adrianeboyd commited on
Commit
e8e4307
1 Parent(s): a8035b6

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -14,41 +14,41 @@ model-index:
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
 
@@ -57,8 +57,8 @@ English transformer pipeline (Transformer(name='roberta-base', piece_encoder='by
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) |
@@ -88,12 +88,12 @@ English transformer pipeline (Transformer(name='roberta-base', piece_encoder='by
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 |
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.9008293365
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.9029947917
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.9019107643
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9812819818
31
  - task:
32
  name: UNLABELED_DEPENDENCIES
33
  type: token-classification
34
  metrics:
35
  - name: Unlabeled Attachment Score (UAS)
36
  type: f_score
37
+ value: 0.9526219812
38
  - task:
39
  name: LABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Labeled Attachment Score (LAS)
43
  type: f_score
44
+ value: 0.9390746643
45
  - task:
46
  name: SENTS
47
  type: token-classification
48
  metrics:
49
  - name: Sentences F-Score
50
  type: f_score
51
+ value: 0.9011225055
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** | `3.7.3` |
61
+ | **spaCy** | `>=3.7.2,<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` | 98.13 |
92
+ | `SENTS_P` | 94.89 |
93
+ | `SENTS_R` | 85.79 |
94
+ | `SENTS_F` | 90.11 |
95
+ | `DEP_UAS` | 95.26 |
96
+ | `DEP_LAS` | 93.91 |
97
+ | `ENTS_P` | 90.08 |
98
+ | `ENTS_R` | 90.30 |
99
+ | `ENTS_F` | 90.19 |
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": 0.9815755741,
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
  }
3
  "token_p": 0.9956819193,
4
  "token_r": 0.9957659295,
5
  "token_f": 0.9957239226,
6
+ "tag_acc": 0.9812819818,
7
+ "sents_p": 0.9489237505,
8
+ "sents_r": 0.8579061943,
9
+ "sents_f": 0.9011225055,
10
+ "dep_uas": 0.9526219812,
11
+ "dep_las": 0.9390746643,
12
  "dep_las_per_type": {
13
  "prep": {
14
+ "p": 0.9223201786,
15
+ "r": 0.9249098843,
16
+ "f": 0.9236132161
17
  },
18
  "det": {
19
+ "p": 0.990090935,
20
+ "r": 0.9899698279,
21
+ "f": 0.9900303778
22
  },
23
  "pobj": {
24
+ "p": 0.9835570206,
25
+ "r": 0.9842136265,
26
+ "f": 0.983885214
27
  },
28
  "nsubj": {
29
+ "p": 0.9807776705,
30
+ "r": 0.979101862,
31
+ "f": 0.9799390498
32
  },
33
  "aux": {
34
+ "p": 0.9887940235,
35
+ "r": 0.9897623075,
36
+ "f": 0.9892779285
37
  },
38
  "advmod": {
39
+ "p": 0.9001865672,
40
+ "r": 0.8930674743,
41
+ "f": 0.8966128896
42
  },
43
  "relcl": {
44
+ "p": 0.8803418803,
45
+ "r": 0.8969521045,
46
+ "f": 0.8885693746
47
  },
48
  "root": {
49
+ "p": 0.9669463699,
50
+ "r": 0.8742001451,
51
+ "f": 0.9182372506
52
  },
53
  "xcomp": {
54
+ "p": 0.9461705202,
55
+ "r": 0.94005743,
56
+ "f": 0.9431040691
57
  },
58
  "amod": {
59
+ "p": 0.9438537344,
60
+ "r": 0.943181082,
61
+ "f": 0.9435172883
62
  },
63
  "compound": {
64
+ "p": 0.9548618909,
65
+ "r": 0.9472042771,
66
+ "f": 0.9510176694
67
  },
68
  "poss": {
69
+ "p": 0.9867389994,
70
+ "r": 0.98852657,
71
+ "f": 0.9876319759
