Hugging Face's logo

spacy
/
en_core_web_lg

Token Classification
spaCy
English
Eval Results
Model card Files
xet
Community
4
osanseviero commited on
Commit
9a8869b
·
1 Parent(s): fce6aa6

Update spaCy pipeline

Browse files
Files changed (16) hide show
  1. README.md +24 -21
  2. accuracy.json +191 -188
  3. attribute_ruler/patterns +0 -0
  4. config.cfg +29 -31
  5. en_core_web_lg-any-py3-none-any.whl +2 -2
  6. meta.json +194 -191
  7. ner/model +0 -0
  8. parser/model +0 -0
  9. senter/cfg +1 -1
  10. senter/model +0 -0
  11. tagger/cfg +2 -1
  12. tagger/model +0 -0
  13. tok2vec/model +2 -2
  14. tokenizer +0 -0
  15. vocab/strings.json +2 -2
  16. vocab/vectors.cfg +3 -0
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  tags:
3
  - spacy
4
- - sentence-similarity
5
  language:
6
  - en
7
  license: mit
@@ -14,47 +14,47 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8537926165
18
  - name: NER Recall
19
  type: recall
20
- value: 0.8478064904
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.850789024
24
  - task:
25
  name: POS
26
  type: token-classification
27
  metrics:
28
  - name: POS Accuracy
29
  type: accuracy
30
- value: 0.9728657496
31
  - task:
32
  name: SENTER
33
  type: token-classification
34
  metrics:
35
  - name: SENTER Precision
36
  type: precision
37
- value: 0.9029447521
38
  - name: SENTER Recall
39
  type: recall
40
- value: 0.8819183323
41
  - name: SENTER F Score
42
  type: f_score
43
- value: 0.8923076923
44
  - task:
45
  name: UNLABELED_DEPENDENCIES
46
  type: token-classification
47
  metrics:
48
  - name: Unlabeled Dependencies Accuracy
49
  type: accuracy
50
- value: 0.9184566079
51
  - task:
52
  name: LABELED_DEPENDENCIES
53
  type: token-classification
54
  metrics:
55
  - name: Labeled Dependencies Accuracy
56
  type: accuracy
57
- value: 0.9184566079
58
  ---
59
  ### Details: https://spacy.io/models/en#en_core_web_lg
60
 
@@ -63,8 +63,8 @@ English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
63
  | Feature | Description |
64
  | --- | --- |
65
  | **Name** | `en_core_web_lg` |
66
- | **Version** | `3.1.0` |
67
- | **spaCy** | `>=3.1.0,<3.2.0` |
68
  | **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
69
  | **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
70
  | **Vectors** | 684830 keys, 684830 unique vectors (300 dimensions) |
@@ -92,12 +92,15 @@ English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
92
  | Type | Score |
93
  | --- | --- |
94
  | `TOKEN_ACC` | 99.93 |
95
- | `TAG_ACC` | 97.29 |
96
- | `DEP_UAS` | 91.85 |
97
- | `DEP_LAS` | 90.02 |
98
- | `ENTS_P` | 85.38 |
99
- | `ENTS_R` | 84.78 |
100
- | `ENTS_F` | 85.08 |
101
- | `SENTS_P` | 90.29 |
102
- | `SENTS_R` | 88.19 |
103
- | `SENTS_F` | 89.23 |
 
 
 
 
1
  ---
2
  tags:
3
  - spacy
4
+ - token-classification
5
  language:
6
  - en
7
  license: mit
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8574246409
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.8490084135
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8531957725
24
  - task:
25
  name: POS
26
  type: token-classification
27
  metrics:
28
  - name: POS Accuracy
29
  type: accuracy
30
+ value: 0.9741780493
31
  - task:
32
  name: SENTER
33
  type: token-classification
34
  metrics:
35
  - name: SENTER Precision
36
  type: precision
37
+ value: 0.9179358172
38
  - name: SENTER Recall
39
  type: recall
40
+ value: 0.8906260307
41
  - name: SENTER F Score
42
  type: f_score
43
+ value: 0.9040747313
44
  - task:
45
  name: UNLABELED_DEPENDENCIES
46
  type: token-classification
47
  metrics:
48
  - name: Unlabeled Dependencies Accuracy
49
  type: accuracy
50
+ value: 0.9200593914
51
  - task:
52
  name: LABELED_DEPENDENCIES
53
  type: token-classification
54
  metrics:
55
  - name: Labeled Dependencies Accuracy
56
  type: accuracy
57
+ value: 0.9200593914
58
  ---
59
  ### Details: https://spacy.io/models/en#en_core_web_lg
60
 
