adrianeboyd
commited on
Commit
•
a8035b6
1
Parent(s):
383907d
Update spaCy pipeline
Browse files- README.md +18 -18
- accuracy.json +195 -195
- attribute_ruler/patterns +0 -0
- config.cfg +51 -24
- en_core_web_trf-any-py3-none-any.whl +2 -2
- meta.json +200 -200
- ner/model +2 -2
- parser/model +2 -2
- tagger/model +2 -2
- transformer/cfg +1 -1
- transformer/model +2 -2
- vocab/lookups.bin +2 -2
- vocab/strings.json +2 -2
README.md
CHANGED
@@ -14,51 +14,51 @@ model-index:
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
-
value: 0.
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
-
value: 0.
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
-
value: 0.
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
-
value: 0.
|
31 |
- task:
|
32 |
name: UNLABELED_DEPENDENCIES
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: Unlabeled Attachment Score (UAS)
|
36 |
type: f_score
|
37 |
-
value: 0.
|
38 |
- task:
|
39 |
name: LABELED_DEPENDENCIES
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Labeled Attachment Score (LAS)
|
43 |
type: f_score
|
44 |
-
value: 0.
|
45 |
- task:
|
46 |
name: SENTS
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Sentences F-Score
|
50 |
type: f_score
|
51 |
-
value: 0.
|
52 |
---
|
53 |
### Details: https://spacy.io/models/en#en_core_web_trf
|
54 |
|
55 |
-
English transformer pipeline (roberta-base). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.
|
56 |
|
57 |
| Feature | Description |
|
58 |
| --- | --- |
|
59 |
| **Name** | `en_core_web_trf` |
|
60 |
-
| **Version** | `3.
|
61 |
-
| **spaCy** | `>=3.
|
62 |
| **Default Pipeline** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
63 |
| **Components** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
64 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
@@ -88,12 +88,12 @@ English transformer pipeline (roberta-base). Components: transformer, tagger, pa
|
|
88 |
| `TOKEN_P` | 99.57 |
|
89 |
| `TOKEN_R` | 99.58 |
|
90 |
| `TOKEN_F` | 99.57 |
|
91 |
-
| `TAG_ACC` |
|
92 |
-
| `SENTS_P` | 94.
|
93 |
-
| `SENTS_R` |
|
94 |
-
| `SENTS_F` |
|
95 |
-
| `DEP_UAS` | 95.
|
96 |
-
| `DEP_LAS` | 93.
|
97 |
-
| `ENTS_P` | 89.
|
98 |
-
| `ENTS_R` | 89.
|
99 |
| `ENTS_F` | 89.90 |
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.8994886705
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.8985877404
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.8990379798
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.9815755741
|
31 |
- task:
|
32 |
name: UNLABELED_DEPENDENCIES
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: Unlabeled Attachment Score (UAS)
|
36 |
type: f_score
|
37 |
+
value: 0.9505463996
|
38 |
- task:
|
39 |
name: LABELED_DEPENDENCIES
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Labeled Attachment Score (LAS)
|
43 |
type: f_score
|
44 |
+
value: 0.9368643771
|
45 |
- task:
|
46 |
name: SENTS
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Sentences F-Score
|
50 |
type: f_score
|
51 |
+
value: 0.8881133524
|
52 |
---
|
53 |
### Details: https://spacy.io/models/en#en_core_web_trf
|
54 |
|
55 |
+
English transformer pipeline (Transformer(name='roberta-base', piece_encoder='byte-bpe', stride=104, type='roberta', width=768, window=144, vocab_size=50265)). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.
|
56 |
|
57 |
| Feature | Description |
|
58 |
| --- | --- |
|
59 |
| **Name** | `en_core_web_trf` |
|
60 |
+
| **Version** | `3.7.2` |
|
61 |
+
| **spaCy** | `>=3.7.0,<3.8.0` |
|
62 |
| **Default Pipeline** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
63 |
| **Components** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
64 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
|
|
88 |
| `TOKEN_P` | 99.57 |
|
89 |
| `TOKEN_R` | 99.58 |
|
90 |
| `TOKEN_F` | 99.57 |
|
91 |
+
| `TAG_ACC` | 98.16 |
|
92 |
+
| `SENTS_P` | 94.29 |
|
93 |
+
| `SENTS_R` | 83.94 |
|
94 |
+
| `SENTS_F` | 88.81 |
|
95 |
+
| `DEP_UAS` | 95.05 |
|
96 |
+
| `DEP_LAS` | 93.69 |
|
97 |
+
| `ENTS_P` | 89.95 |
|
98 |
+
| `ENTS_R` | 89.86 |
|
99 |
| `ENTS_F` | 89.90 |
|
accuracy.json
CHANGED
@@ -3,328 +3,328 @@
|
|
3 |
"token_p": 0.9956819193,
|
4 |
"token_r": 0.9957659295,
|
5 |
"token_f": 0.9957239226,
|
6 |
-
"tag_acc": 0.
|
7 |
-
"sents_p": 0.
|
8 |
-
"sents_r": 0.
|
9 |
-
"sents_f": 0.
|
10 |
-
"dep_uas": 0.
|
11 |
-
"dep_las": 0.
|
12 |
"dep_las_per_type": {
|
13 |
"prep": {
|
14 |
-
"p": 0.
|
15 |
-
"r": 0.
|
16 |
-
"f": 0.
|
17 |
},
|
18 |
"det": {
|
19 |
-
"p": 0.
|
20 |
-
"r": 0.
|
21 |
-
"f": 0.
|
22 |
},
|
23 |
"pobj": {
|
24 |
-
"p": 0.
|
25 |
-
"r": 0.
|
26 |
-
"f": 0.
|
27 |
},
|
28 |
"nsubj": {
|
29 |
-
"p": 0.
|
30 |
-
"r": 0.
|
31 |
-
"f": 0.
|
32 |
},
|
33 |
"aux": {
|
34 |
-
"p": 0.
|
35 |
-
"r": 0.
|
36 |
-
"f": 0.
|
37 |
},
|
38 |
"advmod": {
|
39 |
-
"p": 0.
|
40 |
-
"r": 0.
|
41 |
-
"f": 0.
|
42 |
},
|
43 |
"relcl": {
|
44 |
-
"p": 0.
|
45 |
-
"r": 0.
|
46 |
-
"f": 0.
|
47 |
},
|
48 |
"root": {
|
49 |
-
"p": 0.
|
50 |
-
"r": 0.
|
51 |
-
"f": 0.
|
52 |
},
|
53 |
"xcomp": {
|
54 |
-
"p": 0.
|
55 |
-
"r": 0.
|
56 |
-
"f": 0.
|
57 |
},
|
58 |
"amod": {
|
59 |
-
"p": 0.
|
60 |
-
"r": 0.
|
61 |
-
"f": 0.
|
62 |
},
|
63 |
"compound": {
|
64 |
-
"p": 0.
|
65 |
-
"r": 0.
|
66 |
-
"f": 0.
|
67 |
},
|
68 |
"poss": {
|
69 |
-
"p": 0.
|
70 |
-
"r": 0.
|
71 |
-
"f": 0.
|
72 |
},
|
73 |
"ccomp": {
|
74 |
-
"p": 0.
|
75 |
-
"r": 0.
|
76 |
-
"f": 0.
|
77 |
},
|
78 |
"attr": {
|
79 |
-
"p": 0.
|
80 |
-
"r": 0.
|
81 |
-
"f": 0.
|
82 |
},
|
83 |
"case": {
|
84 |
-
"p": 0.
|
85 |
-
"r": 0.
|
86 |
-
"f": 0.
|
87 |
},
|
88 |
"mark": {
|
89 |
-
"p": 0.
|
90 |
-
"r": 0.
|
91 |
-
"f": 0.
