfer model which enables the automatic induction of VerbNet-style verb classifications across multiple languages. The transfer is based on a word vector space specialisation framework, utilised to directly model the assumption of cross-linguistic validity of VerbNet-style classifications. Our results indicate strong improvements in verb classification accuracy across all six target languages explored. All automatically induced VerbNets are available at: github.com/cambridgeltl/verbnets. ### Acknowledgments
This work is supported by the ERC Consolidator Grant LEXICAL: Lexical Acquisition Across Languages (no 648909). The authors are grateful to the entire LEXICAL team, especially to Roi Reichart, and also to the three anonymous reviewers for their helpful and constructive suggestions. Figure 1: Transferring VerbNet information from a resource-rich to a resource-lean language through a word vector space: an English→ French toy example. Representations of words described by two types of ATTRACT constraints are pulled closer together in the joint vector space. (1) Monolingual pairwise constraints in English (e.g., (en_ruin, en_shatter), (en_destroy, en_undo)) reflect the EN VerbNet structure and are generated from the readily available verb classification in English (solid lines). They are used to specialise the distributional EN vector subspace for the VerbNet relation. (2) Cross-lingual English-French pairwise constraints (extracted from BabelNet) describe cross-lingual synonyms (i.e., translation links) such as (en_ruin, fr_ruiner) or (en_shatter, fr_fracasser) (dashed lines). The post-processing fine-tuning specialisation procedure based on (1) and (2) effectively transforms the initial distributional French vector subspace to also emphasise the VerbNet-style structure, facilitating the induction of verb classes in French. Table 1: Example pairwise ATTRACT constraints extracted from three VerbNet classes in English. Table 2: Statistics of the experimental setup for each target language: training/test data and constraints. Coverage refers to the percentage of test verbs represented in the target language vocabularies. Figure 2: F-1 scores in six target languages using the post-processing specialisation procedure from Sect. 2.1 and different sets of constraints: Distributional refers to the initial vector space in each target language; Mono-Syn is the vector space tuned using monolingual synonymy constraints from BabelNet; XLing uses cross-lingual EN-TARGET constraints from BabelNet (TARGET refers to any of the six target languages); XLing+VerbNet-EN is a fine-tuned vector space which uses both cross-lingual EN-TARGET constraints plus EN VerbNet constraints. Results are provided with (a) SGNS-BOW2 and (b) SGNS-DEPS source vector space in English for the XLing and XLing+VerbNet variants, see Sect. 3. Table 3: The effect of multilingual vector space specialisation. Results are reported for FR and IT using: a) cross-lingual constraints only (XLing); and b) the VerbNet transfer model (XLing+VN). Table 4: Comparison of verb classification (VC) and verb semantic similarity (Sim) for English. VC is measured on the EN test set of Sun et al. (2008). Sim is measured on SimVerb-3500 (Gerz et al., 2016). The scores are Spearman’s ρ correlation scores. EN-Dist is the initial distributional English vector space: SGNS-BOW2; EN-VN is the same space transformed using monolingual EN VerbNet constraints only, an upper bound for the specialisation-based approach in EN. Figure 3: F-1 scores when PanLex is used as the source of cross-lingual ATTRACT constraints (instead of BabelNet). EN Vectors: SGNS-BOW2.
|
MNCut spectral clustering algorithm BIBREF58
|
How does Giles change with the knowledge of his aging?
A. He resigns to his fate, because he doesn’t know what else to do.
B. He doesn’t. He goes right back to doing what he’d been doing out of habit.
C. He feels a new fondness for his son and family.
D. He shows a much greater appreciation for every aspect of his life.
|
The Dwindling Years He didn’t expect to be last—but neither did he anticipate the horror of being the first! By LESTER DEL REY Illustrated by JOHNS NEARLY TWO hundred years of habit carried the chairman of Exodus Corporation through the morning ritual of crossing the executive floor. Giles made the expected comments, smiled the proper smiles and greeted his staff by the right names, but it was purely automatic. Somehow, thinking had grown difficult in the mornings recently. Inside his private office, he dropped all pretense and slumped into the padding of his chair, gasping for breath and feeling his heart hammering in his chest. He’d been a fool to come to work, he realized. But with the Procyon shuttle arriving yesterday, there was no telling what might turn up. Besides, that fool of a medicist had sworn the shot would cure any allergy or asthma. Giles heard his secretary come in, but it wasn’t until the smell of the coffee reached his nose that he looked up. She handed him a filled cup and set the carafe down on the age-polished surface of the big desk. She watched solicitously as he drank. “That bad, Arthur?” she asked. “Just a little tired,” he told her, refilling the cup. She’d made the coffee stronger than usual and it seemed to cut through some of the thickness in his head. “I guess I’m getting old, Amanda.” She smiled dutifully at the time-worn joke, but he knew she wasn’t fooled. She’d cycled to middle age four times in her job and she probably knew him better than he knew himself—which wouldn’t be hard, he thought. He’d hardly recognized the stranger in the mirror as he tried to shave. His normal thinness had looked almost gaunt and there were hollows in his face and circles under his eyes. Even his hair had seemed thinner, though that, of course, was impossible. “Anything urgent on the Procyon shuttle?” he asked as she continue staring at him with worried eyes. SHE JERKED her gaze away guiltily and turned to the incoming basket. “Mostly drugs for experimenting. A personal letter for you, relayed from some place I never heard of. And one of the super-light missiles! They found it drifting half a light-year out and captured it. Jordan’s got a report on it and he’s going crazy. But if you don’t feel well—” “I’m all right!” he told her sharply. Then he steadied himself and managed to smile. “Thanks for the coffee, Amanda.” She accepted dismissal reluctantly. When she was gone, he sat gazing at the report from Jordan at Research. For eighty years now, they’d been sending out the little ships that vanished at greater than the speed of light, equipped with every conceivable device to make them return automatically after taking pictures of wherever they arrived. So far, none had ever returned or been located. This was the first hope they’d found that the century-long trips between stars in the ponderous shuttles might be ended and he should have been filled with excitement at Jordan’s hasty preliminary report. He leafed through it. The little ship apparently had been picked up by accident when it almost collided with a Sirius-local ship. Scientists there had puzzled over it, reset it and sent it back. The two white rats on it had still been alive. Giles dropped the report wearily and picked up the personal message that had come on the shuttle. He fingered the microstrip inside while he drank another coffee, and finally pulled out the microviewer. There were three frames to the message, he saw with some surprise. He didn’t need to see the signature on the first projection. Only his youngest son would have sent an elaborate tercentenary greeting verse—one that would arrive ninety years too late! Harry had been born just before Earth passed the drastic birth limitation act and his mother had spoiled him. He’d even tried to avoid the compulsory emigration draft and stay on with his mother. It had been the bitter quarrels over that which had finally broken Giles’ fifth marriage. Oddly enough, the message in the next frame showed none of that. Harry had nothing but praise for the solar system where he’d been sent. He barely mentioned being married on the way or his dozen children, but filled most of the frame with glowing description and a plea for his father to join him there! GILES SNORTED and turned to the third frame, which showed a group picture of the family in some sort of vehicle, against the background of an alien but attractive world. He had no desire to spend ninety years cooped up with a bunch of callow young emigrants, even in one of the improved Exodus shuttles. And even if Exodus ever got the super-light drive working, there was no reason he should give up his work. The discovery that men could live practically forever had put an end to most family ties; sentiment wore thin in half a century—which wasn’t much time now, though it had once seemed long enough. Strange how the years seemed to get shorter as their number increased. There’d been a song once—something about the years dwindling down. He groped for the lines and couldn’t remember. Drat it! Now he’d probably lie awake most of the night again, trying to recall them. The outside line buzzed musically, flashing Research’s number. Giles grunted in irritation. He wasn’t ready to face Jordan yet. But he shrugged and pressed the button. The intense face that looked from the screen was frowning as Jordan’s eyes seemed to sweep around the room. He was still young—one of the few under a hundred who’d escaped deportation because of special ability—and patience was still foreign to him. Then the frown vanished as an expression of shock replaced it, and Giles felt a sinking sensation. If he looked that bad— But Jordan wasn’t looking at him; the man’s interest lay in the projected picture from Harry, across the desk from the communicator. “Antigravity!” His voice was unbelieving as he turned his head to face the older man. “What world is that?” Giles forced his attention on the picture again and this time he noticed the vehicle shown. It was enough like an old model Earth conveyance to pass casual inspection, but it floated wheellessly above the ground. Faint blur lines indicated it had been moving when the picture was taken. “One of my sons—” Giles started to answer. “I could find the star’s designation....” Jordan cursed harshly. “So we can send a message on the shuttle, begging for their secret in a couple of hundred years! While a hundred other worlds make a thousand major discoveries they don’t bother reporting! Can’t the Council see anything ?” Giles had heard it all before. Earth was becoming a backwater world; no real progress had been made in two centuries; the young men were sent out as soon as their first fifty years of education were finished, and the older men were too conservative for really new thinking. There was a measure of truth in it, unfortunately. “They’ll slow up when their populations fill,” Giles repeated his old answers. “We’re still ahead in medicine and we’ll get the other discoveries eventually, without interrupting the work of making the Earth fit for our longevity. We can wait. We’ll have to.” THE YOUNGER man stared at him with the strange puzzled look Giles had seen too often lately. “Damn it, haven’t you read my report? We know the super-light drive works! That missile reached Sirius in less than ten days. We can have the secret of this antigravity in less than a year! We—” “Wait a minute.” Giles felt the thickness pushing back at his mind and tried to fight it off. He’d only skimmed the report, but this made no sense. “You mean you can calibrate your guiding devices accurately enough to get a missile where you want it and back?” “ What? ” Jordan’s voice rattled the speaker. “Of course not! It took two accidents to get the thing back to us—and with a half-light-year miss that delayed it about twenty years before the Procyon shuttle heard its signal. Pre-setting a course may take centuries, if we can ever master it. Even with Sirius expecting the missiles and ready to cooperate. I mean the big ship. We’ve had it drafted for building long enough; now we can finish it in three months. We know the drive works. We know it’s fast enough to reach Procyon in two weeks. We even know life can stand the trip. The rats were unharmed.” Giles shook his head at what the other was proposing, only partly believing it. “Rats don’t have minds that could show any real damage such as the loss of power to rejuvenate. We can’t put human pilots into a ship with our drive until we’ve tested it more thoroughly, Bill, even if they could correct for errors on arrival. Maybe if we put in stronger signaling transmitters....” “Yeah. Maybe in two centuries we’d have a through route charted to Sirius. And we still wouldn’t have proved it safe for human pilots. Mr. Giles, we’ve got to have the big ship. All we need is one volunteer!” It occurred to Giles then that the man had been too fired with the idea to think. He leaned back, shaking his head again wearily. “All right, Bill. Find me one volunteer. Or how about you? Do you really want to risk losing the rest of your life rather than waiting a couple more centuries until we know it’s safe? If you do, I’ll order the big ship.” Jordan opened his mouth and for a second Giles’ heart caught in a flux of emotions as the man’s offer hovered on his lips. Then the engineer shut his mouth slowly. The belligerence ran out of him. He looked sick, for he had no answer. NO SANE man would risk a chance for near eternity against such a relatively short wait. Heroism had belonged to those who knew their days were numbered, anyhow. “Forget it, Bill,” Giles advised. “It may take longer, but eventually we’ll find a way. With time enough, we’re bound to. And when we do, the ship will be ready.” The engineer nodded miserably and clicked off. Giles turned from the blank screen to stare out of the windows, while his hand came up to twist at the lock of hair over his forehead. Eternity! They had to plan and build for it. They couldn’t risk that plan for short-term benefits. Usually it was too easy to realize that, and the sight of the solid, time-enduring buildings outside should have given him a sense of security. Today, though, nothing seemed to help. He felt choked, imprisoned, somehow lost; the city beyond the window blurred as he studied it, and he swung the chair back so violently that his hand jerked painfully on the forelock he’d been twisting. Then he was staring unbelievingly at the single white hair that was twisted with the dark ones between his fingers. Like an automaton, he bent forward, his other hand groping for the mirror that should be in one of the drawers. The dull pain in his chest sharpened and his breath was hoarse in his throat, but he hardly noticed as he found the mirror and brought it up. His eyes focused reluctantly. There were other white strands in his dark hair. The mirror crashed to the floor as he staggered out of the office. It was only two blocks to Giles’ residence club, but he had to stop twice to catch his breath and fight against the pain that clawed at his chest. When he reached the wood-paneled lobby, he was barely able to stand. Dubbins was at his side almost at once, with a hand under his arm to guide him toward his suite. “Let me help you, sir,” Dubbins suggested, in the tones Giles hadn’t heard since the man had been his valet, back when it was still possible to find personal servants. Now he managed the club on a level of quasi-equality with the members. For the moment, though, he’d slipped back into the old ways. GILES FOUND himself lying on his couch, partially undressed, with the pillows just right and a long drink in his hand. The alcohol combined with the reaction from his panic to leave him almost himself again. After all, there was nothing to worry about; Earth’s doctors could cure anything. “I guess you’d better call Dr. Vincenti,” he decided. Vincenti was a member and would probably be the quickest to get. Dubbins shook his head. “Dr. Vincenti isn’t with us, sir. He left a year ago to visit a son in the Centauri system. There’s a Dr. Cobb whose reputation is very good, sir.” Giles puzzled over it doubtfully. Vincenti had been an oddly morose man the last few times he’d seen him, but that could hardly explain his taking a twenty-year shuttle trip for such a slim reason. It was no concern of his, though. “Dr. Cobb, then,” he said. Giles heard the other man’s voice on the study phone, too low for the words to be distinguishable. He finished the drink, feeling still better, and was sitting up when Dubbins came back. “Dr. Cobb wants you to come to his office at once, sir,” he said, dropping to his knee to help Giles with his shoes. “I’d be pleased to drive you there.” Giles frowned. He’d expected Cobb to come to him. Then he grimaced at his own thoughts. Dubbins’ manners must have carried him back into the past; doctors didn’t go in for home visits now—they preferred to see their patients in the laboratories that housed their offices. If this kept on, he’d be missing the old days when he’d had a mansion and counted his wealth in possessions, instead of the treasures he could build inside himself for the future ahead. He was getting positively childish! Yet he relished the feeling of having Dubbins drive his car. More than anything else, he’d loved being driven. Even after chauffeurs were a thing of the past, Harry had driven him around. Now he’d taken to walking, as so many others had, for even with modern safety measures so strict, there was always a small chance of some accident and nobody had any desire to spend the long future as a cripple. “I’ll wait for you, sir,” Dubbins offered as they stopped beside the low, massive medical building. It was almost too much consideration. Giles nodded, got out and headed down the hall uncertainly. Just how bad did he look? Well, he’d soon find out. He located the directory and finally found the right office, its reception room wall covered with all the degrees Dr. Cobb had picked up in some three hundred years of practice. Giles felt better, realizing it wouldn’t be one of the younger men. COBB APPEARED himself, before the nurse could take over, and led Giles into a room with an old-fashioned desk and chairs that almost concealed the cabinets of equipment beyond. He listened as Giles stumbled out his story. Halfway through, the nurse took a blood sample with one of the little mosquito needles and the machinery behind the doctor began working on it. “Your friend told me about the gray hair, of course,” Cobb said. At Giles’ look, he smiled faintly. “Surely you didn’t think people could miss that in this day and age? Let’s see it.” He inspected it and began making tests. Some were older than Giles could remember—knee reflex, blood pressure, pulse and fluoroscope. Others involved complicated little gadgets that ran over his body, while meters bobbed and wiggled. The blood check came through and Cobb studied it, to go back and make further inspections of his own. At last he nodded slowly. “Hyper-catabolism, of course. I thought it might be. How long since you had your last rejuvenation? And who gave it?” “About ten years ago,” Giles answered. He found his identity card and passed it over, while the doctor studied it. “My sixteenth.” It wasn’t going right. He could feel it. Some of the panic symptoms were returning; the pulse in his neck was pounding and his breath was growing difficult. Sweat ran down his sides from his armpit and he wiped his palms against his coat. “Any particular emotional strain when you were treated—some major upset in your life?” Cobb asked. Giles thought as carefully as he could, but he remembered nothing like that. “You mean—it didn’t take? But I never had any trouble, Doctor. I was one of the first million cases, when a lot of people couldn’t rejuvenate at all, and I had no trouble even then.” Cobb considered it, hesitated as if making up his mind to be frank against his better judgment. “I can’t see any other explanation. You’ve got a slight case of angina—nothing serious, but quite definite—as well as other signs of aging. I’m afraid the treatment didn’t take fully. It might have been some unconscious block on your part, some infection not diagnosed at the time, or even a fault in the treatment. That’s pretty rare, but we can’t neglect the possibility.” HE STUDIED his charts again and then smiled. “So we’ll give you another treatment. Any reason you can’t begin immediately?” Giles remembered that Dubbins was waiting for him, but this was more important. It hadn’t been a joke about his growing old, after all. But now, in a few days, he’d be his old—no, of course not—his young self again! They went down the hall to another office, where Giles waited outside while Cobb conferred with another doctor and technician, with much waving of charts. He resented every second of it. It was as if the almost forgotten specter of age stood beside him, counting the seconds. But at last they were through and he was led into the quiet rejuvenation room, where the clamps were adjusted about his head and the earpieces were fitted. The drugs were shot painlessly into his arm and the light-pulser was adjusted to his brain-wave pattern. It had been nothing like this his first time. Then it had required months of mental training, followed by crude mechanical and drug hypnosis for other months. Somewhere in every human brain lay the memory of what his cells had been like when he was young. Or perhaps it lay in the cells themselves, with the brain as only a linkage to it. They’d discovered that, and the fact that the mind could effect physical changes in the body. Even such things as cancer could be willed out of existence—provided the brain could be reached far below the conscious level and forced to operate. There had been impossible faith cures for millenia—cataracts removed from blinded eyes within minutes, even—but finding the mechanism in the brain that worked those miracles had taken an incredible amount of study and finding a means of bringing it under control had taken even longer. Now they did it with dozens of mechanical aids in addition to the hypnotic instructions—and did it usually in a single sitting, with the full transformation of the body taking less than a week after the treatment! But with all the equipment, it wasn’t impossible for a mistake to happen. It had been no fault of his ... he was sure of that ... his mind was easy to reach ... he could relax so easily.... He came out of it without even a headache, while they were removing the probes, but the fatigue on the operator’s face told him it had been a long and difficult job. He stretched experimentally, with the eternal unconscious expectation that he would find himself suddenly young again. But that, of course, was ridiculous. It took days for the mind to work on all the cells and to repair the damage of time. COBB LED him back to the first office, where he was given an injection of some kind and another sample of his blood was taken, while the earlier tests were repeated. But finally the doctor nodded. “That’s all for now, Mr. Giles. You might drop in tomorrow morning, after I’ve had a chance to complete my study of all this. We’ll know by then whether you’ll need more treatment. Ten o’clock okay?” “But I’ll be all right?” Cobb smiled the automatic reassurance of his profession. “We haven’t lost a patient in two hundred years, to my knowledge.” “Thanks,” said Giles. “Ten o’clock is fine.” Dubbins was still waiting, reading a paper whose headlined feature carried a glowing account of the discovery of the super-light missile and what it might mean. He took a quick look at Giles and pointed to it. “Great work, Mr. Giles. Maybe we’ll all get to see some of those other worlds yet.” Then he studied Giles more carefully. “Everything’s in good shape now, sir?” “The doctor says everything’s going to be fine,” Giles answered. It was then he realized for the first time that Cobb had said no such thing. A statement that lightning had never struck a house was no guarantee that it never would. It was an evasion meant to give such an impression. The worry nagged at him all the way back. Word had already gone around the club that he’d had some kind of attack and there were endless questions that kept it on his mind. And even when it had been covered and recovered, he could still sense the glances of the others, as if he were Vincenti in one of the man’s more morose moods. He found a single table in the dining room and picked his way through the meal, listening to the conversation about him only when it was necessary because someone called across to him. Ordinarily, he was quick to support the idea of clubs in place of private families. A man here could choose his group and grow into them. Yet he wasn’t swallowed by them, as he might be by a family. Giles had been living here for nearly a century now and he’d never regretted it. But tonight his own group irritated him. He puzzled over it, finding no real reason. Certainly they weren’t forcing themselves on him. He remembered once when he’d had a cold, before they finally licked that; Harry had been a complete nuisance, running around with various nostrums, giving him no peace. Constant questions about how he felt, constant little looks of worry—until he’d been ready to yell at the boy. In fact, he had. Funny, he couldn’t picture really losing his temper here. Families did odd things to a man. HE LISTENED to a few of the discussions after the dinner, but he’d heard them all before, except for one about the super-speed drive, and there he had no wish to talk until he could study the final report. He gave up at last and went to his own suite. What he needed was a good night’s sleep after a little relaxation. Even that failed him, though. He’d developed one of the finest chess collections in the world, but tonight it held no interest. And when he drew out his tools and tried working on the delicate, lovely jade for the set he was carving his hands seemed to be all thumbs. None of the other interests he’d developed through the years helped to add to the richness of living now. He gave it up and went to bed—to have the fragment of that song pop into his head. Now there was no escaping it. Something about the years—or was it days—dwindling down to something or other. Could they really dwindle down? Suppose he couldn’t rejuvenate all the way? He knew that there were some people who didn’t respond as well as others. Sol Graves, for instance. He’d been fifty when he finally learned how to work with the doctors and they could only bring him back to about thirty, instead of the normal early twenties. Would that reduce the slice of eternity that rejuvenation meant? And what had happened to Sol? Or suppose it wasn’t rejuvenation, after all; suppose something had gone wrong with him permanently? He fought that off, but he couldn’t escape the nagging doubts at the doctor’s words. He got up once to stare at himself in the mirror. Ten hours had gone by and there should have been some signs of improvement. He couldn’t be sure, though, whether there were or not. He looked no better the next morning when he finally dragged himself up from the little sleep he’d managed to get. The hollows were still there and the circles under his eyes. He searched for the gray in his hair, but the traitorous strands had been removed at the doctor’s office and he could find no new ones. He looked into the dining room and then went by hastily. He wanted no solicitous glances this morning. Drat it, maybe he should move out. Maybe trying family life again would give him some new interests. Amanda probably would be willing to marry him; she’d hinted at a date once. He stopped, shocked by the awareness that he hadn’t been out with a woman for.... He couldn’t remember how long it had been. Nor why. “In the spring, a young man’s fancy,” he quoted to himself, and then shuddered. It hadn’t been that kind of spring for him—not this rejuvenation nor the last, nor the one before that. GILES TRIED to stop scaring himself and partially succeeded, until he reached the doctor’s office. Then it was no longer necessary to frighten himself. The wrongness was too strong, no matter how professional Cobb’s smile! He didn’t hear the preliminary words. He watched the smile vanish as the stack of reports came out. There was no nurse here now. The machines were quiet—and all the doors were shut. Giles shook his head, interrupting the doctor’s technical jargon. Now that he knew there was reason for his fear, it seemed to vanish, leaving a coldness that numbed him. “I’d rather know the whole truth,” he said. His voice sounded dead in his ears. “The worst first. The rejuvenation...?” Cobb sighed and yet seemed relieved. “Failed.” He stopped, and his hands touched the reports on his desk. “Completely,” he added in a low, defeated tone. “But I thought that was impossible!” “So did I. I wouldn’t believe it even yet—but now I find it isn’t the first case. I spent the night at Medical Center going up the ranks until I found men who really know about it. And now I wish I hadn’t.” His voice ran down and he gathered himself together by an effort. “It’s a shock to me, too, Mr. Giles. But—well, to simplify it, no memory is perfect—even cellular memory. It loses a little each time. And the effect is cumulative. It’s like an asymptotic curve—the further it goes, the steeper the curve. And—well, you’ve passed too far.” He faced away from Giles, dropping the reports into a drawer and locking it. “I wasn’t supposed to tell you, of course. It’s going to be tough enough when they’re ready to let people know. But you aren’t the first and you won’t be the last, if that’s any consolation. We’ve got a longer time scale than we used to have—but it’s in centuries, not in eons. For everybody, not just you.” It was no consolation. Giles nodded mechanically. “I won’t talk, of course. How—how long?” Cobb spread his hands unhappily. “Thirty years, maybe. But we can make them better. Geriatric knowledge is still on record. We can fix the heart and all the rest. You’ll be in good physical condition, better than your grandfather—” “And then....” Giles couldn’t pronounce the words. He’d grown old and he’d grow older. And eventually he’d die! An immortal man had suddenly found death hovering on his trail. The years had dwindled and gone, and only a few were left. He stood up, holding out his hand. “Thank you, Doctor,” he said, and was surprised to find he meant it. The man had done all he could and had at least saved him the suspense of growing doubt and horrible eventual discovery. OUTSIDE ON the street, he looked up at the Sun and then at the buildings built to last for thousands of years. Their eternity was no longer a part of him. Even his car would outlast him. He climbed into it, still partly numbed, and began driving mechanically, no longer wondering about the dangers that might possibly arise. Those wouldn’t matter much now. For a man who had thought of living almost forever, thirty years was too short a time to count. He was passing near the club and started to slow. Then he went on without stopping. He wanted no chance to have them asking questions he couldn’t answer. It was none of their business. Dubbins had been kind—but now Giles wanted no kindness. The street led to the office and he drove on. What else was there for him? There, at least, he could still fill his time with work—work that might even be useful. In the future, men would need the super-light drive if they were to span much more of the Universe than now. And he could speed up the work in some ways still, even if he could never see its finish. It would be cold comfort but it was something. And he might keep busy enough to forget sometimes that the years were gone for him. Automatic habit carried him through the office again, to Amanda’s desk, where her worry was still riding her. He managed a grin and somehow the right words came to his lips. “I saw the doctor, Amanda, so you can stop figuring ways to get me there.” She smiled back suddenly, without feigning it. “Then you’re all right?” “As all right as I’ll ever be,” he told her. “They tell me I’m just growing old.” This time her laugh was heartier. He caught himself before he could echo her mirth in a different voice and went inside where she had the coffee waiting for him. Oddly, it still tasted good to him. The projection was off, he saw, wondering whether he’d left it on or not. He snapped the switch and saw the screen light up, with the people still in the odd, wheelless vehicle on the alien planet. FOR A long moment, he stared at the picture without thinking, and then bent closer. Harry’s face hadn’t changed much. Giles had almost forgotten it, but there was still the same grin there. And his grandchildren had a touch of it, too. And of their grandfather’s nose, he thought. Funny, he’d never seen even pictures of his other grandchildren. Family ties melted away too fast for interstellar travel. Yet there seemed to be no slackening of them in Harry’s case, and somehow it looked like a family, rather than a mere group. A very pleasant family in a very pleasant world. He read Harry’s note again, with its praise for the planet and its invitation. He wondered if Dr. Vincenti had received an invitation like that, before he left. Or had he even been one of those to whom the same report had been delivered by some doctor? It didn’t matter, but it would explain things, at least. Twenty years to Centaurus, while the years dwindled down— Then abruptly the line finished itself. “The years dwindle down to a precious few....” he remembered. “A precious few.” Those dwindling years had been precious once. He unexpectedly recalled his own grandfather holding him on an old knee and slipping him candy that was forbidden. The years seemed precious to the old man then. Amanda’s voice came abruptly over the intercom. “Jordan wants to talk to you,” she said, and the irritation was sharp in her voice. “He won’t take no!” Giles shrugged and reached for the projector, to cut it off. Then, on impulse, he set it back to the picture, studying the group again as he switched on Jordan’s wire. But he didn’t wait for the hot words about whatever was the trouble. “Bill,” he said, “start getting the big ship into production. I’ve found a volunteer.” He’d been driven to it, he knew, as he watched the man’s amazed face snap from the screen. From the first suspicion of his trouble, something inside him had been forcing him to make this decision. And maybe it would do no good. Maybe the ship would fail. But thirty years was a number a man could risk. If he made it, though.... Well, he’d see those grandchildren of his this year—and Harry. Maybe he’d even tell Harry the truth, once they got done celebrating the reunion. And there’d be other grandchildren. With the ship, he’d have time enough to look them up. Plenty of time! Thirty years was a long time, when he stopped to think of it. —LESTER DEL REY
|
C. He feels a new fondness for his son and family.
|
What is the baseline for the experiments?
|
### Introduction
In natural language, subjectivity refers to the aspects of communication used to express opinions, evaluations, and speculationsBIBREF0, often influenced by one's emotional state and viewpoints. Writers and editors of texts like news and textbooks try to avoid the use of biased language, yet subjective bias is pervasive in these texts. More than $56\%$ of Americans believe that news sources do not report the news objectively , thus implying the prevalence of the bias. Therefore, when presenting factual information, it becomes necessary to differentiate subjective language from objective language. There has been considerable work on capturing subjectivity using text-classification models ranging from linguistic-feature-based modelsBIBREF1 to finetuned pre-trained word embeddings like BERTBIBREF2. The detection of bias-inducing words in a Wikipedia statement was explored in BIBREF1. The authors propose the "Neutral Point of View" (NPOV) corpus made using Wikipedia revision history, containing Wikipedia edits that are specifically designed to remove subjective bias. They use logistic regression with linguistic features, including factive verbs, hedges, and subjective intensifiers to detect bias-inducing words. In BIBREF2, the authors extend this work by mitigating subjective bias after detecting bias-inducing words using a BERT-based model. However, they primarily focused on detecting and mitigating subjective bias for single-word edits. We extend their work by incorporating multi-word edits by detecting bias at the sentence level. We further use their version of the NPOV corpus called Wiki Neutrality Corpus(WNC) for this work. The task of detecting sentences containing subjective bias rather than individual words inducing the bias has been explored in BIBREF3. However, they conduct majority of their experiments in controlled settings, limiting the type of articles from which the revisions were extracted. Their attempt to test their models in a general setting is dwarfed by the fact that they used revisions from a single Wikipedia article resulting in just 100 instances to evaluate their proposed models robustly. Consequently, we perform our experiments in the complete WNC corpus, which consists of $423,823$ revisions in Wikipedia marked by its editors over a period of 15 years, to simulate a more general setting for the bias. In this work, we investigate the application of BERT-based models for the task of subjective language detection. We explore various BERT-based models, including BERT, RoBERTa, ALBERT, with their base and large specifications along with their native classifiers. We propose an ensemble model exploiting predictions from these models using multiple ensembling techniques. We show that our model outperforms the baselines by a margin of $5.6$ of F1 score and $5.95\%$ of Accuracy. ### Baselines and Approach
In this section, we outline baseline models like $BERT_{large}$. We further propose three approaches: optimized BERT-based models, distilled pretrained models, and the use of ensemble methods for the task of subjectivity detection. ### Baselines and Approach ::: Baselines
FastTextBIBREF4: It uses bag of words and bag of n-grams as features for text classification, capturing partial information about the local word order efficiently. BiLSTM: Unlike feedforward neural networks, recurrent neural networks like BiLSTMs use memory based on history information to learn long-distance features and then predict the output. We use a two-layer BiLSTM architecture with GloVe word embeddings as a strong RNN baseline. BERT BIBREF5: It is a contextualized word representation model that uses bidirectional transformers, pretrained on a large $3.3B$ word corpus. We use the $BERT_{large}$ model finetuned on the training dataset. ### Baselines and Approach ::: Proposed Approaches
Optimized BERT-based models: We use BERT-based models optimized as in BIBREF6 and BIBREF7, pretrained on a dataset as large as twelve times as compared to $BERT_{large}$, with bigger batches, and longer sequences. ALBERT, introduced in BIBREF7, uses factorized embedding parameterization and cross-layer parameter sharing for parameter reduction. These optimizations have led both the models to outperform $BERT_{large}$ in various benchmarking tests, like GLUE for text classification and SQuAD for Question Answering. Distilled BERT-based models: Secondly, we propose to use distilled BERT-based models, as introduced in BIBREF8. They are smaller general-purpose language representation model, pre-trained by leveraging distillation knowledge. This results in significantly smaller and faster models with performance comparable to their undistilled versions. We finetune these pretrained distilled models on the training corpus to efficiently detect subjectivity. BERT-based ensemble models: Lastly, we use the weighted-average ensembling technique to exploit the predictions made by different variations of the above models. Ensembling methodology entails engendering a predictive model by utilizing predictions from multiple models in order to improve Accuracy and F1, decrease variance, and bias. We experiment with variations of $RoBERTa_{large}$, $ALBERT_{xxlarge.v2}$, $DistilRoBERTa$ and $BERT$ and outline selected combinations in tab:experimental-results. ### Experiments ::: Dataset and Experimental Settings
We perform our experiments on the WNC dataset open-sourced by the authors of BIBREF2. It consists of aligned pre and post neutralized sentences made by Wikipedia editors under the neutral point of view. It contains $180k$ biased sentences, and their neutral counterparts crawled from $423,823$ Wikipedia revisions between 2004 and 2019. We randomly shuffled these sentences and split this dataset into two parts in a $90:10$ Train-Test split and perform the evaluation on the held-out test dataset. For all BERT-based models, we use a learning rate of $2*10^{-5}$, a maximum sequence length of 50, and a weight decay of $0.01$ while finetuning the model. We use FastText's recently open-sourced automatic hyperparameter optimization functionality while training the model. For the BiLSTM baseline, we use a dropout of $0.05$ along with a recurrent dropout of $0.2$ in two 64 unit sized stacked BiLSTMs, using softmax activation layer as the final dense layer. ### Experiments ::: Experimental Results
tab:experimental-results shows the performance of different models on the WNC corpus evaluated on the following four metrics: Precision, Recall, F1, and Accuracy. Our proposed methodology, the use of finetuned optimized BERT based models, and BERT-based ensemble models outperform the baselines for all the metrics. Among the optimized BERT based models, $RoBERTa_{large}$ outperforms all other non-ensemble models and the baselines for all metrics. It further achieves a maximum recall of $0.681$ for all the proposed models. We note that DistillRoBERTa, a distilled model, performs competitively, achieving $69.69\%$ accuracy, and $0.672$ F1 score. This observation shows that distilled pretrained models can replace their undistilled counterparts in a low-computing environment. We further observe that ensemble models perform better than optimized BERT-based models and distilled pretrained models. Our proposed ensemble comprising of $RoBERTa_{large}$, $ALBERT_{xxlarge.v2}$, $DistilRoBERTa$ and $BERT$ outperforms all the proposed models obtaining $0.704$ F1 score, $0.733$ precision, and $71.61\%$ Accuracy. ### Conclusion
In this paper, we investigated BERT-based architectures for sentence level subjective bias detection. We perform our experiments on a general Wikipedia corpus consisting of more than $360k$ pre and post subjective bias neutralized sentences. We found our proposed architectures to outperform the existing baselines significantly. BERT-based ensemble consisting of RoBERTa, ALBERT, DistillRoBERTa, and BERT led to the highest F1 and Accuracy. In the future, we would like to explore document-level detection of subjective bias, multi-word mitigation of the bias, applications of detecting the bias in recommendation systems. Table 1: Experimental Results for the Subjectivity Detection Task
|
FastText, BERT , two-layer BiLSTM architecture with GloVe word embeddings
|
What is a star mother?