72
  },
73
  "ccomp": {
74
+ "p": 0.8474957794,
75
+ "r": 0.9201629328,
76
+ "f": 0.8823357094
77
  },
78
  "attr": {
79
+ "p": 0.9543568465,
80
+ "r": 0.9671993272,
81
+ "f": 0.9607351713
82
  },
83
  "case": {
84
+ "p": 0.9890547264,
85
+ "r": 0.994994995,
86
+ "f": 0.9920159681
87
  },
88
  "mark": {
89
+ "p": 0.943876213,
90
+ "r": 0.9536301007,
91
+ "f": 0.9487280875
92
  },
93
  "intj": {
94
+ "p": 0.6127684964,
95
+ "r": 0.7523809524,
96
+ "f": 0.6754357119
97
  },
98
  "advcl": {
99
+ "p": 0.8114080164,
100
+ "r": 0.7952656762,
101
+ "f": 0.8032557548
102
  },
103
  "cc": {
104
+ "p": 0.898903195,
105
+ "r": 0.9018060041,
106
+ "f": 0.9003522598
107
  },
108
  "neg": {
109
+ "p": 0.9633901705,
110
+ "r": 0.9638735575,
111
+ "f": 0.9636318034
112
  },
113
  "conj": {
114
+ "p": 0.8711377246,
115
+ "r": 0.9156596173,
116
+ "f": 0.8928439917
117
  },
118
  "nsubjpass": {
119
+ "p": 0.9503797468,
120
  "r": 0.9625641026,
121
+ "f": 0.956433121
122
  },
123
  "auxpass": {
124
+ "p": 0.9619516562,
125
+ "r": 0.9790432802,
126
+ "f": 0.9704222172
127
  },
128
  "dobj": {
129
+ "p": 0.9721071087,
130
+ "r": 0.9720296438,
131
+ "f": 0.9720683747
132
  },
133
  "nummod": {
134
+ "p": 0.9453538152,
135
+ "r": 0.947979798,
136
+ "f": 0.9466649855
137
  },
138
  "npadvmod": {
139
+ "p": 0.8455314454,
140
+ "r": 0.81669627,
141
+ "f": 0.8308637514
142
  },
143
  "prt": {
144
+ "p": 0.8753180662,
145
+ "r": 0.9247311828,
146
+ "f": 0.8993464052
147
  },
148
  "pcomp": {
149
+ "p": 0.9215277778,
150
+ "r": 0.9292717087,
151
+ "f": 0.9253835425
152
  },
153
  "expl": {
154
+ "p": 0.9935897436,
155
  "r": 0.9957173448,
156
+ "f": 0.9946524064
157
  },
158
  "acl": {
159
+ "p": 0.8507135016,
160
+ "r": 0.8456082924,
161
+ "f": 0.8481532148
162
  },
163
  "agent": {
164
+ "p": 0.9444444444,
165
  "r": 0.9749103943,
166
+ "f": 0.9594356261
167
  },
168
  "dative": {
169
+ "p": 0.8310185185,
170
+ "r": 0.8233944954,
171
+ "f": 0.8271889401
172
  },
173
  "acomp": {
174
+ "p": 0.9469312413,
175
+ "r": 0.9306122449,
176
+ "f": 0.9387008234
177
  },
178
  "dep": {
179
+ "p": 0.4040747029,
180
+ "r": 0.3863636364,
181
+ "f": 0.3950207469
182
  },
183
  "csubj": {
184
+ "p": 0.8882352941,
185
+ "r": 0.8934911243,
186
+ "f": 0.8908554572
187
  },
188
  "quantmod": {
189
+ "p": 0.8506711409,
190
+ "r": 0.8237205524,
191
+ "f": 0.8369789517
192
  },
193
  "nmod": {
194
+ "p": 0.8208248817,
195
+ "r": 0.7397928093,
196
+ "f": 0.7782051282
197
  },
198
  "appos": {
199
+ "p": 0.8061396131,
200
+ "r": 0.831670282,
201
+ "f": 0.8187059577
202
  },
203
  "predet": {
204
+ "p": 0.8503937008,
205
+ "r": 0.9270386266,
206
+ "f": 0.887063655
207
  },
208
  "preconj": {
209
+ "p": 0.6631578947,
210
+ "r": 0.7325581395,
211
+ "f": 0.6961325967
212
  },
213
  "oprd": {
214
+ "p": 0.8792569659,
215
  "r": 0.847761194,
216
+ "f": 0.8632218845
217
+ },
218
+ "csubjpass": {
219
+ "p": 0.8333333333,
220
+ "r": 0.8333333333,
221
+ "f": 0.8333333333
222
  },
223
  "parataxis": {
224
+ "p": 0.6084452975,
225
+ "r": 0.6876355748,
226
+ "f": 0.6456211813
227
  },
228
  "meta": {
229
+ "p": 0.3076923077,
230
+ "r": 0.6923076923,
231
+ "f": 0.426035503
 