|
92 |
},
|
93 |
"intj": {
|
94 |
-
"p": 0.
|
95 |
-
"r": 0.
|
96 |
-
"f": 0.
|
97 |
},
|
98 |
"advcl": {
|
99 |
-
"p": 0.
|
100 |
-
"r": 0.
|
101 |
-
"f": 0.
|
102 |
},
|
103 |
"cc": {
|
104 |
-
"p": 0.
|
105 |
-
"r": 0.
|
106 |
-
"f": 0.
|
107 |
},
|
108 |
"neg": {
|
109 |
-
"p": 0.
|
110 |
-
"r": 0.
|
111 |
-
"f": 0.
|
112 |
},
|
113 |
"conj": {
|
114 |
-
"p": 0.
|
115 |
-
"r": 0.
|
116 |
-
"f": 0.
|
117 |
},
|
118 |
"nsubjpass": {
|
119 |
-
"p": 0.
|
120 |
-
"r": 0.
|
121 |
-
"f": 0.
|
122 |
},
|
123 |
"auxpass": {
|
124 |
-
"p": 0.
|
125 |
-
"r": 0.
|
126 |
-
"f": 0.
|
127 |
},
|
128 |
"dobj": {
|
129 |
-
"p": 0.
|
130 |
-
"r": 0.
|
131 |
-
"f": 0.
|
132 |
},
|
133 |
"nummod": {
|
134 |
-
"p": 0.
|
135 |
-
"r": 0.
|
136 |
-
"f": 0.
|
137 |
},
|
138 |
"npadvmod": {
|
139 |
-
"p": 0.
|
140 |
-
"r": 0.
|
141 |
-
"f": 0.
|
142 |
},
|
143 |
"prt": {
|
144 |
-
"p": 0.
|
145 |
-
"r": 0.
|
146 |
-
"f": 0.
|
147 |
},
|
148 |
"pcomp": {
|
149 |
-
"p": 0.
|
150 |
-
"r": 0.
|
151 |
-
"f": 0.
|
152 |
},
|
153 |
"expl": {
|
154 |
-
"p": 0.
|
155 |
"r": 0.9957173448,
|
156 |
-
"f": 0.
|
157 |
},
|
158 |
"acl": {
|
159 |
-
"p": 0.
|
160 |
-
"r": 0.
|
161 |
-
"f": 0.
|
162 |
},
|
163 |
"agent": {
|
164 |
-
"p": 0.
|
165 |
-
"r": 0.
|
166 |
-
"f": 0.
|
167 |
},
|
168 |
"dative": {
|
169 |
-
"p": 0.
|
170 |
-
"r": 0.
|
171 |
-
"f": 0.
|
172 |
},
|
173 |
"acomp": {
|
174 |
-
"p": 0.
|
175 |
-
"r": 0.
|
176 |
-
"f": 0.
|
177 |
},
|
178 |
"dep": {
|
179 |
-
"p": 0.
|
180 |
-
"r": 0.
|
181 |
-
"f": 0.
|
182 |
},
|
183 |
"csubj": {
|
184 |
-
"p": 0.
|
185 |
"r": 0.9053254438,
|
186 |
-
"f": 0.
|
187 |
},
|
188 |
"quantmod": {
|
189 |
-
"p": 0.
|
190 |
-
"r": 0.
|
191 |
-
"f": 0.
|
192 |
},
|
193 |
"nmod": {
|
194 |
-
"p": 0.
|
195 |
-
"r": 0.
|
196 |
-
"f": 0.
|
197 |
},
|
198 |
"appos": {
|
199 |
-
"p": 0.
|
200 |
-
"r": 0.
|
201 |
-
"f": 0.
|
202 |
},
|
203 |
"predet": {
|
204 |
-
"p": 0.
|
205 |
-
"r": 0.
|
206 |
-
"f": 0.
|
207 |
},
|
208 |
"preconj": {
|
209 |
-
"p": 0.
|
210 |
-
"r": 0.
|
211 |
-
"f": 0.
|
212 |
},
|
213 |
"oprd": {
|
214 |
-
"p": 0.
|
215 |
-
"r": 0.
|
216 |
-
"f": 0.
|
217 |
},
|
218 |
"parataxis": {
|
219 |
-
"p": 0.
|
220 |
-
"r": 0.
|
221 |
-
"f": 0.
|
222 |
},
|
223 |
"meta": {
|
224 |
-
"p": 0.
|
225 |
"r": 0.6538461538,
|
226 |
-
"f": 0.
|
227 |
},
|
228 |
"csubjpass": {
|
229 |
-
"p": 0
|
230 |
"r": 0.8333333333,
|
231 |
-
"f": 0.
|
232 |
}
|
233 |
},
|
234 |
-
"ents_p": 0.
|
235 |
-
"ents_r": 0.
|
236 |
-
"ents_f": 0.
|
237 |
"ents_per_type": {
|
238 |
"DATE": {
|
239 |
-
"p": 0.
|
240 |
-
"r": 0.
|
241 |
-
"f": 0.
|
242 |
},
|
243 |
"GPE": {
|
244 |
-
"p": 0.
|
245 |
-
"r": 0.
|
246 |
-
"f": 0.
|
247 |
},
|
248 |
"ORDINAL": {
|
249 |
-
"p": 0.
|
250 |
-
"r": 0.
|
251 |
-
"f": 0.
|
252 |
},
|
253 |
"ORG": {
|
254 |
-
"p": 0.
|
255 |
-
"r": 0.
|
256 |
-
"f": 0.
|
257 |
},
|
258 |
"FAC": {
|
259 |
-
"p": 0.
|
260 |
-
"r": 0.
|
261 |
-
"f": 0.
|
262 |
},
|
263 |
"QUANTITY": {
|
264 |
-
"p": 0.
|
265 |
-
"r": 0.
|
266 |
-
"f": 0.
|
267 |
},
|
268 |
"LOC": {
|
269 |
-
"p": 0.
|
270 |
-
"r": 0.
|
271 |
-
"f": 0.
|
272 |
},
|
273 |
"CARDINAL": {
|
274 |
-
"p": 0.
|
275 |
-
"r": 0.
|
276 |
-
"f": 0.
|
277 |
},
|
278 |
"PERSON": {
|
279 |
-
"p": 0.
|
280 |
-
"r": 0.
|
281 |
-
"f": 0.
|
282 |
},
|
283 |
"NORP": {
|
284 |
-
"p": 0.
|
285 |
-
"r": 0.
|
286 |
-
"f": 0.
|
287 |
},
|
288 |
"LAW": {
|
289 |
-
"p": 0.
|
290 |
"r": 0.609375,
|
291 |
-
"f": 0.
|
292 |
-
},
|
293 |
-
"MONEY": {
|
294 |
-
"p": 0.9325153374,
|
295 |
-
"r": 0.8972845336,
|
296 |
-
"f": 0.9145607702
|
297 |
},
|
298 |
"TIME": {
|
299 |
-
"p": 0.
|
300 |
-
"r": 0.
|
301 |
-
"f": 0.
|
302 |
},
|
303 |
"EVENT": {
|
304 |
-
"p": 0.
|
305 |
-
"r": 0.
|
306 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
307 |
},
|
308 |
"WORK_OF_ART": {
|
309 |
-
"p": 0.
|
310 |
-
"r": 0.
|
311 |
-
"f": 0.
|
312 |
},
|
313 |
-
"
|
314 |
-
"p": 0.
|
315 |
-
"r": 0.
|
316 |
-
"f": 0.
|
317 |
},
|
318 |
-
"
|
319 |
-
"p": 0.
|
320 |
-
"r": 0.
|
321 |
-
"f": 0.
|
322 |
},
|
323 |
"LANGUAGE": {
|
324 |
-
"p": 0.
|
325 |
-
"r": 0.
|
326 |
-
"f": 0.