A. A star mother is a mother who becomes a celebrity.
B. A star mother is the mother of an astronaut.
C. A star mother is the mother of someone in the military.
D. A star mother is the mother of a celebrity.
|
STAR MOTHER By ROBERT F. YOUNG A touching story of the most enduring love in all eternity. That night her son was the first star. She stood motionless in the garden, one hand pressed against her heart, watching him rise above the fields where he had played as a boy, where he had worked as a young man; and she wondered whether he was thinking of those fields now, whether he was thinking of her standing alone in the April night with her memories; whether he was thinking of the verandahed house behind her, with its empty rooms and silent halls, that once upon a time had been his birthplace. Higher still and higher he rose in the southern sky, and then, when he had reached his zenith, he dropped swiftly down past the dark edge of the Earth and disappeared from sight. A boy grown up too soon, riding round and round the world on a celestial carousel, encased in an airtight metal capsule in an airtight metal chariot ... Why don't they leave the stars alone? she thought. Why don't they leave the stars to God? The general's second telegram came early the next morning: Explorer XII doing splendidly. Expect to bring your son down sometime tomorrow . She went about her work as usual, collecting the eggs and allocating them in their cardboard boxes, then setting off in the station wagon on her Tuesday morning run. She had expected a deluge of questions from her customers. She was not disappointed. "Is Terry really way up there all alone, Martha?" "Aren't you scared , Martha?" "I do hope they can get him back down all right, Martha." She supposed it must have given them quite a turn to have their egg woman change into a star mother overnight. She hadn't expected the TV interview, though, and she would have avoided it if it had been politely possible. But what could she do when the line of cars and trucks pulled into the drive and the technicians got out and started setting up their equipment in the backyard? What could she say when the suave young man came up to her and said, "We want you to know that we're all very proud of your boy up there, ma'am, and we hope you'll do us the honor of answering a few questions." Most of the questions concerned Terry, as was fitting. From the way the suave young man asked them, though, she got the impression that he was trying to prove that her son was just like any other average American boy, and such just didn't happen to be the case. But whenever she opened her mouth to mention, say, how he used to study till all hours of the night, or how difficult it had been for him to make friends because of his shyness, or the fact that he had never gone out for football—whenever she started to mention any of these things, the suave young man was in great haste to interrupt her and to twist her words, by requestioning, into a different meaning altogether, till Terry's behavior pattern seemed to coincide with the behavior pattern which the suave young man apparently considered the norm, but which, if followed, Martha was sure, would produce not young men bent on exploring space but young men bent on exploring trivia. A few of the questions concerned herself: Was Terry her only child? ("Yes.") What had happened to her husband? ("He was killed in the Korean War.") What did she think of the new law granting star mothers top priority on any and all information relating to their sons? ("I think it's a fine law ... It's too bad they couldn't have shown similar humanity toward the war mothers of World War II.") It was late in the afternoon by the time the TV crew got everything repacked into their cars and trucks and made their departure. Martha fixed herself a light supper, then donned an old suede jacket of Terry's and went out into the garden to wait for the sun to go down. According to the time table the general had outlined in his first telegram, Terry's first Tuesday night passage wasn't due to occur till 9:05. But it seemed only right that she should be outside when the stars started to come out. Presently they did, and she watched them wink on, one by one, in the deepening darkness of the sky. She'd never been much of a one for the stars; most of her life she'd been much too busy on Earth to bother with things celestial. She could remember, when she was much younger and Bill was courting her, looking up at the moon sometimes; and once in a while, when a star fell, making a wish. But this was different. It was different because now she had a personal interest in the sky, a new affinity with its myriad inhabitants. And how bright they became when you kept looking at them! They seemed to come alive, almost, pulsing brilliantly down out of the blackness of the night ... And they were different colors, too, she noticed with a start. Some of them were blue and some were red, others were yellow ... green ... orange ... It grew cold in the April garden and she could see her breath. There was a strange crispness, a strange clarity about the night, that she had never known before ... She glanced at her watch, was astonished to see that the hands indicated two minutes after nine. Where had the time gone? Tremulously she faced the southern horizon ... and saw her Terry appear in his shining chariot, riding up the star-pebbled path of his orbit, a star in his own right, dropping swiftly now, down, down, and out of sight beyond the dark wheeling mass of the Earth ... She took a deep, proud breath, realized that she was wildly waving her hand and let it fall slowly to her side. Make a wish! she thought, like a little girl, and she wished him pleasant dreams and a safe return and wrapped the wish in all her love and cast it starward. Sometime tomorrow, the general's telegram had said— That meant sometime today! She rose with the sun and fed the chickens, fixed and ate her breakfast, collected the eggs and put them in their cardboard boxes, then started out on her Wednesday morning run. "My land, Martha, I don't see how you stand it with him way up there! Doesn't it get on your nerves ?" ("Yes ... Yes, it does.") "Martha, when are they bringing him back down?" ("Today ... Today !") "It must be wonderful being a star mother, Martha." ("Yes, it is—in a way.") Wonderful ... and terrible. If only he can last it out for a few more hours, she thought. If only they can bring him down safe and sound. Then the vigil will be over, and some other mother can take over the awesome responsibility of having a son become a star— If only ... The general's third telegram arrived that afternoon: Regret to inform you that meteorite impact on satellite hull severely damaged capsule-detachment mechanism, making ejection impossible. Will make every effort to find another means of accomplishing your son's return. Terry!— See the little boy playing beneath the maple tree, moving his tiny cars up and down the tiny streets of his make-believe village; the little boy, his fuzz of hair gold in the sunlight, his cherub-cheeks pink in the summer wind— Terry!— Up the lane the blue-denimed young man walks, swinging his thin tanned arms, his long legs making near-grownup strides over the sun-seared grass; the sky blue and bright behind him, the song of cicada rising and falling in the hazy September air— Terry ... —probably won't get a chance to write you again before take-off, but don't worry, Ma. The Explorer XII is the greatest bird they ever built. Nothing short of a direct meteorite hit can hurt it, and the odds are a million to one ... Why don't they leave the stars alone? Why don't they leave the stars to God? The afternoon shadows lengthened on the lawn and the sun grew red and swollen over the western hills. Martha fixed supper, tried to eat, and couldn't. After a while, when the light began to fade, she slipped into Terry's jacket and went outside. Slowly the sky darkened and the stars began to appear. At length her star appeared, but its swift passage blurred before her eyes. Tires crunched on the gravel then, and headlights washed the darkness from the drive. A car door slammed. Martha did not move. Please God , she thought, let it be Terry , even though she knew that it couldn't possibly be Terry. Footsteps sounded behind her, paused. Someone coughed softly. She turned then— "Good evening, ma'am." She saw the circlet of stars on the gray epaulet; she saw the stern handsome face; she saw the dark tired eyes. And she knew. Even before he spoke again, she knew— "The same meteorite that damaged the ejection mechanism, ma'am. It penetrated the capsule, too. We didn't find out till just a while ago—but there was nothing we could have done anyway ... Are you all right, ma'am?" "Yes. I'm all right." "I wanted to express my regrets personally. I know how you must feel." "It's all right." "We will, of course, make every effort to bring back his ... remains ... so that he can have a fitting burial on Earth." "No," she said. "I beg your pardon, ma'am?" She raised her eyes to the patch of sky where her son had passed in his shining metal sarcophagus. Sirius blossomed there, blue-white and beautiful. She raised her eyes still higher—and beheld the vast parterre of Orion with its central motif of vivid forget-me-nots, its far-flung blooms of Betelguese and Rigel, of Bellatrix and Saiph ... And higher yet—and there flamed the exquisite flower beds of Taurus and Gemini, there burgeoned the riotous wreath of the Crab; there lay the pulsing petals of the Pleiades ... And down the ecliptic garden path, wafted by a stellar breeze, drifted the ocher rose of Mars ... "No," she said again. The general had raised his eyes, too; now, slowly, he lowered them. "I think I understand, ma'am. And I'm glad that's the way you want it ... The stars are beautiful tonight, aren't they." "More beautiful than they've ever been," she said. After the general had gone, she looked up once more at the vast and variegated garden of the sky where her son lay buried, then she turned and walked slowly back to the memoried house. THE END Transcriber's Note: This etext was produced from Amazing Stories January 1959. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed. Minor spelling and typographical errors have been corrected without note.
|
B. A star mother is the mother of an astronaut.
|
Which conventional alignment models do they use as guidance?
|
### Introduction
Neural Machine Translation (NMT) has achieved great successes on machine translation tasks recently BIBREF0 , BIBREF1 . Generally, it relies on a recurrent neural network under the Encode-Decode framework: it firstly encodes a source sentence into context vectors and then generates its translation token-by-token, selecting from the target vocabulary. Among different variants of NMT, attention based NMT, which is the focus of this paper, is attracting increasing interests in the community BIBREF0 , BIBREF2 . One of its advantages is that it is able to dynamically make use of the encoded context through an attention mechanism thereby allowing the use of fewer hidden layers while still maintaining high levels of translation performance. An attention mechanism is designed to predict the alignment of a target word with respect to source words. In order to facilitate incremental decoding, it tries to make this alignment prediction without any information about the target word itself, and thus this attention can be considered to be a form of a reordering model (see § SECREF2 for more details). However, it differs from conventional alignment models that are able to use the target word to infer its alignments BIBREF3 , BIBREF4 , BIBREF5 , and as a result there is a substantial gap in quality between the alignments derived by this attention based NMT and conventional alignment models (54 VS 30 in terms of AER for Chinese-to-English as reported in BIBREF6 ). This discrepancy might be an indication that the potential of NMT is limited. In addition, the attention in NMT is learned in an unsupervised manner without explicit prior knowledge about alignment. In contrast, in conventional statistical machine translation (SMT), it is standard practice to learn reordering models in a supervised manner with the guidance from conventional alignment models. Inspired by the supervised reordering in conventional SMT, in this paper, we propose a Supervised Attention based NMT (SA-NMT) model. Specifically, similar to conventional SMT, we first run off-the-shelf aligners (GIZA++ BIBREF3 or fast_align BIBREF4 etc.) to obtain the alignment of the bilingual training corpus in advance. Then, treating this alignment result as the supervision of attention, we jointly learn attention and translation, both in supervised manners. Since the conventional aligners delivers higher quality alignment, it is expected that the alignment in the supervised attention NMT will be improved leading to better end-to-end translation performance. One advantage of the proposed SA-NMT is that it implements the supervision of attention as a regularization in the joint training objective (§3.2). Furthermore, since the supervision of attention lies in the middle of the entire network architecture rather than the top ( as in the supervision of translation (see Figure 1(b)), it serves to mitigate the vanishing gradient problem during the back-propagation BIBREF7 . This paper makes the following contributions: ### Revisiting Neural Machine Translation
Suppose INLINEFORM0 denotes a source sentence, INLINEFORM1 a target sentence. In addition, let INLINEFORM2 denote a prefix of INLINEFORM3 . Neural Machine Translation (NMT) directly maps a source sentence into a target under an encode-decode framework. In the encoding stage, it uses two bidirectional recurrent neural networks to encode INLINEFORM4 into a sequence of vectors INLINEFORM5 , with INLINEFORM6 representing the concatenation of two vectors for INLINEFORM7 source word from two directional RNNs. In the decoding stage, it generates the target translation from the conditional probability over the pair of sequences INLINEFORM8 and INLINEFORM9 via a recurrent neural network parametrized by INLINEFORM10 as follows: DISPLAYFORM0 where INLINEFORM0 and INLINEFORM1 respectively denote an RNN hidden state (i.e. a vector) and a context vector at timestep INLINEFORM2 ; INLINEFORM3 is a transformation function mapping into a vector with dimension of the target vocabulary size; and INLINEFORM4 denotes the INLINEFORM5 component of a vector. Furthermore, INLINEFORM7 is defined by an activation function, i.e. a Gated Recurrent Unit BIBREF8 ; and the context vector INLINEFORM8 is a dynamical source representation at timestep INLINEFORM9 , and calculated as the weighted sum of source encodings INLINEFORM10 , i.e. INLINEFORM11 . Here the weight INLINEFORM12 implements an attention mechanism, and INLINEFORM13 is the alignment probability of INLINEFORM14 being aligned to INLINEFORM15 . INLINEFORM16 is derived through a feedforward neural network INLINEFORM17 as follows: DISPLAYFORM0 where INLINEFORM0 consists of two layers, the top one being a softmax layer. We skip the detailed definitions of INLINEFORM1 together with INLINEFORM2 , INLINEFORM3 and INLINEFORM4 , and refer the readers to BIBREF0 instead. Figure 1(a) shows one slice of computational graph for NMT definition at time step INLINEFORM9 . To train NMT, the following negative log-likelyhood is minimized: DISPLAYFORM0 where INLINEFORM0 is a bilingual sentence pair from a given training corpus, INLINEFORM1 is as defined in Eq.( EQREF5 ). Note that even though the training is conducted in a supervised manner with respect to translation, i.e., INLINEFORM2 are observable in Figure 1(a), the attention is learned in a unsupervised manner, since INLINEFORM3 is hidden. In Figure 1(a), INLINEFORM0 can not be dependent on INLINEFORM1 , as the target word INLINEFORM2 is unknown at the timestep INLINEFORM3 during the testing. Therefore, at timestep INLINEFORM4 , NMT firstly tries to calculate INLINEFORM5 , through which NMT figures out those source words will be translated next, even though the next target word INLINEFORM6 is unavailable. From this point of view, the attention mechanism plays a role in reordering and thus can be considered as a reordering model. Unlike this attention model, conventional alignment models define the alignment INLINEFORM7 directly over INLINEFORM8 and INLINEFORM9 as follows: INLINEFORM10 where INLINEFORM0 denotes either a log-probability INLINEFORM1 for a generative model like IBM models BIBREF9 or a feature function for discriminative models BIBREF5 . In order to infer INLINEFORM2 , alignment models can readily use the entire INLINEFORM3 , of course including INLINEFORM4 as well, thereby they can model the alignment between INLINEFORM5 and INLINEFORM6 more sufficiently. As a result, the attention based NMT might not deliver satisfying alignments, as reported in BIBREF6 , compared to conventional alignment models. This may be a sign that the potential of NMT is limited in end-to-end translation. ### Supervised Attention
In this section, we introduce supervised attention to improve the alignment, which consequently leads to better translation performance for NMT. Our basic idea is simple: similar to conventional SMT, it firstly uses a conventional aligner to obtain the alignment on the training corpus; then it employs these alignment results as supervision to train the NMT. During testing, decoding proceeds in exactly the same manner as standard NMT, since there is no alignment supervision available for unseen test sentences. ### Preprocessing Alignment Supervision
As described in §2, the attention model outputs a soft alignment INLINEFORM0 , such that INLINEFORM1 is a normalized probability distribution. In contrast, most aligners are typically oriented to grammar induction for conventional SMT, and they usually output `hard' alignments, such as BIBREF3 . They only indicate whether a target word is aligned to a source word or not, and this might not correspond to a distribution for each target word. For example, one target word may align to multiple source words, or no source words at all. Therefore, we apply the following heuristics to preprocess the hard alignment: if a target word does not align to any source words, we inherit its affiliation from the closest aligned word with preference given to the right, following BIBREF10 ; if a target word is aligned to multiple source words, we assume it aligns to each one evenly. In addition, in the implementation of NMT, there are two special tokens `eol' added to both source and target sentences. We assume they are aligned to each other. In this way, we can obtain the final supervision of attention, denoted as INLINEFORM0 . ### Jointly Supervising Translation and Attention
We propose a soft constraint method to jointly supervise the translation and attention as follows: DISPLAYFORM0 where INLINEFORM0 is as defined in Eq. ( EQREF5 ), INLINEFORM1 is a loss function that penalizes the disagreement between INLINEFORM2 and INLINEFORM3 , and INLINEFORM4 is a hyper-parameter that balances the preference between likelihood and disagreement. In this way, we treat the attention variable INLINEFORM5 as an observable variable as shown in Figure 1(b), and this is different from the standard NMT as shown in Figure 1(a) in essence. Note that this training objective resembles to that in multi-task learning BIBREF11 . Our supervised attention method has two further advantages: firstly, it is able to alleviate overfitting by means of the INLINEFORM6 ; and secondly it is capable of addressing the vanishing gradient problem because the supervision of INLINEFORM7 is more close to INLINEFORM8 than INLINEFORM9 as in Figure 1(b). In order to quantify the disagreement between INLINEFORM0 and INLINEFORM1 , three different methods are investigated in our experiments: Mean Squared Error (MSE) INLINEFORM0 MSE is widely used as a loss for regression tasks BIBREF12 , and it directly encourages INLINEFORM0 to be equal to INLINEFORM1 . Multiplication (MUL) INLINEFORM0 MUL is particularly designed for agreement in word alignment and it has been shown to be effective BIBREF13 , BIBREF6 . Note that different from those in BIBREF6 , INLINEFORM0 is not a parametrized variable but a constant in this paper. Cross Entropy (CE) INLINEFORM0 Since for each INLINEFORM0 , INLINEFORM1 is a distribution, it is natural to use CE as the metric to evaluate the disagreement BIBREF14 . ### Experiments
We conducted experiments on two Chinese-to-English translation tasks: one is the NIST task oriented to NEWS domain, which is a large scale task and suitable to NMT; and the other is the speech translation oriented to travel domain, which is a low resource task and thus is very challenging for NMT. We used the case-insensitive BLEU4 to evaluate translation quality and adopted the multi-bleu.perl as its implementation. ### The Large Scale Translation Task
We used the data from the NIST2008 Open Machine Translation Campaign. The training data consisted of 1.8M sentence pairs, the development set was nist02 (878 sentences), and the test sets are were nist05 (1082 sentences), nist06 (1664 sentences) and nist08 (1357 sentences). We compared the proposed approach with three strong baselines: Moses: a phrase-based machine translation system BIBREF15 ; NMT1: an attention based NMT BIBREF0 system at https://github.com/lisa-groundhog/GroundHog; NMT2: another implementation of BIBREF0 at https://github.com/nyu-dl/dl4mt-tutorial. We developed the proposed approach based on NMT2, and denoted it as SA-NMT. We followed the standard pipeline to run Moses. GIZA++ with grow-diag-final-and was used to build the translation model. We trained a 5-gram target language model on the Gigaword corpus, and used a lexicalized distortion model. All experiments were run with the default settings. To train NMT1, NMT2 and SA-NMT, we employed the same settings for fair comparison. Specifically, except the stopping iteration which was selected using development data, we used the default settings set out in BIBREF0 for all NMT-based systems: the dimension of word embedding was 620, the dimension of hidden units was 1000, the batch size was 80, the source and target side vocabulary sizes were 30000, the maximum sequence length was 50, the beam size for decoding was 12, and the optimization was done by Adadelta with all hyper-parameters suggested by BIBREF16 . Particularly for SA-NMT, we employed a conventional word aligner to obtain the word alignment on the training data before training SA-NMT. In this paper, we used two different aligners, which are fast_align and GIZA++. We tuned the hyper-parameter INLINEFORM0 to be 0.3 on the development set, to balance the preference between the translation and alignment. Training was conducted on a single Tesla K40 GPU machine. Each update took about 3.0 seconds for both NMT2 and SA-NMT, and 2.4 seconds for NMT1. Roughly, it took about 10 days to NMT2 to finish 300000 updates. We implemented three different losses to supervise the attention as described in §3.2. To explore their behaviors on the development set, we employed the GIZA++ to generate the alignment on the training set prior to the training SA-NMT. In Table TABREF21 , we can see that MUL is better than MSE. Furthermore, CE performs best among all losses, and thus we adopt it for the following experiments. In addition, we also run fast_align to generate alignments as the supervision for SA-NMT and the results were reported in Table TABREF22 . We can see that GIZA++ performs slightly better than fast_align and thus we fix the external aligner as GIZA++ in the following experiments. Figure FIGREF26 shows the learning curves of NMT2 and SA-NMT on the development set. We can see that NMT2 generally obtains higher BLEU as the increasing of updates before peaking at update of 150000, while it is unstable from then on. On the other hand, SA-NMT delivers much better BLEU for the beginning updates and performs more steadily along with the updates, although it takes more updates to reach the peaking point. Table TABREF27 reports the main end-to-end translation results for the large scale task. We find that both standard NMT generally outperforms Moses except NMT1 on nist05. The proposed SA-NMT achieves significant and consistent improvements over all three baseline systems, and it obtains the averaged gains of 2.2 BLEU points on test sets over its direct baseline NMT2. It is clear from these results that our supervised attention mechanism is highly effective in practice. As explained in §2, standard NMT can not use the target word information to predict its aligned source words, and thus might fail to predict the correct source words for some target words. For example, for the sentence in the training set in Figure FIGREF29 (a), NMT2 aligned `following' to `皮诺契特 (gloss: pinochet)' rather than `继 (gloss: follow)', and worse still it aligned the word `.' to `在 (gloss: in)' rather than `。' even though this word is relatively easy to align correctly. In contrast, with the help of information from the target word itself, GIZA++ successfully aligned both `following' and `.' to the expected source words (see Figure FIGREF29 (c)). With the alignment results from GIZA++ as supervision, we can see that our SA-NMT can imitate GIZA++ and thus align both words correctly. More importantly, for sentences in the unseen test set, like GIZA++, SA-NMT confidently aligned `but' and `.' to their correct source words respectively as in Figure FIGREF29 (b), where NMT2 failed. It seems that SA-NMT can learn its alignment behavior from GIZA++, and subsequently apply the alignment abilities it has learned to unseen test sentences. Table TABREF30 shows the overall alignment results on word alignment task in terms of the metric, alignment error rate. We used the manually-aligned dataset as in BIBREF5 as the test set. Following BIBREF17 , we force-decode both the bilingual sentences including source and reference sentences to obtain the alignment matrices, and then for each target word we extract one-to-one alignments by picking up the source word with the highest alignment confidence as the hard alignment. From Table TABREF30 , we can see clearly that standard NMT (NMT2) is far behind GIZA++ in alignment quality. This shows that it is possible and promising to supervise the attention with GIZA++. With the help from GIZA++, our supervised attention based NMT (SA-NMT) significantly reduces the AER, compared with the unsupervised counterpart (NMT2). This shows that the proposed approach is able to realize our intuition: the alignment is improved, leading to better translation performance. Note that there is still a gap between SA-NMT and GIZA++ as indicated in Table TABREF30 . Since SA-NMT was trained for machine translation instead of word alignment, it is possible to reduce its AER if we aim to the word alignment task only. For example, we can enlarge INLINEFORM0 in Eq.( EQREF12 ) to bias the training objective towards word alignment task, or we can change the architecture slightly to add the target information crucial for alignment as in BIBREF18 , BIBREF19 . ### Results on the Low Resource Translation Task
For the low resource translation task, we used the BTEC corpus as the training data, which consists of 30k sentence pairs with 0.27M Chinese words and 0.33M English words. As development and test sets, we used the CSTAR03 and IWSLT04 held out sets, respectively. We trained a 4-gram language model on the target side of training corpus for running Moses. For training all NMT systems, we employed the same settings as those in the large scale task, except that vocabulary size is 6000, batch size is 16, and the hyper-parameter INLINEFORM0 for SA-NMT. Table TABREF32 reports the final results. Firstly, we can see that both standard neural machine translation systems NMT1 and NMT2 are much worse than Moses with a substantial gap. This result is not difficult to understand: neural network systems typically require sufficient data to boost their performance, and thus low resource translation tasks are very challenging for them. Secondly, the proposed SA-NMT gains much over NMT2 similar to the case in the large scale task, and the gap towards Moses is narrowed substantially. While our SA-NMT does not advance the state-of-the-art Moses as in large scale translation, this is a strong result if we consider that previous works on low resource translation tasks: arthur+:2016 gained over Moses on the Japanese-to-English BTEC corpus, but they resorted to a corpus consisting of 464k sentence pairs; luong+manning:2015 revealed the comparable performance to Moses on English-to-Vietnamese with 133k sentences pairs, which is more than 4 times of our corprus size. Our method is possible to advance Moses by using reranking as in BIBREF20 , BIBREF21 , but it is beyond the scope of this paper and instead we remain it as future work. ### Related Work
Many recent works have led to notable improvements in the attention mechanism for neural machine translation. tu+:2016 introduced an explicit coverage vector into the attention mechanism to address the over-translation and under-translation inherent in NMT. feng+:2016 proposed an additional recurrent structure for attention to capture long-term dependencies. cheng+:2016 proposed an agreement-based bidirectional NMT model for symmetrizing alignment. cohn+:2016 incorporated multiple structural alignment biases into attention learning for better alignment. All of them improved the attention models that were learned in an unsupervised manner. While we do not modify the attention model itself, we learn it in a supervised manner, therefore our approach is orthogonal to theirs. It has always been standard practice to learn reordering models from alignments for conventional SMT either at the phrase level or word level. At the phrase level, koehn+:2007 proposed a lexicalized MSD model for phrasal reordering; xiong+:2006 proposed a feature-rich model to learn phrase reordering for BTG; and li+:2014 proposed a neural network method to learn a BTG reordering model. At the word level, bisazza+federico:2016 surveyed many word reordering models learned from alignment models for SMT, and in particular there are some neural network based reordering models, such as BIBREF22 . Our work is inspired by these works in spirit, and it can be considered to be a recurrent neural network based word-level reordering model. The main difference is that in our approach the reordering model and translation model are trained jointly rather than separately as theirs. ### Conclusion
It has been shown that attention mechanism in NMT is worse than conventional word alignment models in its alignment accuracy. This paper firstly provides an explanation for this by viewing the atten- tion mechanism from the point view of reordering. Then it proposes a supervised attention for NMT with guidance from external conventional alignment models, inspired by the supervised reordering models in conventional SMT. Experiments on two Chinese-to-English translation tasks show that the proposed approach achieves better alignment results leading to significant gains relative to standard attention based NMT. ### Acknowledgements
We would like to thank Xugang Lu for invaluable discussions on this work. Figure 1: One slice of the computational graphs for both (a) NMT and (b) SA-NMT. Circles denote the hidden variables; while squares denote the observable variables, which receive supervision during training. The difference (marked in red) in (b) regarding to (a) is treating αt as an observable variable instead of a hidden variable. Table 1: Performance of SA-NMT on development set for different loss functions to supervise the attention in terms of BLEU. Table 2: Comparision of aligners between fast align and GIZA++ for SA-NMT in terms of BLEU on the development set. Figure 2: Learning curves of NMT2 and SA-NMT on the development set. Figure 3: Example (soft) alignments of (a) NMT2 (i.e., standard NMT with unsupervised attention), (b) SA-NMT (i.e. NMT with supervised attention), and (c) GIZA++ on two Chinese-English sentence pairs. The soft alignments of (c) is converted from hard alignment as in §3.1. The first row shows the alignments of the sentence pair from the training set while the second row shows the alignments from test sets. Table 4: Results on word alignment task for the large scale data. The evaluation metric is Alignment Error Rate (AER). ‘*’ denotes that the corresponding result is significanly better than NMT2 with p < 0.01. Table 5: BLEU comparison for low-resource translation task. CSTAR03 is the development set while IWSLT04 is the test set. ‘*’ denotes that SA-NMT is significantly better than both NMT1 and NMT2 with p < 0.01.
|
GIZA++ BIBREF3 or fast_align BIBREF4
|
What is the FY2017 operating cash flow ratio for Adobe? Operating cash flow ratio is defined as: cash from operations / total current liabilities. Round your answer to two decimal places. Please utilize information provided primarily within the balance sheet and the cash flow statement.
|
Evidence 0:
Table of Contents
57
ADOBE SYSTEMS INCORPORATED
CONSOLIDATED BALANCE SHEETS
(In thousands, except par value)
December 1,
2017
December 2,
2016
ASSETS
Current assets:
Cash and cash equivalents
$
2,306,072
$
1,011,315
Short-term investments
3,513,702
3,749,985
Trade receivables, net of allowances for doubtful accounts of $9,151 and $6,214, respectively
1,217,968
833,033
Prepaid expenses and other current assets
210,071
245,441
Total current assets
7,247,813
5,839,774
Property and equipment, net
936,976
816,264
Goodwill
5,821,561
5,406,474
Purchased and other intangibles, net
385,658
414,405
Investment in lease receivable
80,439
Other assets
143,548
139,890
Total assets
$
14,535,556
$
12,697,246
LIABILITIES AND STOCKHOLDERS EQUITY
Current liabilities:
Trade payables
$
113,538
$
88,024
Accrued expenses
993,773
739,630
Income taxes payable
14,196
38,362
Deferred revenue
2,405,950
1,945,619
Total current liabilities
3,527,457
2,811,635
Long-term liabilities:
Debt and capital lease obligations
1,881,421
1,892,200
Deferred revenue
88,592
69,131
Income taxes payable
173,088
184,381
Deferred income taxes
279,941
217,660
Other liabilities
125,188
97,404
Total liabilities
6,075,687
5,272,411
Commitments and contingencies
Stockholders equity:
Preferred stock, $0.0001 par value; 2,000 shares authorized; none issued
Common stock, $0.0001 par value; 900,000 shares authorized; 600,834 shares issued;
491,262 and 494,254 shares outstanding, respectively
61
61
Additional paid-in-capital
5,082,195
4,616,331
Retained earnings
9,573,870
8,114,517
Accumulated other comprehensive income (loss)
(111,821)
(173,602)
Treasury stock, at cost (109,572 and 106,580 shares, respectively), net of reissuances
(6,084,436)
(5,132,472)
Total stockholders equity
8,459,869
7,424,835
Total liabilities and stockholders equity
$
14,535,556
$
12,697,246
See accompanying Notes to Consolidated Financial Statements.
