adrianeboyd commited on
Commit
a134d22
1 Parent(s): 11764b8

Update spaCy pipeline

Browse files
Files changed (10) hide show
  1. README.md +19 -19
  2. accuracy.json +193 -193
  3. config.cfg +1 -0
  4. en_core_web_trf-any-py3-none-any.whl +2 -2
  5. meta.json +197 -197
  6. ner/model +1 -1
  7. parser/model +1 -1
  8. tagger/model +1 -1
  9. tokenizer +0 -0
  10. transformer/model +2 -2
README.md CHANGED
@@ -14,41 +14,41 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8953563447
18
  - name: NER Recall
19
  type: recall
20
- value: 0.9028445513
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.8990848565
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9780884117
31
  - task:
32
  name: UNLABELED_DEPENDENCIES
33
  type: token-classification
34
  metrics:
35
  - name: Unlabeled Attachment Score (UAS)
36
  type: f_score
37
- value: 0.9532621063
38
  - task:
39
  name: LABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Labeled Attachment Score (LAS)
43
  type: f_score
44
- value: 0.9398782759
45
  - task:
46
  name: SENTS
47
  type: token-classification
48
  metrics:
49
  - name: Sentences F-Score
50
  type: f_score
51
- value: 0.9121217361
52
  ---
53
  ### Details: https://spacy.io/models/en#en_core_web_trf
54
 
@@ -57,8 +57,8 @@ English transformer pipeline (roberta-base). Components: transformer, tagger, pa
57
  | Feature | Description |
58
  | --- | --- |
59
  | **Name** | `en_core_web_trf` |
60
- | **Version** | `3.4.1` |
61
- | **spaCy** | `>=3.4.0,<3.5.0` |
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) |
@@ -84,16 +84,16 @@ English transformer pipeline (roberta-base). Components: transformer, tagger, pa
84
 
85
  | Type | Score |
86
  | --- | --- |
87
- | `TOKEN_ACC` | 99.93 |
88
  | `TOKEN_P` | 99.57 |
89
  | `TOKEN_R` | 99.58 |
90
  | `TOKEN_F` | 99.57 |
91
- | `TAG_ACC` | 97.81 |
92
- | `SENTS_P` | 95.86 |
93
- | `SENTS_R` | 86.99 |
94
- | `SENTS_F` | 91.21 |
95
- | `DEP_UAS` | 95.33 |
96
- | `DEP_LAS` | 93.99 |
97
- | `ENTS_P` | 89.54 |
98
- | `ENTS_R` | 90.28 |
99
- | `ENTS_F` | 89.91 |
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8977938984
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.9048978365
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.9013318701
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9778773818
31
  - task:
32
  name: UNLABELED_DEPENDENCIES
33
  type: token-classification
34
  metrics:
35
  - name: Unlabeled Attachment Score (UAS)
36
  type: f_score
37
+ value: 0.9527427739
38
  - task:
39
  name: LABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Labeled Attachment Score (LAS)
43
  type: f_score
44
+ value: 0.9395456671
45
  - task:
46
  name: SENTS
47
  type: token-classification
48
  metrics:
49
  - name: Sentences F-Score
50
  type: f_score
51
+ value: 0.8969481605
52
  ---
53
  ### Details: https://spacy.io/models/en#en_core_web_trf
54
 
 
57
  | Feature | Description |
58
  | --- | --- |
59
  | **Name** | `en_core_web_trf` |
60
+ | **Version** | `3.5.0` |
61
+ | **spaCy** | `>=3.5.0,<3.6.0` |
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) |
 
