metadata

tags:
  - setfit
  - absa
  - sentence-transformers
  - text-classification
  - generated_from_setfit_trainer
widget:
  - text: even the wine by the glass was good.:even the wine by the glass was good.
  - text: >-
      I had the Pad Thai and the noodles:I had the Pad Thai and the noodles were
      sticky.
  - text: >-
      happy and the food was delicious,:The have over 100 different beers to
      offer thier guest so that made my husband very happy and the food was
      delicious, if I must recommend a dish it must be the pumkin tortelini.
  - text: >-
      The takeout menu says to keep:The takeout menu says to keep an eye out for
      an expanded menu offering more italian dishes, I can't wait!
  - text: >-
      fresh garlic or eggplant.:Try their plain pizza with fresh garlic or
      eggplant.
metrics:
  - f1_micro
  - f1_macro
  - precision_macro
  - recall_macro
pipeline_tag: text-classification
library_name: setfit
inference: false
base_model: sentence-transformers/all-mpnet-base-v2
model-index:
  - name: SetFit Polarity Model with sentence-transformers/all-mpnet-base-v2
    results:
      - task:
          type: text-classification
          name: Text Classification
        dataset:
          name: Unknown
          type: unknown
          split: test
        metrics:
          - type: f1_micro
            value: 0.7398546335554209
            name: F1_Micro
          - type: f1_macro
            value: 0.47927842814066474
            name: F1_Macro
          - type: precision_macro
            value: 0.49187400153564864
            name: Precision_Macro
          - type: recall_macro
            value: 0.48087480356207435
            name: Recall_Macro

SetFit Polarity Model with sentence-transformers/all-mpnet-base-v2

This is a SetFit model that can be used for Aspect Based Sentiment Analysis (ABSA). This SetFit model uses sentence-transformers/all-mpnet-base-v2 as the Sentence Transformer embedding model. A LogisticRegression instance is used for classification. In particular, this model is in charge of classifying aspect polarities.

The model has been trained using an efficient few-shot learning technique that involves:

Fine-tuning a Sentence Transformer with contrastive learning.
Training a classification head with features from the fine-tuned Sentence Transformer.

This model was trained within the context of a larger system for ABSA, which looks like so:

Use a spaCy model to select possible aspect span candidates.
Use a SetFit model to filter these possible aspect span candidates.
Use this SetFit model to classify the filtered aspect span candidates.

Model Details

Model Description

Model Type: SetFit
Sentence Transformer body: sentence-transformers/all-mpnet-base-v2
Classification head: a LogisticRegression instance
spaCy Model: en_core_web_lg
SetFitABSA Aspect Model: setfit-absa-aspect
SetFitABSA Polarity Model: ronalhung/setfit-absa-restaurants-polarity-128
Maximum Sequence Length: 384 tokens
Number of Classes: 4 classes

Model Sources

Repository: SetFit on GitHub
Paper: Efficient Few-Shot Learning Without Prompts
Blogpost: SetFit: Efficient Few-Shot Learning Without Prompts

Model Labels

Label	Examples
negative	'But the staff was so horrible:But the staff was so horrible to us.' ', forgot our toast, left out:They did not have mayonnaise, forgot our toast, left out ingredients (ie cheese in an omelet), below hot temperatures and the bacon was so over cooked it crumbled on the plate when you touched it.' 'did not have mayonnaise, forgot our:They did not have mayonnaise, forgot our toast, left out ingredients (ie cheese in an omelet), below hot temperatures and the bacon was so over cooked it crumbled on the plate when you touched it.'
positive	"factor was the food, which was:To be completely fair, the only redeeming factor was the food, which was above average, but couldn't make up for all the other deficiencies of Teodora." "The food is uniformly exceptional:The food is uniformly exceptional, with a very capable kitchen which will proudly whip up whatever you feel like eating, whether it's on the menu or not." "a very capable kitchen which will proudly:The food is uniformly exceptional, with a very capable kitchen which will proudly whip up whatever you feel like eating, whether it's on the menu or not."
neutral	"'s on the menu or not.:The food is uniformly exceptional, with a very capable kitchen which will proudly whip up whatever you feel like eating, whether it's on the menu or not." 'to sample both meats).:Our agreed favorite is the orrechiete with sausage and chicken (usually the waiters are kind enough to split the dish in half so you get to sample both meats).' 'to split the dish in half so:Our agreed favorite is the orrechiete with sausage and chicken (usually the waiters are kind enough to split the dish in half so you get to sample both meats).'
conflict	'The food was delicious but:The food was delicious but do not come here on a empty stomach.' "The service varys from day:The service varys from day to day- sometimes they're very nice, and sometimes not."

Evaluation

Metrics

Label	F1_Micro	F1_Macro	Precision_Macro	Recall_Macro
all	0.7399	0.4793	0.4919	0.4809

Uses

Direct Use for Inference

First install the SetFit library:

pip install setfit

Then you can load this model and run inference.

from setfit import AbsaModel

# Download from the 🤗 Hub
model = AbsaModel.from_pretrained(
    "setfit-absa-aspect",
    "ronalhung/setfit-absa-restaurants-polarity-128",
)
# Run inference
preds = model("The food was great, but the venue is just way too busy.")

Training Details

Training Set Metrics

Training set	Min	Median	Max
Word count	6	21.3594	43

Label	Training Sample Count
conflict	2
negative	19
neutral	25
positive	82

Training Hyperparameters

batch_size: (64, 64)
num_epochs: (5, 5)
max_steps: -1
sampling_strategy: oversampling
body_learning_rate: (2e-05, 1e-05)
head_learning_rate: 0.01
loss: CosineSimilarityLoss
distance_metric: cosine_distance
margin: 0.25
end_to_end: False
use_amp: False
warmup_proportion: 0.1
l2_weight: 0.01
seed: 42
eval_max_steps: -1
load_best_model_at_end: True

Training Results

Epoch	Step	Training Loss	Validation Loss
0.0074	1	0.3008	-
0.3676	50	0.1867	0.1974
0.7353	100	0.0346	0.1855
1.1029	150	0.0061	0.2165
1.4706	200	0.0007	0.2194
1.8382	250	0.0003	0.2145
2.2059	300	0.0006	0.2150
2.5735	350	0.0002	0.2223

Framework Versions

Python: 3.11.13
SetFit: 1.1.2
Sentence Transformers: 4.1.0
spaCy: 3.8.7
Transformers: 4.52.4
PyTorch: 2.6.0+cu124
Datasets: 3.6.0
Tokenizers: 0.21.1

Citation

BibTeX

@article{https://doi.org/10.48550/arxiv.2209.11055,
    doi = {10.48550/ARXIV.2209.11055},
    url = {https://arxiv.org/abs/2209.11055},
    author = {Tunstall, Lewis and Reimers, Nils and Jo, Unso Eun Seo and Bates, Luke and Korat, Daniel and Wasserblat, Moshe and Pereg, Oren},
    keywords = {Computation and Language (cs.CL), FOS: Computer and information sciences, FOS: Computer and information sciences},
    title = {Efficient Few-Shot Learning Without Prompts},
    publisher = {arXiv},
    year = {2022},
    copyright = {Creative Commons Attribution 4.0 International}
}