Evidence 1:
Table of Contents
61
ADOBE SYSTEMS INCORPORATED
CONSOLIDATED STATEMENTS OF CASH FLOWS
(In thousands)
Years Ended
December 1,
2017
December 2,
2016
November 27,
2015
Cash flows from operating activities:
Net income
$
1,693,954
$
1,168,782
$
629,551
Adjustments to reconcile net income to net cash provided by operating activities:
Depreciation, amortization and accretion
325,997
331,535
339,473
Stock-based compensation
451,451
349,912
335,859
Deferred income taxes
51,605
24,222
(69,657)
Gain on the sale of property
(21,415)
Unrealized (gains) losses on investments
(5,494)
3,145
(9,210)
Excess tax benefits from stock-based compensation
(75,105)
(68,153)
Other non-cash items
4,625
2,022
1,216
Changes in operating assets and liabilities, net of acquired assets and
assumed liabilities:
Trade receivables, net
(187,173)
(160,416)
(79,502)
Prepaid expenses and other current assets
28,040
(71,021)
(7,701)
Trade payables
(45,186)
(6,281)
22,870
Accrued expenses
154,125
64,978
(22,564)
Income taxes payable
(34,493)
43,115
97,934
Deferred revenue
475,402
524,840
320,801
Net cash provided by operating activities
2,912,853
2,199,728
1,469,502
Cash flows from investing activities:
Purchases of short-term investments
(1,931,011)
(2,285,222)
(2,064,833)
Maturities of short-term investments
759,737
769,228
371,790
Proceeds from sales of short-term investments
1,393,929
860,849
1,176,476
Acquisitions, net of cash acquired
(459,626)
(48,427)
(826,004)
Purchases of property and equipment
(178,122)
(203,805)
(184,936)
Proceeds from sale of property
57,779
Purchases of long-term investments, intangibles and other assets
(29,918)
(58,433)
(22,779)
Proceeds from sale of long-term investments
2,134
5,777
4,149
Net cash used for investing activities
(442,877)
(960,033)
(1,488,358)
Cash flows from financing activities:
Purchases of treasury stock
(1,100,000)
(1,075,000)
(625,000)
Proceeds from issuance of treasury stock
158,351
145,697
164,270
Taxes paid related to net share settlement of equity awards
(240,126)
(236,400)
(186,373)
Excess tax benefits from stock-based compensation
75,105
68,153
Proceeds from debt issuance
989,280
Repayment of debt and capital lease obligations
(1,960)
(108)
(602,189)
Debt issuance costs
(8,828)
Net cash used for financing activities
(1,183,735)
(1,090,706)
(200,687)
Effect of foreign currency exchange rates on cash and cash equivalents
8,516
(14,234)
(21,297)
Net increase (decrease) in cash and cash equivalents
1,294,757
134,755
(240,840)
Cash and cash equivalents at beginning of year
1,011,315
876,560
1,117,400
Cash and cash equivalents at end of year
$
2,306,072
$
1,011,315
$
876,560
Supplemental disclosures:
Cash paid for income taxes, net of refunds
$
396,668
$
249,884
$
203,010
Cash paid for interest
$
69,430
$
66,193
$
56,014
Non-cash investing activities:
Investment in lease receivable applied to building purchase
$
80,439
$
$
Issuance of common stock and stock awards assumed in business acquisitions
$
10,348
$
$
677
See accompanying Notes to Consolidated Financial Statements.
|
0.83
|
What is the role of the stewardess in the bomb situation?
A. She is able to interact with the narrator consistently to keep him calm
B. She likely never becomes aware of the situation at all
C. She is the first person the narrator confides in about the bomb
D. She keeps the passengers calm when she is aware there is a threat
|
Nuts to wild talents! Mine was no satisfaction, never earned me a penny—and now it had me fighting for my life in ... THE LITTLE RED BAG By JERRY SOHL [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, January 1960. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] About an hour out of San Francisco on the flight to Los Angeles, I made the discovery. I had finished reading the Chronicle , folded and put it beside me, turned and looked out the window, expecting to see the San Joaquin Valley but finding only a sea of clouds instead. So I returned my attention to the inside of the plane, to the overstuffed gray-haired woman asleep beside me, to the backs of heads in seats before me, across the aisle to other heads, and down to the blonde. I had seen her in the concourse and at the gate, a shapely thing. Now she had crossed her legs and I was privileged to view a trim ankle and calf, and her profile as she stared moodily across the aisle and out a window where there was nothing to see. I slid my eyes past her to others. A crossword-puzzle worker, a togetherness-type-magazine reader. Inventory completed, I went back to looking at the clouds, knowing I should be thinking about the printing order I was going to Los Angeles for, and not wanting to. So I started going through the purse of the woman next to me. Perhaps that sounds bad. It wasn't. I'd been doing it for years and nobody ever complained. It started when I was a kid, this business of being able to explore the insides of things like purses and sealed boxes and locked drawers and—well, human beings. But human beings aren't worth the trouble. It's like swimming through spaghetti. And I've got to stay away from electric wires. They hurt. Now don't ask me how they hurt. Maybe you think it's fun. For the most part, it really isn't. I always knew what was in Christmas presents before I unwrapped them, and therefore Christmas was always spoiled for me as a kid. I can't feel the color of anything, just its consistency. An apple senses about the same as a potato, except for the core and the stem. I can't even tell if there's writing on a piece of paper. So you see it isn't much. Just the feel of shapes, the hardnesses and softnesses. But I've learned to become pretty good at guessing. Like this woman next to me. She had a short, cylindrical metal object in her purse with waxlike stuff inside it—a lipstick. A round, hard object with dust inside—a compact. Handkerchief, chewing gum, a small book, probably an address book, money in a change purse—a few bills and coins. Not much else. I was a little disappointed. I've run across a gun or two in my time. But I never say anything. I learned the wisdom of keeping my mouth shut in the fourth grade when Miss Winters, a stern, white-haired disciplinarian, ordered me to eat my sack lunch in the classroom with her instead of outside with some of the other kids. This was the punishment for some minor infraction. Lunchtime was nearly over and we'd both finished eating; she said she'd be gone for a few moments and that I was to erase the blackboard during her absence, which I dutifully did. Class had hardly resumed when she started looking around the desk for her favorite mechanical pencil, asking if any of us had seen it, and looking straight at me. I didn't want her to think I had taken it while she was out of the room, so I probed the contents of her purse, which she always kept in the upper right drawer of her desk. "It's in your purse," I blurted out. I was sent home with a stinging note. Since then I've kept quiet. At one time I assumed everybody was able to sense. I've known better for years. Still, I wonder how many other people are as close-mouthed about their special gift as I am about mine. I used to think that some day I'd make a lot of money out of it, but how? I can't read thoughts. I can't even be sure what some of the things I sense in probing really are. But I've learned to move things. Ever so little. A piece of paper. A feather. Once I stopped one of those little glass-enclosed light or heat-powered devices with vanes you see now and then in a jeweler's window. And I can stop clocks. Take this morning, for example. I had set my alarm for five-thirty because I had to catch the seven o'clock plane at San Francisco International Airport. This being earlier than I usually get up, it seems all I did during the night was feel my way past the escapement and balance wheel to see where the notch for the alarm was. The last time I did it there was just the merest fraction of an inch between the pawl and the notch. So I sighed and moved to the balance wheel and its delicate ribbon of spiraling steel. I hung onto the wheel, exerting influence to decrease the restoring torque. The wheel slowed down until there was no more ticking. It took quite a bit of effort, as it always does, but I did it, as I usually do. I can't stand the alarm. When I first learned to do this, I thought I had it made. I even went to Las Vegas to try my hand, so to speak, with the ratchets and pawls and cams and springs on the slot machines. But there's nothing delicate about a slot machine, and the spring tensions are too strong. I dropped quite a lot of nickels before I finally gave up. So I'm stuck with a talent I've found little real use for. Except that it amuses me. Sometimes. Not like this time on the plane. The woman beside me stirred, sat up suddenly and looked across me out the window. "Where are we?" she asked in a surprised voice. I told her we were probably a little north of Bakersfield. She said, "Oh," glanced at her wristwatch and sank back again. Soon the stewardesses would bring coffee and doughnuts around, so I contented myself with looking at the clouds and trying to think about Amos Magaffey, who was purchasing agent for a Los Angeles amusement chain, and how I was going to convince him our printing prices were maybe a little higher but the quality and service were better. My mind wandered below where I was sitting, idly moving from one piece of luggage to another, looking for my beat-up suitcase. I went through slips and slippers, lingerie and laundry, a jig saw puzzle and a ukulele. I never did find my suitcase because I found the bomb first. The bomb was in a small bag—a woman's bag judging by the soft, flimsy things you'd never find in a man's—and I didn't know it was a bomb right away. I thought it was just a clock, one of those small, quiet alarms. I was going to pass it by and go on, but what held me was that something was taped to it. By the feel, I knew it must be electrician's tape. Interested and curious, I explored the clock more closely, found two wires. One went to a battery and the other to hard round cylinders taped together. The hairs stood up at the base of my neck when I suddenly realized what it was. The clock's balance wheel was rocking merrily. Quickly I went up past the train of gears to the alarm wheel. If this was anything like my own alarm clock, this one had something like ten minutes to go. It was forty minutes to Burbank and Lockheed Air Terminal. My mind was churning when I turned from the window to look around at the unconcerned passengers, the woman at my side asleep again. I thought: Which one of these.... No, none of them would know it was there. I glanced out the window again; clouds were still in the way. We'd be leaving the valley for the mountain range north of Los Angeles soon, if we hadn't left it already. No place to land the plane there. But of course that had been the plan! My heart was beating in jackhammer rhythm; my mouth was dry and my mind was numb. Tell somebody about the bomb before it's too late! No, they'd think I put it there. Besides, what good would it do? There would be panic and they'd never get the plane down in time—if they believed me. "Sir." My head jerked around. The stewardess stood in the aisle, smiling, extending a tray to me, a brown plastic tray bearing a small paper cup of tomato juice, a cup of coffee, a cellophane-wrapped doughnut, paper spoon, sugar and dehydrated cream envelopes, and a napkin. I goggled at her, managed to croak, "No, thanks." She gave me an odd look and moved along. My seatmate had accepted hers and was tearing at the cellophane. I couldn't bear to watch her. I closed my eyes, forced my mind back to the luggage compartment, spent a frantic moment before I found the bag again. I had to stop that balance wheel, just as I stopped my alarm clock every morning. I tried to close everything off—the throb of engines, the rush of air, the woman sipping coffee noisily beside me—and I went into the clock and surrounded the seesawing wheel. When it went forward, I pulled it back; when it went back, I pulled it forward. I struggled with it, and it was like trying to work with greasy hands, and I was afraid I wasn't going to be able to stop it. Then, little by little, it started to slow its beat. But I could not afford to relax. I pushed and pulled and didn't dare release my hold until it came to a dead stop. "Anything the matter?" My eyelids flew open and I looked into the eyes of the woman next to me. There was sugar from the doughnut around her mouth and she was still chewing. "No," I said, letting out my breath. "I'm all right." "You were moaning, it sounded like. And you kept moving your head back and forth." "Must have been dreaming," I said as I rang for the stewardess. When she came I told her I'd take some of that coffee now. No, nothing else, just coffee. I didn't tell her how much I needed it. I sat there clammy with sweat until she returned. Coffee never tasted so good. All right, so I had stopped the bomb's timer. My mind raced ahead to the landing. When they unloaded the luggage, the balance wheel would start again. I wouldn't be able to stay with it, keeping it still. I considered telling the authorities as soon as we landed, or maybe calling in ahead, but wouldn't that just bring suspicion, questions. Maybe I could convince them I could stop a clock—but not before the bomb exploded. And then what? My secret would be out and my life would be changed. I'd be a man not to be trusted, a prying man, a man literally with gimlet eyes. Mountain crags jutted through the clouds. We were in the range north of the city. Here and there were clear spots and I could see roads below, but there were also clouds far above us. It was very beautiful, but it was also very bumpy, and we started to slip and slide. To my horror I found that the balance wheel was rocking again. Closing my eyes and gritting my teeth, I forced my senses to the wheel, tugging and pulling and shoving and pushing until it finally stopped. A jab in the shoulder. I jumped, startled. "Your cup," my seat partner said, pointing. I looked down at the coffee cup I had crushed in my hands. Then I looked up into the eyes of the stewardess. I handed it to her. She took it without a word and went away. "Were you really asleep that time?" "Not really," I said. I was tempted to tell the woman I was subject to fits, but I didn't. It was only a few minutes to landing, but they became the longest minutes of my life as time after time I stopped the rocking wheel when the plane dipped and bumped to a landing. Leaving the apron with the other passengers, I tried to walk as unconcernedly as they through the exit gate. I would have liked walking through the terminal and out the entrance and away, but I could not. I had my suitcase to get, for one thing. The damned bomb was the other. So I strolled out into the concourse again to look at the plane and watch the baggagemen at work, transferring the luggage to two airfield carts. They weren't as careful as I would have been. It was impossible to tell from this distance just which bag contained the bomb; I could hardly identify my own scarred suitcase. The assortment of bags—a strange conglomeration of sizes and colors—was packed in some places six deep, and it rolled toward the gate where I was standing. I didn't know whether to stay or run, imagining the balance wheel now happily rocking again. The load went past me down a ramp to the front of the air terminal where the luggage was unloaded and placed in a long rack. I went with it. There was a flurry of ticket matching, hands grabbing for suitcases, and a general exodus on the part of my fellow passengers, too fast to determine who had got the one with the bomb. Now all that was left was the attendant and I had two bags—my own battered veteran of years, and a fine new red overnight case, small enough to be the one. I lit a cigarette, reached out. Inside were a woman's things and—a clock. The escapement was clicking vigorously. I didn't moan this time. I just closed my eyes, stretched toward and grabbed the balance wheel I was getting to know like my own. I entered into a union with it so strong that after I had reduced it to immobility, it was like waking when I opened my eyes. The baggage claim attendant was staring at me. For only a moment I stared back. Then I quickly reached for my baggage check and presented it to him. His hand hovered over the handle of the little red bag and I was ready to yell at him. But then, matching numbers on the tags with his eyes, his hand grasped the handle of my own suitcase and pushed it toward me. "Thanks," I said, taking it. I glanced ever so casually toward the remaining bag. "One left over, eh?" "Yeah." He was so bored I was tempted to tell him what was in it. But he was eying me with a "well-why-don't-you-get-along?" look. I said, "What happens if nobody claims it?" "Take it inside. Why?" He was getting too curious. "Oh, I just wondered, that's all." I stepped on my cigarette and walked toward the air terminal entrance and put my suitcase on the stone steps there. A redcap came hurrying over. "Cab?" I shook my head. "Just waiting." Just waiting for somebody to pick up a bomb. I lit another cigarette and glanced now and then toward the baggage claim area. The red bag was still there. All sorts of theories ran through my head as to why it should still be there, and none satisfied me. I should not have been there, that much I knew; I should be with a man named Amos Magaffey on Sixth Street at ten o'clock, discussing something very mundane, the matter of a printing order. But what could I do? If I left the airport, the attendant would eventually take the bag inside and there would be an explosion, and I wouldn't be able to live with myself. No. I had to stay to keep the balance wheel stationary until—until what? A man in tan gabardine, wearing a police cap and badge, walked out of the entrance to stand on the stone steps beside me while he put on a pair of dark glasses. A member of the airport police detail. I could tell him. I could take him down to the little red bag and explain the whole thing. Then it would be his baby and I would be off on my own business. But he moved on down the steps, nodded at the redcap, and started across the street to the parking area. I could have called to him, "Hey, officer, let me tell you about a bomb in a little red bag." But I didn't. I didn't because I caught a movement at the baggage claim counter out of the side of my eye. The attendant had picked up the bag and was walking with it up the ramp to the rear of the air terminal. Picking up my own suitcase, I went inside in time to see him enter through a side door and deposit the bag on the scales at the airline desk and say something to the clerk. The clerk nodded and moved the bag to the rear room. I could visualize the balance wheel once again rocking like crazy. How many minutes—or seconds—were left? I was sweating when I moved to the counter, and it wasn't because of the sunshine I'd been soaking in. I had to get as close to the bag as I could if I was going to stop the clock again. "Can I help you?" the clerk asked. "No. I'm waiting for someone." I turned my back to him, put down my suitcase, leaned against the counter and reached out for the wheel. I found I could reach the device, but it was far away. When I tried to dampen it, the wheel escaped my grasp. "Do you have my suitcase?" I blinked my eyes open and looked around. The blonde in the plane stood there looking very fresh and bright and unconcerned. In her right hand she had a green baggage claim check. The clerk took it, nodded, and in a moment brought out the overnight case and set it on the scales. The girl thanked him, picked it up, glanced at me indifferently, and then started for the entrance with it. "Just a moment," I found myself saying, grabbing my bag and hurrying after her. At her side and a little ahead of her, I said, "Listen to me." She looked annoyed and increased her stride toward the door. "It's a matter of life or death," I said. I wanted to wrest the bag from her and hurl it out through the doorway into the street, but I restrained myself. She stopped and stared. I noticed a short, fat man in a rumpled suitcoat and unpressed pants staring, too. Ignoring him, I said, "Please put the bag down. Over there." I indicated a spot beside a telephone booth where it would be out of the way. She didn't move. She just said, "Why?" "For God's sake!" I took the case. She offered no resistance. I put her bag and mine next to the booth. When I turned around she was standing there looking at me as if I had gone out of my mind. Her eyes were blue and brown-flecked, very pretty eyes, and my thought at the moment was, I'm glad the bomb didn't go off; these eyes wouldn't be looking at me or anything else right now if it had. "I've got to talk to you. It's very important." The girl said, "Why?" I was beginning to think it was the only word she knew. At the same time I was wondering why anyone would want to kill someone so lovely. "I'll explain in a moment. Please stand right here while I make a telephone call." I moved toward the phone booth, paused and said, "And don't ask me why." She gave me a speculative look. I must not have seemed a complete idiot because she said, "All right, but—" I didn't listen for the rest. I went into the booth, closed the door, pretended to drop a coin and dial a number. But all the time I was in there, I was reaching out through the glass for the clock. At this range it wasn't difficult to stop the balance wheel. Just the same, when I came out I was wringing wet. "Now will you please tell me what this is all about?" she said stiffly. "Gladly. Let me buy you a cup of coffee and I'll explain." She glanced at the bags. I told her they'd be all right. We followed the short, fat man into the coffee shop. Over coffee I explained it all to her, how I had this extrasensory ability, how she was the first person I had ever revealed it to, and how I had discovered what was in her overnight bag. During the telling, her untouched coffee grew a skin, her face grew pale, her eyes grew less curious and more troubled. There were tears there when I finished. I asked her who put the bomb in her bag. "Joe did," she said in a toneless voice, not looking at me any more but staring vacantly across the room. "Joe put it there." Behind her eyes she was reliving some recent scene. "Who is Joe?" "My husband." I thought she was going to really bawl, but she got control again. "This trip was his idea, my coming down here to visit my sister." Her smile was bleak. "I see now why he wanted to put in those books. I'd finished packing and was in the bathroom. He said he'd put in some books we'd both finished reading—for my sister. That's when he must have put the—put it in there." I said gently, "Why would he want to do a thing like that?" "I don't know." She shook her head. "I just don't know." And she was close to bawling again. Then she recovered and said, "I'm not sure I want to know." I admired her for saying it. Joe must have been crazy. "It's all right now?" she asked. I nodded. "As long as we don't move it." I told her I didn't know how much more time there was, that I'd been thinking it over and that the only way out seemed to be to tell the airport policeman. After I explained it to her, the girl—she said her name was Julia Claremont—agreed to tell him she thought there was a bomb in her bag, that she had noticed a ticking and had become worried because she knew she hadn't packed a clock. It wasn't good, but it would have to do. "We've got to get it deactivated," I said, watching the fat man pay for his coffee and leave. "The sooner the better." I finished my coffee in one gulp and went to pay the bill with her. I asked her why she didn't claim the bag at the same time the other people had. She said she had called her sister and the phone was busy for a long while. "She was supposed to meet me, and when she wasn't here, I got worried. She said she isn't feeling well and asked me to take a cab." She smiled a little. It was a bright, cheery thing. I had the feeling it was all for me. "That's where I was going when you caught up with me." It had become a very nice day. But the bottom dropped out of it again when we reached the lobby. The two bags weren't there. I ran to the entrance and nearly collided with the redcap. "See anybody go out of here with a little red bag and an old battered suitcase?" "Bag? Suitcase?" he mumbled. Then he became excited. "Why, a man just stepped out of here—" He turned to look down the street. "That's him." The dumpy man I'd seen was walking off; Julia's bag in his right hand, mine in his left. He seemed in no hurry. "Hey!" I shouted, starting toward him. The man turned, took one look at me, and started to run. He came abreast an old gray, mud-spattered coupe, ran around, opened the door and threw both bags into the rear seat as he got in. The car was a hundred feet away and gathering speed by the time I reached where it had been parked. I watched it for a moment, then walked back to the entranceway where Julia was standing with the redcap, who said, "That man steal them suitcases?" "That he did," I said. Just then the airport policeman started across the street from the parking lot. Redcap said, "Better tell him about it." The policeman was sympathetic and concerned. He said, "We'd better get over to the office." But we never left the spot because an explosion some blocks distant shattered the air. Julia's hand grasped my arm. Hard. "Jets," the redcap said, eying the sky. "I don't know," the policeman said. "Didn't sound much like a jet to me." We stood there. I could visualize the wreckage of an old gray coupe in the middle of a street, but I couldn't visualize the driver. That was all right. I didn't want to see him. I didn't know what Julia was thinking. She said, "About those bags," and looked at me. The officer said, "Yes, miss?" "I—I don't care about mine. I didn't have much of anything in it." "I feel the same way," I said. "Would it be all right if we didn't bother to report it?" "Well," the policeman said, "I can't make you report it." "I'd rather not then," Julia said. She turned to me. "I'd like some air. Can't we walk a little?" "Sure," I said. We started down the street, her arm in mine, as the air began to fill with the distant sounds of sirens.
|
B. She likely never becomes aware of the situation at all
|
Which best describes the relationship between Neena and Var?