84
 
85
  | Type | Score |
86
  | --- | --- |
87
+ | `TOKEN_ACC` | 99.86 |
88
  | `TOKEN_P` | 99.57 |
89
  | `TOKEN_R` | 99.58 |
90
  | `TOKEN_F` | 99.57 |
91
+ | `TAG_ACC` | 97.79 |
92
+ | `SENTS_P` | 95.04 |
93
+ | `SENTS_R` | 84.92 |
94
+ | `SENTS_F` | 89.69 |
95
+ | `DEP_UAS` | 95.27 |
96
+ | `DEP_LAS` | 93.95 |
97
+ | `ENTS_P` | 89.78 |
98
+ | `ENTS_R` | 90.49 |
99
+ | `ENTS_F` | 90.13 |
accuracy.json CHANGED
@@ -1,330 +1,330 @@
1
  {
2
- "token_acc": 0.9993092439,
3
  "token_p": 0.9956819193,
4
  "token_r": 0.9957659295,
5
  "token_f": 0.9957239226,
6
- "tag_acc": 0.9780884117,
7
- "sents_p": 0.9586362315,
8
- "sents_r": 0.8699122633,
9
- "sents_f": 0.9121217361,
10
- "dep_uas": 0.9532621063,
11
- "dep_las": 0.9398782759,
12
  "dep_las_per_type": {
13
  "prep": {
14
- "p": 0.9227600801,
15
- "r": 0.9265414532,
16
- "f": 0.9246469007
17
  },
18
  "det": {
19
- "p": 0.9898458527,
20
- "r": 0.9896844165,
21
- "f": 0.989765128
22
  },
23
  "pobj": {
24
- "p": 0.9832568717,
25
- "r": 0.9847241312,
26
- "f": 0.9839899545
27
  },
28
  "nsubj": {
29
- "p": 0.9798134606,
30
- "r": 0.9803285871,
31
- "f": 0.9800709562
32
  },
33
  "aux": {
34
- "p": 0.9896677652,
35
- "r": 0.9891391436,
36
- "f": 0.9894033838
37
  },
38
  "advmod": {
39
- "p": 0.8973109244,
40
- "r": 0.8983678277,
41
- "f": 0.897839065
42
  },
43
  "relcl": {
44
- "p": 0.8737623762,
45
- "r": 0.8965892598,
46
- "f": 0.8850286533
47
  },
48
  "root": {
49
- "p": 0.9681547186,
50
- "r": 0.8784220595,
51
- "f": 0.921108152
52
  },
53
  "xcomp": {
54
- "p": 0.9436212505,
55
- "r": 0.9371859296,
56
- "f": 0.9403925806
57
  },
58
  "amod": {
59
- "p": 0.9436409624,
60
- "r": 0.9426627794,
61
- "f": 0.9431516173
62
  },
63
  "compound": {
64
- "p": 0.9528043393,
65
- "r": 0.9489307195,
66
- "f": 0.9508635844
67
  },
68
  "poss": {
69
- "p": 0.9863426391,
70
- "r": 0.98852657,
71
- "f": 0.987433397
72
  },
73
  "ccomp": {
74
- "p": 0.8568164509,
75
- "r": 0.916496945,
76
- "f": 0.8856524306
77
  },
78
  "attr": {
79
- "p": 0.9539036545,
80
- "r": 0.9659377628,
81
- "f": 0.9598829921
82
  },
83
  "case": {
84
- "p": 0.9885742673,
85
- "r": 0.995995996,
86
- "f": 0.9922712541
87
  },
88
  "mark": {
89
- "p": 0.9500131544,
90
- "r": 0.9568097509,
91
- "f": 0.9533993399
92
  },
93
  "intj": {
94
- "p": 0.6179976162,
95
- "r": 0.7597069597,
96
- "f": 0.6815642458
97
  },
98
  "advcl": {
99
- "p": 0.8078893443,
100
- "r": 0.7942583732,
101
- "f": 0.801015873
102
  },
103
  "cc": {
104
- "p": 0.8980490126,
105
- "r": 0.9028824303,
106
- "f": 0.9004592354
107
  },
108
  "neg": {
109
- "p": 0.9594594595,
110
- "r": 0.9618665329,
111
- "f": 0.9606614883
112
  },
113
  "conj": {
114
- "p": 0.8712276061,
115
- "r": 0.9121349446,
116
- "f": 0.8912121026
117
  },
118
  "nsubjpass": {
119
- "p": 0.9558748076,
120
- "r": 0.9553846154,
121
- "f": 0.9556296486
122
  },
123
  "auxpass": {
124
- "p": 0.9683257919,
125
- "r": 0.9749430524,
126
- "f": 0.9716231555
127
  },
128
  "dobj": {
129
- "p": 0.9751418751,
130
- "r": 0.972189019,
131
- "f": 0.9736632083
132
  },
133
  "nummod": {
134
- "p": 0.9544876684,
135
  "r": 0.947979798,
136
- "f": 0.9512226023
137
  },
138
  "npadvmod": {
139
- "p": 0.8592321755,
140
- "r": 0.8348134991,
141
- "f": 0.8468468468
142
  },
143
  "prt": {
144
- "p": 0.8991071429,
145
- "r": 0.9023297491,