|
327 |
}
|
328 |
},
|
329 |
-
"speed":
|
330 |
}
|
|
|
3 |
"token_p": 0.9956819193,
|
4 |
"token_r": 0.9957659295,
|
5 |
"token_f": 0.9957239226,
|
6 |
+
"tag_acc": 0.9815755741,
|
7 |
+
"sents_p": 0.9428677288,
|
8 |
+
"sents_r": 0.8393693515,
|
9 |
+
"sents_f": 0.8881133524,
|
10 |
+
"dep_uas": 0.9505463996,
|
11 |
+
"dep_las": 0.9368643771,
|
12 |
"dep_las_per_type": {
|
13 |
"prep": {
|
14 |
+
"p": 0.9213844814,
|
15 |
+
"r": 0.9232024284,
|
16 |
+
"f": 0.922292559
|
17 |
},
|
18 |
"det": {
|
19 |
+
"p": 0.9907293964,
|
20 |
+
"r": 0.9891135937,
|
21 |
+
"f": 0.9899208357
|
22 |
},
|
23 |
"pobj": {
|
24 |
+
"p": 0.9835255354,
|
25 |
+
"r": 0.984645592,
|
26 |
+
"f": 0.984085245
|
27 |
},
|
28 |
"nsubj": {
|
29 |
+
"p": 0.9810607725,
|
30 |
+
"r": 0.9781380066,
|
31 |
+
"f": 0.9795972094
|
32 |
},
|
33 |
"aux": {
|
34 |
+
"p": 0.9886879843,
|
35 |
+
"r": 0.9881598861,
|
36 |
+
"f": 0.9884238646
|
37 |
},
|
38 |
"advmod": {
|
39 |
+
"p": 0.8934343434,
|
40 |
+
"r": 0.8929833417,
|
41 |
+
"f": 0.8932087857
|
42 |
},
|
43 |
"relcl": {
|
44 |
+
"p": 0.8716783217,
|
45 |
+
"r": 0.9045718433,
|
46 |
+
"f": 0.8878205128
|
47 |
},
|
48 |
"root": {
|
49 |
+
"p": 0.9662097073,
|
50 |
+
"r": 0.8601490864,
|
51 |
+
"f": 0.9100998115
|
52 |
},
|
53 |
"xcomp": {
|
54 |
+
"p": 0.9495982469,
|
55 |
+
"r": 0.9332376167,
|
56 |
+
"f": 0.9413468501
|
57 |
},
|
58 |
"amod": {
|
59 |
+
"p": 0.945387166,
|
60 |
+
"r": 0.942079689,
|
61 |
+
"f": 0.9437305296
|
62 |
},
|
63 |
"compound": {
|
64 |
+
"p": 0.9498658618,
|
65 |
+
"r": 0.9464802851,
|
66 |
+
"f": 0.9481700513
|
67 |
},
|
68 |
"poss": {
|
69 |
+
"p": 0.9851375778,
|
70 |
+
"r": 0.9873188406,
|
71 |
+
"f": 0.9862270031
|
72 |
},
|
73 |
"ccomp": {
|
74 |
+
"p": 0.8387701537,
|
75 |
+
"r": 0.9112016293,
|
76 |
+
"f": 0.8734869192
|
77 |
},
|
78 |
"attr": {
|
79 |
+
"p": 0.9384928717,
|
80 |
+
"r": 0.968881413,
|
81 |
+
"f": 0.9534450652
|
82 |
},
|
83 |
"case": {
|
84 |
+
"p": 0.9860904123,
|
85 |
+
"r": 0.9934934935,
|
86 |
+
"f": 0.9897781102
|
87 |
},
|
88 |
"mark": {
|
89 |
+
"p": 0.9469537815,
|
90 |
+
"r": 0.9554848967,
|
91 |
+
"f": 0.951200211
|
92 |
},
|
93 |
"intj": {
|
94 |
+
"p": 0.5938967136,
|
95 |
+
"r": 0.7413919414,
|
96 |
+
"f": 0.6594982079
|
97 |
},
|
98 |
"advcl": {
|
99 |
+
"p": 0.7986680328,
|
100 |
+
"r": 0.7851926467,
|
101 |
+
"f": 0.7918730159
|
102 |
},
|
103 |
"cc": {
|
104 |
+
"p": 0.8966257303,
|
105 |
+
"r": 0.8994139457,
|
106 |
+
"f": 0.8980176738
|
107 |
},
|
108 |
"neg": {
|
109 |
+
"p": 0.9603214465,
|
110 |
+
"r": 0.9593577521,
|
111 |
+
"f": 0.9598393574
|
112 |
},
|
113 |
"conj": {
|
114 |
+
"p": 0.8554216867,
|
115 |
+
"r": 0.9116314199,
|
116 |
+
"f": 0.8826325411
|
117 |
},
|
118 |
"nsubjpass": {
|
119 |
+
"p": 0.9484588176,
|
120 |
+
"r": 0.9625641026,
|
121 |
+
"f": 0.9554594044
|
122 |
},
|
123 |
"auxpass": {
|
124 |
+
"p": 0.9582407819,
|
125 |
+
"r": 0.9826879271,
|
126 |
+
"f": 0.9703103914
|
127 |
},
|
128 |
"dobj": {
|
129 |
+
"p": 0.9704970179,
|
130 |
+
"r": 0.9725077695,
|
131 |
+
"f": 0.9715013533
|
132 |
},
|
133 |
"nummod": {
|
134 |
+
"p": 0.9509357613,
|
135 |
+
"r": 0.9494949495,
|
136 |
+
"f": 0.9502148092
|
137 |
},
|
138 |
"npadvmod": {
|
139 |
+
"p": 0.8354978355,
|
140 |
+
"r": 0.8227353464,
|
141 |
+
"f": 0.8290674781
|
142 |
},
|
143 |
"prt": {
|
144 |
+
"p": 0.8928884987,
|
145 |
+
"r": 0.9112903226,
|
146 |
+
"f": 0.9019955654
|
147 |
},
|
148 |
"pcomp": {
|
149 |
+
"p": 0.9309372798,
|
150 |
+
"r": 0.925070028,
|
151 |
+
"f": 0.92799438
|
152 |
},
|
153 |
"expl": {
|
154 |
+
"p": 0.9914712154,
|
155 |
"r": 0.9957173448,
|
156 |
+
"f": 0.9935897436
|
157 |
},
|
158 |
"acl": {
|
159 |
+
"p": 0.8481012658,
|
160 |
+
"r": 0.8406983088,
|
161 |
+
"f": 0.8443835616
|
162 |
},
|
163 |
"agent": {
|
164 |
+
"p": 0.9577464789,
|
165 |
+
"r": 0.9749103943,
|
166 |
+
"f": 0.9662522202
|
167 |
},
|
168 |
"dative": {
|
169 |
+
"p": 0.8218262806,
|
170 |
+
"r": 0.8463302752,
|
171 |
+
"f": 0.8338983051
|
172 |
},
|
173 |
"acomp": {
|
174 |
+
"p": 0.9484440316,
|
175 |
+
"r": 0.9260770975,
|
176 |
+
"f": 0.9371271225
|
177 |
},
|
178 |
"dep": {
|
179 |
+
"p": 0.4476744186,
|
180 |
+
"r": 0.375,
|
181 |
+
"f": 0.4081272085
|
182 |
},
|
183 |
"csubj": {
|
184 |
+
"p": 0.9,
|
185 |
"r": 0.9053254438,
|
186 |
+
"f": 0.9026548673
|
187 |
},
|
188 |
"quantmod": {
|
189 |
+
"p": 0.8608624898,
|
190 |
+
"r": 0.8594638505,
|
191 |
+
"f": 0.8601626016
|
192 |
},
|
193 |
"nmod": {
|
194 |
+
"p": 0.818815331,
|
195 |
+
"r": 0.7160268129,
|
196 |
+
"f": 0.7639791938
|
197 |
},
|
198 |
"appos": {
|
199 |
+
"p": 0.781092437,
|
200 |
+
"r": 0.8065075922,
|
201 |
+
"f": 0.7935965848
|