A. They are marrying out of familial responsibility more than love but are still happy to be together
B. They have roughly equal footing in their dedication to one another
C. Neena gets to make all of the decision in return for going with Var to stay with his people
D. Var has convinced Neena to go with him after he won her in battle
|
WHEN THE MOUNTAIN SHOOK By Robert Abernathy Illustrated by Kelly Freas [Transcriber Note: This etext was produced from IF Worlds of Science Fiction March 1954. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Dark was the Ryzga mountain and forbidding; steep were its cliffs and sheer its crevasses. But its outward perils could not compare with the Ryzgas themselves, who slept within, ready to wake and conquer.... At sunset they were in sight of the Ryzga mountain. Strangely it towered among the cliffs and snow-slopes of the surrounding ranges: an immense and repellently geometric cone, black, its sides blood-tinted by the dying sun. Neena shivered, even though the surrounding cold could not reach her. The ice-wind blew from the glacier, but Var's love was round her as a warming cloak, a cloak that glowed softly golden in the deepening twilight, even as her love was about him. Var said, "The Watcher's cave should be three miles beyond this pass." He stood rigid, trying to catch an echo of the Watcher's thoughts, but there was nothing. Perhaps the old man was resting. From the other direction, the long way that they two had come, it was not difficult to sense the thought of Groz. That thought was powerful, and heavy with vengeance. "Hurry," said Neena. "They're closer than they were an hour ago." She was beautiful and defiant, facing the red sunset and the black mountain. Var sensed her fear, and the love that had conquered it. He felt a wave of tenderness and bitterness. For him she had come to this. For the flame that had sprung between them at the Truce of New Grass, she had challenged the feud of their peoples and had left her home, to follow him. Now, if her father and his kinsmen overtook them, it would be death for Var, and for Neena living shame. Which of the two was worse was no longer a simple problem to Var, who had grown much older in the last days. "Wait," he commanded. While she waited he spun a dream, attaching it to the crags that loomed over the pass, and to the frozen ground underfoot. It was black night, as it would really be when Groz and his henchmen reached this place; lurid fire spewed from the Ryzga mountain, and strange lights dipped above it; and for good measure there was an avalanche in the dream, and hideous beasts rushed snapping and ravening from the crevices of the rock. "Oh!" cried Neena in involuntary alarm. Var sighed, shaking his head. "It won't hold them for long, but it's the best I can do now. Come on." There was no path. Now they were descending the steeper face of the sierra, and the way led over bottomless crevasses, sheer drops and sheer ascents, sheets of traitorous glare ice. Place after place had to be crossed on the air, and both grew weary with the effort such crossings cost. They hoarded their strength, helping one another; one alone might never have won through. It was starry night already when they saw the light from the Watcher's cave. The light shone watery and dim from beneath the hoary back of the glacier, and as they came nearer they saw why: the cave entrance was sealed by a sheet of ice, a frozen waterfall that fell motionless from the rocks above. They heard no sound. The two young people stared for a long minute, intrigued and fearful. Both had heard of this place, and the ancient who lived there to keep watch on the Ryzga mountain, as a part of the oldest legends of their childhood; but neither had been here before. But this was no time for shyness. Var eyed the ice-curtain closely to make sure that it was real, not dream-stuff; then he struck it boldly with his fist. It shattered and fell in a rain of splinters, sparkling in the light that poured from within. They felt the Watcher rouse, heard his footsteps, and finally saw him—a shrunken old man, white-haired, with a lined beardless face. The sight of him, more marred by age than anyone they had ever seen before, was disappointing. They had expected something more—an ancient giant, a tower of wisdom and strength. The Watcher was four hundred years old; beside him even Groz, who had always seemed so ancient, was like a boy. The Watcher peered at them in turn. "Welcome," he said in a cracked voice. He did not speak again; the rest of his conversation was in thought only. "Welcome indeed. I am too much alone here." "You were asleep!" said Var. Shock made his thought accusing, though he had not meant to be. The old man grinned toothlessly. "Never fear. Asleep or awake, I watch. Come in! You're letting in the wind." Inside the cave it was warm as summer. Var saw with some surprise that all the walls were sheathed in ice—warm to the touch, bound fast against melting by the Watcher's will. Light blazed in reflections from the ice walls, till there was no shadow in the place. Behind them began a tinkling of falling water, thawed from the glacial ridges above to descend sheet-wise over the cave mouth, freezing as it fell into lengthening icicles. The old man gazed at his work for a moment, then turned questioningly to the young pair. "We need a little rest out of the cold," said Var. "And food, if you can spare it. We're pursued." "Yes, yes. You shall have what I can give you. Make yourselves comfortable, and in one minute.... Pursued, eh? A pity. I see the world is as bad as it was when I was last in it." Hot food and drink were before them almost at once. The Watcher regarded them with compassion as their eyes brightened and some of the shadow of weariness lifted from them. "You have stolen your enemy's daughter, no doubt, young man? Such things happened when I was young." Warming to the old man now, Var sketched his and Neena's history briefly. "We should have been safe among my people by now. And before very long, I'm sure, I would have performed some deed which Groz would recognize as a worthy exploit, and would thus have healed the feud between our families. But our flight was found out too soon. They cut us off and forced us into the mountains, and now they are only a few hours behind us." "A pity, indeed. I would like to help you—but, you understand, I am the Mountain Watcher. I must be above feuds and families." Var nodded somberly, thinking that an old recluse would in any case be able to do little for them against Groz and his violent kinsfolk. "And what will you do now?" Var grinned mirthlessly. "We haven't much choice, since they're overtaking us. I have only one idea left: we can go where Groz may fear to follow us." "To the mountain, you mean." "And into it, if need be." The Watcher was broodingly silent; his eyes shifted to Neena, where she nestled by Var's side. He asked, "And you—are you willing to follow your lover in this?" Neena returned his gaze without flinching; then she looked sidelong at Var, and her lips curled with a proud and tender mockery. "Follow? Why, I will lead, if his courage should fail him." The old man said, "It is no part of my duty to dissuade you from this thing. You are free persons. But I must be sure that you know what you are doing. That is the second part of the law the First Watcher made: to guard lest the unwary and the ignorant should bring harm on themselves and on all men." "We know the stories," Var said brusquely. "In the hollow heart of their mountain the Ryzgas sleep, as they chose to do when their world crumbled. But if they are wakened, the mountain will tremble, and the Ryzgas will come forth." "Do you believe that?" "As one believes stories." "It is true," said the Watcher heavily. "In my youth I penetrated farther into the mountain than anyone before, farther even than did the First Watcher. I did not see the sleepers, nor will any man until they come again, but I met their sentries, the sentinel machines that guard them now as they have for two thousand years. When I had gone that far, the mountain began to shake, the force that is in the Earth rumbled below, and I returned in time." Now for the first time Var sensed the power in the old man's look, the power of four hundred years' wisdom. Var stared down at his hands. "The Ryzgas also were men," said the Watcher. "But they were such a race as the world has not seen before or since. There were tyrannies before the Ryzgas, there was lust for power, and atrocious cruelty; but such tyranny, power, and cruelty as theirs, had never been known. They ruled the Earth for four generations, and the Earth was too little for them. They laid the world waste, stripped it of metals and fuels and bored to its heart for energy, poisoned its seas and its air with the fume of their works, wrung its peoples dry for their labor ... and in each of those four generations they launched a ship of space. They were great and evil as no other people has been, because they wanted the stars. "Because of them we must build with dreams instead of iron, and our only fire is that of the Sun, and even now, two thousand years later, the Earth is still slowly recovering from the pangs and poison of that age. If you turn up the sod in the plain where the wild herds graze, you will find numberless fragments of rusted or corroded metal, bits of glass and strange plastic substances, debris of artifacts still showing the marks of their shaping—the scattered wreckage of the things they made. And we—we too are a remnant, the descendants of the few out of all humanity that survived when the Ryzgas' world went down in flame and thunder. "In the last generation of their power the Ryzgas knew by their science that the race of man would endure them no longer. They made ready their weapons, they mined the cities and the factories for destruction, making sure that their works and their knowledge would perish with them. Meanwhile they redoubled the yoke and the punishments, hastening the completion of the last of the starships. "From the memories that the old Watchers have left here, and from the memories of dead men that still echo in the air, I have gathered a picture of that world's end. I will show it to you...." Var and Neena stared, unstirring, with wide vacant eyes, while the old man wove a dream around them, and the bright ice-cave faded from their vision, and they saw— Black starless night, a sky of rolling smoke above the greatest city that was ever built. Only the angry light of fires relieved the city's darkness—that, and the blue-white lightning flashes that silhouetted the naked skeletons of buildings and were followed by thunder and a shaking of the earth. Along lightless streets, half choked with rubble and with the dead, poured a mad, hating horde. The recurrent flashes lit scarred faces, naked bodies blackened and maimed from the hell of the workshops where the Ryzgas' might had been forged, eyes that stared white and half sightless from the glare of the furnaces, gnarled hands that now at long last clutched the weapons of the last rebellion—a rebellion without hope of new life on a world gutted and smoldering from the fulfilment of the Ryzgas' dream, without slogans other than a cry for blood. Before them death waited around the citadel where the masters still fought. All round, from the lowest and most poisonous levels of the shattered city, the slaves swarmed up in their millions. And the lightning blazed, and the city howled and screamed and burned. Then, unbelievably, the thunder fell silent, and the silence swept outward like a wave, from ruined street to street. The mouths that had shouted their wrath were speechless, and the rage-blinded eyes were lifted in sudden awe. From the center, over the citadel, an immense white globe soared upward, rising swiftly without sound. They had never seen its like, but they knew. It was the last starship, and it was leaving. It poised motionless. For an instant the burning city lay mute; then the millions found voice. Some roared ferocious threats and curses; others cried desolately— wait! Then the whole city, the dark tumuli of its buildings and its leaping fires and tormented faces, and the black sky over it, seemed to twist and swim, like a scene under water when a great fish sweeps past, and the ship was gone. The stunned paralysis fell apart in fury. Flame towered over the citadel. The hordes ran and shrieked again toward the central inferno, and the city burned and burned.... Var blinked dazedly in the shadowless glow of the ice-cave. His arm tightened about Neena till she gasped. He was momentarily uncertain that he and she were real and here, such had been the force of the dream, a vision of such scope and reality as Var had never seen—no, lived through—before. With deep respect now he gazed upon the bent old man who was the Mountain Watcher. "Some of the Ryzgas took flight to the stars, and some perished on Earth. But there was a group of them who believed that their time to rule would come again. These raised a black mountain from the Earth's heart, and in hollows within it cast themselves into deathless sleep, their deathless and lifeless sentinels round them, to wait till someone dare arouse them, or until their chosen time—no one knows surely. "I have told you the story you know, and have shown you a glimpse of the old time, because I must make sure that you do not approach the mountain in ignorance. Our world is unwise and sometimes evil, full of arrogance, folly, and passion that are in the nature of man. Yet it is a happy world, compared to that the Ryzgas made and will make again." The Watcher eyed them speculatively. "Before all," he said finally, "this is a world where you are free to risk wakening the old tyrants, if in your own judgment your great need renders the chance worth taking." Neena pressed her face against Var's shoulder, hiding her eyes. In her mind as it groped for his there was a confusion of horror and pity. Var looked grimly at the Watcher, and would have spoken; but the Watcher seemed suddenly a very long way off, and Var could no longer feel his own limbs, his face was a numb mask. Dully he heard the old man say, "You are tired. Best sleep until morning." Var strove to cry out that there was no time, that Groz was near and that sleep was for infants and the aged, but his intention sank and drowned under wave upon wave of unconquerable languor. The bright cave swam and dissolved; his eyelids closed. Var woke. Daylight glimmered through the ice of the cave mouth. He had been unconscious, helpless, for hours! At the thought of that, panic gripped him. He had not slept since childhood, and he had forgotten how it was. He came to his feet in one quick movement, realizing in that action that sleep had refreshed his mind and body—realizing also that a footstep had wakened him. Across the cave he faced a young man who watched him coolly with dark piercing eyes that were familiar though he did not know the face. Neena sat up and stifled a cry of fright. Var growled, "Who are you? Where's the Watcher?" The other flashed white teeth in a smile. "I'm the Watcher," he answered. "Often I become a youth at morning, and relax into age as the day passes. A foolish amusement, no doubt, but amusements are few here." "You made us fall asleep. Groz will be on us—" "Groz and his people could not detect your thoughts as you slept. They were all night chasing elusive dreams on the high ridges, miles away." Var passed a hand across bewildered eyes. Neena said softly, "Thank you, Watcher." "Don't thank me. I take no sides in your valley feuds. But now you are rested, your minds are clear. Do you still mean to go on to the Ryzga mountain?" Not looking at the Watcher, Var muttered unsteadily, "We have no alternative." There was a liquid tinkling as the ice-curtain collapsed; the fresh breeze of morning swept into the cave. The youth beckoned to them, and they followed him outside. The glacial slope on which the cavern opened faced toward the mountain. It rose black and forbidding in the dawn as it had by sunset. To right and left of it, the grand cliffs, ocher and red, were lit splendidly by the morning sun, but the mountain of the Ryzgas drank in the light and gave nothing back. Below their feet the slope fell away into an opaque sea of fog, filling a mile-wide gorge. There was a sound of turbulent water, of a river dashed from rock to rock in its struggle toward the plain, but the curling fog hid everything. "You have an alternative," said the Watcher crisply. The two took their eyes from the black mountain and gazed at him in sudden hope, but his face was unsmiling. "It is this. You, Var, can flee up the canyon to the north, by a way I will show you, disguising your thoughts and masking your presence as well as you are able, while the girl goes in the other direction, southward, without seeking to conceal herself. Your pursuers will be deceived and follow her, and by the time they catch her it will be too late for them to overtake Var." That possibility had not occurred to them at all. Var and Neena looked at one another. Then by common consent they blended their minds into one. They thought, in the warm intimacy of unreserved understanding: " It would work: I-you would make the sacrifice of shame and mockery—yet these can be borne—that I-you might be saved from death—which is alone irreparable.... But to become I and you again—that cannot be borne. " They said in unison, "No. Not that." The Watcher's face did not change. He said gravely, "Very well. I will give you what knowledge I have that may help you when you enter the Ryzga mountain." Quickly, he impressed on them what he had learned of the structure of the mountain and of its guardian machines. Var closed his eyes, a little dizzied by the rapid flood of detail. "You are ready to go," said the Watcher. He spoke aloud, and his voice was cracked and harsh. Var opened his eyes in surprise, and saw that the Watcher had become again the hoary ancient of last night. Var felt a twinge of unfamiliar emotion; only by its echo in Neena's mind did he recognize it as a sense of guilt. He said stiffly, "You don't blame us?" "You have taken life in your own hands," rasped the Watcher. "Who does that needs no blessing and feels no curse. Go!" They groped through the fog above blank abysses that hid the snarling river, crept hand in hand, sharing their strength, across unstable dream bridges from crag to crag. Groz and his pack, in their numbers, would cross the gorge more surely and swiftly. When Var and Neena set foot at last on the cindery slope of the great volcanic cone, they sensed that the pursuit already halved their lead. They stood high on the side of the Ryzga mountain, and gazed at the doorway. It was an opaque yet penetrable well of darkness, opening into the face of a lava cliff, closed only by an intangible curtain—so little had the Ryzgas feared those who might assail them in their sleep. Var sent his thoughts probing beyond the curtain, listened intently, head thrown back, to their echoes that returned. The tunnel beyond slanted steeply downward. Var's hands moved, molding a radiant globe from the feeble sunshine that straggled through the fog-bank. With an abrupt motion he hurled it. The sun-globe vanished, as if the darkness had drunk it up, but though sight did not serve they both sensed that it had passed through to light up the depths beyond. For within the mountain something snapped suddenly alert—something alive yet not living, seeing yet blind. They felt light-sensitive cells tingle in response, felt electric currents sting along buried, long-idle circuits.... The two stood shivering together. The morning wind stirred, freshening, the fog lifted a little, and they heard a great voice crying, "There they are!" Var and Neena turned. Far out in the sea of fog, on a dream bridge that they could not see, stood Groz. He shook the staff he carried. It was too far to discern the rage that must contort his features, but the thought he hurled at them was a soundless bellow: "Young fools! I've caught you now!" Behind Groz the figures of his followers loomed up as striding shadows. Neena's hand tightened on Var's. Var sent a thought of defiance: "Go back! Or you'll drive us to enter the mountain!" Groz seemed to hesitate. Then he swung his staff up like a weapon, and for the two on the mountainside the world turned upside down, the mountain's black shoulder hung inverted above them and the dizzy gulf of sky was beneath. Var fought for footing with his balance gone, feeling Neena reel against him until, summoning all his strength, he broke the grip of the illusion and the world seemed to right itself. The mist billowed again and Groz was out of sight, but they could hear him exhorting his men to haste. Neena's face was deadly pale and her lips trembled, but her urgent whisper said, "Come on!" Together they plunged into the curtain of darkness. At Var's thought command Neena froze instantly. "Feel that!" he muttered, and she, listening, sensed it too: the infinitesimal trickle of currents behind what appeared to be a blank tunnel wall, a rising potential that seemed to whisper Ready ... ready.... The sun-globe floated behind them, casting light before them down the featureless tunnel that sloped always toward the mountain's heart. Var summoned it, and it drifted ahead, a dozen feet, a little more— Between wall and wall a blinding spindle of flame sprang into being, pulsed briefly with radiant energy that pained the eyes, and went out. The immaterial globe of light danced on before them. "Forward, before the charge builds up again!" said Var. A few feet further on, they stumbled over a pile of charred bones. Someone else had made it only this far. It was farther than the Watcher had gone into these uncharted regions, and only the utmost alertness of mind and sense had saved them from death in traps like this. But as yet the way was not blocked.... Then they felt the mountain begin to tremble. A very faint and remote vibration at first, then an increasingly potent shuddering of the floor under their feet and the walls around them. Somewhere far below immense energies were stirring for the first time in centuries. The power that was in the Earth was rising; great wheels commenced to turn, the mechanical servitors of the Ryzgas woke one by one and began to make ready, while their masters yet slept, for the moment of rebirth that might be near at hand. From behind, up the tunnel, came a clear involuntary thought of dismay, then a directed thought, echoing and ghostly in the confinement of the dark burrow: " Stop! —before you go too far!" Var faced that way and thought coldly: "Only if you return and let us go free." In the black reaches of the shaft his will groped for and locked with that of Groz, like the grip of two strong wrestlers. In that grip each knew with finality that the other's stubbornness matched his own—that neither would yield, though the mountain above them and the world outside should crumble to ruin around them. "Follow us, then!" They plunged deeper into the mountain. And the shaking of the mountain increased with every step, its vibrations became sound, and its sound was like that of the terrible city which they had seen in the dream. Through the slow-rolling thunder of the hidden machines seemed to echo the death-cries of a billion slaves, the despair of all flesh and blood before their monstrous and inhuman power. Without warning, lights went on. Blinking in their glare, Var and Neena saw that fifty paces before them the way opened out into a great rounded room that was likewise ablaze with light. Cautiously they crept forward to the threshold of that chamber at the mountain's heart. Its roof was vaulted; its circular walls were lined with panels studded with gleaming control buttons, levers, colored lights. As they watched light flicked on and off in changing patterns, registering the progressive changes in the vast complex of mechanisms for which this must be the central control station. Behind those boards circuits opened and closed in bewildering confusion; the two invaders felt the rapid shifting of magnetic fields, the fury of electrons boiling in vacuum.... For long moments they forgot the pursuit, forgot everything in wonder at this place whose remotest like they had never seen in the simplicity of their machineless culture. In all the brilliant space there was no life. They looked at one another, the same thought coming to both at once: perhaps, after two thousand years, the masters were dead after all, and only the machines remained? As if irresistibly drawn, they stepped over the threshold. There was a clang of metal like a signal. Halfway up the wall opposite, above a narrow ramp that descended between the instrument panels, a massive doorway swung wide, and in its opening a figure stood. Var and Neena huddled frozenly, half expecting each instant to be their last. And the Ryzga too stood motionless, looking down at them. He was a man of middle height and stocky build, clad in a garment of changing colors, of fabric delicate as dream-stuff. In his right hand, with the care one uses with a weapon, he grasped a gleaming metal tube; his other hand rested as for support against the frame of the doorway. That, and his movements when he came slowly down the ramp toward them, conveyed a queer suggestion of weariness or weakness, as if he were yet not wholly roused from his two millenia of slumber. But the Ryzga's manner and his mind radiated a consciousness of power, a pride and assurance of self that smote them like a numbing blow. With a new shock, Var realized that the Ryzga's thoughts were quite open. They had a terse, disconnected quality that was strange and unsettling, and in part they were couched in alien and unintelligible symbols. But there was no block. Apparently the Ryzga felt no need to close his mind in the presence of inferior creatures.... He paused with his back to the central control panel, and studied the interlopers with the dispassionate gaze of a scientist examining a new, but not novel, species of insect. His thoughts seemed to click, like metal parts of a mechanism falling into places prepared for them. The image occurred oddly to Var, to whom such a comparison would ordinarily have been totally strange. "Culture: late barbarism. Handwork of high quality—good. Physically excellent stock...." There was a complicated and incomprehensible schemata of numbers and abstract forms. "The time: two thousand years—more progress might have been expected, if any survivors at all initially postulated; but this will do. The pessimists were mistaken. We can begin again." Then, startlingly super-imposed on the cool progression of logical thought, came a wave of raw emotion, devastating in its force. It was a lustful image of a world once more obedient, crawling, laboring to do the Ryzgas' will— toward the stars, the stars! The icy calculation resumed: "Immobilize these and the ones indicated in the passage above. Then wake the rest...." Var was staring in fascination at the Ryzga's face. It was a face formed by the custom of unquestioned command; yet it was lined by a deeply ingrained weariness, the signs of premature age—denied, overridden by the driving will they had sensed a moment earlier. It was a sick man's face. The Ryzga's final thought clicked into place: Decision! He turned toward the switchboard behind him, reaching with practised certainty for one spot upon it. Neena screamed. Between the Ryzga and the control panel a nightmare shape reared up seven feet tall, flapping black amorphous limbs and flashing red eyes and white fangs. The Ryzga recoiled, and the weapon in his hand came up. There was an instantaneous glare like heat lightning, and the monster crumpled in on itself, twitched briefly and vanished. But in that moment a light of inspiration had flashed upon Var, and it remained. As the Ryzga stretched out his hand again, Var acted. The Ryzga froze, teetering off balance and almost falling, as a numbing grip closed down on all his motor nerves. Holding that grip, Var strode across the floor and looked straight into the Ryzga's frantic eyes. They glared back at him with such hatred and such evil that for an instant he almost faltered. But the Ryzga's efforts, as he strove to free himself from the neural hold, were as misdirected and unavailing as those of a child who has not learned to wrestle with the mind. Var had guessed right. When Neena in her terror had flung a dream monster into the Ryzga's way—a mere child's bogey out of a fairy tale—the Ryzga had not recognized it as such, but had taken it for a real being. Var laughed aloud, and with great care, as one communicates with an infant, he projected his thoughts into the other's mind. "There will be no new beginning for you in our world, Ryzga! In two thousand years, we've learned some new things. Now at last I understand why you built so many machines, such complicated arrangements of matter and energy to do simple tasks—it was because you knew no other way." Behind the hate-filled eyes the cold brain tried to reason still. "Barbarians...? Our party was wrong after all. After us the machine civilization could never rise again, because it was a fire that consumed its fuel. After us man could not survive on the Earth, because the conditions that made him great were gone. The survivors must be something else—capacities undeveloped by our science—after us the end of man, the beginning.... But those of us who chose to die were right." The tide of hate and sick desire rose up to drown all coherence. The Ryzga made a savage, wholly futile effort to lift the weapon in his paralyzed hand. Then his eyes rolled upward, and abruptly he went limp and fell in a heap, like a mechanical doll whose motive power has failed. Var felt Neena beside him, and drew her close. As she sobbed her relief, he continued to look down absently at the dead man. When at last he raised his head, he saw that the drama's end had had a further audience. In the outer doorway, backed by his clansmen, stood Groz, gazing first in stupefaction at the fallen Ryzga, then with something like awe at Var. Var eyed him for a long moment; then he smiled, and asked, "Well, Groz? Is our feud finished, or does your ambition for a worthy son-in-law go beyond the conqueror of the Ryzgas?"
|
B. They have roughly equal footing in their dedication to one another
|
Of the four main crew members, who are focused on the most in the story?
A. Kelburn and Halden
B. Meredith and Emmer
C. Halden and Meredith
D. Kelburn and Meredith
|
BIG ANCESTOR By F. L. WALLACE Illustrated by EMSH [Transcriber's Note: This etext was produced from Galaxy Science Fiction November 1954. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] Man's family tree was awesome enough to give every galactic race an inferiority complex—but then he tried to climb it! In repose, Taphetta the Ribboneer resembled a fancy giant bow on a package. His four flat legs looped out and in, the ends tucked under his wide, thin body, which constituted the knot at the middle. His neck was flat, too, arching out in another loop. Of all his features, only his head had appreciable thickness and it was crowned with a dozen long though narrower ribbons. Taphetta rattled the head fronds together in a surprisingly good imitation of speech. "Yes, I've heard the legend." "It's more than a legend," said Sam Halden, biologist. The reaction was not unexpected—non-humans tended to dismiss the data as convenient speculation and nothing more. "There are at least a hundred kinds of humans, each supposedly originating in strict seclusion on as many widely scattered planets. Obviously there was no contact throughout the ages before space travel— and yet each planetary race can interbreed with a minimum of ten others ! That's more than a legend—one hell of a lot more!" "It is impressive," admitted Taphetta. "But I find it mildly distasteful to consider mating with someone who does not belong to my species." "That's because you're unique," said Halden. "Outside of your own world, there's nothing like your species, except superficially, and that's true of all other creatures, intelligent or not, with the sole exception of mankind. Actually, the four of us here, though it's accidental, very nearly represent the biological spectrum of human development. "Emmer, a Neanderthal type and our archeologist, is around the beginning of the scale. I'm from Earth, near the middle, though on Emmer's side. Meredith, linguist, is on the other side of the middle. And beyond her, toward the far end, is Kelburn, mathematician. There's a corresponding span of fertility. Emmer just misses being able to breed with my kind, but there's a fair chance that I'd be fertile with Meredith and a similar though lesser chance that her fertility may extend to Kelburn." Taphetta rustled his speech ribbons quizzically. "But I thought it was proved that some humans did originate on one planet, that there was an unbroken line of evolution that could be traced back a billion years." "You're thinking of Earth," said Halden. "Humans require a certain kind of planet. It's reasonable to assume that, if men were set down on a hundred such worlds, they'd seem to fit in with native life-forms on a few of them. That's what happened on Earth; when Man arrived, there was actually a manlike creature there. Naturally our early evolutionists stretched their theories to cover the facts they had. "But there are other worlds in which humans who were there before the Stone Age aren't related to anything else there. We have to conclude that Man didn't originate on any of the planets on which he is now found. Instead, he evolved elsewhere and later was scattered throughout this section of the Milky Way." "And so, to account for the unique race that can interbreed across thousands of light-years, you've brought in the big ancestor," commented Taphetta dryly. "It seems an unnecessary simplification." "Can you think of a better explanation?" asked Kelburn. "Something had to distribute one species so widely and it's not the result of parallel evolution—not when a hundred human races are involved, and only the human race." "I can't think of a better explanation." Taphetta rearranged his ribbons. "Frankly, no one else is much interested in Man's theories about himself." It was easy to understand the attitude. Man was the most numerous though not always the most advanced—Ribboneers had a civilization as high as anything in the known section of the Milky Way, and there were others—and humans were more than a little feared. If they ever got together—but they hadn't except in agreement as to their common origin. Still, Taphetta the Ribboneer was an experienced pilot and could be very useful. A clear statement of their position was essential in helping him make up his mind. "You've heard of the adjacency mating principle?" asked Sam Halden. "Vaguely. Most people have if they've been around men." "We've got new data and are able to interpret it better. The theory is that humans who can mate with each other were once physically close. We've got a list of all our races arranged in sequence. If planetary race F can mate with race E back to A and forward to M, and race G is fertile only back to B, but forward to O, then we assume that whatever their positions are now, at once time G was actually adjacent to F, but was a little further along. When we project back into time those star systems on which humans existed prior to space travel, we get a certain pattern. Kelburn can explain it to you." The normally pink body of the Ribboneer flushed slightly. The color change was almost imperceptible, but it was enough to indicate that he was interested. Kelburn went to the projector. "It would be easier if we knew all the stars in the Milky Way, but though we've explored only a small portion of it, we can reconstruct a fairly accurate representation of the past." He pressed the controls and stars twinkled on the screen. "We're looking down on the plane of the Galaxy. This is one arm of it as it is today and here are the human systems." He pressed another control and, for purposes of identification, certain stars became more brilliant. There was no pattern, merely a scattering of stars. "The whole Milky Way is rotating. And while stars in a given region tend to remain together, there's also a random motion. Here's what happens when we calculate the positions of stars in the past." Flecks of light shifted and flowed across the screen. Kelburn stopped the motion. "Two hundred thousand years ago," he said. There was a pattern of the identified stars. They were spaced at fairly equal intervals along a regular curve, a horseshoe loop that didn't close, though if the ends were extended, the lines would have crossed. Taphetta rustled. "The math is accurate?" "As accurate as it can be with a million-plus body problem." "And that's the hypothetical route of the unknown ancestor?" "To the best of our knowledge," said Kelburn. "And whereas there are humans who are relatively near and not fertile, they can always mate with those they were adjacent to two hundred thousand years ago !" "The adjacency mating principle. I've never seen it demonstrated," murmured Taphetta, flexing his ribbons. "Is that the only era that satisfies the calculations?" "Plus or minus a hundred thousand years, we can still get something that might be the path of a spaceship attempting to cover a representative section of territory," said Kelburn. "However, we have other ways of dating it. On some worlds on which there are no other mammals, we're able to place the first human fossils chronologically. The evidence is sometimes contradictory, but we believe we've got the time right." Taphetta waved a ribbon at the chart. "And you think that where the two ends of the curve cross is your original home?" "We think so," said Kelburn. "We've narrowed it down to several cubic light-years—then. Now it's far more. And, of course, if it were a fast-moving star, it might be completely out of the field of our exploration. But we're certain we've got a good chance of finding it this trip." "It seems I must decide quickly." The Ribboneer glanced out the visionport, where another ship hung motionless in space beside them. "Do you mind if I ask other questions?" "Go ahead," Kelburn invited sardonically. "But if it's not math, you'd better ask Halden. He's the leader of the expedition." Halden flushed; the sarcasm wasn't necessary. It was true that Kelburn was the most advanced human type present, but while there were differences, biological and in the scale of intelligence, it wasn't as great as once was thought. Anyway, non-humans weren't trained in the fine distinctions that men made among themselves. And, higher or lower, he was as good a biologist as the other was a mathematician. And there was the matter of training; he'd been on several expeditions and this was Kelburn's first trip. Damn it, he thought, that rated some respect. The Ribboneer shifted his attention. "Aside from the sudden illness of your pilot, why did you ask for me?" "We didn't. The man became sick and required treatment we can't give him. Luckily, a ship was passing and we hailed it because it's four months to the nearest planet. They consented to take him back and told us that there was a passenger on board who was an experienced pilot. We have men who could do the job in a makeshift fashion, but the region we're heading for, while mapped, is largely unknown. We'd prefer to have an expert—and Ribboneers are famous for their navigational ability." Taphetta crinkled politely at the reference to his skill. "I had other plans, but I can't evade professional obligations, and an emergency such as this should cancel out any previous agreements. Still, what are the incentives?" Sam Halden coughed. "The usual, plus a little extra. We've copied the Ribboneer's standard nature, simplifying it a little and adding a per cent here and there for the crew pilot and scientist's share of the profits from any discoveries we may make." "I'm complimented that you like our contract so well," said Taphetta, "but I really must have our own unsimplified version. If you want me, you'll take my contract. I came prepared." He extended a tightly bound roll that he had kept somewhere on his person. They glanced at one another as Halden took it. "You can read it if you want," offered Taphetta. "But it will take you all day—it's micro-printing. However, you needn't be afraid that I'm defrauding you. It's honored everywhere we go and we go nearly everywhere in this sector—places men have never been." There was no choice if they wanted him, and they did. Besides, the integrity of Ribboneers was not to be questioned. Halden signed. "Good." Taphetta crinkled. "Send it to the ship; they'll forward it for me. And you can tell the ship to go on without me." He rubbed his ribbons together. "Now if you'll get me the charts, I'll examine the region toward which we're heading." Firmon of hydroponics slouched in, a tall man with scanty hair and an equal lack of grace. He seemed to have difficulty in taking his eyes off Meredith, though, since he was a notch or so above her in the mating scale, he shouldn't have been so interested. But his planet had been inexplicably slow in developing and he wasn't completely aware of his place in the human hierarchy. Disdainfully, Meredith adjusted a skirt that, a few inches shorter, wouldn't have been a skirt at all, revealing, while doing so, just how long and beautiful a woman's legs could be. Her people had never given much thought to physical modesty and, with legs like that, it was easy to see why. Muttering something about primitive women, Firmon turned to the biologist. "The pilot doesn't like our air." "Then change it to suit him. He's in charge of the ship and knows more about these things than I do." "More than a man?" Firmon leered at Meredith and, when she failed to smile, added plaintively, "I did try to change it, but he still complains." Halden took a deep breath. "Seems all right to me." "To everybody else, too, but the tapeworm hasn't got lungs. He breathes through a million tubes scattered over his body." It would do no good to explain that Taphetta wasn't a worm, that his evolution had taken a different course, but that he was in no sense less complex than Man. It was a paradox that some biologically higher humans hadn't developed as much as lower races and actually weren't prepared for the multitude of life-forms they'd meet in space. Firmon's reaction was quite typical. "If he asks for cleaner air, it's because his system needs it," said Halden. "Do anything you can to give it to him." "Can't. This is as good as I can get it. Taphetta thought you could do something about it." "Hydroponics is your job. There's nothing I can do." Halden paused thoughtfully. "Is there something wrong with the plants?" "In a way, I guess, and yet not really." "What is it, some kind of toxic condition?" "The plants are healthy enough, but something's chewing them down as fast as they grow." "Insects? There shouldn't be any, but if there are, we've got sprays. Use them." "It's an animal," said Firmon. "We tried poison and got a few, but now they won't touch the stuff. I had electronics rig up some traps. The animals seem to know what they are and we've never caught one that way." Halden glowered at the man. "How long has this been going on?" "About three months. It's not bad; we can keep up with them." It was probably nothing to become alarmed at, but an animal on the ship was a nuisance, doubly so because of their pilot. "Tell me what you know about it," said Halden. "They're little things." Firmon held out his hands to show how small. "I don't know how they got on, but once they did, there were plenty of places to hide." He looked up defensively. "This is an old ship with new equipment and they hide under the machinery. There's nothing we can do except rebuild the ship from the hull inward." Firmon was right. The new equipment had been installed in any place just to get it in and now there were inaccessible corners and crevices everywhere that couldn't be closed off without rebuilding. They couldn't set up a continuous watch and shoot the animals down because there weren't that many men to spare. Besides, the use of weapons in hydroponics would cause more damage to the thing they were trying to protect than to the pest. He'd have to devise other ways. Sam Halden got up. "I'll take a look and see what I can do." "I'll come along and help," said Meredith, untwining her legs and leaning against him. "Your mistress ought to have some sort of privileges." Halden started. So she knew that the crew was calling her that! Perhaps it was intended to discourage Firmon, but he wished she hadn't said it. It didn't help the situation at all. Taphetta sat in a chair designed for humans. With a less flexible body, he wouldn't have fitted. Maybe it wasn't sitting, but his flat legs were folded neatly around the arms and his head rested comfortably on the seat. The head ribbons, which were his hands and voice, were never quite still. He looked from Halden to Emmer and back again. "The hydroponics tech tells me you're contemplating an experiment. I don't like it." Halden shrugged. "We've got to have better air. It might work." "Pests on the ship? It's filthy! My people would never tolerate it!" "Neither do we." The Ribboneer's distaste subsided. "What kind of creatures are they?" "I have a description, though I've never seen one. It's a small four-legged animal with two antennae at the lower base of its skull. A typical pest." Taphetta rustled. "Have you found out how it got on?" "It was probably brought in with the supplies," said the biologist. "Considering how far we've come, it may have been any one of a half a dozen planets. Anyway, it hid, and since most of the places it had access to were near the outer hull, it got an extra dose of hard radiation, or it may have nested near the atomic engines; both are possibilities. Either way, it mutated, became a different animal. It's developed a tolerance for the poisons we spray on plants. Other things it detects and avoids, even electronic traps." "Then you believe it changed mentally as well as physically, that it's smarter?" "I'd say that, yes. It must be a fairly intelligent creature to be so hard to get rid of. But it can be lured into traps, if the bait's strong enough." "That's what I don't like," said Taphetta, curling. "Let me think it over while I ask questions." He turned to Emmer. "I'm curious about humans. Is there anything else you can tell me about the hypothetical ancestor?" Emmer didn't look like the genius he was—a Neanderthal genius, but nonetheless a real one. In his field, he rated very high. He raised a stubble-flecked cheek from a large thick-fingered paw and ran shaggy hands through shaggier hair. "I can speak with some authority," he rumbled. "I was born on a world with the most extensive relics. As a child, I played in the ruins of their camp." "I don't question your authority," crinkled Taphetta. "To me, all humans—late or early and male or female—look remarkably alike. If you are an archeologist, that's enough for me." He paused and flicked his speech ribbons. "Camp, did you say?" Emmer smiled, unsheathing great teeth. "You've never seen any pictures? Impressive, but just a camp, monolithic one-story structures, and we'd give something to know what they're made of. Presumably my world was one of the first they stopped at. They weren't used to roughing it, so they built more elaborately than they did later on. One-story structures and that's how we can guess at their size. The doorways were forty feet high." "Very large," agreed Taphetta. It was difficult to tell whether he was impressed. "What did you find in the ruins?" "Nothing," said Emmer. "There were buildings there and that was all, not a scrap of writing or a tool or a single picture. They covered a route estimated at thirty thousand light-years in less than five thousand years—and not one of them died that we have a record of." "A faster-than-light drive and an extremely long life," mused Taphetta. "But they didn't leave any information for their descendants. Why?" "Who knows? Their mental processes were certainly far different from ours. They may have thought we'd be better off without it. We do know they were looking for a special kind of planet, like Earth, because they visited so many of that type, yet different from it because they never stayed. They were pretty special people themselves, big and long-lived, and maybe they couldn't survive on any planet they found. Perhaps they had ways of determining there wasn't the kind of planet they needed in the entire Milky Way. Their science was tremendously advanced and when they learned that, they may have altered their germ plasm and left us, hoping that some of us would survive. Most of us did." "This special planet sounds strange," murmured Taphetta. "Not really," said Emmer. "Fifty human races reached space travel independently and those who did were scattered equally among early and late species. It's well known that individuals among my people are often as bright as any of Halden's or Meredith's, but as a whole we don't have the total capacity that later Man does, and yet we're as advanced in civilization. The difference? It must lie somewhere in the planets we live on and it's hard to say just what it is." "What happened to those who didn't develop space travel?" asked Taphetta. "We helped them," said Emmer. And they had, no matter who or what they were, biologically late or early, in the depths of the bronze age or the threshold of atomic—because they were human. That was sometimes a frightening thing for non-humans, that the race stuck together. They weren't actually aggressive, but their total number was great and they held themselves aloof. The unknown ancestor again. Who else had such an origin and, it was tacitly assumed, such a destiny? Taphetta changed his questioning. "What do you expect to gain from this discovery of the unknown ancestor?" It was Halden who answered him. "There's the satisfaction of knowing where we came from." "Of course," rustled the Ribboneer. "But a lot of money and equipment was required for this expedition. I can't believe that the educational institutions that are backing you did so purely out of intellectual curiosity." "Cultural discoveries," rumbled Emmer. "How did our ancestors live? When a creature is greatly reduced in size, as we are, more than physiology is changed—the pattern of life itself is altered. Things that were easy for them are impossible for us. Look at their life span." "No doubt," said Taphetta. "An archeologist would be interested in cultural discoveries." "Two hundred thousand years ago, they had an extremely advanced civilization," added Halden. "A faster-than-light drive, and we've achieved that only within the last thousand years." "But I think we have a better one than they did," said the Ribboneer. "There may be things we can learn from them in mechanics or physics, but wouldn't you say they were better biologists than anything else?" Halden nodded. "Agreed. They couldn't find a suitable planet. So, working directly with their germ plasm, they modified themselves and produced us. They were master biologists." "I thought so," said Taphetta. "I never paid much attention to your fantastic theories before I signed to pilot this ship, but you've built up a convincing case." He raised his head, speech ribbons curling fractionally and ceaselessly. "I don't like to, but we'll have to risk using bait for your pest." He'd have done it anyway, but it was better to have the pilot's consent. And there was one question Halden wanted to ask; it had been bothering him vaguely. "What's the difference between the Ribboneer contract and the one we offered you? Our terms are more liberal." "To the individual, they are, but it won't matter if you discover as much as you think you will. The difference is this: My terms don't permit you to withhold any discovery for the benefit of one race." Taphetta was wrong; there had been no intention of withholding anything. Halden examined his own attitudes. He hadn't intended, but could he say that was true of the institutions backing the expedition? He couldn't, and it was too late now—whatever knowledge they acquired would have to be shared. That was what Taphetta had been afraid of—there was one kind of technical advancement that multiplied unceasingly. The race that could improve itself through scientific control of its germ plasm had a start that could never be headed. The Ribboneer needn't worry now. "Why do we have to watch it on the screen?" asked Meredith, glancing up. "I'd rather be in hydroponics." Halden shrugged. "They may or may not be smarter than planetbound animals, but they're warier. They don't come out when anyone's near." Lights dimmed in the distant hydroponic section and the screen with it, until he adjusted the infra-red frequencies. He motioned to the two crew members, each with his own peculiar screen, below which was a miniature keyboard. "Ready?" When they nodded, Halden said: "Do as you've rehearsed. Keep noise at a minimum, but when you do use it, be vague. Don't try to imitate them exactly." At first, nothing happened on the big screen, and then a gray shape crept out. It slid through leaves, listened intently before coming forward. It jumped off one hydroponic section and fled across the open floor to the next. It paused, eyes glittering and antennae twitching. Looking around once, it leaped up, seizing the ledge and clawing up the side of the tank. Standing on top and rising to its haunches, it began nibbling what it could reach. Suddenly it whirled. Behind it and hitherto unnoticed was another shape, like it but larger. The newcomer inched forward. The small one retreated, skittering nervously. Without warning, the big one leaped and the small one tried to flee. In a few jumps, the big one caught up and mauled the other unmercifully. It continued to bite even after the little one lay still. At last it backed off and waited, watching for signs of motion. There was none. Then it turned to the plant. When it had chewed off everything within reach, it climbed into the branches. The little one twitched, moved a leg, and cautiously began dragging itself away. It rolled off the raised section and surprisingly made no noise as it fell. It seemed to revive, shaking itself and scurrying away, still within range of the screen. Against the wall was a small platform. The little one climbed on top and there found something that seemed to interest it. It sniffed around and reached and felt the discovery. Wounds were forgotten as it snatched up the object and frisked back to the scene of its recent defeat. This time it had no trouble with the raised section. It leaped and landed on top and made considerable noise in doing so. The big animal heard and twisted around. It saw and clambered down hastily, jumping the last few feet. Squealing, it hit the floor and charged. The small one stood still till the last instant—and then a paw flickered out and an inch-long knife blade plunged into the throat of the charging creature. Red spurted out as the bigger beast screamed. The knife flashed in and out until the big animal collapsed and stopped moving. The small creature removed the knife and wiped it on the pelt of its foe. Then it scampered back to the platform on which the knife had been found— and laid it down . At Halden's signal, the lights flared up and the screen became too bright for anything to be visible. "Go in and get them," said Halden. "We don't want the pests to find out that the bodies aren't flesh." "It was realistic enough," said Meredith as the crewmen shut off their machines and went out. "Do you think it will work?" "It might. We had an audience." "Did we? I didn't notice." Meredith leaned back. "Were the puppets exactly like the pests? And if not, will the pests be fooled?" "The electronic puppets were a good imitation, but the animals don't have to identify them as their species. If they're smart enough, they'll know the value of a knife, no matter who uses it." "What if they're smarter? Suppose they know a knife can't be used by a creature without real hands?" "That's part of our precautions. They'll never know until they try—and they'll never get away from the trap to try." "Very good. I never thought of that," said Meredith, coming closer. "I like the way your primitive mind works. At times I actually think of marrying you." "Primitive," he said, alternately frozen and thawed, though he knew that, in relation to her, he was not advanced. "It's almost a curse, isn't it?" She laughed and took the curse away by leaning provocatively against him. "But barbaric lovers are often nice." Here we go again, he thought drearily, sliding his arm around her. To her, I'm merely a passionate savage. They went to his cabin. She sat down, smiling. Was she pretty? Maybe. For her own race, she wasn't tall, only by Terran standards. Her legs were disproportionately long and well shaped and her face was somewhat bland and featureless, except for a thin, straight, short nose. It was her eyes that made the difference, he decided. A notch or two up the scale of visual development, her eyes were larger and she could see an extra color on the violet end of the spectrum. She settled back and looked at him. "It might be fun living with you on primeval Earth." He said nothing; she knew as well as he that Earth was as advanced as her own world. She had something else in mind. "I don't think I will, though. We might have children." "Would it be wrong?" he asked. "I'm as intelligent as you. We wouldn't have subhuman monsters." "It would be a step up—for you." Under her calm, there was tension. It had been there as long as he'd known her, but it was closer to the surface now. "Do I have the right to condemn the unborn? Should I make them start lower than I am?" The conflict was not new nor confined to them. In one form or another, it governed personal relations between races that were united against non-humans, but held sharp distinctions themselves. "I haven't asked you to marry me," he said bluntly. "Because you're afraid I'd refuse." It was true; no one asked a member of a higher race to enter a permanent union. "Why did you ever have anything to do with me?" demanded Halden. "Love," she said gloomily. "Physical attraction. But I can't let it lead me astray." "Why not make a play for Kelburn? If you're going to be scientific about it, he'd give you children of the higher type." "Kelburn." It didn't sound like a name, the way she said it. "I don't like him and he wouldn't marry me." "He wouldn't, but he'd give you children if you were humble enough. There's a fifty per cent chance you might conceive." She provocatively arched her back. Not even the women of Kelburn's race had a body like hers and she knew it. "Racially, there should be a chance," she said. "Actually, Kelburn and I would be infertile." "Can you be sure?" he asked, knowing it was a poor attempt to act unconcerned. "How can anyone be sure on a theoretical basis?" she asked, an oblique smile narrowing her eyes. "I know we can't." His face felt anesthetized. "Did you have to tell me that?" She got up and came to him. She nuzzled against him and his reaction was purely reflexive. His hand swung out and he could feel the flesh give when his knuckles struck it. She fell back and dazedly covered her face with her hand. When she took it away, blood spurted. She groped toward the mirror and stood in front of it. She wiped the blood off, examining her features carefully. "You've broken my nose," she said factually. "I'll have to stop the blood and pain." She pushed her nose back into place and waggled it to make sure. She closed her eyes and stood silent and motionless. Then she stepped back and looked at herself critically. "It's set and partially knitted. I'll concentrate tonight and have it healed by morning." She felt in the cabinet and attached an invisible strip firmly across the bridge. Then she came over to him. "I wondered what you'd do. You didn't disappoint me." He scowled miserably at her. Her face was almost plain and the bandage, invisible or not, didn't improve her appearance any. How could he still feel that attraction to her? "Try Emmer," he suggested tiredly. "He'll find you irresistible, and he's even more savage than I am." "Is he?" She smiled enigmatically. "Maybe, in a biological sense. Too much, though. You're just right." He sat down on the bed. Again there was only one way of knowing what Emmer would do—and she knew. She had no concept of love outside of the physical, to make use of her body so as to gain an advantage—what advantage?—for the children she intended to have. Outside of that, nothing mattered, and for the sake of alloying the lower with the higher, she was as cruel to herself as she was to him. And yet he wanted her. "I do think I love you," she said. "And if love's enough, I may marry you in spite of everything. But you'll have to watch out whose children I have." She wriggled into his arms. The racial disparity was great and she had provoked him, but it was not completely her fault. Besides.... Besides what? She had a beautiful body that could bear superior children—and they might be his. He twisted away. With those thoughts, he was as bad as she was. Were they all that way, every one of them, crawling upward out of the slime toward the highest goal they could conceive of? Climbing over—no, through —everybody they could coerce, seduce or marry—onward and upward. He raised his hand, but it was against himself that his anger was turned. "Careful of the nose," she said, pressing against him. "You've already broken it once." He kissed her with sudden passion that even he knew was primitive.