 
63
  | Feature | Description |
64
  | --- | --- |
65
  | **Name** | `en_core_web_lg` |
66
+ | **Version** | `3.2.0` |
67
+ | **spaCy** | `>=3.2.0,<3.3.0` |
68
  | **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
69
  | **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
70
  | **Vectors** | 684830 keys, 684830 unique vectors (300 dimensions) |
 
92
  | Type | Score |
93
  | --- | --- |
94
  | `TOKEN_ACC` | 99.93 |
95
+ | `TOKEN_P` | 99.57 |
96
+ | `TOKEN_R` | 99.58 |
97
+ | `TOKEN_F` | 99.57 |
98
+ | `TAG_ACC` | 97.42 |
99
+ | `SENTS_P` | 91.79 |
100
+ | `SENTS_R` | 89.06 |
101
+ | `SENTS_F` | 90.41 |
102
+ | `DEP_UAS` | 92.01 |
103
+ | `DEP_LAS` | 90.22 |
104
+ | `ENTS_P` | 85.74 |
105
+ | `ENTS_R` | 84.90 |
106
+ | `ENTS_F` | 85.32 |
accuracy.json CHANGED
@@ -1,145 +1,144 @@
1
  {
2
  "token_acc": 0.9993053983,
3
- "tag_acc": 0.9728657496,
4
- "dep_uas": 0.9184566079,
5
- "dep_las": 0.9001671544,
6
- "ents_p": 0.8537926165,
7
- "ents_r": 0.8478064904,
8
- "ents_f": 0.850789024,
9
- "sents_p": 0.9029447521,
10
- "sents_r": 0.8819183323,
11
- "sents_f": 0.8923076923,
12
- "speed": 9380.6157273927,
13
  "dep_las_per_type": {
14
  "prep": {
15
- "p": 0.8554759314,
16
- "r": 0.8651489281,
17
- "f": 0.86028524
18
  },
19
  "det": {
20
- "p": 0.9781155758,
21
- "r": 0.978594145,
22
- "f": 0.9783548019
23
  },
24
  "pobj": {
25
- "p": 0.9612475634,
26
- "r": 0.9682309052,
27
- "f": 0.9647265969
28
  },
29
  "nsubj": {
30
- "p": 0.9584851987,
31
- "r": 0.9447535597,
32
- "f": 0.9515698431
33
  },
34
  "aux": {
35
- "p": 0.9797459359,
36
- "r": 0.9818392237,
37
- "f": 0.9807914629
38
  },
39
  "advmod": {
40
- "p": 0.8577342232,
41
- "r": 0.8541982164,
42
- "f": 0.855962568
43
  },
44
  "relcl": {
45
- "p": 0.7635782748,
46
- "r": 0.780478955,
47
- "f": 0.7719361206
48
  },
49
  "root": {
50
- "p": 0.9167794317,
51
- "r": 0.8938584339,
52
- "f": 0.9051738535
53
  },
54
  "xcomp": {
55
- "p": 0.8808435852,
56
- "r": 0.8994974874,
57
- "f": 0.8900728112
58
  },
59
  "amod": {
60
- "p": 0.9213768825,
61
- "r": 0.9156462585,
62
- "f": 0.9185026321
63
  },
64
  "compound": {
65
- "p": 0.9190853122,
66
- "r": 0.9311650702,
67
- "f": 0.9250857585
68
  },
69
  "poss": {
70
- "p": 0.9742661842,
71
- "r": 0.9754428341,
72
- "f": 0.9748541541
73
  },
74
  "ccomp": {
75
- "p": 0.7662144583,
76
- "r": 0.8397148676,
77
- "f": 0.8012826742
78
  },
79
  "attr": {
80
- "p": 0.8953068592,
81
- "r": 0.9386038688,
82
- "f": 0.916444262
83
  },
84
  "case": {
85
- "p": 0.9777337952,
86
- "r": 0.988988989,
87
- "f": 0.9833291864
88
  },
89
  "mark": {
90
- "p": 0.9056,
91
- "r": 0.8998410175,
92
- "f": 0.9027113238
93
  },
94
  "intj": {
95
- "p": 0.6828872668,
96
- "r": 0.6168498168,
97