146
- "f": 0.9007155635
147
  },
148
  "pcomp": {
149
- "p": 0.9302816901,
150
- "r": 0.925070028,
151
- "f": 0.9276685393
152
  },
153
  "expl": {
154
- "p": 0.9914529915,
155
  "r": 0.9935760171,
156
- "f": 0.992513369
157
  },
158
  "acl": {
159
- "p": 0.8488499452,
160
- "r": 0.8456082924,
161
- "f": 0.847226018
162
  },
163
  "agent": {
164
- "p": 0.9576719577,
165
- "r": 0.9731182796,
166
- "f": 0.9653333333
167
  },
168
  "dative": {
169
- "p": 0.835214447,
170
- "r": 0.8486238532,
171
- "f": 0.8418657565
172
  },
173
  "acomp": {
174
- "p": 0.94,
175
- "r": 0.9378684807,
176
- "f": 0.9389330306
177
  },
178
  "dep": {
179
- "p": 0.4232081911,
180
- "r": 0.4025974026,
181
- "f": 0.4126455907
182
  },
183
  "csubj": {
184
- "p": 0.8636363636,
185
- "r": 0.899408284,
186
- "f": 0.8811594203
187
  },
188
  "quantmod": {
189
- "p": 0.8827004219,
190
- "r": 0.8497156783,
191
- "f": 0.8658940397
192
  },
193
  "nmod": {
194
- "p": 0.8265657261,
195
  "r": 0.7318708105,
196
- "f": 0.7763413058
197
  },
198
  "appos": {
199
- "p": 0.8265618174,
200
- "r": 0.820824295,
201
- "f": 0.8236830649
202
  },
203
  "predet": {
204
- "p": 0.8548387097,
205
- "r": 0.9098712446,
206
- "f": 0.8814968815
207
  },
208
  "preconj": {
209
- "p": 0.6703296703,
210
- "r": 0.7093023256,
211
- "f": 0.6892655367
212
  },
213
  "oprd": {
214
- "p": 0.9015873016,
215
- "r": 0.847761194,
216
- "f": 0.8738461538
217
  },
218
  "parataxis": {
219
- "p": 0.6003752345,
220
- "r": 0.694143167,
221
- "f": 0.6438631791
222
  },
223
  "meta": {
224
- "p": 0.2156862745,
225
- "r": 0.6346153846,
226
- "f": 0.3219512195
227
  },
228
  "csubjpass": {
229
- "p": 0.7142857143,
230
  "r": 0.8333333333,
231
- "f": 0.7692307692
232
  }
233
  },
234
- "ents_p": 0.8953563447,
235
- "ents_r": 0.9028445513,
236
- "ents_f": 0.8990848565,
237
  "ents_per_type": {
238
  "DATE": {
239
- "p": 0.8842563783,
240
- "r": 0.9022222222,
241
- "f": 0.8931489629
242
  },
243
  "GPE": {
244
- "p": 0.9562166713,
245
- "r": 0.950348675,
246
- "f": 0.953273643
247
  },
248
  "ORDINAL": {
249
- "p": 0.8053892216,
250
- "r": 0.8354037267,
251
- "f": 0.8201219512
252
  },
253
  "ORG": {
254
- "p": 0.8987006099,
255
- "r": 0.8984623542,
256
- "f": 0.8985814663
257
  },
258
  "FAC": {
259
- "p": 0.5353535354,
260
- "r": 0.8153846154,
261
- "f": 0.6463414634
262
  },
263
  "QUANTITY": {
264
- "p": 0.7120418848,
265
- "r": 0.7472527473,
266
- "f": 0.7292225201
267
  },
268
  "LOC": {
269
- "p": 0.8248407643,
270
- "r": 0.8248407643,
271
- "f": 0.8248407643
272
  },
273
  "CARDINAL": {
274
- "p": 0.8490241102,
275
- "r": 0.8793103448,
276
- "f": 0.8639018692
277
  },
278
  "PERSON": {
279
- "p": 0.9408020369,
280
- "r": 0.9647519582,
281
- "f": 0.9526264905
282
  },
283
  "NORP": {
284
- "p": 0.9305666401,
285
  "r": 0.9328,
286
- "f": 0.9316819816
287
- },
288
- "LAW": {
289
- "p": 0.625,
290
- "r": 0.703125,
291
- "f": 0.6617647059
292
  },
293
  "PRODUCT": {
294
- "p": 0.6823529412,
295
- "r": 0.5497630332,
296
- "f": 0.6089238845
297
  },
298
  "TIME": {
299
- "p": 0.7527472527,
300
- "r": 0.8011695906,
301
- "f": 0.776203966
302
  },
303
  "EVENT": {
304
- "p": 0.7883211679,
305
- "r": 0.6206896552,
306
- "f": 0.6945337621
307
  },
308
  "WORK_OF_ART": {
309
- "p": 0.6077348066,
310
- "r": 0.5670103093,
311
- "f": 0.5866666667
 