|
C. Halden and Meredith
|
How does Kolin feel about Ashlew?
A. He does not trust him because he has many features not standard for trees.
B. He is hesitant but drawn to him all the same.
C. He is certain that Ashlew is trying to trick him.
D. He trusts them, as the highest ranking person in this new planet he has met so far.
|
By H. B. Fyfe THE TALKATIVE TREE Dang vines! Beats all how some plants have no manners—but what do you expect, when they used to be men! All things considered—the obscure star, the undetermined damage to the stellar drive and the way the small planet's murky atmosphere defied precision scanners—the pilot made a reasonably good landing. Despite sour feelings for the space service of Haurtoz, steward Peter Kolin had to admit that casualties might have been far worse. Chief Steward Slichow led his little command, less two third-class ration keepers thought to have been trapped in the lower hold, to a point two hundred meters from the steaming hull of the Peace State . He lined them up as if on parade. Kolin made himself inconspicuous. "Since the crew will be on emergency watches repairing the damage," announced the Chief in clipped, aggressive tones, "I have volunteered my section for preliminary scouting, as is suitable. It may be useful to discover temporary sources in this area of natural foods." Volunteered HIS section! thought Kolin rebelliously. Like the Supreme Director of Haurtoz! Being conscripted into this idiotic space fleet that never fights is bad enough without a tin god on jets like Slichow! Prudently, he did not express this resentment overtly. His well-schooled features revealed no trace of the idea—or of any other idea. The Planetary State of Haurtoz had been organized some fifteen light-years from old Earth, but many of the home world's less kindly techniques had been employed. Lack of complete loyalty to the state was likely to result in a siege of treatment that left the subject suitably "re-personalized." Kolin had heard of instances wherein mere unenthusiastic posture had betrayed intentions to harbor treasonable thoughts. "You will scout in five details of three persons each," Chief Slichow said. "Every hour, each detail will send one person in to report, and he will be replaced by one of the five I shall keep here to issue rations." Kolin permitted himself to wonder when anyone might get some rest, but assumed a mildly willing look. (Too eager an attitude could arouse suspicion of disguising an improper viewpoint.) The maintenance of a proper viewpoint was a necessity if the Planetary State were to survive the hostile plots of Earth and the latter's decadent colonies. That, at least, was the official line. Kolin found himself in a group with Jak Ammet, a third cook, and Eva Yrtok, powdered foods storekeeper. Since the crew would be eating packaged rations during repairs, Yrtok could be spared to command a scout detail. Each scout was issued a rocket pistol and a plastic water tube. Chief Slichow emphasized that the keepers of rations could hardly, in an emergency, give even the appearance of favoring themselves in regard to food. They would go without. Kolin maintained a standard expression as the Chief's sharp stare measured them. Yrtok, a dark, lean-faced girl, led the way with a quiet monosyllable. She carried the small radio they would be permitted to use for messages of utmost urgency. Ammet followed, and Kolin brought up the rear. To reach their assigned sector, they had to climb a forbidding ridge of rock within half a kilometer. Only a sparse creeper grew along their way, its elongated leaves shimmering with bronze-green reflections against a stony surface; but when they topped the ridge a thick forest was in sight. Yrtok and Ammet paused momentarily before descending. Kolin shared their sense of isolation. They would be out of sight of authority and responsible for their own actions. It was a strange sensation. They marched down into the valley at a brisk pace, becoming more aware of the clouds and atmospheric haze. Distant objects seemed blurred by the mist, taking on a somber, brooding grayness. For all Kolin could tell, he and the others were isolated in a world bounded by the rocky ridge behind them and a semi-circle of damp trees and bushes several hundred meters away. He suspected that the hills rising mistily ahead were part of a continuous slope, but could not be sure. Yrtok led the way along the most nearly level ground. Low creepers became more plentiful, interspersed with scrubby thickets of tangled, spike-armored bushes. Occasionally, small flying things flickered among the foliage. Once, a shrub puffed out an enormous cloud of tiny spores. "Be a job to find anything edible here," grunted Ammet, and Kolin agreed. Finally, after a longer hike than he had anticipated, they approached the edge of the deceptively distant forest. Yrtok paused to examine some purple berries glistening dangerously on a low shrub. Kolin regarded the trees with misgiving. "Looks as tough to get through as a tropical jungle," he remarked. "I think the stuff puts out shoots that grow back into the ground to root as they spread," said the woman. "Maybe we can find a way through." In two or three minutes, they reached the abrupt border of the odd-looking trees. Except for one thick trunked giant, all of them were about the same height. They craned their necks to estimate the altitude of the monster, but the top was hidden by the wide spread of branches. The depths behind it looked dark and impenetrable. "We'd better explore along the edge," decided Yrtok. "Ammet, now is the time to go back and tell the Chief which way we're— Ammet! " Kolin looked over his shoulder. Fifty meters away, Ammet sat beside the bush with the purple berries, utterly relaxed. "He must have tasted some!" exclaimed Kolin. "I'll see how he is." He ran back to the cook and shook him by the shoulder. Ammet's head lolled loosely to one side. His rather heavy features were vacant, lending him a doped appearance. Kolin straightened up and beckoned to Yrtok. For some reason, he had trouble attracting her attention. Then he noticed that she was kneeling. "Hope she didn't eat some stupid thing too!" he grumbled, trotting back. As he reached her, whatever Yrtok was examining came to life and scooted into the underbrush with a flash of greenish fur. All Kolin saw was that it had several legs too many. He pulled Yrtok to her feet. She pawed at him weakly, eyes as vacant as Ammet's. When he let go in sudden horror, she folded gently to the ground. She lay comfortably on her side, twitching one hand as if to brush something away. When she began to smile dreamily, Kolin backed away. The corners of his mouth felt oddly stiff; they had involuntarily drawn back to expose his clenched teeth. He glanced warily about, but nothing appeared to threaten him. "It's time to end this scout," he told himself. "It's dangerous. One good look and I'm jetting off! What I need is an easy tree to climb." He considered the massive giant. Soaring thirty or forty meters into the thin fog and dwarfing other growth, it seemed the most promising choice. At first, Kolin saw no way, but then the network of vines clinging to the rugged trunk suggested a route. He tried his weight gingerly, then began to climb. "I should have brought Yrtok's radio," he muttered. "Oh, well, I can take it when I come down, if she hasn't snapped out of her spell by then. Funny … I wonder if that green thing bit her." Footholds were plentiful among the interlaced lianas. Kolin progressed rapidly. When he reached the first thick limbs, twice head height, he felt safer. Later, at what he hoped was the halfway mark, he hooked one knee over a branch and paused to wipe sweat from his eyes. Peering down, he discovered the ground to be obscured by foliage. "I should have checked from down there to see how open the top is," he mused. "I wonder how the view will be from up there?" "Depends on what you're looking for, Sonny!" something remarked in a soughing wheeze. Kolin, slipping, grabbed desperately for the branch. His fingers clutched a handful of twigs and leaves, which just barely supported him until he regained a grip with the other hand. The branch quivered resentfully under him. "Careful, there!" whooshed the eerie voice. "It took me all summer to grow those!" Kolin could feel the skin crawling along his backbone. "Who are you?" he gasped. The answering sigh of laughter gave him a distinct chill despite its suggestion of amiability. "Name's Johnny Ashlew. Kinda thought you'd start with what I am. Didn't figure you'd ever seen a man grown into a tree before." Kolin looked about, seeing little but leaves and fog. "I have to climb down," he told himself in a reasonable tone. "It's bad enough that the other two passed out without me going space happy too." "What's your hurry?" demanded the voice. "I can talk to you just as easy all the way down, you know. Airholes in my bark—I'm not like an Earth tree." Kolin examined the bark of the crotch in which he sat. It did seem to have assorted holes and hollows in its rough surface. "I never saw an Earth tree," he admitted. "We came from Haurtoz." "Where's that? Oh, never mind—some little planet. I don't bother with them all, since I came here and found out I could be anything I wanted." "What do you mean, anything you wanted?" asked Kolin, testing the firmness of a vertical vine. "Just what I said," continued the voice, sounding closer in his ear as his cheek brushed the ridged bark of the tree trunk. "And, if I do have to remind you, it would be nicer if you said 'Mr. Ashlew,' considering my age." "Your age? How old—?" "Can't really count it in Earth years any more. Lost track. I always figured bein' a tree was a nice, peaceful life; and when I remembered how long some of them live, that settled it. Sonny, this world ain't all it looks like." "It isn't, Mr. Ashlew?" asked Kolin, twisting about in an effort to see what the higher branches might hide. "Nope. Most everything here is run by the Life—that is, by the thing that first grew big enough to do some thinking, and set its roots down all over until it had control. That's the outskirts of it down below." "The other trees? That jungle?" "It's more'n a jungle, Sonny. When I landed here, along with the others from the Arcturan Spark , the planet looked pretty empty to me, just like it must have to—Watch it, there, Boy! If I didn't twist that branch over in time, you'd be bouncing off my roots right now!" "Th-thanks!" grunted Kolin, hanging on grimly. "Doggone vine!" commented the windy whisper. " He ain't one of my crowd. Landed years later in a ship from some star towards the center of the galaxy. You should have seen his looks before the Life got in touch with his mind and set up a mental field to help him change form. He looks twice as good as a vine!" "He's very handy," agreed Kolin politely. He groped for a foothold. "Well … matter of fact, I can't get through to him much, even with the Life's mental field helping. Guess he started living with a different way of thinking. It burns me. I thought of being a tree, and then he came along to take advantage of it!" Kolin braced himself securely to stretch tiring muscles. "Maybe I'd better stay a while," he muttered. "I don't know where I am." "You're about fifty feet up," the sighing voice informed him. "You ought to let me tell you how the Life helps you change form. You don't have to be a tree." "No?" " Uh -uh! Some of the boys that landed with me wanted to get around and see things. Lots changed to animals or birds. One even stayed a man—on the outside anyway. Most of them have to change as the bodies wear out, which I don't, and some made bad mistakes tryin' to be things they saw on other planets." "I wouldn't want to do that, Mr. Ashlew." "There's just one thing. The Life don't like taking chances on word about this place gettin' around. It sorta believes in peace and quiet. You might not get back to your ship in any form that could tell tales." "Listen!" Kolin blurted out. "I wasn't so much enjoying being what I was that getting back matters to me!" "Don't like your home planet, whatever the name was?" "Haurtoz. It's a rotten place. A Planetary State! You have to think and even look the way that's standard thirty hours a day, asleep or awake. You get scared to sleep for fear you might dream treason and they'd find out somehow." "Whooeee! Heard about them places. Must be tough just to live." Suddenly, Kolin found himself telling the tree about life on Haurtoz, and of the officially announced threats to the Planetary State's planned expansion. He dwelt upon the desperation of having no place to hide in case of trouble with the authorities. A multiple system of such worlds was agonizing to imagine. Somehow, the oddity of talking to a tree wore off. Kolin heard opinions spouting out which he had prudently kept bottled up for years. The more he talked and stormed and complained, the more relaxed he felt. "If there was ever a fellow ready for this planet," decided the tree named Ashlew, "you're it, Sonny! Hang on there while I signal the Life by root!" Kolin sensed a lack of direct attention. The rustle about him was natural, caused by an ordinary breeze. He noticed his hands shaking. "Don't know what got into me, talking that way to a tree," he muttered. "If Yrtok snapped out of it and heard, I'm as good as re-personalized right now." As he brooded upon the sorry choice of arousing a search by hiding where he was or going back to bluff things out, the tree spoke. "Maybe you're all set, Sonny. The Life has been thinkin' of learning about other worlds. If you can think of a safe form to jet off in, you might make yourself a deal. How'd you like to stay here?" "I don't know," said Kolin. "The penalty for desertion—" "Whoosh! Who'd find you? You could be a bird, a tree, even a cloud." Silenced but doubting, Kolin permitted himself to try the dream on for size. He considered what form might most easily escape the notice of search parties and still be tough enough to live a long time without renewal. Another factor slipped into his musings: mere hope of escape was unsatisfying after the outburst that had defined his fuming hatred for Haurtoz. I'd better watch myself! he thought. Don't drop diamonds to grab at stars! "What I wish I could do is not just get away but get even for the way they make us live … the whole damn set-up. They could just as easy make peace with the Earth colonies. You know why they don't?" "Why?" wheezed Ashlew. "They're scared that without talk of war, and scouting for Earth fleets that never come, people would have time to think about the way they have to live and who's running things in the Planetary State. Then the gravy train would get blown up—and I mean blown up!" The tree was silent for a moment. Kolin felt the branches stir meditatively. Then Ashlew offered a suggestion. "I could tell the Life your side of it," he hissed. "Once in with us, you can always make thinking connections, no matter how far away. Maybe you could make a deal to kill two birds with one stone, as they used to say on Earth…." Chief Steward Slichow paced up and down beside the ration crate turned up to serve him as a field desk. He scowled in turn, impartially, at his watch and at the weary stewards of his headquarters detail. The latter stumbled about, stacking and distributing small packets of emergency rations. The line of crewmen released temporarily from repair work was transient as to individuals but immutable as to length. Slichow muttered something profane about disregard of orders as he glared at the rocky ridges surrounding the landing place. He was so intent upon planning greetings with which to favor the tardy scouting parties that he failed to notice the loose cloud drifting over the ridge. It was tenuous, almost a haze. Close examination would have revealed it to be made up of myriads of tiny spores. They resembled those cast forth by one of the bushes Kolin's party had passed. Along the edges, the haze faded raggedly into thin air, but the units evidently formed a cohesive body. They drifted together, approaching the men as if taking intelligent advantage of the breeze. One of Chief Slichow's staggering flunkies, stealing a few seconds of relaxation on the pretext of dumping an armful of light plastic packing, wandered into the haze. He froze. After a few heartbeats, he dropped the trash and stared at ship and men as if he had never seen either. A hail from his master moved him. "Coming, Chief!" he called but, returning at a moderate pace, he murmured, "My name is Frazer. I'm a second assistant steward. I'll think as Unit One." Throughout the cloud of spores, the mind formerly known as Peter Kolin congratulated itself upon its choice of form. Nearer to the original shape of the Life than Ashlew got , he thought. He paused to consider the state of the tree named Ashlew, half immortal but rooted to one spot, unable to float on a breeze or through space itself on the pressure of light. Especially, it was unable to insinuate any part of itself into the control center of another form of life, as a second spore was taking charge of the body of Chief Slichow at that very instant. There are not enough men , thought Kolin. Some of me must drift through the airlock. In space, I can spread through the air system to the command group. Repairs to the Peace State and the return to Haurtoz passed like weeks to some of the crew but like brief moments in infinity to other units. At last, the ship parted the air above Headquarters City and landed. The unit known as Captain Theodor Kessel hesitated before descending the ramp. He surveyed the field, the city and the waiting team of inspecting officers. "Could hardly be better, could it?" he chuckled to the companion unit called Security Officer Tarth. "Hardly, sir. All ready for the liberation of Haurtoz." "Reformation of the Planetary State," mused the captain, smiling dreamily as he grasped the handrail. "And then—formation of the Planetary Mind!" END Transcriber's Note: This e-text was produced from Worlds of If January 1962 . Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.
|
B. He is hesitant but drawn to him all the same.
|
What reason did the newspaper have to focus on the possible active volcano theory and not the opinion of the geographer?