- "f": 0.6481909161
98
  },
99
  "advcl": {
100
- "p": 0.6682631712,
101
- "r": 0.6675900277,
102
- "f": 0.6679264298
103
  },
104
  "cc": {
105
- "p": 0.8339341504,
106
- "r": 0.8300442531,
107
- "f": 0.831984655
108
  },
109
  "neg": {
110
- "p": 0.9440838742,
111
- "r": 0.9488208731,
112
- "f": 0.9464464464
113
  },
114
  "conj": {
115
- "p": 0.7651796778,
116
- "r": 0.7773162135,
117
- "f": 0.7712001998
118
  },
119
  "nsubjpass": {
120
- "p": 0.9289074752,
121
- "r": 0.9112820513,
122
- "f": 0.9200103546
123
  },
124
  "auxpass": {
125
- "p": 0.9491298527,
126
- "r": 0.9690205011,
127
- "f": 0.9589720469
128
  },
129
  "dobj": {
130
- "p": 0.9230350195,
131
- "r": 0.9451749143,
132
- "f": 0.9339737785
133
  },
134
  "nummod": {
135
- "p": 0.9318642351,
136
- "r": 0.929040404,
137
- "f": 0.930450177
138
  },
139
  "npadvmod": {
140
- "p": 0.7657013915,
141
- "r": 0.723268206,
142
- "f": 0.7438801608
143
  },
144
  "prt": {
145
  "p": 0.8190082645,
@@ -147,64 +146,64 @@
147
  "f": 0.8521066208
148
  },
149
  "pcomp": {
150
- "p": 0.8813202247,
151
- "r": 0.8788515406,
152
- "f": 0.8800841515
153
  },
154
  "expl": {
155
- "p": 0.983014862,
156
- "r": 0.9914346895,
157
- "f": 0.987206823
158
  },
159
  "acl": {
160
- "p": 0.7536148062,
161
- "r": 0.7108565194,
162
- "f": 0.7316114542
163
  },
164
  "agent": {
165
- "p": 0.8974358974,
166
  "r": 0.9408602151,
167
- "f": 0.9186351706
168
  },
169
  "dative": {
170
- "p": 0.7647058824,
171
- "r": 0.6857798165,
172
- "f": 0.723095526
173
  },
174
  "acomp": {
175
- "p": 0.9172413793,
176
- "r": 0.9047619048,
177
- "f": 0.9109589041
178
  },
179
  "dep": {
180
- "p": 0.3886792453,
181
- "r": 0.1672077922,
182
- "f": 0.2338251986
183
  },
184
  "csubj": {
185
- "p": 0.7133333333,
186
- "r": 0.6331360947,
187
- "f": 0.670846395
188
  },
189
  "quantmod": {
190
- "p": 0.8654545455,
191
- "r": 0.7733549959,
192
- "f": 0.8168168168
193
  },
194
  "nmod": {
195
- "p": 0.7545526524,
196
- "r": 0.5807434491,
197
- "f": 0.6563360882
198
  },
199
  "appos": {
200
- "p": 0.6708074534,
201
- "r": 0.6559652928,
202
- "f": 0.663303356
203
  },
204
  "predet": {
205
- "p": 0.828685259,
206
- "r": 0.8927038627,
207
- "f": 0.8595041322
208
  },
209
  "preconj": {
210
  "p": 0.5784313725,
@@ -212,19 +211,19 @@
212
  "f": 0.6276595745
213
  },
214
  "oprd": {
215
- "p": 0.8758865248,
216
- "r": 0.7373134328,
217
- "f": 0.8006482982
218
  },
219
  "parataxis": {
220
- "p": 0.6073446328,
221
- "r": 0.4663774403,
222
- "f": 0.527607362
223
  },
224
  "meta": {
225
- "p": 0.95,
226
- "r": 0.3653846154,
227
- "f": 0.5277777778
228
  },
229
  "csubjpass": {
230
  "p": 0.5555555556,
@@ -232,96 +231,100 @@
232
  "f": 0.6666666667
233
  }
234
  },
 