 
 
 
 
312
  },
313
  "MONEY": {
314
- "p": 0.9120481928,
315
  "r": 0.893742621,
316
- "f": 0.9028026237
317
  },
318
  "PERCENT": {
319
- "p": 0.9225908373,
320
- "r": 0.8943338438,
321
- "f": 0.9082426128
322
  },
323
  "LANGUAGE": {
324
- "p": 0.9615384615,
325
- "r": 0.78125,
326
- "f": 0.8620689655
327
  }
328
  },
329
- "speed": 6118.8721996645
330
  }
 
1
  {
2
+ "token_acc": 0.9986194413,
3
  "token_p": 0.9956819193,
4
  "token_r": 0.9957659295,
5
  "token_f": 0.9957239226,
6
+ "tag_acc": 0.9778773818,
7
+ "sents_p": 0.9503875969,
8
+ "sents_r": 0.8491984959,
9
+ "sents_f": 0.8969481605,
10
+ "dep_uas": 0.9527427739,
11
+ "dep_las": 0.9395456671,
12
  "dep_las_per_type": {
13
  "prep": {
14
+ "p": 0.9243897824,
15
+ "r": 0.9268450009,
16
+ "f": 0.9256157635
17
  },
18
  "det": {
19
+ "p": 0.9903740262,
20
+ "r": 0.990010601,
21
+ "f": 0.9901922802
22
  },
23
  "pobj": {
24
+ "p": 0.9844203752,
25
+ "r": 0.9850775574,
26
+ "f": 0.9847488567
27
  },
28
  "nsubj": {
29
+ "p": 0.9805339997,
30
+ "r": 0.9798466594,
31
+ "f": 0.9801902091
32
  },
33
  "aux": {
34
+ "p": 0.9880814729,
35
+ "r": 0.9889610968,
36
+ "f": 0.9885210892
37
  },
38
  "advmod": {
39
+ "p": 0.8982352941,
40
+ "r": 0.8992932862,
41
+ "f": 0.8987639788
42
  },
43
  "relcl": {
44
+ "p": 0.8786803831,
45
+ "r": 0.898766328,
46
+ "f": 0.8886098655
47
  },
48
  "root": {
49
+ "p": 0.9681063123,
50
+ "r": 0.8650306748,
51
+ "f": 0.9136705686
52
  },
53
  "xcomp": {
54
+ "p": 0.9437432384,
55
+ "r": 0.9393395549,
56
+ "f": 0.9415362475
57
  },
58
  "amod": {
59
+ "p": 0.9438063721,
60
+ "r": 0.9423388403,
61
+ "f": 0.9430720353
62
  },
63
  "compound": {
64
+ "p": 0.9517433752,
65
+ "r": 0.950100245,
66
+ "f": 0.9509211003
67
  },
68
  "poss": {
69
+ "p": 0.9875426964,
70
+ "r": 0.989331723,
71
+ "f": 0.9884364002
72
  },
73
  "ccomp": {
74
+ "p": 0.8524404086,
75
+ "r": 0.9177189409,
76
+ "f": 0.8838760298
77
  },
78
  "attr": {
79
+ "p": 0.9554723263,
80
+ "r": 0.9655172414,
81
+ "f": 0.9604685212
82
  },
83
  "case": {
84
+ "p": 0.9885515182,
85
+ "r": 0.993993994,
86
+ "f": 0.9912652857
87
  },
88
  "mark": {
89
+ "p": 0.950065703,
90
+ "r": 0.9578696343,
91
+ "f": 0.9539517087
92
  },
93
  "intj": {
94
+ "p": 0.6128461992,
95
+ "r": 0.7619047619,
96
+ "f": 0.6792945787
97
  },
98
  "advcl": {
99
+ "p": 0.8079774994,
100
+ "r": 0.7957693276,
101
+ "f": 0.8018269475
102
  },
103
  "cc": {
104
+ "p": 0.8930443068,
105
+ "r": 0.8967826815,
106
+ "f": 0.89490959
107
  },
108
  "neg": {
109
+ "p": 0.9629258517,
110
+ "r": 0.9643753136,
111
+ "f": 0.9636500376
112
  },
113
  "conj": {
114
+ "p": 0.8663254374,
115
+ "r": 0.916163142,
116
+ "f": 0.8905475681
117
  },
118
  "nsubjpass": {
119
+ "p": 0.9555214724,
120
+ "r": 0.9584615385,
121
+ "f": 0.9569892473
122
  },
123
  "auxpass": {
124
+ "p": 0.9675236806,
125
+ "r": 0.9772209567,
126
+ "f": 0.9723481414
127
  },
128
  "dobj": {
129
+ "p": 0.9736800128,
130
+ "r": 0.97282652,
131
+ "f": 0.9732530793
132
  },
133
  "nummod": {
134
+ "p": 0.9586312564,
135
  "r": 0.947979798,
136
+ "f": 0.9532757745
137
  },
138
  "npadvmod": {
139
+ "p": 0.8557833089,
140
+ "r": 0.8305506217,
141
+ "f": 0.8429781864
142
  },
143
  "prt": {
144
+ "p": 0.8916299559,
145
+ "r": 0.9068100358,
146
+ "f": 0.8991559307
147
  },
148
  "pcomp": {
149
+ "p": 0.9331926864,
150
+ "r": 0.9292717087,
151
+ "f": 0.9312280702
152
  },
153
  "expl": {
154
+ "p": 0.9935760171,
155
  "r": 0.9935760171,
156
+ "f": 0.9935760171
157
  },
158
  "acl": {
159
+ "p": 0.8561230093,
160
+ "r": 0.8505182761,
161
+ "f": 0.8533114395
162
  },
163
  "agent": {
164
+ "p": 0.9543859649,
165
+ "r": 0.9749103943,
166
+ "f": 0.9645390071
167
  },
168
  "dative": {
169
+ "p": 0.8498845266,
170
+ "r": 0.8440366972,
171
+ "f": 0.8469505178
172
  },
173
  "acomp": {
174
+ "p": 0.939462904,
175
+ "r": 0.9360544218,
176
+ "f": 0.9377555657
177
  },
178
  "dep": {
179
+ "p": 0.4197730956,
180
+ "r": 0.4204545455,
181
+ "f": 0.4201135442
182
  },
183
  "csubj": {
184
+ "p": 0.901734104,
185
+ "r": 0.9230769231,
186
+ "f": 0.9122807018
187
  },
188
  "quantmod": {
189
+ "p": 0.8879598662,
190
+ "r": 0.8627132413,
191
+ "f": 0.8751545117
192
  },
193
  "nmod": {
194
+ "p": 0.8340277778,
195
  "r": 0.7318708105,
196
+ "f": 0.7796170075
197
  },
198
  "appos": {
199
+ "p": 0.8211346903,
200
+ "r": 0.8225596529,
201
+ "f": 0.821846554
202
  },
203
  "predet": {
204
+ "p": 0.8473895582,
205
+ "r": 0.9055793991,
206
+ "f": 0.8755186722
207
  },
208
  "preconj": {
209
+ "p": 0.6526315789,
210
+ "r": 0.7209302326,
211
+ "f": 0.6850828729
212
  },
213
  "oprd": {
214
+ "p": 0.8861538462,
215
+ "r": 0.8597014925,
216
+ "f": 0.8727272727
217
  },
218
  "parataxis": {
219
+ "p": 0.6038461538,
220
+ "r": 0.6811279826,
221
+ "f": 0.6401630989
222
  },
223
  "meta": {
224
+ "p": 0.1724137931,
225
+ "r": 0.6730769231,
226
+ "f": 0.2745098039
227
  },
228
  "csubjpass": {
229
+ "p": 1.0,
230
  "r": 0.8333333333,
231
+ "f": 0.9090909091
232
  }
233
  },
234
+ "ents_p": 0.8977938984,
235
+ "ents_r": 0.9048978365,
236
+ "ents_f": 0.9013318701,
237
  "ents_per_type": {
238
  "DATE": {
239
+ "p": 0.8915360502,
240
+ "r": 0.9028571429,
241
+ "f": 0.8971608833
242
  },
243
  "GPE": {
244
+ "p": 0.9549524342,
245
+ "r": 0.9520223152,
246
+ "f": 0.9534851236
247
  },
248
  "ORDINAL": {
249
+ "p": 0.7771260997,
250
+ "r": 0.8229813665,
251
+ "f": 0.7993966817
252
  },
253
  "ORG": {
254
+ "p": 0.8985736926,
255
+ "r": 0.9019088017,
256
+ "f": 0.9002381582
257
  },
258
  "FAC": {
259
+ "p": 0.5635359116,
260
+ "r": 0.7846153846,
261
+ "f": 0.6559485531
262
  },
263
  "QUANTITY": {
264
+ "p": 0.7823529412,
265
+ "r": 0.7307692308,
266
+ "f": 0.7556818182
267
  },
268
  "LOC": {
269
+ "p": 0.8443708609,
270
+ "r": 0.8121019108,
271
+ "f": 0.8279220779
272
  },
273
  "CARDINAL": {
274
+ "p": 0.8491208168,
275
+ "r": 0.8900118906,
276
+ "f": 0.8690856313
277
  },
278
  "PERSON": {
279
+ "p": 0.9398162813,
280
+ "r": 0.9683420366,
281
+ "f": 0.953865938
282
  },
283
  "NORP": {
284
+ "p": 0.9253968254,
285
  "r": 0.9328,
286
+ "f": 0.9290836653
 
 
 
 
 