202 |
},
|
203 |
"predet": {
|
204 |
+
"p": 0.8464566929,
|
205 |
+
"r": 0.9227467811,
|
206 |
+
"f": 0.8829568789
|
207 |
},
|
208 |
"preconj": {
|
209 |
+
"p": 0.6703296703,
|
210 |
+
"r": 0.7093023256,
|
211 |
+
"f": 0.6892655367
|
212 |
},
|
213 |
"oprd": {
|
214 |
+
"p": 0.8711656442,
|
215 |
+
"r": 0.847761194,
|
216 |
+
"f": 0.8593040847
|
217 |
},
|
218 |
"parataxis": {
|
219 |
+
"p": 0.5409836066,
|
220 |
+
"r": 0.6442516269,
|
221 |
+
"f": 0.5881188119
|
222 |
},
|
223 |
"meta": {
|
224 |
+
"p": 0.3063063063,
|
225 |
"r": 0.6538461538,
|
226 |
+
"f": 0.4171779141
|
227 |
},
|
228 |
"csubjpass": {
|
229 |
+
"p": 1.0,
|
230 |
"r": 0.8333333333,
|
231 |
+
"f": 0.9090909091
|
232 |
}
|
233 |
},
|
234 |
+
"ents_p": 0.8994886705,
|
235 |
+
"ents_r": 0.8985877404,
|
236 |
+
"ents_f": 0.8990379798,
|
237 |
"ents_per_type": {
|
238 |
"DATE": {
|
239 |
+
"p": 0.8913798548,
|
240 |
+
"r": 0.8961904762,
|
241 |
+
"f": 0.8937786924
|
242 |
},
|
243 |
"GPE": {
|
244 |
+
"p": 0.9586402266,
|
245 |
+
"r": 0.9439330544,
|
246 |
+
"f": 0.9512297962
|
247 |
},
|
248 |
"ORDINAL": {
|
249 |
+
"p": 0.8011869436,
|
250 |
+
"r": 0.8385093168,
|
251 |
+
"f": 0.8194233687
|
252 |
},
|
253 |
"ORG": {
|
254 |
+
"p": 0.9049542272,
|
255 |
+
"r": 0.8910392365,
|
256 |
+
"f": 0.8979428266
|
257 |
},
|
258 |
"FAC": {
|
259 |
+
"p": 0.6049382716,
|
260 |
+
"r": 0.7538461538,
|
261 |
+
"f": 0.6712328767
|
262 |
},
|
263 |
"QUANTITY": {
|
264 |
+
"p": 0.7831325301,
|
265 |
+
"r": 0.7142857143,
|
266 |
+
"f": 0.7471264368
|
267 |
},
|
268 |
"LOC": {
|
269 |
+
"p": 0.8184615385,
|
270 |
+
"r": 0.847133758,
|
271 |
+
"f": 0.8325508607
|
272 |
},
|
273 |
"CARDINAL": {
|
274 |
+
"p": 0.8476517755,
|
275 |
+
"r": 0.8799048751,
|
276 |
+
"f": 0.8634772462
|
277 |
},
|
278 |
"PERSON": {
|
279 |
+
"p": 0.9409898477,
|
280 |
+
"r": 0.9680156658,
|
281 |
+
"f": 0.9543114543
|
282 |
},
|
283 |
"NORP": {
|
284 |
+
"p": 0.9311183144,
|
285 |
+
"r": 0.9192,
|
286 |
+
"f": 0.9251207729
|
287 |
},
|
288 |
"LAW": {
|
289 |
+
"p": 0.527027027,
|
290 |
"r": 0.609375,
|
291 |
+
"f": 0.5652173913
|
|
|
|
|
|
|
|
|
|
|
292 |
},
|
293 |
"TIME": {
|
294 |
+
"p": 0.7458100559,
|
295 |
+
"r": 0.7807017544,
|
296 |
+
"f": 0.7628571429
|
297 |
},
|
298 |
"EVENT": {
|
299 |
+
"p": 0.7407407407,
|
300 |
+
"r": 0.5747126437,
|
301 |
+
"f": 0.6472491909
|
302 |
+
},
|
303 |
+
"PRODUCT": {
|
304 |
+
"p": 0.6310160428,
|
305 |
+
"r": 0.5592417062,
|
306 |
+
"f": 0.5929648241
|
307 |
},
|
308 |
"WORK_OF_ART": {
|
309 |
+
"p": 0.6534090909,
|
310 |
+
"r": 0.5927835052,
|
311 |
+
"f": 0.6216216216
|
312 |
},
|
313 |
+
"MONEY": {
|
314 |
+
"p": 0.9356796117,
|
315 |
+
"r": 0.9102715466,
|
316 |
+
"f": 0.9228007181
|
317 |
},
|
318 |
+
"PERCENT": {
|
319 |
+
"p": 0.9146919431,
|
320 |
+
"r": 0.886676876,
|
321 |
+
"f": 0.900466563
|
322 |
},
|
323 |
"LANGUAGE": {
|
324 |
+
"p": 0.9642857143,
|
325 |
+
"r": 0.84375,
|
326 |
+
"f": 0.9
|
327 |
}
|
328 |
},
|
329 |
+
"speed": 3882.7148648089
|
330 |
}
|
attribute_ruler/patterns
CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
|
|
config.cfg
CHANGED
@@ -17,6 +17,7 @@ after_creation = null
|
|
17 |
after_pipeline_creation = null
|
18 |
batch_size = 64
|
19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
|
|
20 |
|
21 |
[components]
|
22 |
|
@@ -49,10 +50,11 @@ use_upper = false
|
|
49 |
nO = null
|
50 |
|
51 |
[components.ner.model.tok2vec]
|
52 |
-
@architectures = "spacy-transformers.
|
53 |
-
|
54 |
upstream = "transformer"
|
55 |
pooling = {"@layers":"reduce_mean.v1"}
|
|
|
56 |
|
57 |
[components.parser]
|
58 |
factory = "parser"
|
@@ -72,10 +74,11 @@ use_upper = false
|
|
72 |
nO = null
|
73 |
|
74 |
[components.parser.model.tok2vec]
|
75 |
-
@architectures = "spacy-transformers.
|
76 |
-
|
77 |
upstream = "transformer"
|
78 |
pooling = {"@layers":"reduce_mean.v1"}
|
|
|
79 |
|
80 |
[components.tagger]
|
81 |
factory = "tagger"
|
@@ -90,32 +93,44 @@ nO = null
|
|
90 |
normalize = false
|
91 |
|
92 |
[components.tagger.model.tok2vec]
|
93 |
-
@architectures = "spacy-transformers.
|
94 |
-
|
95 |
upstream = "transformer"
|
96 |
pooling = {"@layers":"reduce_mean.v1"}
|
|
|
97 |
|
98 |
[components.transformer]
|
99 |
-
factory = "
|
100 |
-
|
101 |
-
|
102 |
|
103 |
[components.transformer.model]
|
104 |
-
|
105 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
mixed_precision = false
|
107 |
-
|
108 |
-
[components.transformer.model.get_spans]
|
109 |
-
@span_getters = "spacy-transformers.strided_spans.v1"
|
110 |
-
window = 128
|
111 |
-
stride = 96
|
112 |
|
113 |
[components.transformer.model.grad_scaler_config]
|
114 |
|
115 |
-
[components.transformer.model.