 
 
235
  "ents_per_type": {
236
  "DATE": {
237
- "p": 0.8650594865,
238
- "r": 0.8771428571,
239
- "f": 0.8710592686
240
  },
241
  "GPE": {
242
- "p": 0.916572717,
243
- "r": 0.9071129707,
244
- "f": 0.9118183093
245
  },
246
  "ORDINAL": {
247
- "p": 0.785915493,
248
  "r": 0.8664596273,
249
- "f": 0.8242245199
250
  },
251
  "ORG": {
252
- "p": 0.8143681175,
253
- "r": 0.8234358431,
254
- "f": 0.8188768785
255
  },
256
  "QUANTITY": {
257
- "p": 0.7769784173,
258
- "r": 0.5934065934,
259
- "f": 0.6728971963
260
  },
261
  "CARDINAL": {
262
- "p": 0.8160403814,
263
- "r": 0.8650416171,
264
- "f": 0.8398268398
265
  },
266
  "PERSON": {
267
- "p": 0.8838289963,
268
- "r": 0.9311357702,
269
- "f": 0.9068658614
270
  },
271
  "NORP": {
272
- "p": 0.8933969769,
273
- "r": 0.8984,
274
- "f": 0.8958915038
 
 
 
 
 
275
  },
276
  "FAC": {
277
- "p": 0.4141414141,
278
- "r": 0.3153846154,
279
- "f": 0.3580786026
280
  },
281
  "TIME": {
282
  "p": 0.7396825397,
283
  "r": 0.6812865497,
284
  "f": 0.7092846271
285
  },
286
- "LOC": {
287
- "p": 0.6937269373,
288
- "r": 0.5987261146,
289
- "f": 0.6427350427
290
- },
291
- "MONEY": {
292
- "p": 0.9008363202,
293
- "r": 0.8902007084,
294
- "f": 0.8954869359
295
  },
296
  "EVENT": {
297
- "p": 0.597826087,
298
- "r": 0.316091954,
299
- "f": 0.4135338346
300
  },
301
  "WORK_OF_ART": {
302
- "p": 0.4827586207,
303
- "r": 0.2886597938,
304
- "f": 0.3612903226
305
  },
306
  "LAW": {
307
- "p": 0.5,
308
- "r": 0.3125,
309
- "f": 0.3846153846
310
  },
311
- "PERCENT": {
312
- "p": 0.9089456869,
313
- "r": 0.8713629403,
314
- "f": 0.8897576231
315
  },
316
- "PRODUCT": {
317
- "p": 0.6195652174,
318
- "r": 0.2701421801,
319
- "f": 0.3762376238
320
  },
321
  "LANGUAGE": {
322
- "p": 0.7727272727,
323
- "r": 0.53125,
324
- "f": 0.6296296296
325
  }
326
- }
 
327
  }
 
1
  {
2
  "token_acc": 0.9993053983,
3
+ "token_p": 0.9956742163,
4
+ "token_r": 0.9957505887,
5
+ "token_f": 0.9957124011,
6
+ "tag_acc": 0.9741780493,
7
+ "sents_p": 0.9179358172,
8
+ "sents_r": 0.8906260307,
9
+ "sents_f": 0.9040747313,
10
+ "dep_uas": 0.9200593914,
11
+ "dep_las": 0.9021556352,
 