287
  },
288
  "PRODUCT": {
289
+ "p": 0.6804733728,
290
+ "r": 0.5450236967,
291
+ "f": 0.6052631579
292
  },
293
  "TIME": {
294
+ "p": 0.7663043478,
295
+ "r": 0.8245614035,
296
+ "f": 0.7943661972
297
  },
298
  "EVENT": {
299
+ "p": 0.7898550725,
300
+ "r": 0.6264367816,
301
+ "f": 0.6987179487
302
  },
303
  "WORK_OF_ART": {
304
+ "p": 0.6514285714,
305
+ "r": 0.587628866,
306
+ "f": 0.6178861789
307
+ },
308
+ "LAW": {
309
+ "p": 0.6363636364,
310
+ "r": 0.65625,
311
+ "f": 0.6461538462
312
  },
313
  "MONEY": {
314
+ "p": 0.9109506619,
315
  "r": 0.893742621,
316
+ "f": 0.9022646007
317
  },
318
  "PERCENT": {
319
+ "p": 0.9224683544,
320
+ "r": 0.8928024502,
321
+ "f": 0.9073929961
322
  },
323
  "LANGUAGE": {
324
+ "p": 1.0,
325
+ "r": 0.71875,
326
+ "f": 0.8363636364
327
  }
328
  },
329
+ "speed": 6031.0542416801
330
  }
config.cfg CHANGED
@@ -148,6 +148,7 @@ eval_frequency = 1000
148
  frozen_components = []
149
  before_to_disk = null
150
  annotating_components = []
 
151
 
152
  [training.batcher]
153
  @batchers = "spacy.batch_by_padded.v1"
 
148
  frozen_components = []
149
  before_to_disk = null
150
  annotating_components = []
151
+ before_update = null
152
 
153
  [training.batcher]
154
  @batchers = "spacy.batch_by_padded.v1"
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 sha256:35c8490d34e9cebe129ee1c9143977aaf02d4bd6d224f30a79baf3838627339b
3
- size 460264340
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8902305d2ced83d98a8e88efd93ea8970a70dda9bb24b0024a8b798d1cc913d5
3
+ size 460267966
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"en",
3
  "name":"core_web_trf",
4
- "version":"3.4.1",
5
  "description":"English transformer pipeline (roberta-base). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"MIT",
10
- "spacy_version":">=3.4.1,<3.5.0",
11
- "spacy_git_version":"Unknown",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -164,334 +164,334 @@
164
 