|
116 |
-
|
117 |
-
|
118 |
-
|
|
|
119 |
|
120 |
[corpora]
|
121 |
|
@@ -152,11 +167,11 @@ annotating_components = []
|
|
152 |
before_update = null
|
153 |
|
154 |
[training.batcher]
|
155 |
-
@batchers = "spacy.
|
156 |
-
discard_oversize =
|
157 |
-
get_length = null
|
158 |
size = 2000
|
159 |
-
|
|
|
160 |
|
161 |
[training.logger]
|
162 |
@loggers = "spacy.ConsoleLogger.v1"
|
@@ -225,6 +240,18 @@ require = false
|
|
225 |
path = "corpus/labels/tagger.json"
|
226 |
require = false
|
227 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
228 |
[initialize.lookups]
|
229 |
@misc = "spacy.LookupsDataLoader.v1"
|
230 |
lang = ${nlp.lang}
|
|
|
17 |
after_pipeline_creation = null
|
18 |
batch_size = 64
|
19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
20 |
+
vectors = {"@vectors":"spacy.Vectors.v1"}
|
21 |
|
22 |
[components]
|
23 |
|
|
|
50 |
nO = null
|
51 |
|
52 |
[components.ner.model.tok2vec]
|
53 |
+
@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
|
54 |
+
width = ${components.transformer.model.hidden_width}
|
55 |
upstream = "transformer"
|
56 |
pooling = {"@layers":"reduce_mean.v1"}
|
57 |
+
grad_factor = 1.0
|
58 |
|
59 |
[components.parser]
|
60 |
factory = "parser"
|
|
|
74 |
nO = null
|
75 |
|
76 |
[components.parser.model.tok2vec]
|
77 |
+
@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
|
78 |
+
width = ${components.transformer.model.hidden_width}
|
79 |
upstream = "transformer"
|
80 |
pooling = {"@layers":"reduce_mean.v1"}
|
81 |
+
grad_factor = 1.0
|
82 |
|
83 |
[components.tagger]
|
84 |
factory = "tagger"
|
|
|
93 |
normalize = false
|
94 |
|
95 |
[components.tagger.model.tok2vec]
|
96 |
+
@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
|
97 |
+
width = ${components.transformer.model.hidden_width}
|
98 |
upstream = "transformer"
|
99 |
pooling = {"@layers":"reduce_mean.v1"}
|
100 |
+
grad_factor = 1.0
|
101 |
|
102 |
[components.transformer]
|
103 |
+
factory = "curated_transformer"
|
104 |
+
all_layer_outputs = false
|
105 |
+
frozen = false
|
106 |
|
107 |
[components.transformer.model]
|
108 |
+
@architectures = "spacy-curated-transformers.RobertaTransformer.v1"
|
109 |
+
vocab_size = 50265
|
110 |
+
hidden_width = 768
|
111 |
+
piece_encoder = {"@architectures":"spacy-curated-transformers.ByteBpeEncoder.v1"}
|
112 |
+
attention_probs_dropout_prob = 0.1
|
113 |
+
hidden_act = "gelu"
|
114 |
+
hidden_dropout_prob = 0.1
|
115 |
+
intermediate_width = 3072
|
116 |
+
layer_norm_eps = 0.00001
|
117 |
+
max_position_embeddings = 514
|
118 |
+
model_max_length = 512
|
119 |
+
num_attention_heads = 12
|
120 |
+
num_hidden_layers = 12
|
121 |
+
padding_idx = 1
|
122 |
+
type_vocab_size = 1
|
123 |
+
torchscript = false
|
124 |
mixed_precision = false
|
125 |
+
wrapped_listener = null
|
|
|
|
|
|
|
|
|
126 |
|
127 |
[components.transformer.model.grad_scaler_config]
|
128 |
|
129 |
+
[components.transformer.model.with_spans]
|
130 |
+
@architectures = "spacy-curated-transformers.WithStridedSpans.v1"
|
131 |
+
stride = 104
|
132 |
+
window = 144
|
133 |
+
batch_size = 384
|
134 |
|
135 |
[corpora]
|
136 |
|
|
|
167 |
before_update = null
|
168 |
|
169 |
[training.batcher]
|
170 |
+
@batchers = "spacy.batch_by_words.v1"
|
171 |
+
discard_oversize = false
|
|
|
172 |
size = 2000
|
173 |
+
tolerance = 0.2
|
174 |
+
get_length = null
|
175 |
|
176 |
[training.logger]
|
177 |
@loggers = "spacy.ConsoleLogger.v1"
|
|
|
240 |
path = "corpus/labels/tagger.json"
|
241 |
require = false
|
242 |
|
243 |
+
[initialize.components.transformer]
|
244 |
+
|
245 |
+
[initialize.components.transformer.encoder_loader]
|
246 |
+
@model_loaders = "spacy-curated-transformers.HFTransformerEncoderLoader.v1"
|
247 |
+
name = "roberta-base"
|
248 |
+
revision = "main"
|
249 |
+
|
250 |
+
[initialize.components.transformer.piecer_loader]
|
251 |
+
@model_loaders = "spacy-curated-transformers.HFPieceEncoderLoader.v1"
|
252 |
+
name = "roberta-base"
|
253 |
+
revision = "main"
|
254 |
+
|
255 |
[initialize.lookups]
|
256 |
@misc = "spacy.LookupsDataLoader.v1"
|
257 |
lang = ${nlp.lang}
|
en_core_web_trf-any-py3-none-any.whl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd56d80640411c2e81c3b0cfcb6068156a459c259ae11a4ea51c625c751e3e0a
|
3 |
+
size 457388473
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"en",
|
3 |
"name":"core_web_trf",
|
4 |
-
"version":"3.
|
5 |
-
"description":"English transformer pipeline (roberta-base). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.",
|
6 |
"author":"Explosion",
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"MIT",
|
10 |
-
"spacy_version":">=3.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
@@ -168,330 +168,330 @@
|
|
168 |
"token_p":0.9956819193,
|
169 |
"token_r":0.9957659295,
|
170 |
"token_f":0.9957239226,
|
171 |
-
"tag_acc":0.
|
172 |
-
"sents_p":0.
|
173 |
-
"sents_r":0.
|
174 |
-
"sents_f":0.
|
175 |
-
"dep_uas":0.
|
176 |
-
"dep_las":0.
|
177 |
"dep_las_per_type":{
|
178 |
"prep":{
|
179 |
-
"p":0.
|
180 |
-
"r":0.
|
181 |
-
"f":0.
|
182 |
},
|
183 |
"det":{
|
184 |
-
"p":0.
|
185 |
-
"r":0.
|
186 |
-
"f":0.
|
187 |
},
|
188 |
"pobj":{
|
189 |
-
"p":0.
|
190 |
-
"r":0.
|
191 |
-
"f":0.
|
192 |
},
|
193 |
"nsubj":{
|
194 |
-
"p":0.
|
195 |
-
"r":0.
|
196 |
-
"f":0.
|
197 |
},
|
198 |
"aux":{
|
199 |
-
"p":0.
|
200 |
-
"r":0.
|
201 |
-
"f":0.
|
202 |
},
|
203 |
"advmod":{
|
204 |
-
"p":0.
|
205 |
-
"r":0.
|
206 |
-
"f":0.
|
207 |
},
|
208 |
"relcl":{
|
209 |
-
"p":0.
|
210 |
-
"r":0.
|
211 |
-
"f":0.
|
212 |
},
|
213 |
"root":{
|
214 |
-
"p":0.
|
215 |
-
"r":0.
|
216 |
-
"f":0.
|
217 |
},
|
218 |
"xcomp":{
|
219 |
-
"p":0.
|
220 |
-
"r":0.
|
221 |
-
"f":0.
|
222 |
},
|
223 |
"amod":{
|
224 |
-
"p":0.
|
225 |
-
"r":0.
|
226 |
-
"f":0.