 
 
 
 
232
  }
233
  },
234
+ "ents_p": 0.9008293365,
235
+ "ents_r": 0.9029947917,
236
+ "ents_f": 0.9019107643,
237
  "ents_per_type": {
238
  "DATE": {
239
+ "p": 0.8887152235,
240
+ "r": 0.9025396825,
241
+ "f": 0.8955741062
242
  },
243
  "GPE": {
244
+ "p": 0.9587454083,
245
+ "r": 0.9464435146,
246
+ "f": 0.9525547445
247
  },
248
  "ORDINAL": {
249
+ "p": 0.8054711246,
250
+ "r": 0.8229813665,
251
+ "f": 0.8141321045
252
  },
253
  "ORG": {
254
+ "p": 0.9053191489,
255
+ "r": 0.9024390244,
256
+ "f": 0.9038767924
 
 
 
 
 
257
  },
258
  "QUANTITY": {
259
+ "p": 0.7784431138,
260
  "r": 0.7142857143,
261
+ "f": 0.7449856734
262
  },
263
  "LOC": {
264
+ "p": 0.843537415,
265
+ "r": 0.7898089172,
266
+ "f": 0.8157894737
267
  },
268
  "CARDINAL": {
269
+ "p": 0.860915493,
270
+ "r": 0.872175981,
271
+ "f": 0.8665091553
272
  },
273
  "PERSON": {
274
+ "p": 0.9385492556,
275
+ "r": 0.9670365535,
276
+ "f": 0.9525799711
277
  },
278
  "NORP": {
279
+ "p": 0.9271417134,
280
+ "r": 0.9264,
281
+ "f": 0.9267707083
282
+ },
283
+ "FAC": {
284
+ "p": 0.5524861878,
285
+ "r": 0.7692307692,
286
+ "f": 0.6430868167
287
  },
288
  "LAW": {
289
+ "p": 0.5970149254,
290
+ "r": 0.625,
291
+ "f": 0.6106870229
292
  },
293
  "TIME": {
294
+ "p": 0.7486631016,
295
+ "r": 0.8187134503,
296
+ "f": 0.782122905
 
 
 
 
 
297
  },
298
  "PRODUCT": {
299
+ "p": 0.6411483254,
300
+ "r": 0.63507109,
301
+ "f": 0.6380952381
 
 
 
 
 