165
  ],
166
  "performance":{
167
- "token_acc":0.9993092439,
168
  "token_p":0.9956819193,
169
  "token_r":0.9957659295,
170
  "token_f":0.9957239226,
171
- "tag_acc":0.9780884117,
172
- "sents_p":0.9586362315,
173
- "sents_r":0.8699122633,
174
- "sents_f":0.9121217361,
175
- "dep_uas":0.9532621063,
176
- "dep_las":0.9398782759,
177
  "dep_las_per_type":{
178
  "prep":{
179
- "p":0.9227600801,
180
- "r":0.9265414532,
181
- "f":0.9246469007
182
  },
183
  "det":{
184
- "p":0.9898458527,
185
- "r":0.9896844165,
186
- "f":0.989765128
187
  },
188
  "pobj":{
189
- "p":0.9832568717,
190
- "r":0.9847241312,
191
- "f":0.9839899545
192
  },
193
  "nsubj":{
194
- "p":0.9798134606,
195
- "r":0.9803285871,
196
- "f":0.9800709562
197
  },
198
  "aux":{
199
- "p":0.9896677652,
200
- "r":0.9891391436,
201
- "f":0.9894033838
202
  },
203
  "advmod":{
204
- "p":0.8973109244,
205
- "r":0.8983678277,
206
- "f":0.897839065
207
  },
208
  "relcl":{
209
- "p":0.8737623762,
210
- "r":0.8965892598,
211
- "f":0.8850286533
212
  },
213
  "root":{
214
- "p":0.9681547186,
215
- "r":0.8784220595,
216
- "f":0.921108152
217
  },
218
  "xcomp":{
219
- "p":0.9436212505,
220
- "r":0.9371859296,
221
- "f":0.9403925806
222
  },
223
  "amod":{
224
- "p":0.9436409624,
225
- "r":0.9426627794,
226
- "f":0.9431516173
227
  },
228
  "compound":{
229
- "p":0.9528043393,
230
- "r":0.9489307195,
231
- "f":0.9508635844
232
  },
233
  "poss":{
234
- "p":0.9863426391,
235
- "r":0.98852657,
236
- "f":0.987433397
237
  },
238
  "ccomp":{
239
- "p":0.8568164509,
240
- "r":0.916496945,
241
- "f":0.8856524306
242
  },
243
  "attr":{
244
- "p":0.9539036545,
245
- "r":0.9659377628,
246
- "f":0.9598829921
247
  },
248
  "case":{
249
- "p":0.9885742673,
250
- "r":0.995995996,
251
- "f":0.9922712541
252
  },
253
  "mark":{
254
- "p":0.9500131544,
255
- "r":0.9568097509,
256
- "f":0.9533993399
257
  },
258
  "intj":{
259
- "p":0.6179976162,
260
- "r":0.7597069597,
261
- "f":0.6815642458
262
  },
263
  "advcl":{
264
- "p":0.8078893443,
265
- "r":0.7942583732,
266
- "f":0.801015873
267
  },
268
  "cc":{
269
- "p":0.8980490126,
270
- "r":0.9028824303,
271
- "f":0.9004592354
272
  },
273
  "neg":{
274
- "p":0.9594594595,
275
- "r":0.9618665329,
276
- "f":0.9606614883
277
  },
278
  "conj":{
279
- "p":0.8712276061,
280
- "r":0.9121349446,
281
- "f":0.8912121026
282
  },
283
  "nsubjpass":{
284
- "p":0.9558748076,
285
- "r":0.9553846154,
286
- "f":0.9556296486
287
  },
288
  "auxpass":{
289
- "p":0.9683257919,
290
- "r":0.9749430524,
291
- "f":0.9716231555
292
  },
293
  "dobj":{
294
- "p":0.9751418751,
295
- "r":0.972189019,
296
- "f":0.9736632083
297
  },
298
  "nummod":{
299
- "p":0.9544876684,
300
  "r":0.947979798,
301
- "f":0.9512226023
302
  },
303
  "npadvmod":{
304
- "p":0.8592321755,
305
- "r":0.8348134991,
306
- "f":0.8468468468
307
  },
308
  "prt":{
309
- "p":0.8991071429,
310
- "r":0.9023297491,
311
- "f":0.9007155635
312
  },
313
  "pcomp":{
314
- "p":0.9302816901,
315
- "r":0.925070028,
316
- "f":0.9276685393
317
  },
318
  "expl":{
319
- "p":0.9914529915,
320
  "r":0.9935760171,
321
- "f":0.992513369
322
  },
323
  "acl":{
324
- "p":0.8488499452,
325
- "r":0.8456082924,
326
- "f":0.847226018
327
  },
328
  "agent":{
329
- "p":0.9576719577,
330
- "r":0.9731182796,
331
- "f":0.9653333333
332
  },
333
  "dative":{
334
- "p":0.835214447,
335
- "r":0.8486238532,
336
- "f":0.8418657565
337
  },
338
  "acomp":{
339
- "p":0.94,
340
- "r":0.9378684807,
341
- "f":0.9389330306
342
  },
343
  "dep":{
344
- "p":0.4232081911,
345
- "r":0.4025974026,
346
- "f":0.4126455907
347
  },
348
  "csubj":{
349
- "p":0.8636363636,
350
- "r":0.899408284,
351
- "f":0.8811594203
352
  },
353
  "quantmod":{
354
- "p":0.8827004219,
355
- "r":0.8497156783,
356
- "f":0.8658940397
357
  },
358
  "nmod":{
359
- "p":0.8265657261,
360
  "r":0.7318708105,
361
- "f":0.7763413058
362
  },
363
  "appos":{
364
- "p":0.8265618174,
365
- "r":0.820824295,
366
- "f":0.8236830649
367
  },
368
  "predet":{
369
- "p":0.8548387097,
370
- "r":0.9098712446,
371
- "f":0.8814968815
372
  },
373
  "preconj":{
374
- "p":0.6703296703,
375
- "r":0.7093023256,
376
- "f":0.6892655367
377
  },
378
  "oprd":{
379
- "p":0.9015873016,
380
- "r":0.847761194,
381
- "f":0.8738461538
382
  },
383
  "parataxis":{
384
- "p":0.6003752345,
385
- "r":0.694143167,
386
- "f":0.6438631791
387
  },
388
  "meta":{
389
- "p":0.2156862745,
390
- "r":0.6346153846,
391
- "f":0.3219512195
392
  },
393
  "csubjpass":{
394
- "p":0.7142857143,
395
  "r":0.8333333333,
396
- "f":0.7692307692
397
  }
398
  },
399
- "ents_p":0.8953563447,
400
- "ents_r":0.9028445513,
401
- "ents_f":0.8990848565,
402
  "ents_per_type":{
403
  "DATE":{
404
- "p":0.8842563783,
405
- "r":0.9022222222,
406
- "f":0.8931489629
407
  },
408
  "GPE":{
409
- "p":0.9562166713,
410
- "r":0.950348675,
411
- "f":0.953273643
412
  },
413
  "ORDINAL":{
414
- "p":0.8053892216,
415
- "r":0.8354037267,
416
- "f":0.8201219512
417
  },
418
  "ORG":{
419
- "p":0.8987006099,
420
- "r":0.8984623542,
421
- "f":0.8985814663
422
  },
423
  "FAC":{
424
- "p":0.5353535354,
425
- "r":0.8153846154,
426
- "f":0.6463414634
427
  },
428
  "QUANTITY":{
429
- "p":0.7120418848,
430
- "r":0.7472527473,
431
- "f":0.7292225201
432
  },
433
  "LOC":{
434
- "p":0.8248407643,
435
- "r":0.8248407643,
436
- "f":0.8248407643
437
  },
438
  "CARDINAL":{
439
- "p":0.8490241102,
440
- "r":0.8793103448,
441
- "f":0.8639018692
442
  },
443
  "PERSON":{
444
- "p":0.9408020369,
445
- "r":0.9647519582,
446
- "f":0.9526264905
447
  },
448
  "NORP":{
449
- "p":0.9305666401,
450
  "r":0.9328,
451
- "f":0.9316819816
452
- },
453
- "LAW":{
454
- "p":0.625,
455
- "r":0.703125,
456
- "f":0.6617647059
457
  },
458
  "PRODUCT":{
459
- "p":0.6823529412,
460
- "r":0.5497630332,
461
- "f":0.6089238845
462
  },
463
  "TIME":{
464
- "p":0.7527472527,
465
- "r":0.8011695906,
466
- "f":0.776203966
467
  },
468
  "EVENT":{
469
- "p":0.7883211679,
470
- "r":0.6206896552,
471
- "f":0.6945337621
472
  },
473
  "WORK_OF_ART":{
474
- "p":0.6077348066,
475
- "r":0.5670103093,
476
- "f":0.5866666667
 
 
 
 
 
477
  },
478
  "MONEY":{
479
- "p":0.9120481928,
480
  "r":0.893742621,
481
- "f":0.9028026237
482
  },
483
  "PERCENT":{
484
- "p":0.9225908373,
485
- "r":0.8943338438,
486
- "f":0.9082426128
487
  },
488
  "LANGUAGE":{
489
- "p":0.9615384615,
490
- "r":0.78125,
491
- "f":0.8620689655
492
  }
493
  },
494
- "speed":6118.8721996645
495
  },
496
  "sources":[
497
  {
@@ -520,6 +520,6 @@
520
  }
521
  ],
522
  "requirements":[
523
- "spacy-transformers>=1.1.2,<1.2.0"
524
  ]
525
  }
 