|
227 |
},
|
228 |
"compound":{
|
229 |
-
"p":0.
|
230 |
-
"r":0.
|
231 |
-
"f":0.
|
232 |
},
|
233 |
"poss":{
|
234 |
-
"p":0.
|
235 |
-
"r":0.
|
236 |
-
"f":0.
|
237 |
},
|
238 |
"ccomp":{
|
239 |
-
"p":0.
|
240 |
-
"r":0.
|
241 |
-
"f":0.
|
242 |
},
|
243 |
"attr":{
|
244 |
-
"p":0.
|
245 |
-
"r":0.
|
246 |
-
"f":0.
|
247 |
},
|
248 |
"case":{
|
249 |
-
"p":0.
|
250 |
-
"r":0.
|
251 |
-
"f":0.
|
252 |
},
|
253 |
"mark":{
|
254 |
-
"p":0.
|
255 |
-
"r":0.
|
256 |
-
"f":0.
|
257 |
},
|
258 |
"intj":{
|
259 |
-
"p":0.
|
260 |
-
"r":0.
|
261 |
-
"f":0.
|
262 |
},
|
263 |
"advcl":{
|
264 |
-
"p":0.
|
265 |
-
"r":0.
|
266 |
-
"f":0.
|
267 |
},
|
268 |
"cc":{
|
269 |
-
"p":0.
|
270 |
-
"r":0.
|
271 |
-
"f":0.
|
272 |
},
|
273 |
"neg":{
|
274 |
-
"p":0.
|
275 |
-
"r":0.
|
276 |
-
"f":0.
|
277 |
},
|
278 |
"conj":{
|
279 |
-
"p":0.
|
280 |
-
"r":0.
|
281 |
-
"f":0.
|
282 |
},
|
283 |
"nsubjpass":{
|
284 |
-
"p":0.
|
285 |
-
"r":0.
|
286 |
-
"f":0.
|
287 |
},
|
288 |
"auxpass":{
|
289 |
-
"p":0.
|
290 |
-
"r":0.
|
291 |
-
"f":0.
|
292 |
},
|
293 |
"dobj":{
|
294 |
-
"p":0.
|
295 |
-
"r":0.
|
296 |
-
"f":0.
|
297 |
},
|
298 |
"nummod":{
|
299 |
-
"p":0.
|
300 |
-
"r":0.
|
301 |
-
"f":0.
|
302 |
},
|
303 |
"npadvmod":{
|
304 |
-
"p":0.
|
305 |
-
"r":0.
|
306 |
-
"f":0.
|
307 |
},
|
308 |
"prt":{
|
309 |
-
"p":0.
|
310 |
-
"r":0.
|
311 |
-
"f":0.
|
312 |
},
|
313 |
"pcomp":{
|
314 |
-
"p":0.
|
315 |
-
"r":0.
|
316 |
-
"f":0.
|
317 |
},
|
318 |
"expl":{
|
319 |
-
"p":0.
|
320 |
"r":0.9957173448,
|
321 |
-
"f":0.
|
322 |
},
|
323 |
"acl":{
|
324 |
-
"p":0.
|
325 |
-
"r":0.
|
326 |
-
"f":0.
|
327 |
},
|
328 |
"agent":{
|
329 |
-
"p":0.
|
330 |
-
"r":0.
|
331 |
-
"f":0.
|
332 |
},
|
333 |
"dative":{
|
334 |
-
"p":0.
|
335 |
-
"r":0.
|
336 |
-
"f":0.
|
337 |
},
|
338 |
"acomp":{
|
339 |
-
"p":0.
|
340 |
-
"r":0.
|
341 |
-
"f":0.
|
342 |
},
|
343 |
"dep":{
|
344 |
-
"p":0.
|
345 |
-
"r":0.
|
346 |
-
"f":0.
|
347 |
},
|
348 |
"csubj":{
|
349 |
-
"p":0.
|
350 |
"r":0.9053254438,
|
351 |
-
"f":0.
|
352 |
},
|
353 |
"quantmod":{
|
354 |
-
"p":0.
|
355 |
-
"r":0.
|
356 |
-
"f":0.
|
357 |
},
|
358 |
"nmod":{
|
359 |
-
"p":0.
|
360 |
-
"r":0.
|
361 |
-
"f":0.
|
362 |
},
|
363 |
"appos":{
|
364 |
-
"p":0.
|
365 |
-
"r":0.
|
366 |
-
"f":0.
|
367 |
},
|
368 |
"predet":{
|
369 |
-
"p":0.
|
370 |
-
"r":0.
|
371 |
-
"f":0.
|
372 |
},
|
373 |
"preconj":{
|
374 |
-
"p":0.
|
375 |
-
"r":0.
|
376 |
-
"f":0.
|
377 |
},
|
378 |
"oprd":{
|
379 |
-
"p":0.
|
380 |
-
"r":0.
|
381 |
-
"f":0.
|
382 |
},
|
383 |
"parataxis":{
|
384 |
-
"p":0.
|
385 |
-
"r":0.
|
386 |
-
"f":0.
|
387 |
},
|
388 |
"meta":{
|
389 |
-
"p":0.
|
390 |
"r":0.6538461538,
|
391 |
-
"f":0.
|
392 |
},
|
393 |
"csubjpass":{
|
394 |
-
"p":0
|
395 |
"r":0.8333333333,
|
396 |
-
"f":0.
|
397 |
}
|
398 |
},
|
399 |
-
"ents_p":0.
|
400 |
-
"ents_r":0.
|
401 |
-
"ents_f":0.
|
402 |
"ents_per_type":{
|
403 |
"DATE":{
|
404 |
-
"p":0.
|
405 |
-
"r":0.
|
406 |
-
"f":0.
|
407 |
},
|
408 |
"GPE":{
|
409 |
-
"p":0.
|
410 |
-
"r":0.
|
411 |
-
"f":0.
|
412 |
},
|
413 |
"ORDINAL":{
|
414 |
-
"p":0.
|
415 |
-
"r":0.
|
416 |
-
"f":0.
|
417 |
},
|
418 |
"ORG":{
|
419 |
-
"p":0.
|
420 |
-
"r":0.
|
421 |
-
"f":0.
|
422 |
},
|
423 |
"FAC":{
|
424 |
-
"p":0.
|
425 |
-
"r":0.
|
426 |
-
"f":0.
|
427 |
},
|
428 |
"QUANTITY":{
|
429 |
-
"p":0.
|
430 |
-
"r":0.
|
431 |
-
"f":0.
|
432 |
},
|
433 |
"LOC":{
|
434 |
-
"p":0.
|
435 |
-
"r":0.
|
436 |
-
"f":0.
|
437 |
},
|
438 |
"CARDINAL":{
|
439 |
-
"p":0.
|
440 |
-
"r":0.
|
441 |
-
"f":0.
|
442 |
},
|
443 |
"PERSON":{
|
444 |
-
"p":0.
|
445 |
-
"r":0.
|
446 |
-
"f":0.
|
447 |
},
|
448 |
"NORP":{
|
449 |
-
"p":0.
|
450 |
-
"r":0.
|
451 |
-
"f":0.
|
452 |
},
|
453 |
"LAW":{
|
454 |
-
"p":0.
|
455 |
"r":0.609375,
|
456 |
-
"f":0.
|
457 |
-
},
|
458 |
-
"MONEY":{
|
459 |
-
"p":0.9325153374,
|
460 |
-
"r":0.8972845336,
|
461 |
-
"f":0.9145607702
|
462 |
},
|
463 |
"TIME":{
|
464 |
-
"p":0.
|
465 |
-
"r":0.
|
466 |
-
"f":0.
|
467 |
},
|
468 |
"EVENT":{
|
469 |
-
"p":0.
|
470 |
-
"r":0.
|
471 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
472 |
},
|
473 |
"WORK_OF_ART":{
|
474 |
-
"p":0.