302
  },
303
  "MONEY": {
304
+ "p": 0.9220779221,
305
+ "r": 0.9220779221,
306
+ "f": 0.9220779221
307
+ },
308
+ "EVENT": {
309
+ "p": 0.842519685,
310
+ "r": 0.6149425287,
311
+ "f": 0.7109634551
312
+ },
313
+ "WORK_OF_ART": {
314
+ "p": 0.7151898734,
315
+ "r": 0.5824742268,
316
+ "f": 0.6420454545
317
  },
318
  "PERCENT": {
319
+ "p": 0.9207606973,
320
+ "r": 0.8897396631,
321
+ "f": 0.9049844237
322
  },
323
  "LANGUAGE": {
324
+ "p": 1.0,
325
+ "r": 0.75,
326
+ "f": 0.8571428571
327
  }
328
  },
329
+ "speed": 3991.5559399451
330
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
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:dd56d80640411c2e81c3b0cfcb6068156a459c259ae11a4ea51c625c751e3e0a
3
- size 457388473
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f72abb34bdf174876bd4267b29b2501677e605e0a251fdc56c163003182ed68b
3
+ size 457413490
meta.json CHANGED
@@ -1,14 +1,14 @@
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":"contact@explosion.ai",
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,
@@ -168,330 +168,330 @@
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
  {
1
  {
2
  "lang":"en",
3
  "name":"core_web_trf",
4
+ "version":"3.7.3",
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":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"MIT",
10
+ "spacy_version":">=3.7.2,<3.8.0",
11
+ "spacy_git_version":"a89eae928",
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":0.9812819818,
172
+ "sents_p":0.9489237505,
173
+ "sents_r":0.8579061943,
174
+ "sents_f":0.9011225055,
175
+ "dep_uas":0.9526219812,
176
+ "dep_las":0.9390746643,
177
  "dep_las_per_type":{
178
  "prep":{
179
+ "p":0.9223201786,
180
+ "r":0.9249098843,
181
+ "f":0.9236132161
182
  },
183
  "det":{
184
+ "p":0.990090935,
185
+ "r":0.9899698279,
186
+ "f":0.9900303778
187
  },
188
  "pobj":{
189
+ "p":0.9835570206,
190
+ "r":0.9842136265,
191
+ "f":0.983885214
192
  },
193
  "nsubj":{
194
+ "p":0.9807776705,
195
+ "r":0.979101862,
196
+ "f":0.9799390498
197
  },
198
  "aux":{
199
+ "p":0.9887940235,
200
+ "r":0.9897623075,
201
+ "f":0.9892779285
202
  },
203
  "advmod":{
204
+ "p":0.9001865672,
205
+ "r":0.8930674743,
206
+ "f":0.8966128896
207
  },
208
  "relcl":{
209
+ "p":0.8803418803,
210
+ "r":0.8969521045,
211
+ "f":0.8885693746
212
  },
213
  "root":{
214
+ "p":0.9669463699,
215
+ "r":0.8742001451,
216
+ "f":0.9182372506
217
  },
218
  "xcomp":{
219
+ "p":0.9461705202,
220
+ "r":0.94005743,
221
+ "f":0.9431040691
222
  },
223
  "amod":{
224
+ "p":0.9438537344,
225
+ "r":0.943181082,
226
+ "f":0.9435172883
227
  },
228
  "compound":{
229
+ "p":0.9548618909,
230
+ "r":0.9472042771,
231
+ "f":0.9510176694
232
  },
233
  "poss":{
234
+ "p":0.9867389994,
235
+ "r":0.98852657,
236
+ "f":0.9876319759
237
  },
238
  "ccomp":{
239
+ "p":0.8474957794,
240
+ "r":0.9201629328,
241
+ "f":0.8823357094
242
  },
243
  "attr":{
244
+ "p":0.9543568465,
245