1
  {
2
  "lang":"en",
3
  "name":"core_web_trf",
4
+ "version":"3.5.0",
5
  "description":"English transformer pipeline (roberta-base). Components: transformer, tagger, parser, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"MIT",
10
+ "spacy_version":">=3.5.0,<3.6.0",
11
+ "spacy_git_version":"9e0322de1",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
 
164
 
165
  ],
166
  "performance":{
167
+ "token_acc":0.9986194413,
168
  "token_p":0.9956819193,
169
  "token_r":0.9957659295,
170
  "token_f":0.9957239226,
171
+ "tag_acc":0.9778773818,
172
+ "sents_p":0.9503875969,
173
+ "sents_r":0.8491984959,
174
+ "sents_f":0.8969481605,
175
+ "dep_uas":0.9527427739,
176
+ "dep_las":0.9395456671,
177
  "dep_las_per_type":{
178
  "prep":{
179
+ "p":0.9243897824,
180
+ "r":0.9268450009,
181
+ "f":0.9256157635
182
  },
183
  "det":{
184
+ "p":0.9903740262,
185
+ "r":0.990010601,
186
+ "f":0.9901922802
187
  },
188
  "pobj":{
189
+ "p":0.9844203752,
190
+ "r":0.9850775574,
191
+ "f":0.9847488567
192
  },
193
  "nsubj":{
194
+ "p":0.9805339997,
195
+ "r":0.9798466594,
196
+ "f":0.9801902091
197
  },
198
  "aux":{
199
+ "p":0.9880814729,
200
+ "r":0.9889610968,
201
+ "f":0.9885210892
202
  },
203
  "advmod":{
204
+ "p":0.8982352941,
205
+ "r":0.8992932862,
206
+ "f":0.8987639788
207
  },
208
  "relcl":{
209
+ "p":0.8786803831,
210
+ "r":0.898766328,
211
+ "f":0.8886098655
212
  },
213
  "root":{
214
+ "p":0.9681063123,
215
+ "r":0.8650306748,
216
+ "f":0.9136705686
217
  },
218
  "xcomp":{
219
+ "p":0.9437432384,
220
+ "r":0.9393395549,
221
+ "f":0.9415362475
222
  },
223
  "amod":{
224
+ "p":0.9438063721,
225
+ "r":0.9423388403,
226
+ "f":0.9430720353
227
  },
228
  "compound":{
229
+ "p":0.9517433752,
230
+ "r":0.950100245,
231
+ "f":0.9509211003
232
  },
233
  "poss":{
234
+ "p":0.9875426964,
235
+ "r":0.989331723,
236
+ "f":0.9884364002
237
  },
238
  "ccomp":{
239
+ "p":0.8524404086,
240
+ "r":0.9177189409,
241
+ "f":0.8838760298
242
  },
243
  "attr":{
244
+ "p":0.9554723263,
245
+ "r":0.9655172414,
246
+ "f":0.9604685212
247
  },
248
  "case":{
249
+ "p":0.9885515182,
250
+ "r":0.993993994,
251
+ "f":0.9912652857
252
  },
253
  "mark":{
254
+ "p":0.950065703,
255
+ "r":0.9578696343,
256
+ "f":0.9539517087
257
  },
258
  "intj":{
259
+ "p":0.6128461992,
260
+ "r":0.7619047619,
261
+ "f":0.6792945787
262
  },
263
  "advcl":{
264
+ "p":0.8079774994,
265
+ "r":0.7957693276,
266
+ "f":0.8018269475
267
  },
268
  "cc":{
269
+ "p":0.8930443068,
270
+ "r":0.8967826815,
271
+ "f":0.89490959
272
  },
273
  "neg":{
274
+ "p":0.9629258517,
275
+ "r":0.9643753136,
276
+ "f":0.9636500376
277
  },
278
  "conj":{
279
+ "p":0.8663254374,
280
+ "r":0.916163142,
281
+ "f":0.8905475681
282
  },
283
  "nsubjpass":{
284
+ "p":0.9555214724,
285
+ "r":0.9584615385,
286
+ "f":0.9569892473
287
  },
288
  "auxpass":{
289
+ "p":0.9675236806,
290
+ "r":0.9772209567,
291
+ "f":0.9723481414
292
  },
293
  "dobj":{
294
+ "p":0.9736800128,
295
+ "r":0.97282652,
296
+ "f":0.9732530793
297
  },
298
  "nummod":{
299
+ "p":0.9586312564,
300
  "r":0.947979798,
301
+ "f":0.9532757745
302
  },
303
  "npadvmod":{
304
+ "p":0.8557833089,
305
+ "r":0.8305506217,
306
+ "f":0.8429781864
307
  },
308
  "prt":{
309
+ "p":0.8916299559,
310
+ "r":0.9068100358,
311
+ "f":0.8991559307
312
  },
313
  "pcomp":{
314
+ "p":0.9331926864,
315
+ "r":0.9292717087,
316
+ "f":0.9312280702
317
  },
318
  "expl":{
319
+ "p":0.9935760171,
320
  "r":0.9935760171,
321
+ "f":0.9935760171
322
  },
323
  "acl":{
324
+ "p":0.8561230093,
325
+ "r":0.8505182761,
326
+ "f":0.8533114395
327
  },
328
  "agent":{
329
+ "p":0.9543859649,
330
+ "r":0.9749103943,
331
+ "f":0.9645390071
332
  },
333
  "dative":{
334
+ "p":0.8498845266,
335
+ "r":0.8440366972,
336
+ "f":0.8469505178
337
  },
338
  "acomp":{
339
+ "p":0.939462904,
340
+ "r":0.9360544218,
341
+ "f":0.9377555657
342
  },
343
  "dep":{
344
+ "p":0.4197730956,
345
+ "r":0.4204545455,
346
+ "f":0.4201135442
347
  },
348
  "csubj":{
349
+ "p":0.901734104,
350
+ "r":0.9230769231,
351
+ "f":0.9122807018
352
  },
353
  "quantmod":{
354
+ "p":0.8879598662,
355
+ "r":0.8627132413,
356
+ "f":0.8751545117
357
  },
358
  "nmod":{
359
+ "p":0.8340277778,
360
  "r":0.7318708105,
361
+ "f":0.7796170075
362
  },
363
  "appos":{
364
+ "p":0.8211346903,
365
+ "r":0.8225596529,
366
+ "f":0.821846554
367
  },
368
  "predet":{
369
+ "p":0.8473895582,
370
+ "r":0.9055793991,
371
+ "f":0.8755186722
372
  },
373
  "preconj":{
374
+ "p":0.6526315789,
375
+ "r":0.7209302326,
376
+ "f":0.6850828729
377
  },
378
  "oprd":{
379
+ "p":0.8861538462,
380
+ "r":0.8597014925,
381
+ "f":0.8727272727
382
  },
383
  "parataxis":{
384
+ "p":0.6038461538,
385
+ "r":0.6811279826,
386
+ "f":0.6401630989
387
  },
388
  "meta":{
389
+ "p":0.1724137931,
390
+ "r":0.6730769231,
391
+ "f":0.2745098039
392
  },
393
  "csubjpass":{
394
+ "p":1.0,
395
  "r":0.8333333333,
396
+ "f":0.9090909091
397
  }
398
  },
399
+ "ents_p":0.8977938984,
400
+ "ents_r":0.9048978365,
401
+ "ents_f":0.9013318701,
402
  "ents_per_type":{
403
  "DATE":{
404
+ "p":0.8915360502,
405
+ "r":0.9028571429,
406
+ "f":0.8971608833
407
  },
408
  "GPE":{
409
+ "p":0.9549524342,
410
+ "r":0.9520223152,
411
+ "f":0.9534851236
412
  },
413
  "ORDINAL":{
414
+ "p":0.7771260997,
415
+ "r":0.8229813665,
416
+ "f":0.7993966817
417
  },
418
  "ORG":{
419
+ "p":0.8985736926,
420
+ "r":0.9019088017,
421
+ "f":0.9002381582
422
  },
423
  "FAC":{
424
+ "p":0.5635359116,
425
+ "r":0.7846153846,
426
+ "f":0.6559485531
427
  },
428
  "QUANTITY":{
429
+ "p":0.7823529412,
430
+ "r":0.7307692308,
431
+ "f":0.7556818182
432
  },
433
  "LOC":{
434
+ "p":0.8443708609,
435
+ "r":0.8121019108,
436
+ "f":0.8279220779
437
  },
438
  "CARDINAL":{
439
+ "p":0.8491208168,
440
+ "r":0.8900118906,
441
+ "f":0.8690856313
442
  },
443
  "PERSON":{
444
+ "p":0.9398162813,
445
+ "r":0.9683420366,
446
+ "f":0.953865938
447
  },
448
  "NORP":{
449
+ "p":0.9253968254,
450
  "r":0.9328,
451
+ "f":0.9290836653
 