A. There wasn't enough evidence to disprove the active volcano theory.
B. There wasn't enough evidence to write about the fault line theory.
C. Simply that the idea of an active volcano was much more interesting to the public.
D. Joseph Schwartzberg was the only geologist saying otherwise.
|
THE GREAT NEBRASKA SEA By ALLAN DANZIG Illustrated by WOOD [Transcriber's Note: This etext was produced from Galaxy Magazine August 1963. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] It has happened a hundred times in the long history of Earth—and, sooner or later, will happen again! Everyone—all the geologists, at any rate—had known about the Kiowa Fault for years. That was before there was anything very interesting to know about it. The first survey of Colorado traced its course north and south in the narrow valley of Kiowa Creek about twenty miles east of Denver; it extended south to the Arkansas River. And that was about all even the professionals were interested in knowing. There was never so much as a landslide to bring the Fault to the attention of the general public. It was still a matter of academic interest when in the late '40s geologists speculated on the relationship between the Kiowa Fault and the Conchas Fault farther south, in New Mexico, and which followed the Pecos as far south as Texas. Nor was there much in the papers a few years later when it was suggested that the Niobrara Fault (just inside and roughly parallel to the eastern border of Wyoming) was a northerly extension of the Kiowa. By the mid sixties it was definitely established that the three Faults were in fact a single line of fissure in the essential rock, stretching almost from the Canadian border well south of the New Mexico-Texas line. It is not really surprising that it took so long to figure out the connection. The population of the states affected was in places as low as five people per square mile! The land was so dry it seemed impossible that it could ever be used except for sheep-farming. It strikes us today as ironic that from the late '50s there was grave concern about the level of the water table throughout the entire area. The even more ironic solution to the problem began in the summer of 1973. It had been a particularly hot and dry August, and the Forestry Service was keeping an anxious eye out for the fires it knew it could expect. Dense smoke was reported rising above a virtually uninhabited area along Black Squirrel Creek, and a plane was sent out for a report. The report was—no fire at all. The rising cloud was not smoke, but dust. Thousands of cubic feet of dry earth rising lazily on the summer air. Rock slides, they guessed; certainly no fire. The Forestry Service had other worries at the moment, and filed the report. But after a week had gone by, the town of Edison, a good twenty miles away from the slides, was still complaining of the dust. Springs was going dry, too, apparently from underground disturbances. Not even in the Rockies could anyone remember a series of rock slides as bad as this. Newspapers in the mountain states gave it a few inches on the front page; anything is news in late August. And the geologists became interested. Seismologists were reporting unusual activity in the area, tremors too severe to be rock slides. Volcanic activity? Specifically, a dust volcano? Unusual, they knew, but right on the Kiowa Fault—could be. Labor Day crowds read the scientific conjectures with late summer lassitude. Sunday supplements ran four-color artists' conceptions of the possible volcano. "Only Active Volcano in U. S.?" demanded the headlines, and some papers even left off the question mark. It may seem odd that the simplest explanation was practically not mentioned. Only Joseph Schwartzberg, head geographer of the Department of the Interior, wondered if the disturbance might not be a settling of the Kiowa Fault. His suggestion was mentioned on page nine or ten of the Monday newspapers (page 27 of the New York Times ). The idea was not nearly so exciting as a volcano, even a lava-less one, and you couldn't draw a very dramatic picture of it. To excuse the other geologists, it must be said that the Kiowa Fault had never acted up before. It never sidestepped, never jiggled, never, never produced the regular shows of its little sister out in California, which almost daily bounced San Francisco or Los Angeles, or some place in between. The dust volcano was on the face of it a more plausible theory. Still, it was only a theory. It had to be proved. As the tremors grew bigger, along with the affected area, as several towns including Edison were shaken to pieces by incredible earthquakes, whole bus- and plane-loads of geologists set out for Colorado, without even waiting for their university and government department to approve budgets. They found, of course, that Schwartzberg had been perfectly correct. They found themselves on the scene of what was fast becoming the most violent and widespread earthquake North America—probably the world—has ever seen in historic times. To describe it in the simplest terms, land east of the Fault was settling, and at a precipitous rate. Rock scraped rock with a whining roar. Shuddery as a squeaky piece of chalk raked across a blackboard, the noise was deafening. The surfaces of the land east and west of the Fault seemed no longer to have any relation to each other. To the west, tortured rock reared into cliffs. East, where sharp reports and muffled wheezes told of continued buckling and dropping, the earth trembled downward. Atop the new cliffs, which seemed to grow by sudden inches from heaving rubble, dry earth fissured and trembled, sliding acres at a time to fall, smoking, into the bucking, heaving bottom of the depression. There the devastation was even more thorough, if less spectacular. Dry earth churned like mud, and rock shards weighing tons bumped and rolled about like pebbles as they shivered and cracked into pebbles themselves. "It looks like sand dancing in a child's sieve," said the normally impassive Schwartzberg in a nationwide broadcast from the scene of disaster. "No one here has ever seen anything like it." And the landslip was growing, north and south along the Fault. "Get out while you can," Schwartzberg urged the population of the affected area. "When it's over you can come back and pick up the pieces." But the band of scientists who had rallied to his leadership privately wondered if there would be any pieces. The Arkansas River, at Avondale and North Avondale, was sluggishly backing north into the deepening trough. At the rate things were going, there might be a new lake the entire length of El Paso and Pueblo Counties. And, warned Schwartzberg, this might only be the beginning. By 16 September the landslip had crept down the Huerfano River past Cedarwood. Avondale, North Avondale and Boone had totally disappeared. Land west of the Fault was holding firm, though Denver had recorded several small tremors; everywhere east of the Fault, to almost twenty miles away, the now-familiar lurch and steady fall had already sent several thousand Coloradans scurrying for safety. All mountain climbing was prohibited on the Eastern Slope because of the danger of rock slides from minor quakes. The geologists went home to wait. There wasn't much to wait for. The news got worse and worse. The Platte River, now, was creating a vast mud puddle where the town of Orchard had been. Just below Masters, Colorado, the river leaped 70-foot cliffs to add to the heaving chaos below. And the cliffs were higher every day as the land beneath them groaned downward in mile-square gulps. As the Fault moved north and south, new areas quivered into unwelcome life. Fields and whole mountainsides moved with deceptive sloth down, down. They danced "like sand in a sieve"; dry, they boiled into rubble. Telephone lines, railroad tracks, roads snapped and simply disappeared. Virtually all east-west land communication was suspended and the President declared a national emergency. By 23 September the Fault was active well into Wyoming on the north, and rapidly approaching the border of New Mexico to the south. Trinchera and Branson were totally evacuated, but even so the over-all death toll had risen above 1,000. Away to the east the situation was quiet but even more ominous. Tremendous fissures opened up perpendicular to the Fault, and a general subsidence of the land was noticeable well into Kansas and Nebraska. The western borders of these states, and soon of the Dakotas and Oklahoma as well, were slowly sinking. On the actual scene of the disaster (or the scenes ; it is impossible to speak of anything this size in the singular) there was a horrifying confusion. Prairie and hill cracked open under intolerable strains as the land shuddered downward in gasps and leaps. Springs burst to the surface in hot geysers and explosions of steam. The downtown section of North Platte, Nebraska, dropped eight feet, just like that, on the afternoon of 4 October. "We must remain calm," declared the Governor of Nebraska. "We must sit this thing out. Be assured that everything possible is being done." But what could be done, with his state dropping straight down at a mean rate of a foot a day? The Fault nicked off the south-east corner of Montana. It worked its way north along the Little Missouri. South, it ripped past Roswell, New Mexico, and tore down the Pecos toward Texas. All the upper reaches of the Missouri were standing puddles by now, and the Red River west of Paris, Texas, had begun to run backward. Soon the Missouri began slowly slipping away westward over the slowly churning land. Abandoning its bed, the river spread uncertainly across farmland and prairie, becoming a sea of mud beneath the sharp new cliffs which rose in rending line, ever taller as the land continued to sink, almost from Canada to the Mexican border. There were virtually no floods, in the usual sense. The water moved too slowly, spread itself with no real direction or force. But the vast sheets of sluggish water and jelly-like mud formed death-traps for the countless refugees now streaming east. Perhaps the North Platte disaster had been more than anyone could take. 193 people had died in that one cave-in. Certainly by 7 October it had to be officially admitted that there was an exodus of epic proportion. Nearly two million people were on the move, and the U. S. was faced with a gigantic wave of refugees. Rails, roads and air-lanes were jammed with terrified hordes who had left everything behind to crowd eastward. All through October hollow-eyed motorists flocked into Tulsa, Topeka, Omaha, Sioux Falls and Fargo. St. Louis was made distributing center for emergency squads which flew everywhere with milk for babies and dog food for evacuating pets. Gasoline trucks boomed west to meet the demand for gas, but once inside the "zone of terror," as the newspapers now called it, they found their route blocked by eastbound cars on the wrong side of the road. Shops left by their fleeing owners were looted by refugees from further west; an American Airlines plane was wrecked by a mob of would-be passengers in Bismarck, North Dakota. Federal and State troops were called out, but moving two million people was not to be done in an orderly way. And still the landslip grew larger. The new cliffs gleamed in the autumn sunshine, growing higher as the land beneath them continued its inexorable descent. On 21 October, at Lubbock, Texas, there was a noise variously described as a hollow roar, a shriek and a deep musical vibration like a church bell. It was simply the tortured rock of the substrata giving way. The second phase of the national disaster was beginning. The noise traveled due east at better than 85 miles per hour. In its wake the earth to the north "just seemed to collapse on itself like a punctured balloon," read one newspaper report. "Like a cake that's failed," said a Texarkana housewife who fortunately lived a block south of Thayer Street, where the fissure raced through. There was a sigh and a great cloud of dust, and Oklahoma subsided at the astounding rate of about six feet per hour. At Biloxi, on the Gulf, there had been uneasy shufflings under foot all day. "Not tremors, exactly," said the captain of a fishing boat which was somehow to ride out the coming flood, "but like as if the land wanted to be somewhere else." Everyone in doomed Biloxi would have done well to have been somewhere else that evening. At approximately 8:30 p.m. the town shuddered, seemed to rise a little like the edge of a hall carpet caught in a draft, and sank. So did the entire Mississippi and Alabama coast, at about the same moment. The tidal wave which was to gouge the center from the U. S. marched on the land. From the north shore of Lake Ponchartrain to the Appalachicola River in Florida, the Gulf coast simply disappeared. Gulfport, Biloxi, Mobile, Pensacola, Panama City: 200 miles of shoreline vanished, with over two and a half million people. An hour later a wall of water had swept over every town from Dothan, Alabama, to Bogalusa on the Louisiana-Mississippi border. "We must keep panic from our minds," said the Governor of Alabama in a radio message delivered from a hastily arranged all-station hookup. "We of the gallant southland have faced and withstood invasion before." Then, as ominous creakings and groanings of the earth announced the approach of the tidal wave, he flew out of Montgomery half an hour before the town disappeared forever. One head of the wave plunged north, eventually to spend itself in the hills south of Birmingham. The main sweep followed the lowest land. Reaching west, it swallowed Vicksburg and nicked the corner of Louisiana. The whole of East Carroll Parish was scoured from the map. The Mississippi River now ended at about Eudora, Arkansas, and minute by minute the advancing flood bit away miles of river bed, swelling north. Chicot, Jennie, Lake Village, Arkansas City, Snow Lake, Elaine, Helena and Memphis felt the tremors. The tormented city shuddered through the night. The earth continued its descent, eventually tipping 2-1/2 degrees down to the west. The "Memphis Tilt" is today one of the unique and charming characteristics of the gracious Old Town, but during the night of panic Memphis residents were sure they were doomed. South and west the waters carved deeply into Arkansas and Oklahoma. By morning it was plain that all of Arkansas was going under. Waves advanced on Little Rock at almost 100 miles an hour, new crests forming, overtopping the wave's leading edge as towns, hills and the thirst of the soil temporarily broke the furious charge. Washington announced the official hope that the Ozarks would stop the wild gallop of the unleashed Gulf, for in northwest Arkansas the land rose to over 2,000 feet. But nothing could save Oklahoma. By noon the water reached clutching fingers around Mt. Scott and Elk Mountain, deluging Hobart and almost all of Greer County. Despite hopeful announcements that the wave was slowing, had virtually stopped after inundating Oklahoma City, was being swallowed up in the desert near Amarillo, the wall of water continued its advance. For the land was still sinking, and the floods were constantly replenished from the Gulf. Schwartzberg and his geologists advised the utmost haste in evacuating the entire area between Colorado and Missouri, from Texas to North Dakota. Lubbock, Texas, went under. On a curling reflex the tidal wave blotted out Sweetwater and Big Spring. The Texas panhandle disappeared in one great swirl. Whirlpools opened. A great welter of smashed wood and human debris was sucked under, vomited up and pounded to pieces. Gulf-water crashed on the cliffs of New Mexico and fell back on itself in foam. Would-be rescuers on the cliffs along what had been the west bank of the Pecos River afterwards recalled the hiss and scream like tearing silk as the water broke furiously on the newly exposed rock. It was the most terrible sound they had ever heard. "We couldn't hear any shouts, of course, not that far away and with all the noise," said Dan Weaver, Mayor of Carlsbad. "But we knew there were people down there. When the water hit the cliffs, it was like a collision between two solid bodies. We couldn't see for over an hour, because of the spray." Salt spray. The ocean had come to New Mexico. The cliffs proved to be the only effective barrier against the westward march of the water, which turned north, gouging out lumps of rock and tumbling down blocks of earth onto its own back. In places scoops of granite came out like ice cream. The present fishing town of Rockport, Colorado, is built on a harbor created in such a way. The water had found its farthest westering. But still it poured north along the line of the original Fault. Irresistible fingers closed on Sterling, Colorado, on Sidney, Nebraska, on Hot Springs, South Dakota. The entire tier of states settled, from south to north, down to its eventual place of stability one thousand feet below the level of the new sea. Memphis was by now a seaport. The Ozarks, islands in a mad sea, formed precarious havens for half-drowned humanity. Waves bit off a corner of Missouri, flung themselves on Wichita. Topeka, Lawrence and Belleville were the last Kansas towns to disappear. The Governor of Kansas went down with his State. Daniel Bernd of Lincoln, Nebraska, was washed up half-drowned in a cove of the Wyoming cliffs, having been sucked from one end of vanished Nebraska to the other. Similar hair-breadth escapes were recounted on radio and television. Virtually the only people saved out of the entire population of Pierre, South Dakota were the six members of the Creeth family. Plucky Timothy Creeth carried and dragged his aged parents to the loft of their barn on the outskirts of town. His brother Geoffrey brought along the younger children and what provisions they could find—"Mostly a ham and about half a ton of vanilla cookies," he explained to his eventual rescuers. The barn, luckily collapsing in the vibrations as the waves bore down on them, became an ark in which they rode out the disaster. "We must of played cards for four days straight," recalled genial Mrs. Creeth when she afterwards appeared on a popular television spectacular. Her rural good-humor undamaged by an ordeal few women can ever have been called on to face, she added, "We sure wondered why flushes never came out right. Jimanettly, we'd left the king of hearts behind, in the rush!" But such lightheartedness and such happy endings were by no means typical. The world could only watch aghast as the water raced north under the shadow of the cliffs which occasionally crumbled, roaring, into the roaring waves. Day by day the relentless rush swallowed what had been dusty farmland, cities and towns. Some people were saved by the helicopters which flew mercy missions just ahead of the advancing waters. Some found safety in the peaks of western Nebraska and the Dakotas. But when the waters came to rest along what is roughly the present shoreline of our inland sea, it was estimated that over fourteen million people had lost their lives. No one could even estimate the damage to property; almost the entirety of eight states, and portions of twelve others, had simply vanished from the heart of the North American continent forever. It was in such a cataclysmic birth that the now-peaceful Nebraska Sea came to America. Today, nearly one hundred years after the unprecedented—and happily unrepeated—disaster, it is hard to remember the terror and despair of those weeks in October and November, 1973. It is inconceivable to think of the United States without its beautiful and economically essential curve of interior ocean. Two-thirds as long as the Mediterranean, it graduates from the warm waters of the Gulf of Mexico through the equally blue waves of the Mississippi Bight, becoming cooler and greener north and west of the pleasant fishing isles of the Ozark Archipelago, finally shading into the gray-green chop of the Gulf of Dakota. What would the United States have become without the 5600-mile coastline of our inland sea? It is only within the last twenty years that any but the topmost layer of water has cleared sufficiently to permit a really extensive fishing industry. Mud still held in suspension by the restless waves will not precipitate fully even in our lifetimes. Even so, the commercial fisheries of Missouri and Wyoming contribute no small part to the nation's economy. Who can imagine what the middle west must have been like before the amelioration of climate brought about by the proximity of a warm sea? The now-temperate state of Minnesota (to say nothing of the submerged Dakotas) must have been Siberian. From contemporary accounts Missouri, our second California, was unbelievably muggy, almost uninhabitable during the summer months. Our climate today, from Ohio and North Carolina to the rich fields of New Mexico and the orchards of Montana, is directly ameliorated by the marine heart of the continent. Who today could imagine the United States without the majestic sea-cliffs in stately parade from New Mexico to Montana? The beaches of Wyoming, the American Riviera, where fruit trees grow almost to the water's edge? Or incredible Colorado, where the morning skier is the afternoon bather, thanks to the monorail connecting the highest peaks with the glistening white beaches? Of course there have been losses to balance slightly these strong gains. The Mississippi was, before 1973, one of the great rivers of the world. Taken together with its main tributary, the Missouri, it vied favorably with such giant systems as the Amazon and the Ganges. Now, ending as it does at Memphis and drawing its water chiefly from the Appalachian Mountains, it is only a slight remnant of what it was. And though the Nebraska Sea today carries many times the tonnage of shipping in its ceaseless traffic, we have lost the old romance of river shipping. We may only guess what it was like when we look upon the Ohio and the truncated Mississippi. And transcontinental shipping is somewhat more difficult, with trucks and the freight-railroads obliged to take the sea-ferries across the Nebraska Sea. We shall never know what the United States was like with its numerous coast-to-coast highways busy with trucks and private cars. Still, the ferry ride is certainly a welcome break after days of driving, and for those who wish a glimpse of what it must have been like, there is always the Cross-Canada Throughway and the magnificent U. S. Highway 73 looping north through Minnesota and passing through the giant port of Alexis, North Dakota, shipping center for the wheat of Manitoba and crossroad of a nation. The political situation has long been a thorny problem. Only tattered remnants of the eight submerged states remained after the flood, but none of them wanted to surrender its autonomy. The tiny fringe of Kansas seemed, for a time, ready to merge with contiguous Missouri, but following the lead of the Arkansas Forever faction, the remaining population decided to retain political integrity. This has resulted in the continuing anomaly of the seven "fringe States" represented in Congress by the usual two Senators each, though the largest of them is barely the size of Connecticut and all are economically indistinguishable from their neighboring states. Fortunately it was decided some years ago that Oklahoma, only one of the eight to have completely disappeared, could not in any sense be considered to have a continuing political existence. So, though there are still families who proudly call themselves Oklahomans, and the Oklahoma Oil Company continues to pump oil from its submerged real estate, the state has in fact disappeared from the American political scene. But this is by now no more than a petty annoyance, to raise a smile when the talk gets around to the question of State's Rights. Not even the tremendous price the country paid for its new sea—fourteen million dead, untold property destroyed—really offsets the asset we enjoy today. The heart of the continent, now open to the shipping of the world, was once dry and land-locked, cut off from the bustle of trade and the ferment of world culture. It would indeed seem odd to an American of the '50s or '60s of the last century to imagine sailors from the merchant fleets of every nation walking the streets of Denver, fresh ashore at Newport, only fifteen miles away. Or to imagine Lincoln, Fargo, Kansas City and Dallas as world ports and great manufacturing centers. Utterly beyond their ken would be Roswell, New Mexico; Benton, Wyoming; Westport, Missouri, and the other new ports of over a million inhabitants each which have developed on the new harbors of the inland sea. Unimaginable too would have been the general growth of population in the states surrounding the new sea. As the water tables rose and manufacturing and trade moved in to take advantage of the just-created axis of world communication, a population explosion was touched off of which we are only now seeing the diminution. This new westering is to be ranked with the first surge of pioneers which created the American west. But what a difference! Vacation paradises bloom, a new fishing industry thrives; her water road is America's main artery of trade, and fleets of all the world sail ... where once the prairie schooner made its laborious and dusty way west!
|
C. Simply that the idea of an active volcano was much more interesting to the public.
|
Why does Sias believe that the ancients declared 70 as the minimum age for a member of the Conclave?
A. They are the ones who remember things from previous generations that get lost to time
B. They do not have the energy to riot amongst themselves
C. They are closest in lineage to the predecessors that generated the machines
D. They have had sufficient life experience at that point
|
The Birds and the Bees BY DAVE E. FISHER Which goes to prove that, in some instances, being heroic is easy! [Transcriber's Note: This etext was produced from Worlds of If Science Fiction, August 1957. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] I was wandering among the tall grass of the slopes, listening to the soft whistling of the wind; allowing the grass to caress my toga and thighs. It was a day soft and clear; a day accepted by the young, cherished by we old. Across the gently undulating hills stood the magnificent Melopolis, encradling the Oracle of Delni. I do not, of course, believe in the gods per se; still there is a grandeur in the very stones that transcends their human sculptors, and it is no wonder to me that many cling tenaciously, and ignorantly, to the old religion. Cling to the gods of old, who drew man upward from wherever he began. In whose names Man killed and plundered, while struggling up. In whose names Man finally left this earth, to seek his cousins among the stars. But of course there were no cousins. There was nothing. And Man returned, and settled down to live. Saddened, but resigned and content to live in peace with his knowledge and his power. Gone now are all the ancient evils, wars, emergencies. "Sias! Sias—" And they were upon me. That is, Xeon was upon me. But I knew that where Xeon is, Melia must soon appear. And indeed it was but a moment before Melia slipped through the high grass to stand at his side. Their youthful voices were babbling in excitement. Melia was a She, with the swelling breasts that were, so tradition states, quite prevalent among members of the race long ago, and are seldom seen today. Indeed, Melia was on this account made the butt of many jokes and, I fear, would have had a lonely life of it had it not been for the friendship of Xeon. "Sias," they were saying, "the Maternite's gone." I stared in amazement. "Gone? It cannot be gone. It has always been—" "Oh my gods!" Xeon shouted. "I tell you it's gone! Will you—" Melia interrupted him quietly. "Xeon, will you lose all respect for the Elder?" Then turned to me, and said calmly, "The watcher at the Maternite Machine, it appears, has been drunk. The heat rose above the warning, continued to rise, and then—poof. Everything has evaporated in Maternite. All the Prelife is gone." "All of it?" I asked. "There is nothing left," Melia insisted. "Can more be made? And if not, what will happen with no more children?" "That is for the priests to say, not I," I replied. In moments of emergency, it is wise to speak with caution. That is, I suppose so. I have never before been in a real emergency. A man my age does not hurry in the heat of the midday sun—maddugs nenglishmin go out in the midday sun, as the ancients say, although I often wonder why—but Xeon and Melia ran all the way down to the city. They are of an age to enter manhood, and have all the energy such young men do. As we entered the city, we were surrounded by confusion and consternation. And can the simple people be blamed? They were aware that they stood in the midst of an unprecedented happening; indeed, an emergency. For a machine had failed! Not in the memory of the eldest among us has a machine failed. They were created so long ago, indeed, that the ignorant believe them to have been constructed by the gods themselves. And never, so far as I know, has one failed. Small wonder that the watcher had been negligent. Indeed, the watcher is more a tradition than a necessity. Besides, had he been sober, he would not have known what to do. For who knows the mysterious workings of the machines? I hastened to the City Hall and found the Conclave assembled, waiting for me to bring them to order. Xeon and Melia stopped as I mounted the steps, but I smiled and motioned them in. They accompanied me past the marble pillars into the cool recesses of the Hall, then seated themselves on the floor as I took my place by the great table. Well, you know how these things are. At such a time, many men feel impelled to make speeches, and one must not be disrespectful. Prayers and supplications were offered to the gods, priests were sent to sacrifice, and finally, as the light of the sun was falling between the pillars, the High Priest of the Maternite Machine was heard. He rambled through the customary opening remarks and then, continually smoothing his white beard—of which he is excessively proud—approached the crux of the matter and the Conclave finally heard the facts it had assembled to hear. By this time, unfortunately, many of the Conclave had departed for home and supper. Yet perhaps it is for the best, for those left were the most earnest and intelligent. "I would not bore you," he said, "with details of which only the gods are sure. Know, then, that once granted a few cells of Prelife, it is an easy matter for the Maternite Machine to add more and more; thus assuring us, as has always been, a continuous source of Prelife to be born by the Generating Machine as children. The machines bear the exact number of children each year to balance the number of us whom the gods claim. Such it has always been from time immemorial." A murmur of assent and approval of these virtuous words whispered around the Hall. "But now," he continued, however, with less assurance and indeed with even a stutter here and there, "an unprecedented situation has arisen. Indeed, I might call it an emergency. For the M-Maternite Machine has actually failed." Cries of "Treason" sprang up, and I fear it might have gone hard for the priest had I not been able to insure order. "That is not the worst," he cried, as if in defiance. "All the Prelife has been dried up. It will not function. There is no more. And there will be no more children!" At this I feared the Conclave was about to riot. It is at such times that I most revere the wisdom of the ancients, who decreed seventy years the minimum age for a member of the Conclave. They shouted and began to beat their fists, but for how long can a man of seventy years roar like a youngster? They quieted, breathing heavily, and I asked, "Is there no way, then, to produce more Prelife in order that the machines may produce more children for us? "As I have said," he replied, "give the machines but a bit of Prelife and they will produce more. But take away that least bit, and they are helpless." Such heresy could have brought a sad end to the priest had not the Conclave been so exhausted by the events of the day. We leaned back to think. Rocsates leaned forward and asked, "Must there not—must there not have been a beginning to Prelife? For the Machine, it seems, cannot make it; and yet it came from somewhere." "Riddles are not called for," I answered severely. "Are not riddles often the beginning of knowledge?" he asked, in that irritating dumber-than-thou attitude of his. "Must there not, long ago, have been a source of Prelife: a source now forgotten? And may it not even now—should we discover it—be available to us? I am reminded of the story of the animals of old—" "I fear your mind is wandering, Rocsates," I was forced to interrupt. "I know well the legend of the animals, but what does it have to do—" The heads of the Conclave were turning to me, quizzically. I hastened to explain the legend of the animals. "It is said that many thousands of years ago, time without reckoning, there existed on the earth creatures who were alive like us, and yet not like us. It is said they had four legs or more, and no arms, were covered with hair, and although not mute, they could not speak." Rocsates' voice made itself heard. "It is true. Such creatures did indeed exist. It is recorded most scientifically in the films." "If it be so," I said, quieting the hub-bub that followed, "and I would not doubt your word, Rocsates, for all know you are the wisest of men—if it were so, then, what of it?" "May it not be," Rocsates put in, "that these animals had no machines to reproduce their kind? For surely the gods would not grant machines to such creatures. And indeed, if they had Maternite Machines, why then we would yet have these animals among us." "And how, then, did these animals reproduce?" I asked. "How, indeed? And is there not a legend—admitted only a legend—that says there was a time before the machines, and before the Maternite Machine, and that at such a time both the animals and Men reproduced from within their own bodies?" At this two members of the Conclave fell immediately into a faint, and I would gladly have joined them. I hoped that the youngsters, Xeon and Melia, had not heard, but as I turned they were listening most attentively to Rocsates, who, amid cries of "Heresy" and "Treason", went on: "I should like to ask the Conclave for permission to search the ancient records, in the hope of finding some such knowledge that would prove or disprove my words." "You wish to search the films—" I began. "Not the films, Sias, but the books." Gods, this Rocsates! The books, as well he knows, are so ancient, and so delicate, that they are kept in an air-tight tomb; lest, being handled, they be destroyed and all knowledge within them lost. Therefore, they have not been read in the known history of our race. And Rocsates has been anxious for an excuse— "Sias," he went on, "if there exists such knowledge as I seek, is it not indeed lost to the memory of Man? And if so, are not the books the only place where it may be found?" Rocsates, it is suspected, will never ask a question unless he knows the answer beforehand. And so I acquiesced, and agreed, and granted permission. And with much misgiving and foreboding of evil, the Conclave adjourned. Several weeks elapsed before Rocsates requested that the Conclave meet. I called the meeting at dawn and so it was yet early in the afternoon when formalities were concluded and Rocsates granted leave to speak. "Some of those among you are She's," he began. "And you know you are different from the rest of us. To the advantage, your skin is fairer and your features more often handsomer than ours. To the disadvantage, your excretory system is not so mechanically dextrous as ours. And, you may say, why should this not be so? There is, indeed, no reason why we should all be identical. Perforce you have the advantage, perforce we do. Yet there is one other distinction. "Some among you She's have the swelling of the breasts. And does there exist no reason for this? Was there not, perhaps in ancient times, a cause for this? Do you not wonder, She's, whence you come and for what reason?" "Rocsates," I interrupted. "All this is fascinating, of course. But if you could be quick—" "Of course," he replied. "In the course of my reading I have read many books, and while they are all vague on the subject, this I have discovered: "That there was indeed a time before the machines, in fact the books were created in that time, for not one of them mentions the machines. Then reproduction was carried on by individuals, without help of the then nonexistent machines. The She's are not wanderers from another land, but they have lived with us for all time; they are not another race, but we are all types of one race. And the fact of reproduction is somehow intimately related to the physical distinctions of the She's!" These last sentences were shouted to be heard above the roar of the crowd. Yet when Rocsates stopped, so also did the noise, so shocked and amazed at his words were they. And I confess, myself also. "In fact," Rocsates added, sitting down, "this process of reproduction seems to have been so simple that there was once a problem of over-population." Order was lost among the Conclave as each man turned to speak to his neighbor, and for some time I could not restore order. I realized that something had to be done to save Rocsates before the outrage of the assembled overwhelmed him. "It seems," I shouted, "that there is a flaw in your logic." For if such there was, I was hopeful of dismissing the entire affair with no harm done. "For if people reproduced too often, why then this reproduction must have been a pleasant thing to do; otherwise they would not have done so to excess. And if it was a pleasant thing to do, where is the necessity for the machines, and why were they created?" Rocsates seemed perplexed by this problem, whereupon Xeon, who together with Melia were at the Conclave without permission, shouted, "Perhaps the process of reproduction was of such a pleasure that the Conclave ruled it to be a sin? And therefore the machines were necessary!" At this impudence the Conclave dissolved in an uproar, and I was beyond power to restrain them from placing Xeon under arrest. Privately, however, I had to admit that his supposition was a possibility, and thus I authorized Rocsates to continue his search. Now indeed I was sorely worried concerning Xeon, for he must languish in the dungeon until the Conclave is satisfied to release him, and this they cannot do until they meet again. I needed a sufficient excuse to call a meeting of the Conclave, whereupon I might argue for the lad. When I heard that Rocsates again desired audience, I immediately proclaimed a meeting of the Conclave to be held the next day at dawn, and so that night slept well. The Conclave had come to order and formalities had been initiated when Rocsates entered and took his place. He clutched under one shoulder a thin, rectangular object, but that is not what impressed me. His appearance—he looked as if he had not slept of late, nor eaten either. His eyes were sunken, and his features had doubled in age. He was bent and tired. But it was his eyes. There was a horror in them. I was shocked, and could not help staring at him. And then the formalities were over. I intended to speak for Xeon, but Rocsates was on his feet and I gave way. "I have indeed discovered the secret of reproduction," he began. "After many searchings, I came upon this—" and he held forth the object he had carried in. "It is a book. It is entitled, 'Living a Normal Sex Life.' It seems to be some sort of a do-it-yourself pamphlet." He dropped the book on the table and rubbed his hands over his eyes. There was something in the man's behavior that commanded everyone's attention. He went on, speaking low. "The word 'Sex' is not defined, but it seems to mean...." His words trailed off. He was obviously unsure of how to continue. "I had better start at the beginning, I suppose," he said. "You see, once upon a time there were birds and bees...." When he finished the Conclave sat in horrified silence. His words, with all their horror, had the ring of truth and there were no cries of 'Heresy'. There was only stunned disbelief and the beginnings of nausea. It is the mark of honor that a leader shall carry on when others fear to move. I cleared my throat. "Shall not these organs which you mention have atrophied by now? With no use throughout all these generations, will they not have evolved into nothingness?" "I do not think so," Rocsates replied after a while. "What to us is an eon, to evolution is but an instant. And then the swelling of the breasts, I believe, proves that there is still reproductive activity in some, at least, of the She's." We sat shaking our heads, bowed under terrible reality. "Then we must experiment," I said. "But whom could we ask to submit to such horror?" "I have already taken the liberty of asking for volunteers," Rocsates replied. "The She, of course, must be one with the swelling of the breasts. Melia has volunteered, on condition that Xeon be released from dungeon. Are there any objections?" There were none, of course. Who would refuse a boon to one who would undergo such an ordeal for the City? "And who will be the partner?" I asked. "In all honor, could Xeon allow Melia to surpass him in courage? It shall be he," Rocsates said. And with his word the two entered the Hall and stood, noble and naked. Rocsates gestured to the table, and Melia started to climb upon it, but Xeon stepped forward. "My lords," he said, "would not better results be obtained were we to conduct the experiment in the fields before the Oracle of Delni, that the gods may help us?" His glance reached into my soul, and I was proud of Xeon. A true friend, he thought even now of the comfort of Melia. The marble table was indeed hard, and from Rocsates' description it seemed that Melia's position would be as uncomfortable as it would be undignified. The soft fields might be some slight help. I voiced my assent, and the entire Conclave adjourned to the fields. It was nearly dark when we walked home, Rocsates and I, arm in arm. It had been a horrible day. The inhuman indignity, the cries— We tarried before my home, leaned on the stone, stared at the first stars. "They seemed finally to accomplish all the book described," I muttered. "They may indeed have succeeded," Rocsates replied. "There is mentioned a time lapse which is necessary. The child does not appear immediately." "It doesn't matter," I said disconsolately. "Who could ask them to go through such an ordeal again?" And then I looked down to earth again, and saw them standing before me. Melia cast her eyes down, and would not raise them. Xeon held his arm about her shoulders, as if to protect her, but I know not from whom. "Sias," he said. Then stopped, embarrassed. I waited, and Rocsates was silent, and he continued. "Sias, we come to tell.... We will...." He raised his eyes to mine and said manfully, "We shall try again." I am afraid that tears came to my eyes. Such sacrifice— "We beg one favor," Xeon went on. "We are agreed that—Well, we should like to be left alone, in private, to try." "Of course," I replied. Anything they might want they could have. My relief and gratitude must have showed, for Xeon took a deep breath and spoke again. "We do not deserve praise, Sias," he said. "The truth is, we ... we sort of enjoy it." I watched them turn and wander off together under the stars. My heart has a warmth in it, and I no longer fear for the future of our race when our young people can show such nobility and sacrifice.
|
B. They do not have the energy to riot amongst themselves
|
Which model architecture do they use to build a model?