+ "r":0.9671993272,
246
+ "f":0.9607351713
247
  },
248
  "case":{
249
+ "p":0.9890547264,
250
+ "r":0.994994995,
251
+ "f":0.9920159681
252
  },
253
  "mark":{
254
+ "p":0.943876213,
255
+ "r":0.9536301007,
256
+ "f":0.9487280875
257
  },
258
  "intj":{
259
+ "p":0.6127684964,
260
+ "r":0.7523809524,
261
+ "f":0.6754357119
262
  },
263
  "advcl":{
264
+ "p":0.8114080164,
265
+ "r":0.7952656762,
266
+ "f":0.8032557548
267
  },
268
  "cc":{
269
+ "p":0.898903195,
270
+ "r":0.9018060041,
271
+ "f":0.9003522598
272
  },
273
  "neg":{
274
+ "p":0.9633901705,
275
+ "r":0.9638735575,
276
+ "f":0.9636318034
277
  },
278
  "conj":{
279
+ "p":0.8711377246,
280
+ "r":0.9156596173,
281
+ "f":0.8928439917
282
  },
283
  "nsubjpass":{
284
+ "p":0.9503797468,
285
  "r":0.9625641026,
286
+ "f":0.956433121
287
  },
288
  "auxpass":{
289
+ "p":0.9619516562,
290
+ "r":0.9790432802,
291
+ "f":0.9704222172
292
  },
293
  "dobj":{
294
+ "p":0.9721071087,
295
+ "r":0.9720296438,
296
+ "f":0.9720683747
297
  },
298
  "nummod":{
299
+ "p":0.9453538152,
300
+ "r":0.947979798,
301
+ "f":0.9466649855
302
  },
303
  "npadvmod":{
304
+ "p":0.8455314454,
305
+ "r":0.81669627,
306
+ "f":0.8308637514
307
  },
308
  "prt":{
309
+ "p":0.8753180662,
310
+ "r":0.9247311828,
311
+ "f":0.8993464052
312
  },
313
  "pcomp":{
314
+ "p":0.9215277778,
315
+ "r":0.9292717087,
316
+ "f":0.9253835425
317
  },
318
  "expl":{
319
+ "p":0.9935897436,
320
  "r":0.9957173448,
321
+ "f":0.9946524064
322
  },
323
  "acl":{
324
+ "p":0.8507135016,
325
+ "r":0.8456082924,
326
+ "f":0.8481532148
327
  },
328
  "agent":{
329
+ "p":0.9444444444,
330
  "r":0.9749103943,
331
+ "f":0.9594356261
332
  },
333
  "dative":{
334
+ "p":0.8310185185,
335
+ "r":0.8233944954,
336
+ "f":0.8271889401
337
  },
338
  "acomp":{
339
+ "p":0.9469312413,
340
+ "r":0.9306122449,
341
+ "f":0.9387008234
342
  },
343
  "dep":{
344
+ "p":0.4040747029,
345
+ "r":0.3863636364,
346
+ "f":0.3950207469
347
  },
348
  "csubj":{
349
+ "p":0.8882352941,
350
+ "r":0.8934911243,
351
+ "f":0.8908554572
352
  },
353
  "quantmod":{
354
+ "p":0.8506711409,
355
+ "r":0.8237205524,
356
+ "f":0.8369789517
357
  },
358
  "nmod":{
359
+ "p":0.8208248817,
360
+ "r":0.7397928093,
361
+ "f":0.7782051282
362
  },
363
  "appos":{
364
+ "p":0.8061396131,
365
+ "r":0.831670282,
366
+ "f":0.8187059577
367
  },
368
  "predet":{
369
+ "p":0.8503937008,
370
+ "r":0.9270386266,
371
+ "f":0.887063655
372
  },
373
  "preconj":{
374
+ "p":0.6631578947,
375
+ "r":0.7325581395,
376
+ "f":0.6961325967
377
  },
378
  "oprd":{
379
+ "p":0.8792569659,
380
  "r":0.847761194,
381
+ "f":0.8632218845
382
+ },
383
+ "csubjpass":{
384
+ "p":0.8333333333,
385
+ "r":0.8333333333,
386
+ "f":0.8333333333
387
  },
388
  "parataxis":{
389
+ "p":0.6084452975,
390
+ "r":0.6876355748,
391
+ "f":0.6456211813
392
  },
393
  "meta":{
394
+ "p":0.3076923077,
395
+ "r":0.6923076923,
396
+ "f":0.426035503
 