|
475 |
-
"r":0.
|
476 |
-
"f":0.
|
477 |
},
|
478 |
-
"
|
479 |
-
"p":0.
|
480 |
-
"r":0.
|
481 |
-
"f":0.
|
482 |
},
|
483 |
-
"
|
484 |
-
"p":0.
|
485 |
-
"r":0.
|
486 |
-
"f":0.
|
487 |
},
|
488 |
"LANGUAGE":{
|
489 |
-
"p":0.
|
490 |
-
"r":0.
|
491 |
-
"f":0.
|
492 |
}
|
493 |
},
|
494 |
-
"speed":
|
495 |
},
|
496 |
"sources":[
|
497 |
{
|
@@ -520,6 +520,6 @@
|
|
520 |
}
|
521 |
],
|
522 |
"requirements":[
|
523 |
-
"spacy-transformers>=
|
524 |
]
|
525 |
}
|
|
|
1 |
{
|
2 |
"lang":"en",
|
3 |
"name":"core_web_trf",
|
4 |
+
"version":"3.7.2",
|
5 |
+
"description":"English transformer pipeline (Transformer(name='roberta-base', piece_encoder='byte-bpe', stride=104, type='roberta', width=768, window=144, vocab_size=50265)). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.",
|
6 |
"author":"Explosion",
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"MIT",
|
10 |
+
"spacy_version":">=3.7.0,<3.8.0",
|
11 |
+
"spacy_git_version":"6b4f77441",
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
|
|
168 |
"token_p":0.9956819193,
|
169 |
"token_r":0.9957659295,
|
170 |
"token_f":0.9957239226,
|
171 |
+
"tag_acc":0.9815755741,
|
172 |
+
"sents_p":0.9428677288,
|
173 |
+
"sents_r":0.8393693515,
|
174 |
+
"sents_f":0.8881133524,
|
175 |
+
"dep_uas":0.9505463996,
|
176 |
+
"dep_las":0.9368643771,
|
177 |
"dep_las_per_type":{
|
178 |
"prep":{
|
179 |
+
"p":0.9213844814,
|
180 |
+
"r":0.9232024284,
|
181 |
+
"f":0.922292559
|
182 |
},
|
183 |
"det":{
|
184 |
+
"p":0.9907293964,
|
185 |
+
"r":0.9891135937,
|
186 |
+
"f":0.9899208357
|
187 |
},
|
188 |
"pobj":{
|
189 |
+
"p":0.9835255354,
|
190 |
+
"r":0.984645592,
|
191 |
+
"f":0.984085245
|
192 |
},
|
193 |
"nsubj":{
|
194 |
+
"p":0.9810607725,
|
195 |
+
"r":0.9781380066,
|
196 |
+
"f":0.9795972094
|
197 |
},
|
198 |
"aux":{
|
199 |
+
"p":0.9886879843,
|
200 |
+
"r":0.9881598861,
|
201 |
+
"f":0.9884238646
|
202 |
},
|
203 |
"advmod":{
|
204 |
+
"p":0.8934343434,
|
205 |
+
"r":0.8929833417,
|
206 |
+
"f":0.8932087857
|
207 |
},
|
208 |
"relcl":{
|
209 |
+
"p":0.8716783217,
|
210 |
+
"r":0.9045718433,
|
211 |
+
"f":0.8878205128
|
212 |
},
|
213 |
"root":{
|
214 |
+
"p":0.9662097073,
|
215 |
+
"r":0.8601490864,
|
216 |
+
"f":0.9100998115
|
217 |
},
|
218 |
"xcomp":{
|
219 |
+
"p":0.9495982469,
|
220 |
+
"r":0.9332376167,
|
221 |
+
"f":0.9413468501
|
222 |
},
|
223 |
"amod":{
|
224 |
+
"p":0.945387166,
|
225 |
+
"r":0.942079689,
|
226 |
+
"f":0.9437305296
|
227 |
},
|
228 |
"compound":{
|
229 |
+
"p":0.9498658618,
|
230 |
+
"r":0.9464802851,
|
231 |
+
"f":0.9481700513
|
232 |
},
|
233 |
"poss":{
|
234 |
+
"p":0.9851375778,
|
235 |
+
"r":0.9873188406,
|
236 |
+
"f":0.9862270031
|
237 |
},
|
238 |
"ccomp":{
|
239 |
+
"p":0.8387701537,
|
240 |
+
"r":0.9112016293,
|
241 |
+
"f":0.8734869192
|
242 |
},
|
243 |
"attr":{
|
244 |
+
"p":0.9384928717,
|
245 |
+
"r":0.968881413,
|
246 |
+
"f":0.9534450652
|
247 |
},
|
248 |
"case":{
|
249 |
+
"p":0.9860904123,
|
250 |
+
"r":0.9934934935,
|
251 |
+
"f":0.9897781102
|
252 |
},
|
253 |
"mark":{
|
254 |
+
"p":0.9469537815,
|
255 |
+
"r":0.9554848967,
|
256 |
+
"f":0.951200211
|
257 |
},
|
258 |
"intj":{
|
259 |
+
"p":0.5938967136,
|
260 |
+
"r":0.7413919414,
|
261 |
+
"f":0.6594982079
|
262 |
},
|
263 |
"advcl":{
|
264 |
+
"p":0.7986680328,
|
265 |
+
"r":0.7851926467,
|
266 |
+
"f":0.7918730159
|
267 |
},
|
268 |
"cc":{
|
269 |
+
"p":0.8966257303,
|
270 |
+
"r":0.8994139457,
|
271 |
+
"f":0.8980176738
|
272 |
},
|
273 |
"neg":{
|
274 |
+
"p":0.9603214465,
|
275 |
+
"r":0.9593577521,
|
276 |
+
"f":0.9598393574
|
277 |
},
|
278 |
"conj":{
|
279 |
+
"p":0.8554216867,
|
280 |
+
"r":0.9116314199,
|
281 |
+
"f":0.8826325411
|
282 |
},
|
283 |
"nsubjpass":{
|
284 |
+
"p":0.9484588176,
|
285 |
+
"r":0.9625641026,
|
286 |
+
"f":0.9554594044
|
287 |
},
|
288 |
"auxpass":{
|
289 |
+
"p":0.9582407819,
|
290 |
+
"r":0.9826879271,
|
291 |
+
"f":0.9703103914
|
292 |
},
|
293 |
"dobj":{
|
294 |
+
"p":0.9704970179,
|
295 |
+
"r":0.9725077695,
|
296 |
+
"f":0.9715013533
|
297 |
},
|
298 |
"nummod":{
|
299 |
+
"p":0.9509357613,
|
300 |
+
"r":0.9494949495,
|
301 |
+
"f":0.9502148092
|
302 |
},
|
303 |
"npadvmod":{
|
304 |
+
"p":0.8354978355,
|
305 |
+
"r":0.8227353464,
|
306 |
+
"f":0.8290674781
|
307 |
},
|
308 |
"prt":{
|
309 |
+
"p":0.8928884987,
|
310 |
+
"r":0.9112903226,
|
311 |
+
"f":0.9019955654
|
312 |
},
|
313 |
"pcomp":{
|
314 |
+
"p":0.9309372798,
|
315 |
+
"r":0.925070028,
|
316 |
+
"f":0.92799438
|
317 |
},
|
318 |
"expl":{
|
319 |
+
"p":0.9914712154,
|
320 |
"r":0.9957173448,
|
321 |
+
"f":0.9935897436
|
322 |
},
|
323 |
"acl":{
|
324 |
+
"p":0.8481012658,
|
325 |
+
"r":0.8406983088,
|
326 |
+
"f":0.8443835616
|
327 |
},
|
328 |
"agent":{
|
329 |
+
"p":0.9577464789,
|
330 |
+
"r":0.9749103943,
|
331 |
+
"f":0.9662522202
|
332 |
},
|
333 |