|
### Introduction
Simultaneous translation is a translation task where the translation process starts before the end of an input. It helps real-time spoken language communications such as human conversations and public talks. A usual machine translation system works in the sentence level and starts its translation process after it reads the end of a sentence. It would not be appropriate for spoken languages due to roughly two issues: (1) sentence boundaries are not clear and (2) a large latency occurs for a long input. Previous studies tackled this problem by an incremental process, in order to reduce the translation latency for a given input. fujita13interspeech proposed a phrase-based approach to the simultaneous translation based on phrasal reordering probabilities. oda-etal-2015-syntax proposed a syntax-based method to determine when to start translation of observed inputs. Such an approach faces a trade-off between speed and accuracy; reducing the translation latency using very limited context information also causes the loss in the translation accuracy. This becomes more serious especially in a syntactically-distant language pair such as English and Japanese, where we sometimes have to wait a latter part of a source language to determine the corresponding former part in a target language. Recent neural machine translation (NMT) studies tried an incremental processing for the simultaneous translation. gu2017learning proposed a reinforcement learning approach to determine when to translate based on two different actions: READ to take one input token and WRITE to generate one output token. While they reported some latency reduction without the loss of translation accuracy, the NMT model itself is trained independently from this incremental manner and is not fully optimized for simultaneous translation. ma2018stacl proposed a very simple incremental method called Wait-k, where the decoder starts to generate output tokens after the encoder reads k tokens and then works token-by-token. Here, some required inputs may not be observed by the encoder; however, the decoder has to predict the next output token even in that case. This approach enables a simple end-to-end simultaneous NMT with implicit anticipation of unobserved inputs. It showed high translation accuracy with small latency on some common English-to-German and Chinese-to-English datasets. The latency hyperparameter k can be used to control the speed-accuracy trade-off, but it has to be large enough for a distant language pair like English-Japanese. We observed a problem in translating a phrase longer than k tokens in our pilot study on English-to-Japanese translation. In this work, we propose a novel incremental NMT method that uses a special token <wait> in the target language which is generated when the translation model chooses to read the next input token instead of generating an output token. The proposed method uses Connectionist Temporal Classification (CTC) BIBREF0 to handle ambiguities in possible positions inserting <wait> in the training time. CTC is applied to sequential model training such as automatic speech recognition, where we have a reference word sequence but do not have the corresponding segmentation or alignment in an acoustic signal. We conduct experiments in English-to-Japanese simultaneous translation with the proposed and baseline methods and show the proposed method achieves a good translation performance with relatively small latency. The proposed method can determine when to wait or translate in an adaptive manner and is useful in simultaneous translation tasks. ### Simultaneous machine translation by Wait-k model
First, we review a general NMT model following the formulation by BIBREF1 and the “Wait-k" model BIBREF2 that is the baseline model for simultaneous NMT. Given a source sentence $X$ and a target sentence $Y$ as follows: where $\textbf {x}_i \in \mathbb {R}^{S \times 1}$ is a one-hot vector of the i-th input word, $I$ is the length of the input sentence $X$, $\textbf {y}_i \in \mathbb {R}^{T \times 1}$ is a one-hot vector of the i-th output word, and $J$ is the length of the output sentence $Y$. The problem of translation from the source to the target language can be solved by finding the best target language sentence $\hat{Y}$ that maximizes the conditional probability In general NMT manner, the conditional probability is decomposed by the product of conditional generation probabilities of $\textbf {y}_{j}$ given the source sentence $X$ and preceding target words $\textbf {y}_{<j}$: where $\textbf {y}_{<j}$ represents the target words up to position $j$, and $\theta $ indicates the model parameters. In contrast, the model for simultaneous translation has to output translated words given only prefix words of the source sentence. Therefore, the conditional probability is decomposed as follows: where $\textbf {x}_{<g(j)}$ are the target words up to position $g(j)$ and $g(j)$ represents the number of encoded source tokens when the model outputs $j$ words. In the “Wait-k" model, $g(j)$ is defined as follows: Here, $k$ is the hyperparameter which indicates the target sentence generation is $k$ tokens behind the source sentence input and it takes a constant value in the “Wait-k" model. The model is composed of an encoder (§SECREF5) and a decoder with the attention mechanism (§SECREF7) that are both implemented using recurrent neural networks (RNNs); the encoder converts source words into a sequence of vectors, and the decoder generates target language words one-by-one with the attention mechanism based on the conditional probability shown in the equation DISPLAY_FORM2 and DISPLAY_FORM3. The details are described below. ### Simultaneous machine translation by Wait-k model ::: Encoder
The encoder takes a sequence of a source sentence $X$ as inputs and returns forward hidden vectors $\overrightarrow{\textbf {h}_i}(1 \le i \le I)$ of the forward RNNs: In the general NMT model, they also calculate backward hidden vectors of backward RNNs from a reversed source sentence. However, we only use forward hidden vectors because we cannot use the information of the whole sentence on the simultaneous translation task. ### Simultaneous machine translation by Wait-k model ::: Decoder with Attention
The decoder takes source hidden vectors as inputs and returns target language words one-by-one with the attention mechanism. The decoder RNNs recurrently generates target words using its hidden state and an output context. The conditional generation probability of the target word $\textbf {y}_i$ defined as follows: Here, $\textbf {W}_c, \textbf {W}_p$ are trainable parameters and $\textbf {c}_j$ is a context vector to retrieve source language inputs in forms of a weighted sum of the source hidden vectors $\textbf {h}_j$, defined as follows. The score function above can be defined in some different ways as discussed by BIBREF1. In this paper, we use dot attention for this score function. ### Proposed Method
In this work, we proposed the method to decide the output timing adaptively. The proposed method introduces a special token <wait> which is output instead of delaying translation to target-side vocabulary. In this section, we first review a standard objective function, softmax cross-entropy and show the problem that occurs when this function is applied to <wait> (§SECREF10). After that, we introduce an objective function, called Connectionist Temporal Classification, to handle this problem (§SECREF12). Finally, we propose a new objective function to adjust a trade-off between translation accuracy and latency (§SECREF14) and explain how to combine these objective functions (§SECREF16). ### Proposed Method ::: Softmax Cross-Entropy
Softmax Cross-Entropy (SCE) is a commonly used token-level objective function for multi-class classification including word generation in NMT, defined as follows: where $\textbf {y}_{ij}$ is a j-th element of the one-hot vector corresponding to the i-th words of the reference sentence and $p(\textbf {y}_{jk}|\cdot )$ is the generation probability of $\textbf {y}_{jk}$. A correct sequence that corresponds to an output sequence one-by-one is necessary to use SCE as an objective function for NMT. However, in the proposed method, we cannot simply use SCE because we don't know when we should cause delay. To avoid this problem, we set the loss for delay tokens to 0 during the time step $t\ (t \le g(I))$ which the model can output <wait> , or while a source sentence is inputted. ### Proposed Method ::: Connectionist Temporal Classification
As we mentioned in the previous section, we set the loss value for <wait> to 0, but this causes the problem that it does not optimize about generating <wait> . Against this problem, we use an objective function called Connectionist Temporal Classification (CTC) BIBREF0 for sequence-level optimization. CTC extends output sequence, called Path $\mathbf {\pi } = \Omega (\textbf {y})$, to the length $T$ by allowing token repetitions and outputting <wait> . Conversely, we can obtain an original output sequence $\textbf {y} = \Omega ^{-1}(\mathbf {\pi })$ by removing <wait> and all token repetitions. The objective function is defined the sum of the probabilities of all possible paths $\mathbf {\pi } \in \Omega (\textbf {y})$ by using the forward-backward algorithm, as follows: where $\pi _t$ is a t-th element of $\mathbf {\pi }$. ### Proposed Method ::: Delay Penalty
Furthermore, we introduce a new objective function, called Delay Penalty, to control latency. We use this function only when an output token causes the delay; that is, when the model outputs <wait> or the same token as a previous one. Delay Penalty is defined by a negative log-likelihood of the probabilities for non-delayed tokens, as follows: ### Proposed Method ::: Objective Function
For optimization, we combine three objective functions introduced so far, as follows: Here, $\alpha $ is a hyperparameter to adjust the amount of latency directly. ### Experiments
We conducted simultaneous translation experiments from English to Japanese and discussed accuracy, latency, and issues for translation results. ### Experiments ::: Settings
All models were implemented as described in the previous sections using PyTorch. Both the encoders and the decoders were two-layered uni-direcitional LSTM BIBREF3, and the decoder used input feedingBIBREF1. The number of dimensions in word embeddings and hidden vectors was set to 512, and the minibatch size was 64. We use Adam BIBREF4 for optimization with the default parameters. The learning rate was set to $10^{-1}$, and gradient clipping was set to 5. The dropout probability was set to $0.3$. The learning rate was adjusted by a decay factor of $1/\sqrt{2}$ when the validation loss was larger than that in the previous epoch. Then, we chose the best parameter/model with the smallest validation loss for evaluation. We used two different corpora for the experiments: small_parallel_enja and Asian Scientific Paper Excerpt Corpus (ASPEC) BIBREF5. small_parallel_enja is a small-scale corpus that is consist of sentences filtered sentence length 4 to 16 words, and ASPEC is a mid-scale corpus of the scientific paper domain. Table TABREF21 shows their detailed statistics. All datasets were tokenized into subword unit BIBREF6, BIBREF7 by using Sentencepiece . The source and target language vocabularies were independent, and their size was set to 4000 tokens for small_parallel_enja and 8000 tokens for ASPEC, respectively. We filtered out the sentence whose number of tokens was more than 60 tokens, or the length ratio was more than 9 from the training set. We used “Wait-k” models and general NMT models as baseline models. General NMT models were attention-based encoder-decoder and it translated sentences from full-length source sentences (called Full Sentence). For evaluation metrics, we used BLEU BIBREF8 and RIBES BIBREF9 to measure translation accuracy, and token-level delay to measure latency. We used Kytea BIBREF10 as a tokenize method for evaluations of Japanese translation accuracy. ### Experiments ::: Experiments with Small-scale Corpus
We conducted small-scale experiments using small_parallel_enja. We compared different hyperparameters: $k = \lbrace 3, 5\rbrace $ and $\alpha = \lbrace 0, 0.01, 0.03, 0.05\rbrace $. Table TABREF24 shows the results in latency and automatic evaluation scores on small_parallel_enja. The full sentence scores are upper bounds of incremental methods. The proposed method reduced the average latency in more than 50% from the full sentence baseline with some loss in BLEU and RIBES. The BLEU and RIBES results by the proposed method were worse than those by Wait-k. Th would be due to some degradation in smaller latency parts that were determined adaptively by the proposed methods while Wait-k keeps the fixed latency. ### Experiments ::: Experiments with Mid-scale Corpus
We investigated the performance on longer and more complex sentences by the experiments using ASPEC. We compared different hyperparameters: $k = \lbrace 5, 7\rbrace $ and $\alpha = \lbrace 0.03, 0.05, 0.1\rbrace $. Table TABREF26 shows the results in latency and automatic evaluation scores on ASPEC. We can see the proposed method showed much larger latency than Wait-k. This is probably due to many long and complex phrases used in scientific articles in ASPEC. Wait-k has to translate such a long phrase without sufficient input observations due to its strict fixed latency strategy. On the other hand, the proposed method can wait for more input tokens adaptively by generating <wait> at the cost of large latency. ### Experiments ::: Discussion
In the experimental results above, the proposed method determined the translation latency adaptively, short delay for short and simple inputs as in small_parallel_enja and long delay for long and complex inputs as in ASPEC. Here we discuss our results in detail using some examples. Table TABREF28 shows translation examples on small_parallel_enja. In the first example, the proposed method gives a correct translation result by adaptive waits. Wait-k generated unrelated words UTF8min野球 (baseball) and UTF8min飲-み (drink) due to the poor input observations with its small fixed latency. The proposed method waited until a subword swim was observed and successfully generate a word UTF8min泳-ぐ (swim). However, the proposed method sometimes generated consecutive <wait> symbols until the end of input, as shown in the second example. This is probably due to our training strategy; the latency penalty would not be large enough to choose small latency translation at the cost of some increase in SCE- and CTC-based loss. The translation data in the experiments are not from simultaneous interpretation but standard translation, so the current task does not match with the proposed approach. The use of specialized data for simultaneous translation would be important in practice, such as monotonic translations like simultaneous translation. ### Conclusion
In this paper, we proposed an adaptive latency control method for simultaneous neural machine translation in syntactically distant language pairs. We introduced a meta token <wait> to wait until the observation of the next input token. We proposed a CTC-based loss function to perform optimization using bilingual data without appropriate positions of <wait> , which is used along with the latency penalty and a standard word prediction loss. The experimental results suggest the proposed method determines when to translate or when to wait in an adaptive manner. Future work includes further analyses on translation accuracy in different latency conditions and time-based latency evaluation instead of the token-based one. ### Acknowledgments
A part of this work is supported by JSPS Kakenhi JP17H06101. Table 1: Number of sentences for each corpus used in the experiments. Table 2: Latency and automatic evaluation scores with small parallel enja. Latencies are shown by averages and standard deviations (in parentheses) in the number of tokens. Table 3: Latency and automatic evaluation scores with ASPEC. Table 4: Translation examples in small parallel enja. w shows the generation of <wait> token.
|
model is composed of an encoder (§SECREF5) and a decoder with the attention mechanism (§SECREF7) that are both implemented using recurrent neural networks (RNNs)
|
How does the photographer feel about Larry Lessing?
A. Larry is a great guy. They are a huge fan.
B. Larry is a disarming guy.
C. Larry is a frustrating guy.
D. Larry is a nervous guy.
|
Just another free soul In his foreword to the book, Lessig writes that you understand your subjects “by learning to see them in a certain way.” What is that certain way? I think I’m trying to get a mental image of a person, certain expressions, or what I think that person is about. I’m trying to capture what I think they look like, which is many times a minority of their typical expressions, or their typical stance. So, if I’m taking pictures of Larry [Lessig], I want to have his signature hand gestures, and not just random ones. I think I’m trying to capture pictures of people that help others see what they’re about. Some photographers will make someone look the way the photographer wants them to look, and not the way they appear, so they’ll pick the one picture out of 100 where the guy looks more egotistical than he really is. Some photographers are almost medical, and are going after a perfect portrait. I’m somewhere in between. It’s amazing how many people will upload snapshots of people where the pictures don’t look like them at all. To me, uploading a picture that is not an easily recognizable picture of that person defeats the point, which I’m working toward, to try to express who they are. On the other hand, professional photographers usually have a subject whom they don’t know personally, so they end up having to try to capture an image that they’ve created based on who they think the person is or how they want that person to appear. You know how sculptors often say that they’re just freeing an image from a block? What I’m trying to do is free someone’s soul from his or her image. There are a lot of things that make this hard. A lot of people are uncomfortable in front of a camera, or might make expressions that aren’t very natural for them. And if the person is nervous, it’s very difficult to try to see what it is that you’re trying to capture. A lot of what I’m doing is, I just start shooting photos. After half an hour of having their picture taken, people start to ignore you. Or I’ll take pictures when I’m talking to people about what they’re doing, so after a while they get distracted by the conversation and forget about the camera. That’s something that I’m not perfect at, but I’m getting better. I think good photographers are also able to disarm people through conversation, but still, it’s difficult to have a disarming conversation with somebody you don’t know, or to make them laugh. Many times people make a face for me that they wouldn’t make for a professional photographer. For instance, a board meeting picture, like the one with Eric Saltzman: that was during a very tense discussion. I’ve found that people are at their most animated at these kinds of meetings, and look the most alive when they are under a lot of pressure, and super- focused. But usually if an outsider is in the room, they won’t get into that. I mean, it would be difficult for a cameraman to be in a room where a board is having a heated debate. But those are the things that I’m trying to capture, because most people don’t get to see that. At the Creative Commons board meeting, Larry asked me to put the camera away after awhile [laughs] because it was distracting. We were having a very heated discussion and I was taking all of these pictures. But he credited me later because afterward those pictures turned out the best. In your mind, what is a ‘Freesoul’ ? A freesoul is somewhat of a pun. On the one hand it means you are free, liberated. You, as a human spirit, are open. And then, it also has the meaning that you are unencumbered legally, that you are free, as in ‘free software.’ There’s a paradox: with many people’s Wikipedia articles to which I’ve contributed, when it comes to the picture, many of these people don’t have any free photos of themselves on the web, so while they are “notable” on Wikipedia, their images aren’t free of the copyright of the photographer, or the institution who hired the photographer to take the picture. Often, even the subject of the article can’t make an image available to the Wikimedia/Wikipedia community. This means that a lot of people who have a Net presence have a legally encumbered Net presence. People who are invited to conferences get asked all the time, “By the way, do you have a photo that we can use?” But they don’t. By making these pictures available under a Creative Commons license, now they do. This is solving the issue of legal freedom. The third part of the pun is that, since I’m asking for a model release from the subjects, I’m asking everyone to be much more open and giving about their image than most people typically are. I’m giving, you’re giving, we’re all giving to participate and to try to create this wonderful work, and allow others to create derivative works. Of course people can abuse that, just like they can abuse anything. But I want people to see the value in sharing over the fear in sharing. The fact is, it’s much more likely that somebody is going to use these pictures for something positive, rather than for something negative. The benefits greatly outweigh the risks. I think we spend way too much of our lives worrying about the risks, at the cost of a lot of the benefits. This is a celebration of all of the people who are willing to give. In a way, giving up your image and allowing anyone to use it: it’s the ultimate gift. In one way it’s kind of vain. [laughs] But in another way it’s wonderful. A Wikipedia article on some person but with no picture is sad. Besides Wikipedia, how do you imagine these photos being used? They can be used in textbooks and in mainstream media articles about the person. Now they can get a picture that represents the person, at least from my perspective. That said, I shouldn’t be the only person doing this. More people should do the same, and make the photographs available freely. For one, I feel that “free” CC licensed photos have a much higher chance of not disappearing. But I don’t know exactly how these photos are going to be used, so in a sense I’m curious. For example, recently I received the Harvard Berkman Center pamphlet. It was a report of what they’re doing, and they also had a bunch of my pictures in there. They all had attribution, and it made me feel really good. There were pictures of different Berkman Center members that I had taken in various places all over the world. I think that the subject is probably happy with this, and I’m happy, and the Berkman Center’s happy because they’re not all pictures of people sitting at desks in the Berkman Center. There’s one more important thing: Creative Commons is great for original creative works or derivative creative works, but when it involves human images, it gets very complicated. We all know the Virgin Mobile case, where Virgin used CC licensed images in an advertisement without getting permission from the models, and got in trouble. What we’re trying to do here is to expand beyond just copyright, to make it more thorough from a legal perspective. It’s also an important educational point, so people understand that, in addition to the Creative Commons licenses, we need people to provide other rights in cases where the law requires such rights to be cleared before reuse. What have you learned about the people in these networks, just in the past year? That’s a good question. I think that at least Creative Commons has become much more mainstream. Creative Commons has moved from a fringy academic discussion to a boardroom discussion. Yahoo announced that it will be using Creative Commons for all of their basic infrastructure, and integrating it all. Google has CC search in their advanced search. Microsoft is working with CC as well and have a plug-in. Nine Inch Nails released their album, Ghost, under a Creative Commons license. The list goes on. Many people are asking: can you make money and share? The answer is, yes. CC is becoming an important part of the business discussion. But one thing that happens when a movement like CC becomes a business thing, is that a lot of the pioneers fade into the background, and it becomes a part of industry. This happened to the Internet. And so while you still have the core people who still remember and hold the torch for the philosophical side, the Internet has become much more of a business. Now, when you go to many Internet conferences, it’s mostly salesmen in attendance. I believe that the success of the Internet has two parts. The first part is the market- driven business side, which has made the Internet affordable and ubiquitous. The second part is the strong movement of participants who fight to keep the Internet open and try to prevent the business side from corrupting the fundamental elements that make the Internet great. The Net Neutrality or Open Network discussion going on right now is a good example of the importance of continuing to balance these principles with business interests. Similarly, I think that business interests can help make Creative Commons ubiquitous and more easily accessible to everyone. However, I think it’s important to remember to keep pushing to make content more “free” and not allow businesses to use Creative Commons in exploitive or destructive ways. In addition to the business side, Creative Commons is being used by educators to create open courseware around the world and in the area of science and technology to promote sharing in research. And as of now, we have the license ported to at least 44 jurisdictions, and the number of countries with projects continues to grow. In many ways, the movement outside of the United States has become much bigger than the movement in the United States. Although the United States is still slightly farther ahead in terms of commercialization, the size of the whole free culture movement outside of the United States is huge now. The CC China Photo exhibit was just amazing. There were some great images, and a lot of the photographers were professionals. This is beyond what anybody has done in the US. A lot of the progress that we’re making is international. What are your personal realizations or experiences? Well, we’re all getting old, if you look at these pictures. But there’s another thing, though, about this book: the number of professional-quality amateurs has increased significantly due to the importance of digital in both professional and high-end amateur photography I hate to say it, a lot of people love the darkroom, but it really feels like the death of the darkroom with this year. With new 22 megapixel cameras coming in under $10,000, and Lightroom and some of this software at a couple hundred dollars, it doesn’t really make sense, except for particularly fussy artists, to do wet-work anymore. If you’re a commercial photographer or a high-end amateur, you can do anything you used to do in the darkroom. I think it has really lowered the bar. I don’t know how that affects the industry directly, but for me, it bridged a huge gap. I used to be darkroom geek. I loved my darkroom, and even when I didn’t have my darkroom anymore, I still was shooting 6x6 Hasselblad 120 film and processing it in a special lab, and then digitizing it. For me, that film was it. You could never get as good as medium-format film or large-format film At the time, the digital Hasselblad backs were too expensive, and were still not as good as 8x10 film. So there was this whole period where the darkroom was not all that exciting, but the digital wasn’t perfect. I went through a limbo period. I had invested so much in my Hasselblad system, and my Leica M6 set. I had bought the Leica R8, but I was kicking myself because it was terrible. But then the Leica M8 came out, and I bought one at the beginning of 2007. The M8 really got me to where I could use my old gear, and it had enough megapixels to be as good as some film. Another way of saying it was that there was a gear breakthrough at the beginning of last year. Okay, that’s pretty materialistic! So there was a technology breakthrough, let’s call it that, that allowed me to switch completely away from film, and I think this happened to a lot of photographers. It caused an explosion of content and an increase in the quality of content on sites like Flickr. It has allowed amateurs to create a business model with professionals. Interestingly, I think these new high-end amateurs are buying more photography books and photographs and are probably providing an increasing revenue stream for professional photographers. I think most amateurs, including myself, are paying homage to the professionals and not trying to “compete” with them. Despite the existence of social software, what is still important about meeting people face-to-face? For me, the right way to use a lot of the new social software is by making it easier to spend more physical time with the people you like best. Dopplr is a great example. When I visit a city, I will see all of the people who are in the city at the same time. When I went to London awhile ago, there were 47 people I knew in London, and a huge percentage of those people don’t live there. I would bet that more than half of the photos in this book are pictures of friends, and they’re not in their hometown. That’s the really interesting thing that is happening right now: it’s really increasing your ability to spend quality time with, actually, a smaller number of people. It allows you to actively filter. Your meetings don’t have to be random. If I look at the list of people in this book, although there are some obvious people missing whom I didn’t see last year, probably met more of my friends last year, my real friends, than I’ve met in any other year. I know my travels were crazy, but I think that the online world has allowed me to do that. What’s great about photography is that it captures the moment that I was sharing with that person. It’s not just a connection on a social network online, which is really pretty binary. I can look at all these photos and remember exactly what we were doing, what we were eating, what we were drinking, what we were talking about, and to me that’s a much more rich experience. It’s the combination of social software and photography. For me, reality is “the present” plus what you remember from the past. I think this project is really sharing memories with people. Blog posts contribute as well, but to me photography is a really good way of doing that. When I look at the expressions, I remember the moment and get a sense of presence. I think the main problem for me is the environmental impact of flying around. Just as I never believed that we would have a paperless office, being able to connect with people through social software mostly increases your travel, it doesn’t decrease it. It is great because you get to meet all these people. But it is bad for the environment, and bad for our jet lag. How would you characterize your contributions to free culture? I think it’s mostly incremental. I think there is very little we actually do all by ourselves, and I hate saying, “I did this” or “I did that.” I think that in most cases, focusing on individual contributions or achievements undervalues the importance of everyone else involved. Having said that, I think my main contribution is probably in supporting Creative Commons as a fan, board member, chairman of the board and now CEO. I think CC has a significant role, and helping to keep it on track and growing is probably the single most important role that I have in Free Culture. Specifically, I think that trying to keep an international focus and a balance between business and the non-business elements of the movement is essential. My job is to keep that focus and maintain that balance. Also, CC needs to run smoothly as an organization and there is a lot of operational work that we all need to do. My photography is a way for me to participate in a small measure on the creative side of the Free Culture movement, and helps me see things from that perspective as well. However, I believe in emergent democracy and the importance of trying to celebrate the community more than the heroes. Of course, I’m a huge fan of Larry’s and I have great respect for the leaders of our movement. But more than anything, I’m thankful for and respectful of all of the participants who aren’t so well known and who are essential to moving everything forward. Personally, I don’t think it’s ultimately meaningful to talk about one individual’s personal contribution to any movement. The real meaning is in the whole movement. I’m just one participant. Just another free soul.
|
A. Larry is a great guy. They are a huge fan.
|
Why does Hendricks help Joe?
A. Hendricks knows becoming an EX is the way for Joe to get an excellent job.
B. Hendricks helps Joe because they are friends.
C. Hendricks knows Joe will not go for the free treatment.
D. Hendricks thinks he can also become an EX and get an excellent job if he helps Joe.
|
Going straight meant crooked planning. He'd never make it unless he somehow managed to PICK A CRIME By RICHARD R. SMITH Illustrated by DICK FRANCIS [Transcriber's Note: This etext was produced from Galaxy Science Fiction May 1958. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] The girl was tall, wide-eyed and brunette. She had the right curves in the right places and would have been beautiful if her nose had been smaller, if her mouth had been larger and if her hair had been wavy instead of straight. "Hank said you wanted to see me," she said when she stopped beside Joe's table. "Yeah." Joe nodded at the other chair. "Have a seat." He reached into a pocket, withdrew five ten-dollar bills and handed them to her. "I want you to do a job for me. It'll only take a few minutes." The girl counted the money, then placed it in her purse. Joe noticed a small counterfeit-detector inside the purse before she closed it. "What's the job?" "Tell you later." He gulped the remainder of his drink, almost pouring it down his throat. "Hey. You trying to make yourself sick?" "Not sick. Drunk. Been trying to get drunk all afternoon." As the liquor settled in his stomach, he waited for the warm glow. But the glow didn't come ... the bartender had watered his drink again. "Trying to get drunk?" the girl inquired. "Are you crazy?" "No. It's simple. If I get drunk, I can join the AAA and get free room and board for a month while they give me a treatment." It was easy enough to understand, he reflected, but a lot harder to do. The CPA robot bartenders saw to it that anyone got high if they wanted, but comparatively few got drunk. Each bartender could not only mix drinks but could also judge by a man's actions and speech when he was on the verge of drunkenness. At the proper time—since drunkenness was illegal—a bartender always watered the drinks. Joe had tried dozens of times in dozens of bars to outsmart them, but had always failed. And in all of New York's millions, there had been only a hundred cases of intoxication during the previous year. The girl laughed. "If you're that hard up, I don't know if I should take this fifty or not. Why don't you go out and get a job like everyone else?" As an answer, Joe handed her his CPA ID card. She grunted when she saw the large letters that indicated the owner had Dangerous Criminal Tendencies. When she handed the card back, Joe fought an impulse to tear it to pieces. He'd done that once and gone through a mountain of red tape to get another—everyone was required by law to carry a CPA ID card and show it upon request. "I'm sorry," the girl said. "I didn't know you were a DCT." "And who'll hire a guy with criminal tendencies? You know the score. When you try to get a job, they ask to see your ID before they even tell you if there's an opening or not. If your CPA ID says you're a DCT, you're SOL and they tell you there's no openings. Oh, I've had several jobs ... jobs like all DCTs get. I've been a garbage man, street-cleaner, ditch-digger—" On the other side of the room, the jukebox came to life with a roar and a group of teen-agers scrambled to the dance floor. Feeling safe from hidden microphones because of the uproar, he leaned across the table and whispered in the girl's ear, "That's what I want to hire you for. I want you to help me commit a crime. If I get convicted of a crime, I'll be able to get a good job!" The girl's lips formed a bright red circle. "Say! You really got big plans, don't you?" He smiled at her admiration. It was something big to plan a crime. A civilization weary of murder, robbery, kidnapping, counterfeiting, blackmail, rape, arson, and drunkenness had originated the CPA—Crime Prevention Association. There were no longer any prisons—CPA officials had declared loudly and emphatically that their job was to prevent crime, not punish it. And prevent it they did, with thousands of ingenious crime-prevention devices and methods. They had made crime almost impossible, and during the previous year, only a few hundred men in the whole country had been convicted of criminal acts. No crime was ever punished. If a man was smart enough to kill someone, for instance, he wasn't sent to prison to be punished; he wasn't punished at all. Instead, he was sent to a hospital where all criminal tendencies were removed from his mind by psychologists, shock treatments, encephalographic devices, a form of prefrontal lobotomy and a dozen other methods. An expensive operation, but since there were few criminals—only ten in New York during the past year—any city could afford the CPA hospitals. The CPA system was, actually, cheaper than previous methods because it did away with the damage caused by countless crimes; did away with prisons and their guards, large police forces, squad cars and weapons. And, ironically, a man who did commit a crime was a sort of hero. He was a hero to the millions of men and women who had suppressed impulses to kill someone, beat their mates, get drunk, or kick a dog. Not only a hero, but because of the CPA Treatment, he was—when he left one of the CPA hospitals—a thoroughly honest and hard-working individual ... a man who could be trusted with any responsibility, any amount of money. And therefore, an EX (a convicted criminal who received the treatment was commonly called an Ex because he was in the strictest sense of the word an Ex-criminal) ... an Ex was always offered the best jobs. "Well," the girl said. "I'm honored. Really. But I got a date at ten. Let's get it over with. You said it'd only take a few minutes." "Okay. Let's go." The girl followed him across the room, around tables, through a door, down a hall, through a back door and into the alley. She followed him up the dark alley until he turned suddenly and ripped her blouse and skirt. He surprised her completely, but when she recovered, she backed away, her body poised like a wrestler's. "What's the big idea?" "Scream," Joe said. "Scream as loud as you can, and when the cops get here, tell 'em I tried to rape you." The plan was perfect, he told himself. Attempted rape was one of the few things that was a crime merely because a man attempted it. A crime because it theoretically inflicted psychological injury upon the intended victim—and because millions of women voters had voted it a crime. On the other hand, attempted murder, robbery, kidnapping, etc., were not crimes. They weren't crimes because the DCT didn't complete the act, and if he didn't complete the act, that meant simply that the CPA had once again functioned properly. The girl shook her head vigorously. "Sorry, buddy. Can't help you that way. Why didn't you tell me what you wanted?" "What's the matter?" Joe complained. "I'm not asking you to do anything wrong." "You stupid jerk. What do you think this is—the Middle Ages? Don't you know almost every woman knows how to defend herself? I'm a sergeant in the WSDA!" Joe groaned. The WSDA—Women's Self-Defense Association—a branch of the CPA. The WSDA gave free instruction in judo and jujitsu, even developed new techniques of wrestling and instructed only women in those new techniques. The girl was still shaking her head. "Can't do it, buddy. I'd lose my rank if you were convicted of—" "Do I have to make you scream?" Joe inquired tiredly and advanced toward the girl. "—and that rank carries a lot of weight. Hey! Stop it! " Joe discovered to his dismay that the girl was telling the truth when she said she was a sergeant in the WSDA. He felt her hands on his body, and in the time it takes to blink twice, he was flying through the air. The alley's concrete floor was hard—it had always been hard, but he became acutely aware of its lack of resiliency when his head struck it. There was a wonderful moment while the world was filled with beautiful stars and streaks of lightning through which he heard distant police sirens. But the wonderful moment didn't last long and darkness closed in on him. When he awoke, a rough voice was saying, "Okay. Snap out of it." He opened his eyes and recognized the police commissioner's office. It would be hard not to recognize: the room was large, devoid of furniture except for a desk and chairs, but the walls were lined with the controls of television screens, electronic calculators and a hundred other machines that formed New York's mechanical police force. Commissioner Hendricks was a remarkable character. There was something wrong with his glands, and he was a huge, greasy bulk of a man with bushy eyebrows and a double chin. His steel-gray eyes showed something of his intelligence and he would have gone far in politics if fate hadn't made him so ugly, for more than half the voters who elected men to high political positions were women. Anyone who knew Hendricks well liked him, for he was a friendly, likable person. But the millions of women voters who saw his face on posters and on their TV screens saw only the ugly face and heard only the harsh voice. The President of the United States was a capable man, but also a very handsome one, and the fact that a man who looked something like a bulldog had been elected as New York's police commissioner was a credit to Hendricks and millions of women voters. "Where's the girl?" Joe asked. "I processed her while you were out cold. She left. Joe, you—" "Okay," Joe said. "I'll save you the trouble. I admit it. Attempted rape. I confess." Hendricks smiled. "Sorry, Joe. You missed the boat again." He reached out and turned a dial on his desk top. "We had a microphone hidden in that alley. We have a lot of microphones hidden in a lot of alleys. You'd be surprised at the number of conspiracies that take place in alleys!" Joe listened numbly to his voice as it came from one of the hundreds of machines on the walls, " Scream. Scream as loud as you can, and when the cops get here, tell 'em I tried to rape you. " And then the girl's voice, " Sorry, buddy. Can't help— " He waved his hand. "Okay. Shut it off. I confess to conspiracy." Hendricks rose from behind the desk, walked leisurely to where Joe was slouched in a chair. "Give me your CPA ID." Joe handed him the card with trembling fingers. He felt as if the world had collapsed beneath him. Conspiracy to commit a crime wasn't a crime. Anyone could conspire. And if the conspirators were prevented from committing a crime, then that meant the CPA had functioned properly once again. That meant the CPA had once again prevented crime, and the CPA didn't punish crimes or attempted crimes, and it didn't attempt to prevent crimes by punishment. If it did, that would be a violation of the New Civil Rights. Hendricks crossed the room, deposited the card in a slot and punched a button. The machine hummed and a new card appeared. When Hendricks handed him the new card, Joe saw that the words DANGEROUS CRIMINAL TENDENCIES were now in red and larger than before. And, in slightly smaller print, the ID card stated that the owner was a DCT First Class. "You've graduated," Hendricks said coldly. "You guys never learn, do you? Now you're a DCT First Class instead of a Second Class. You know what that means?" Hendricks leaned closer until Joe could feel his breath on his face. "That means your case history will be turned over to the newspapers. You'll be the hobby of thousands of amateur cops. You know how it works? It's like this. The Joneses are sitting around tomorrow night and they're bored. Then Mr. Jones says, 'Let's go watch this Joe Harper.' So they look up your record—amateur cops always keep records of First Classes in scrapbooks—and they see that you stop frequently at Walt's Tavern. "So they go there and they sit and drink and watch you, trying not to let you know they're watching you. They watch you all night, just hoping you'll do something exciting, like trying to kill someone, so they can be the first ones to yell ' Police! ' They'll watch you because it's exciting to be an amateur cop, and if they ever did prevent you from committing a crime, they'd get a nice reward and they'd be famous." "Lay off," Joe said. "I got a headache. That girl—" Hendricks leaned even closer and glared. "You listen, Joe. This is interesting. You see, it doesn't stop with Mr. and Mrs. Jones. There's thousands of people like them. Years ago, they got their kicks from reading about guys like you, but these days things are dull because it's rare when anyone commits a crime. So every time you walk down the street, there'll be at least a dozen of 'em following you, and no matter where you go, you can bet there'll be some of 'em sitting next to you, standing next to you. "During the day, they'll take your picture with their spy cameras that look like buttons on their coats. At night, they'll peep at you through your keyhole. Your neighbors across the street will watch you through binoculars and—" "Lay off!" Joe squirmed in the chair. He'd been lectured by Hendricks before and it was always an unpleasant experience. The huge man was like a talking machine once he got started, a machine that couldn't be stopped. "And the kids are the worst," Hendricks continued. "They have Junior CPA clubs. They keep records of hoodlums like you in little cardboard boxes. They'll stare at you on the street and stare at you through restaurant windows while you're eating meals. They'll follow you in public rest rooms and watch you out of the corners of their eyes while they wash their little hands, and almost every day when you look back, you'll see a dozen freckle-faced little boys following you half a block behind, giggling and gaping at you. They'll follow you until the day you die, because you're a freak!" Joe couldn't stand the breath in his face any longer. He rose and paced the floor. "And it doesn't end there , Joe. It goes on and on. You'll be the object of every do-gooder and parlor psychologist. Strangers will stop you on the street and say, 'I'd like to help you, friend.' Then they'll ask you queer questions like, 'Did your father reject you when you were a child?' 