 
 
 
 
452
  },
453
  "PRODUCT":{
454
+ "p":0.6804733728,
455
+ "r":0.5450236967,
456
+ "f":0.6052631579
457
  },
458
  "TIME":{
459
+ "p":0.7663043478,
460
+ "r":0.8245614035,
461
+ "f":0.7943661972
462
  },
463
  "EVENT":{
464
+ "p":0.7898550725,
465
+ "r":0.6264367816,
466
+ "f":0.6987179487
467
  },
468
  "WORK_OF_ART":{
469
+ "p":0.6514285714,
470
+ "r":0.587628866,
471
+ "f":0.6178861789
472
+ },
473
+ "LAW":{
474
+ "p":0.6363636364,
475
+ "r":0.65625,
476
+ "f":0.6461538462
477
  },
478
  "MONEY":{
479
+ "p":0.9109506619,
480
  "r":0.893742621,
481
+ "f":0.9022646007
482
  },
483
  "PERCENT":{
484
+ "p":0.9224683544,
485
+ "r":0.8928024502,
486
+ "f":0.9073929961
487
  },
488
  "LANGUAGE":{
489
+ "p":1.0,
490
+ "r":0.71875,
491
+ "f":0.8363636364
492
  }
493
  },
494
+ "speed":6031.0542416801
495
  },
496
  "sources":[
497
  {
 
520
  }
521
  ],
522
  "requirements":[
523
+ "spacy-transformers>=1.2.0.dev0,<1.3.0"
524
  ]
525
  }
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:85399156cfbcccd445d57ad20fb69501f94d4472fe023541943eb1cce091089e
3
  size 313773
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b00f4059860e5bafba1d9d8e42b37a0978d5fe55bf2026a572b3875c2081a707
3
  size 313773
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13fbb91e2cd4e1e7d498ac21ffa5748fd619fba0eb0063552c12b1affac15806
3
  size 639549
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94ffa112cbac1c706c1e420bb466279caf88349f61815467daebfc908c0ac1d6
3
  size 639549
tagger/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:022f0ff017152cb4e4d603f8f116bca98460c2d6bcdc5d46256b858ebf20ca86
3
  size 151366
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc8849fe785a554a552694eeadb6db0be49c1bf1653a0a9c3c2d7600806bf8a1
3
  size 151366
tokenizer CHANGED
The diff for this file is too large to render. See raw diff
 
transformer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b5837f06c42711b7554c65f87766f7bf6bc9604438869761082379f1c188de2b
3
- size 502027935
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c3d77b4e98ec4e0b2bca0542fffc7aa788a665bc03df6eb2d054f7c6fbd818fa
3
+ size 502027993