"dative":{
|
334 |
+
"p":0.8218262806,
|
335 |
+
"r":0.8463302752,
|
336 |
+
"f":0.8338983051
|
337 |
},
|
338 |
"acomp":{
|
339 |
+
"p":0.9484440316,
|
340 |
+
"r":0.9260770975,
|
341 |
+
"f":0.9371271225
|
342 |
},
|
343 |
"dep":{
|
344 |
+
"p":0.4476744186,
|
345 |
+
"r":0.375,
|
346 |
+
"f":0.4081272085
|
347 |
},
|
348 |
"csubj":{
|
349 |
+
"p":0.9,
|
350 |
"r":0.9053254438,
|
351 |
+
"f":0.9026548673
|
352 |
},
|
353 |
"quantmod":{
|
354 |
+
"p":0.8608624898,
|
355 |
+
"r":0.8594638505,
|
356 |
+
"f":0.8601626016
|
357 |
},
|
358 |
"nmod":{
|
359 |
+
"p":0.818815331,
|
360 |
+
"r":0.7160268129,
|
361 |
+
"f":0.7639791938
|
362 |
},
|
363 |
"appos":{
|
364 |
+
"p":0.781092437,
|
365 |
+
"r":0.8065075922,
|
366 |
+
"f":0.7935965848
|
367 |
},
|
368 |
"predet":{
|
369 |
+
"p":0.8464566929,
|
370 |
+
"r":0.9227467811,
|
371 |
+
"f":0.8829568789
|
372 |
},
|
373 |
"preconj":{
|
374 |
+
"p":0.6703296703,
|
375 |
+
"r":0.7093023256,
|
376 |
+
"f":0.6892655367
|
377 |
},
|
378 |
"oprd":{
|
379 |
+
"p":0.8711656442,
|
380 |
+
"r":0.847761194,
|
381 |
+
"f":0.8593040847
|
382 |
},
|
383 |
"parataxis":{
|
384 |
+
"p":0.5409836066,
|
385 |
+
"r":0.6442516269,
|
386 |
+
"f":0.5881188119
|
387 |
},
|
388 |
"meta":{
|
389 |
+
"p":0.3063063063,
|
390 |
"r":0.6538461538,
|
391 |
+
"f":0.4171779141
|
392 |
},
|
393 |
"csubjpass":{
|
394 |
+
"p":1.0,
|
395 |
"r":0.8333333333,
|
396 |
+
"f":0.9090909091
|
397 |
}
|
398 |
},
|
399 |
+
"ents_p":0.8994886705,
|
400 |
+
"ents_r":0.8985877404,
|
401 |
+
"ents_f":0.8990379798,
|
402 |
"ents_per_type":{
|
403 |
"DATE":{
|
404 |
+
"p":0.8913798548,
|
405 |
+
"r":0.8961904762,
|
406 |
+
"f":0.8937786924
|
407 |
},
|
408 |
"GPE":{
|
409 |
+
"p":0.9586402266,
|
410 |
+
"r":0.9439330544,
|
411 |
+
"f":0.9512297962
|
412 |
},
|
413 |
"ORDINAL":{
|
414 |
+
"p":0.8011869436,
|
415 |
+
"r":0.8385093168,
|
416 |
+
"f":0.8194233687
|
417 |
},
|
418 |
"ORG":{
|
419 |
+
"p":0.9049542272,
|
420 |
+
"r":0.8910392365,
|
421 |
+
"f":0.8979428266
|
422 |
},
|
423 |
"FAC":{
|
424 |
+
"p":0.6049382716,
|
425 |
+
"r":0.7538461538,
|
426 |
+
"f":0.6712328767
|
427 |
},
|
428 |
"QUANTITY":{
|
429 |
+
"p":0.7831325301,
|
430 |
+
"r":0.7142857143,
|
431 |
+
"f":0.7471264368
|
432 |
},
|
433 |
"LOC":{
|
434 |
+
"p":0.8184615385,
|
435 |
+
"r":0.847133758,
|
436 |
+
"f":0.8325508607
|
437 |
},
|
438 |
"CARDINAL":{
|
439 |
+
"p":0.8476517755,
|
440 |
+
"r":0.8799048751,
|
441 |
+
"f":0.8634772462
|
442 |
},
|
443 |
"PERSON":{
|
444 |
+
"p":0.9409898477,
|
445 |
+
"r":0.9680156658,
|
446 |
+
"f":0.9543114543
|
447 |
},
|
448 |
"NORP":{
|
449 |
+
"p":0.9311183144,
|
450 |
+
"r":0.9192,
|
451 |
+
"f":0.9251207729
|
452 |
},
|
453 |
"LAW":{
|
454 |
+
"p":0.527027027,
|
455 |
"r":0.609375,
|
456 |
+
"f":0.5652173913
|
|
|
|
|
|
|
|
|
|
|
457 |
},
|
458 |
"TIME":{
|
459 |
+
"p":0.7458100559,
|
460 |
+
"r":0.7807017544,
|
461 |
+
"f":0.7628571429
|
462 |
},
|
463 |
"EVENT":{
|
464 |
+
"p":0.7407407407,
|
465 |
+
"r":0.5747126437,
|
466 |
+
"f":0.6472491909
|
467 |
+
},
|
468 |
+
"PRODUCT":{
|
469 |
+
"p":0.6310160428,
|
470 |
+
"r":0.5592417062,
|
471 |
+
"f":0.5929648241
|
472 |
},
|
473 |
"WORK_OF_ART":{
|
474 |
+
"p":0.6534090909,
|
475 |
+
"r":0.5927835052,
|
476 |
+
"f":0.6216216216
|
477 |
},
|
478 |
+
"MONEY":{
|
479 |
+
"p":0.9356796117,
|
480 |
+
"r":0.9102715466,
|
481 |
+
"f":0.9228007181
|
482 |
},
|
483 |
+
"PERCENT":{
|
484 |
+
"p":0.9146919431,
|
485 |
+
"r":0.886676876,
|
486 |
+
"f":0.900466563
|
487 |
},
|
488 |
"LANGUAGE":{
|
489 |
+
"p":0.9642857143,
|
490 |
+
"r":0.84375,
|
491 |
+
"f":0.9
|
492 |
}
|
493 |
},
|
494 |
+
"speed":3882.7148648089
|
495 |
},
|
496 |
"sources":[
|
497 |
{
|
|
|
520 |
}
|
521 |
],
|
522 |
"requirements":[
|
523 |
+
"spacy-curated-transformers>=0.2.0,<0.3.0"
|
524 |
]
|
525 |
}
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:00b5b57be1a3766ad68d11e3e6abb06653bc9d768f6a8dea3831f21158cab0fa
|
3 |
+
size 313857
|
parser/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:252cbce9c57a485ba0074fc0d2c494f50e39e4f77ab5bb16da2d4a34b3322eb8
|
3 |
+
size 639633
|
tagger/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:487171b7e08a8ae2e94c539f7f3af2a0f4fbe45200e580a463319044bf036920
|
3 |
+
size 151450
|
transformer/cfg
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
{
|
2 |
-
|
3 |
}
|
|
|
1 |
{
|
2 |
+
|
3 |
}
|
transformer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f25fe24482dcc5c674abbe73b723562c9d6cdd1c3c24697d78ccf5a33a43b80
|
3 |
+
size 497342613
|
vocab/lookups.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fce9c883c56165f29573cc938c2a1c9d417ac61bd8f56b671dd5f7996de70682
|
3 |
+
size 70040
|
vocab/strings.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c7728f12b29cdb3908bd5d2b5ef0efac558033e58c30246e0d2ce86fd781ed67
|
3 |
+
size 1091498
|