'Do you like girls?' 'How does it feel to be a DCT First Class?' And then there'll be the strangers who hate DCTs. They'll stop you on the street and insult you, call you names, spit on you and—" "Okay, goddam it! Stop it! " Hendricks stopped, wiped the sweat from his face with a handkerchief and lit a cigarette. "I'm doing you a favor, Joe. I'm trying to explain something you're too dumb to realize by yourself. We've taught everyone to hate crime and criminals ... to hate them as nothing has ever been hated before. Today a criminal is a freak, an alien. Your life will be a living hell if you don't leave New York. You should go to some small town where there aren't many people, or be a hermit, or go to Iceland or—" Joe eyed the huge man suspiciously. " Favor , did you say? The day you do me a favor—" Hendricks shrugged his shoulders negligently. "Not entirely a favor. I want to get rid of you. Usually I come up here and sit around and read books. But guys like you are a nuisance and take up my time." "I couldn't leave if I wanted to," Joe said. "I'm flat broke. Thanks to your CPA system, a DCT can't get a decent job." Hendricks reached into a pocket, withdrew several bills and extended them. "I'll loan you some money. You can sign an IOU and pay me back a little at a time." Joe waved the money away. "Listen, why don't you do me a favor? Why don't you frame me? If I'm such a nuisance, pin a crime on me—any crime." "Can't do it. Convicting a man of a crime he didn't commit is a violation of Civil Rights and a crime in itself." "Umm." "Why don't you take the free psycho treatment? A man doesn't have to be a DCT. With the free treatment, psychologists can remove all your criminal tendencies and—" "Go to those head-shrinkers ?" Hendricks shrugged again. "Have it your way." Joe laughed. "If your damned CPA is so all-powerful, why can't you make me go?" "Violation of Civil Rights." "Damn it, there must be some way you can help me! We both want the same thing. We both want to see me convicted of a crime." "How can I help you without committing a crime myself?" Hendricks walked to his desk, opened a drawer and removed a small black book. "See this? It contains names and addresses of all the people in New York who aren't properly protected. Every week we find people who aren't protected properly—blind spots in our protection devices. As soon as we find them, we take steps to install anti-robbery devices, but this is a big city and sometimes it takes days to get the work done. "In the meantime, any one of these people could be robbed. But what can I do? I can't hold this book in front of your nose and say, 'Here, Joe, pick a name and go out and rob him.'" He laughed nervously. "If I did that, I'd be committing a crime myself!" He placed the book on the desk top, took a handkerchief from a pocket again and wiped sweat from his face. "Excuse me a minute. I'm dying of thirst. There's a water cooler in the next room." Joe stared at the door to the adjoining office as it closed behind the big man. Hendricks was—unbelievably—offering him a victim, offering him a crime! Almost running to the desk, Joe opened the book, selected a name and address and memorized it: John Gralewski, Apt. 204, 2141 Orange St. When Hendricks came back, Joe said, "Thanks." "Huh? Thanks for what? I didn't do anything." When Joe reached the street, he hurried toward the nearest subway. As a child, he had been frightened of the dark. As a man, he wasn't afraid of the dark itself, but the darkened city always made him feel ill at ease. The uneasiness was, more than anything else, caused by his own imagination. He hated the CPA and at night he couldn't shrug the feeling that the CPA lurked in every shadow, watching him, waiting for him to make a mistake. Imagination or not, the CPA was almost everywhere a person went. Twenty-four hours a day, millions of microphones hidden in taverns, alleys, restaurants, subways and every other place imaginable waited for someone to say the wrong thing. Everything the microphones picked up was routed to the CPA Brain, a monster electronic calculator. If the words "Let's see a movie" were received in the Brain, they were discarded. But if the words "Let's roll this guy" were received, the message was traced and a police helicopter would be at the scene in two minutes. And scattered all over the city were not only hidden microphones, but hidden television cameras that relayed visual messages to the Brain, and hidden machines that could detect a knife or a gun in someone's pocket at forty yards. Every place of business from the largest bank to the smallest grocery store was absolutely impenetrable. No one had even tried to rob a place of business for years. Arson was next to impossible because of the heat-detectors—devices placed in every building that could detect, radarlike, any intensity of heat above that caused by a cigarette lighter. Chemical research had made poisoning someone an impossibility. There were no drugs containing poison, and while an ant-poison might kill ants, no concentrated amount of it would kill a human. The FBI had always been a powerful organization, but under the supervision of the CPA, it was a scientific colossus and to think of kidnapping someone or to contemplate the use of narcotics was pointless. A counterfeiter's career was always short-lived: every place of business and millions of individuals had small counterfeit-detectors that could spot a fake and report it directly to the Brain. And the percentage of crimes had dwindled even more with the appearance of the robot police officers. Many a criminal in the past had gambled that he could outshoot a pursuing policeman. But the robots were different: they weren't flesh and blood. Bullets bounced off them and their aim was infallible. It was like a fantastic dream come true. Only the dream wasn't fantastic any more. With the huge atomic power plants scattered across the country and supplying endless electrical power at ridiculously low prices, no endeavor that required power was fantastic. The power required to operate the CPA devices cost each taxpayer an average of four dollars a year, and the invention, development and manufacture of the devices had cost even less. And the CPA had attacked crime through society itself, striking at the individual. In every city there were neon signs that blinked subliminally with the statement, CRIME IS FILTH. Listening to a radio or watching television, if a person heard station identification, he invariably heard or saw just below perception the words CRIME IS FILTH. If he went for a walk or a ride, he saw the endless subliminal posters declaring CRIME IS FILTH, and if he read a magazine or newspaper he always found, in those little dead spaces where an editor couldn't fit anything else, the below-perception words CRIME IS FILTH. It was monotonous and, after a while, a person looked at the words and heard them without thinking about them. And they were imprinted on his subconscious over and over, year after year, until he knew that crime was the same as filth and that criminals were filthy things. Except men like Joe Harper. No system is perfect. Along with thousands of other DCTs, Joe refused to believe it, and when he reached apartment 204 at 2141 Orange Street, he felt as if he'd inherited a gold mine. The hall was dimly lit, but when he stood before the door numbered 204, he could see that the wall on either side of it was new . That is, instead of being covered with dust, dirt and stains as the other walls were, it was clean. The building was an old one, the hall was wide, and the owner had obviously constructed a wall across the hall, creating another room. If the owner had reported the new room as required by law, it would have been wired with CPA burglarproof devices, but evidently he didn't want to pay for installation. When Joe entered the cubbyhole, he had to stand to one side in order to close the door behind him. The place was barely large enough for the bed, chair and bureau; it was a place where a man could fall down at night and sleep, but where no normal man could live day after day. Fearing that someone might detect him before he actually committed the crime, Joe hurried to the bureau and searched it. He broke out in a sweat when he found nothing but underwear and old magazines. If he stole underwear and magazines, it would still be a crime, but the newspapers would splash satirical headlines. Instead of being respected as a successful criminal, he would be ridiculed. He stopped sweating when he found a watch under a pile of underwear. The crystal was broken, one hand was missing and it wouldn't run, but—perfection itself—engraved on the back was the inscription, To John with Love . His trial would be a clean-cut one: it would be easy for the CPA to prove ownership and that a crime had been committed. Chuckling with joy, he opened the window and shouted, " Thief! Police! Help! " He waited a few seconds and then ran. When he reached the street, a police helicopter landed next to him. Strong metal arms seized him; cameras clicked and recorded the damning evidence. When Joe was securely handcuffed to a seat inside the helicopter, the metal police officers rang doorbells. There was a reward for anyone who reported a crime, but no one admitted shouting the warning. He was having a nightmare when he heard the voice, "Hey. Wake up. Hey!" He opened his eyes, saw Hendricks' ugly face and thought for a minute he was still having the nightmare. "I just saw your doctor," Hendricks said. "He says your treatment is over. You can go home now. I thought I'd give you a lift." As Joe dressed, he searched his mind and tried to find some difference. During the treatment, he had been unconscious or drugged, unable to think. Now he could think clearly, but he could find no difference in himself. He felt more relaxed than he'd ever felt before, but that could be an after-effect of all the sedatives he'd been given. And, he noticed when he looked in the mirror, he was paler. The treatment had taken months and he had, between operations, been locked in his room. Hendricks was standing by the window. Joe stared at the massive back. Deliberately goading his mind, he discovered the biggest change: Before, the mere sight of the man had aroused an intense hatred. Now, even when he tried, he succeeded in arousing only a mild hatred. They had toned down his capacity to hate, but not done away with it altogether. "Come here and take a look at your public," said Hendricks. Joe went to the window. Three stories below, a large crowd had gathered on the hospital steps: a band, photographers, television trucks, cameramen and autograph hunters. He'd waited a long time for this day. But now—another change in him— He put the emotion into words: "I don't feel like a hero. Funny, but I don't." "Hero!" Hendricks laughed and, with his powerful lungs, it sounded like a bull snorting. "You think a successful criminal is a hero? You stupid—" He laughed again and waved a hand at the crowd below them. "You think those people are down there because they admire what you did? They're down there waiting for you because they're curious, because they're glad the CPA caught you, and because they're glad you're an Ex. You're an ex -criminal now, and because of your treatment, you'll never be able to commit another crime as long as you live. And that's the kind of guy they admire, so they want to see you, shake your hand and get your autograph." Joe didn't understand Hendricks completely, but the part he did understand he didn't believe. A crowd was waiting for him. He could see the people with his own eyes. When he left the hospital, they'd cheer and shout and ask for his autograph. If he wasn't a hero, what was he ? It took half an hour to get through the crowd. Cameras clicked all around him, a hundred kids asked for his autograph, everyone talked at once and cheered, smiled, laughed, patted him on the back and cheered some more. Only one thing confused him during all the excitement: a white-haired old lady with tears in her eyes said, "Thank heaven it was only a watch. Thank heaven you didn't kill someone! God bless you, son." And then the old lady had handed him a box of fudge and left him in total confusion. What she said didn't make sense. If he had killed someone rather than stealing a watch, he would be even more of a hero and the crowd would have cheered even louder. He knew: he had stood outside the CPA hospitals many times and the crowds always cheered louder when an ex-murderer came out. In Hendricks' robot-chauffeured car, he ate the fudge and consoled himself with the thought, People are funny. Who can understand 'em? Feeling happy for one of the few times in his life, he turned toward Hendricks and said, "Thanks for what you did. It turned out great. I'll be able to get a good job now." "That's why I met you at the hospital," Hendricks said. "I want to explain some things. I've known you for a long time and I know you're spectacularly dumb. You can't figure out some things for yourself and I don't want you walking around the rest of your life thinking I did you a favor." Joe frowned. Few men had ever done him a favor and he had rarely thanked anyone for anything. And now ... after thanking the man who'd done him the biggest favor of all, the man was denying it! "You robbed Gralewski's apartment," Hendricks said. "Gralewski is a CPA employee and he doesn't live in the apartment you robbed. The CPA pays the rent for that one and he lives in another. We have a lot of places like that. You see, it gives us a way to get rid of saps like you before they do real damage. We use it as a last resort when a DCT First Class won't take the free psycho treatment or—" "Well, it's still a favor." Hendricks' face hardened. "Favor? You wouldn't know a favor if you stumbled over one. I did it because it's standard procedure for your type of case. Anyone can—free of charge—have treatment by the best psychologists. Any DCT can stop being a DCT by simply asking for the treatment and taking it. But you wouldn't do that. You wanted to commit a crime, get caught and be a hero ... an Ex ." The car passed one of the CPA playgrounds. Boys and girls of all ages were laughing, squealing with joy as they played games designed by CPA psychologists to relieve tension. And—despite the treatment, Joe shuddered when he saw the psychologists standing to one side, quietly watching the children. The whole world was filled with CPA employees and volunteer workers. Everywhere you went, it was there, quietly watching you and analyzing you, and if you showed criminal tendencies, it watched you even more closely and analyzed you even more deeply until it took you apart and put you back together again the way it wanted you to be. "Being an Ex, you'll get the kind of job you always wanted," Hendricks continued. "You'll get a good-paying job, but you'll work for it. You'll work eight hours a day, work harder than you've ever worked before in your life, because every time you start to loaf, a voice in your head is going to say, Work! Work! Exes always get good jobs because employers know they're good workers. "But during these next few days, you'll discover what being an Ex is like. You see, Joe, the treatment can't possibly take all the criminal tendencies out of a man. So the treatment does the next best thing—you'll find a set of laws written in your mind. You might want to break one now and then, but you won't be able. I'll give you an illustration...." Joe's face reddened as Hendricks proceeded to call him a series of names. He wanted to smash the fat, grinning face, but the muscles in his arm froze before it moved it an inch. And worse than that, a brief pain ripped through his skull. A pain so intense that, had it lasted a second longer, he would have screamed in agony. And above the pain, a voice whispered in his head, Unlawful to strike someone except in self-defense . He opened his mouth to tell Hendricks exactly what he thought of him, the CPA, the whole world. But the words stayed in his throat, the pain returned, and the mental voice whispered, Unlawful to curse . He had never heard how the treatment prevented an Ex from committing a crime. And now that he knew, it didn't seem fair. He decided to tell the whole story to the newspapers as soon as he could. And as soon as that decision formed in his mind, his body froze, the pain returned and the voice, Unlawful to divulge CPA procedure . "See what I mean?" Hendricks asked. "A century ago, you would have been locked in a prison and taxpayers' money would have supported you until the day you died. With the CPA system, you're returned to society, a useful citizen, unable to commit the smallest crime. And you've got a big hand in your dirty little mind that's going to slap it every time you get the wrong kind of thought. It'll keep slapping you until you learn. It might take weeks, months or years, but you'll learn sooner or later to not even think about doing anything wrong." He lit a cigarette and blew a smoke ring at the car's plush ceiling. "It's a great system, isn't it, Joe? A true democracy. Even a jerk like you is free to do what he wants, as long as it's legal." "I think it's a lousy, filthy system." Joe's head was still tingling with pain and he felt suffocated. The CPA was everywhere, only now it was also inside his head, telling him he couldn't do this, couldn't do that. All his life it had been telling him he couldn't do things he wanted to do and now .... Hendricks laughed. "You'll change your opinion. We live in a clean, wonderful world, Joe. A world of happy, healthy people. Except for freaks like yourself, criminals are—" "Let me out!" Joe grabbed at the door and was on the sidewalk, slamming the door behind him before the car stopped completely. He stared at the car as it pulled away from the curb and glided into the stream of traffic again. He realized he was a prisoner ... a prisoner inside his own body ... made a prisoner by a world that hated him back. He wanted to spit his contempt, but the increasingly familiar pain and voice prevented him. It was unlawful to spit on a sidewalk.
|
C. Hendricks knows Joe will not go for the free treatment.
|
Which of these does Dr. Niemand believe to be true about the cause of the attacks?
A. The second world war brought out violent tendancies which caused a spread of emotional effects
B. It is the humans' development & use of radio technology that is causing the solar events
C. It is the innate evil of humankind that is causing the emotional disruptions
D. Is it an event on the Sun that causes the attacks
|
DISTURBING SUN By PHILIP LATHAM Illustrated by Freas [Transcriber's Note: This etext was produced from Astounding Science Fiction May 1959. Extensive research did not uncover any evidence that the U.S. copyright on this publication was renewed.] This, be it understood, is fiction—nothing but fiction—and not, under any circumstances, to be considered as having any truth whatever to it. It's obviously utterly impossible ... isn't it? An interview with Dr. I. M. Niemand, Director of the Psychophysical Institute of Solar and Terrestrial Relations, Camarillo, California. In the closing days of December, 1957, at the meeting of the American Association for the Advancement of Science in New York, Dr. Niemand delivered a paper entitled simply, "On the Nature of the Solar S-Regions." Owing to its unassuming title the startling implications contained in the paper were completely overlooked by the press. These implications are discussed here in an exclusive interview with Dr. Niemand by Philip Latham. LATHAM. Dr. Niemand, what would you say is your main job? NIEMAND. I suppose you might say my main job today is to find out all I can between activity on the Sun and various forms of activity on the Earth. LATHAM. What do you mean by activity on the Sun? NIEMAND. Well, a sunspot is a form of solar activity. LATHAM. Just what is a sunspot? NIEMAND. I'm afraid I can't say just what a sunspot is. I can only describe it. A sunspot is a region on the Sun that is cooler than its surroundings. That's why it looks dark. It isn't so hot. Therefore not so bright. LATHAM. Isn't it true that the number of spots on the Sun rises and falls in a cycle of eleven years? NIEMAND. The number of spots on the Sun rises and falls in a cycle of about eleven years. That word about makes quite a difference. LATHAM. In what way? NIEMAND. It means you can only approximately predict the future course of sunspot activity. Sunspots are mighty treacherous things. LATHAM. Haven't there been a great many correlations announced between sunspots and various effects on the Earth? NIEMAND. Scores of them. LATHAM. What is your opinion of these correlations? NIEMAND. Pure bosh in most cases. LATHAM. But some are valid? NIEMAND. A few. There is unquestionably a correlation between sunspots and disturbances of the Earth's magnetic field ... radio fade-outs ... auroras ... things like that. LATHAM. Now, Dr. Niemand, I understand that you have been investigating solar and terrestrial relationships along rather unorthodox lines. NIEMAND. Yes, I suppose some people would say so. LATHAM. You have broken new ground? NIEMAND. That's true. LATHAM. In what way have your investigations differed from those of others? NIEMAND. I think our biggest advance was the discovery that sunspots themselves are not the direct cause of the disturbances we have been studying on the Earth. It's something like the eruptions in rubeola. Attention is concentrated on the bright red papules because they're such a conspicuous symptom of the disease. Whereas the real cause is an invisible filterable virus. In the solar case it turned out to be these S-Regions. LATHAM. Why S-Regions? NIEMAND. We had to call them something. Named after the Sun, I suppose. LATHAM. You say an S-Region is invisible? NIEMAND. It is quite invisible to the eye but readily detected by suitable instrumental methods. It is extremely doubtful, however, if the radiation we detect is the actual cause of the disturbing effects observed. LATHAM. Just what are these effects? NIEMAND. Well, they're common enough, goodness knows. As old as the world, in fact. Yet strangely enough it's hard to describe them in exact terms. LATHAM. Can you give us a general idea? NIEMAND. I'll try. Let's see ... remember that speech from "Julius Caesar" where Cassius is bewailing the evil times that beset ancient Rome? I believe it went like this: "The fault, dear Brutus, is not in our stars but in ourselves that we are underlings." LATHAM. I'm afraid I don't see— NIEMAND. Well, Shakespeare would have been nearer the truth if he had put it the other way around. "The fault, dear Brutus, is not in ourselves but in our stars" or better "in the Sun." LATHAM. In the Sun? NIEMAND. That's right, in the Sun. I suppose the oldest problem in the world is the origin of human evil. Philosophers have wrestled with it ever since the days of Job. And like Job they have usually given up in despair, convinced that the origin of evil is too deep for the human mind to solve. Generally they have concluded that man is inherently wicked and sinful and that is the end of it. Now for the first time science has thrown new light on this subject. LATHAM. How is that? NIEMAND. Consider the record of history. There are occasional periods when conditions are fairly calm and peaceful. Art and industry flourished. Man at last seemed to be making progress toward some higher goal. Then suddenly— for no detectable reason —conditions are reversed. Wars rage. People go mad. The world is plunged into an orgy of bloodshed and misery. LATHAM. But weren't there reasons? NIEMAND. What reasons? LATHAM. Well, disputes over boundaries ... economic rivalry ... border incidents.... NIEMAND. Nonsense. Men always make some flimsy excuse for going to war. The truth of the matter is that men go to war because they want to go to war. They can't help themselves. They are impelled by forces over which they have no control. By forces outside of themselves. LATHAM. Those are broad, sweeping statements. Can't you be more specific? NIEMAND. Perhaps I'd better go back to the beginning. Let me see.... It all started back in March, 1955, when I started getting patients suffering from a complex of symptoms, such as profound mental depression, anxiety, insomnia, alternating with fits of violent rage and resentment against life and the world in general. These people were deeply disturbed. No doubt about that. Yet they were not psychotic and hardly more than mildly neurotic. Now every doctor gets a good many patients of this type. Such a syndrome is characteristic of menopausal women and some men during the climacteric, but these people failed to fit into this picture. They were married and single persons of both sexes and of all ages. They came from all walks of life. The onset of their attack was invariably sudden and with scarcely any warning. They would be going about their work feeling perfectly all right. Then in a minute the whole world was like some scene from a nightmare. A week or ten days later the attack would cease as mysteriously as it had come and they would be their old self again. LATHAM. Aren't such attacks characteristic of the stress and strain of modern life? NIEMAND. I'm afraid that old stress-and-strain theory has been badly overworked. Been hearing about it ever since I was a pre-med student at ucla . Even as a boy I can remember my grandfather deploring the stress and strain of modern life when he was a country doctor practicing in Indiana. In my opinion one of the most valuable contributions anthropologists have made in recent years is the discovery that primitive man is afflicted with essentially the same neurotic conditions as those of us who live a so-called civilized life. They have found savages displaying every symptom of a nervous breakdown among the mountain tribes of the Elgonyi and the Aruntas of Australia. No, Mr. Latham, it's time the stress-and-strain theory was relegated to the junk pile along with demoniac possession and blood letting. LATHAM. You must have done something for your patients— NIEMAND. A doctor must always do something for the patients who come to his office seeking help. First I gave them a thorough physical examination. I turned up some minor ailments—a slight heart murmur or a trace of albumin in the urine—but nothing of any significance. On the whole they were a remarkably healthy bunch of individuals, much more so than an average sample of the population. Then I made a searching inquiry into their personal life. Here again I drew a blank. They had no particular financial worries. Their sex life was generally satisfactory. There was no history of mental illness in the family. In fact, the only thing that seemed to be the matter with them was that there were times when they felt like hell. LATHAM. I suppose you tried tranquilizers? NIEMAND. Oh, yes. In a few cases in which I tried tranquilizing pills of the meprobamate type there was some slight improvement. I want to emphasize, however, that I do not believe in prescribing shotgun remedies for a patient. To my way of thinking it is a lazy slipshod way of carrying on the practice of medicine. The only thing for which I do give myself credit was that I asked my patients to keep a detailed record of their symptoms taking special care to note the time of exacerbation—increase in the severity of the symptoms—as accurately as possible. LATHAM. And this gave you a clue? NIEMAND. It was the beginning. In most instances patients reported the attack struck with almost the impact of a physical blow. The prodromal symptoms were usually slight ... a sudden feeling of uneasiness and guilt ... hot and cold flashes ... dizziness ... double vision. Then this ghastly sense of depression coupled with a blind insensate rage at life. One man said he felt as if the world were closing in on him. Another that he felt the people around him were plotting his destruction. One housewife made her husband lock her in her room for fear she would injure the children. I pored over these case histories for a long time getting absolutely nowhere. Then finally a pattern began to emerge. LATHAM. What sort of pattern? NIEMAND. The first thing that struck me was that the attacks all occurred during the daytime, between the hours of about seven in the morning and five in the evening. Then there were these coincidences— LATHAM. Coincidences? NIEMAND. Total strangers miles apart were stricken at almost the same moment. At first I thought nothing of it but as my records accumulated I became convinced it could not be attributed to chance. A mathematical analysis showed the number of coincidences followed a Poisson distribution very closely. I couldn't possibly see what daylight had to do with it. There is some evidence that mental patients are most disturbed around the time of full moon, but a search of medical literature failed to reveal any connection with the Sun. LATHAM. What did you do? NIEMAND. Naturally I said nothing of this to my patients. I did, however, take pains to impress upon them the necessity of keeping an exact record of the onset of an attack. The better records they kept the more conclusive was the evidence. Men and women were experiencing nearly simultaneous attacks of rage and depression all over southern California, which was as far as my practice extended. One day it occurred to me: if people a few miles apart could be stricken simultaneously, why not people hundreds or thousands of miles apart? It was this idea that prompted me to get in touch with an old colleague of mine I had known at UC medical school, Dr. Max Hillyard, who was in practice in Utica, New York. LATHAM. With what result? NIEMAND. I was afraid the result would be that my old roommate would think I had gone completely crazy. Imagine my surprise and gratification on receiving an answer by return mail to the effect that he also had been getting an increasing number of patients suffering with the same identical symptoms as my own. Furthermore, upon exchanging records we did find that in many cases patients three thousand miles apart had been stricken simultaneously— LATHAM. Just a minute. I would like to know how you define "simultaneous." NIEMAND. We say an attack is simultaneous when one occurred on the east coast, for example, not earlier or later than five minutes of an attack on the west coast. That is about as close as you can hope to time a subjective effect of this nature. And now another fact emerged which gave us another clue. LATHAM. Which was? NIEMAND. In every case of a simultaneous attack the Sun was shining at both New York and California. LATHAM. You mean if it was cloudy— NIEMAND. No, no. The weather had nothing to do with it. I mean the Sun had to be above the horizon at both places. A person might undergo an attack soon after sunrise in New York but there would be no corresponding record of an attack in California where it was still dark. Conversely, a person might be stricken late in the afternoon in California without a corresponding attack in New York where the Sun had set. Dr. Hillyard and I had been searching desperately for a clue. We had both noticed that the attacks occurred only during the daylight hours but this had not seemed especially significant. Here we had evidence pointing directly to the source of trouble. It must have some connection with the Sun. LATHAM. That must have had you badly puzzled at first. NIEMAND. It certainly did. It looked as if we were headed back to the Middle Ages when astrology and medicine went hand in hand. But since it was our only lead we had no other choice but to follow it regardless of the consequences. Here luck played somewhat of a part, for Hillyard happened to have a contact that proved invaluable to us. Several years before Hillyard had gotten to know a young astrophysicist, Henry Middletown, who had come to him suffering from a severe case of myositis in the arms and shoulders. Hillyard had been able to effect a complete cure for which the boy was very grateful, and they had kept up a desultory correspondence. Middletown was now specializing in radio astronomy at the government's new solar observatory on Turtle Back Mountain in Arizona. If it had not been for Middletown's help I'm afraid our investigation would never have gotten past the clinical stage. LATHAM. In what way was Middletown of assistance? NIEMAND. It was the old case of workers in one field of science being completely ignorant of what was going on in another field. Someday we will have to establish a clearing house in science instead of keeping it in tight little compartments as we do at present. Well, Hillyard and I packed up for Arizona with considerable misgivings. We were afraid Middletown wouldn't take our findings seriously but somewhat to our surprise he heard our story with the closest attention. I guess astronomers have gotten so used to hearing from flying saucer enthusiasts and science-fiction addicts that nothing surprises them any more. When we had finished he asked to see our records. Hillyard had them all set down for easy numerical tabulation. Middletown went to work with scarcely a word. Within an hour he had produced a chart that was simply astounding. LATHAM. Can you describe this chart for us? NIEMAND. It was really quite simple. But if it had not been for Middletown's experience in charting other solar phenomena it would never have occurred to us to do it. First, he laid out a series of about thirty squares horizontally across a sheet of graph paper. He dated these beginning March 1, 1955, when our records began. In each square he put a number from 1 to 10 that was a rough index of the number and intensity of the attacks reported on that day. Then he laid out another horizontal row below the first one dated twenty-seven days later. That is, the square under March 1st in the top row was dated March 28th in the row below it. He filled in the chart until he had an array of dozens of rows that included all our data down to May, 1958. When Middletown had finished it was easy to see that the squares of highest index number did not fall at random on the chart. Instead they fell in slightly slanting parallel series so that you could draw straight lines down through them. The connection with the Sun was obvious. LATHAM. In what way? NIEMAND. Why, because twenty-seven days is about the synodic period of solar rotation. That is, if you see a large spot at the center of the Sun's disk today, there is a good chance if it survives that you will see it at the same place twenty-seven days later. But that night Middletown produced another chart that showed the connection with the Sun in a way that was even more convincing. LATHAM. How was that? NIEMAND. I said that the lines drawn down through the days of greatest mental disturbance slanted slightly. On this second chart the squares were dated under one another not at intervals of twenty-seven days, but at intervals of twenty-seven point three days. LATHAM. Why is that so important? NIEMAND. Because the average period of solar rotation in the sunspot zone is not twenty-seven days but twenty-seven point three days. And on this chart the lines did not slant but went vertically downward. The correlation with the synodic rotation of the Sun was practically perfect. LATHAM. But how did you get onto the S-Regions? NIEMAND. Middletown was immediately struck by the resemblance between the chart of mental disturbance and one he had been plotting over the years from his radio observations. Now when he compared the two charts the resemblance between the two was unmistakable. The pattern shown by the chart of mental disturbance corresponded in a striking way with the solar chart but with this difference. The disturbances on the Earth started two days later on the average than the disturbances due to the S-Regions on the Sun. In other words, there was a lag of about forty-eight hours between the two. But otherwise they were almost identical. LATHAM. But if these S-Regions of Middletown's are invisible how could he detect them? NIEMAND. The S-Regions are invisible to the eye through an optical telescope, but are detected with ease by a radio telescope. Middletown had discovered them when he was a graduate student working on radio astronomy in Australia, and he had followed up his researches with the more powerful equipment at Turtle Back Mountain. The formation of an S-Region is heralded by a long series of bursts of a few seconds duration, when the radiation may increase up to several thousand times that of the background intensity. These noise storms have been recorded simultaneously on wavelengths of from one to fifteen meters, which so far is the upper limit of the observations. In a few instances, however, intense bursts have also been detected down to fifty cm. LATHAM. I believe you said the periods of mental disturbance last for about ten or twelve days. How does that tie-in with the S-Regions? NIEMAND. Very closely. You see it takes about twelve days for an S-Region to pass across the face of the Sun, since the synodic rotation is twenty-seven point three days. LATHAM. I should think it would be nearer thirteen or fourteen days. NIEMAND. Apparently an S-Region is not particularly effective when it is just coming on or just going off the disk of the Sun. LATHAM. Are the S-Regions associated with sunspots? NIEMAND. They are connected in this way: that sunspot activity and S-Region activity certainly go together. The more sunspots the more violent and intense is the S-Region activity. But there is not a one-to-one correspondence between sunspots and S-Regions. That is, you cannot connect a particular sunspot group with a particular S-Region. The same thing is true of sunspots and magnetic storms. LATHAM. How do you account for this? NIEMAND. We don't account for it. LATHAM. What other properties of the S-Regions have you discovered? NIEMAND. Middletown says that the radio waves emanating from them are strongly circularly polarized. Moreover, the sense of rotation remains constant while one is passing across the Sun. If the magnetic field associated with an S-Region extends into the high solar corona through which the rays pass, then the sense of rotation corresponds to the ordinary ray of the magneto-ionic theory. LATHAM. Does this mean that the mental disturbances arise from some form of electromagnetic radiation? NIEMAND. We doubt it. As I said before, the charts show a lag of about forty-eight hours between the development of an S-Region and the onset of mental disturbance. This indicates that the malignant energy emanating from an S-Region consists of some highly penetrating form of corpuscular radiation, as yet unidentified. [A] LATHAM. A question that puzzles me is why some people are affected by the S-Regions while others are not. NIEMAND. Our latest results indicate that probably no one is completely immune. All are affected in some degree. Just why some should be affected so much more than others is still a matter of speculation. LATHAM. How long does an S-Region last? NIEMAND. An S-Region may have a lifetime of from three to perhaps a dozen solar rotations. Then it dies out and for a time we are free from this malignant radiation. Then a new region develops in perhaps an entirely different region of the Sun. Sometimes there may be several different S-Regions all going at once. LATHAM. Why were not the S-Regions discovered long ago? NIEMAND. Because the radio exploration of the Sun only began since the end of World War II. LATHAM. How does it happen that you only got patients suffering from S-radiation since about 1955? NIEMAND. I think we did get such patients previously but not in large enough numbers to attract attention. Also the present sunspot cycle started its rise to maximum about 1954. LATHAM. Is there no way of escaping the S-radiation? NIEMAND. I'm afraid the only sure way is to keep on the unilluminated side of the Earth which is rather difficult to do. Apparently the corpuscular beam from an S-Region is several degrees wide and not very sharply defined, since its effects are felt simultaneously over the entire continent. Hillyard and Middletown are working on some form of shielding device but so far without success. LATHAM. What is the present state of S-Region activity? NIEMAND. At the present moment there happens to be no S-Region activity on the Sun. But a new one may develop at any time. Also, the outlook for a decrease in activity is not very favorable. Sunspot activity continues at a high level and is steadily mounting in violence. The last sunspot cycle had the highest maximum of any since 1780, but the present cycle bids fair to set an all time record. LATHAM. And so you believe that the S-Regions are the cause of most of the present trouble in the world. That it is not ourselves but something outside ourselves— NIEMAND. That is the logical outcome of our investigation. We are controlled and swayed by forces which in many cases we are powerless to resist. LATHAM. Could we not be warned of the presence of an S-Region? NIEMAND. The trouble is they seem to develop at random on the Sun. I'm afraid any warning system would be worse than useless. We would be crying WOLF! all the time. LATHAM. How may a person who is not particularly susceptible to this malignant radiation know that one of these regions is active? NIEMAND. If you have a feeling of restlessness and anxiety, if you are unable to concentrate, if you feel suddenly depressed and discouraged about yourself, or are filled with resentment toward the world, then you may be pretty sure that an S-Region is passing across the face of the Sun. Keep a tight rein on yourself. For it seems that evil will always be with us ... as long as the Sun shall continue to shine upon this little world. THE END [A] Middletown believes that the Intense radiation recently discovered from information derived from Explorer I and III has no connection with the corpuscular S-radiation.
|
D. Is it an event on the Sun that causes the attacks
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.