 
 
 
 
397
  }
398
  },
399
+ "ents_p":0.9008293365,
400
+ "ents_r":0.9029947917,
401
+ "ents_f":0.9019107643,
402
  "ents_per_type":{
403
  "DATE":{
404
+ "p":0.8887152235,
405
+ "r":0.9025396825,
406
+ "f":0.8955741062
407
  },
408
  "GPE":{
409
+ "p":0.9587454083,
410
+ "r":0.9464435146,
411
+ "f":0.9525547445
412
  },
413
  "ORDINAL":{
414
+ "p":0.8054711246,
415
+ "r":0.8229813665,
416
+ "f":0.8141321045
417
  },
418
  "ORG":{
419
+ "p":0.9053191489,
420
+ "r":0.9024390244,
421
+ "f":0.9038767924
 
 
 
 
 
422
  },
423
  "QUANTITY":{
424
+ "p":0.7784431138,
425
  "r":0.7142857143,
426
+ "f":0.7449856734
427
  },
428
  "LOC":{
429
+ "p":0.843537415,
430
+ "r":0.7898089172,
431
+ "f":0.8157894737
432
  },
433
  "CARDINAL":{
434
+ "p":0.860915493,
435
+ "r":0.872175981,
436
+ "f":0.8665091553
437
  },
438
  "PERSON":{
439
+ "p":0.9385492556,
440
+ "r":0.9670365535,
441
+ "f":0.9525799711
442
  },
443
  "NORP":{
444
+ "p":0.9271417134,
445
+ "r":0.9264,
446
+ "f":0.9267707083
447
+ },
448
+ "FAC":{
449
+ "p":0.5524861878,
450
+ "r":0.7692307692,
451
+ "f":0.6430868167
452
  },
453
  "LAW":{
454
+ "p":0.5970149254,
455
+ "r":0.625,
456
+ "f":0.6106870229
457
  },
458
  "TIME":{
459
+ "p":0.7486631016,
460
+ "r":0.8187134503,
461
+ "f":0.782122905
 
 
 
 
 
462
  },
463
  "PRODUCT":{
464
+ "p":0.6411483254,
465
+ "r":0.63507109,
466
+ "f":0.6380952381
 
 
 
 
 
467
  },
468
  "MONEY":{
469
+ "p":0.9220779221,
470
+ "r":0.9220779221,
471
+ "f":0.9220779221
472
+ },
473
+ "EVENT":{
474
+ "p":0.842519685,
475
+ "r":0.6149425287,
476
+ "f":0.7109634551
477
+ },
478
+ "WORK_OF_ART":{
479
+ "p":0.7151898734,
480
+ "r":0.5824742268,
481
+ "f":0.6420454545
482
  },
483
  "PERCENT":{
484
+ "p":0.9207606973,
485
+ "r":0.8897396631,
486
+ "f":0.9049844237
487
  },
488
  "LANGUAGE":{
489
+ "p":1.0,
490
+ "r":0.75,
491
+ "f":0.8571428571
492
  }
493
  },
494
+ "speed":3991.5559399451
495
  },
496
  "sources":[
497
  {
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:00b5b57be1a3766ad68d11e3e6abb06653bc9d768f6a8dea3831f21158cab0fa
3
  size 313857
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:952dd14f98ed0b181283c19092c294507243206b0abfc7e702a193b850f4eeed
3
  size 313857
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:252cbce9c57a485ba0074fc0d2c494f50e39e4f77ab5bb16da2d4a34b3322eb8
3
  size 639633
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:59a6147c5c05d90a5265c8fa6b49aaa8bc8c796be700e55b2511cb95fd207e27
3
  size 639633
tagger/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:487171b7e08a8ae2e94c539f7f3af2a0f4fbe45200e580a463319044bf036920
3
  size 151450
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:023a9b98c9e5b689ea6bab9bdcb240f720c563a89a48199f4c60300a2ff6228d
3
  size 151450
transformer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f25fe24482dcc5c674abbe73b723562c9d6cdd1c3c24697d78ccf5a33a43b80
3
- size 497342613
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:622857d297d82f3771abc9dcac0a5a666344c1f3efbbc0db4a53d5ab4024914e
3
+ size 497343046