12
  "dep_las_per_type": {
13
  "prep": {
14
+ "p": 0.8578239976,
15
+ "r": 0.8669702144,
16
+ "f": 0.8623728558
17
  },
18
  "det": {
19
+ "p": 0.9798012706,
20
+ "r": 0.9809997554,
21
+ "f": 0.9804001467
22
  },
23
  "pobj": {
24
+ "p": 0.9617211838,
25
+ "r": 0.9698409582,
26
+ "f": 0.9657640043
27
  },
28
  "nsubj": {
29
+ "p": 0.9608471258,
30
+ "r": 0.9461555312,
31
+ "f": 0.9534447363
32
  },
33
  "aux": {
34
+ "p": 0.9807231056,
35
+ "r": 0.9828184813,
36
+ "f": 0.9817696754
37
  },
38
  "advmod": {
39
+ "p": 0.8600169779,
40
+ "r": 0.8523472993,
41
+ "f": 0.8561649624
42
  },
43
  "relcl": {
44
+ "p": 0.755259467,
45
+ "r": 0.7815674891,
46
+ "f": 0.7681883024
47
  },
48
  "root": {
49
+ "p": 0.9196325281,
50
+ "r": 0.8914836071,
51
+ "f": 0.905339318
52
  },
53
  "xcomp": {
54
+ "p": 0.8886906885,
55
+ "r": 0.8941134243,
56
+ "f": 0.8913938093
57
  },
58
  "amod": {
59
+ "p": 0.9216490817,
60
+ "r": 0.9168124393,
61
+ "f": 0.9192243983
62
  },
63
  "compound": {
64
+ "p": 0.9188224309,
65
+ "r": 0.9316662954,
66
+ "f": 0.9251997898
67
  },
68
  "poss": {
69
+ "p": 0.9760755931,
70
+ "r": 0.9772544283,
71
+ "f": 0.976664655
72
  },
73
  "ccomp": {
74
+ "p": 0.7797340326,
75
+ "r": 0.8478615071,
76
+ "f": 0.8123719387
77
  },
78
  "attr": {
79
+ "p": 0.8931845357,
80
+ "r": 0.9423885618,
81
+ "f": 0.9171270718
82
  },
83
  "case": {
84
+ "p": 0.9782823297,
85
+ "r": 0.991991992,
86
+ "f": 0.9850894632
87
  },
88
  "mark": {
89
+ "p": 0.9105669417,
90
+ "r": 0.9064652888,
91
+ "f": 0.9085114859
92
  },
93
  "intj": {
94
+ "p": 0.6737089202,
95
+ "r": 0.6307692308,
96
+ "f": 0.6515323496
97
  },
98
  "advcl": {
99
+ "p": 0.67003282,
100
+ "r": 0.6683455049,
101
+ "f": 0.6691880988
102
  },
103
  "cc": {
104
+ "p": 0.8372232916,
105
+ "r": 0.8323167085,
106
+ "f": 0.8347627901
107
  },
108
  "neg": {
109
+ "p": 0.9408548708,
110
+ "r": 0.9498243853,
111
+ "f": 0.9453183521
112
  },
113
  "conj": {
114
+ "p": 0.7653624433,
115
+ "r": 0.7854984894,
116
+ "f": 0.7752997453
117
  },
118
  "nsubjpass": {
119
+ "p": 0.9327377824,
120
+ "r": 0.9102564103,
121
+ "f": 0.9213599792
122
  },
123
  "auxpass": {
124
+ "p": 0.9543624161,
125
+ "r": 0.9717539863,
126
+ "f": 0.962979684
127
  },
128
  "dobj": {
129
+ "p": 0.9222826087,
130
+ "r": 0.9466092916,
131
+ "f": 0.9342876244
132
  },
133
  "nummod": {
134
+ "p": 0.9430395913,
135
+ "r": 0.9323232323,
136
+ "f": 0.9376507937
137
  },
138
  "npadvmod": {
139
+ "p": 0.7866254349,
140
+ "r": 0.7229129663,
141
+ "f": 0.7534246575
142
  },
143
  "prt": {
144
  "p": 0.8190082645,
 
146
  "f": 0.8521066208
147
  },
148
  "pcomp": {
149
+ "p": 0.879020979,
150
+ "r": 0.8802521008,
151
+ "f": 0.8796361092
152
  },
153
  "expl": {
154
+ "p": 0.9809725159,
155
+ "r": 0.9935760171,
156
+ "f": 0.9872340426
157
  },
158
  "acl": {
159
+ "p": 0.7443997702,
160
+ "r": 0.7070376432,
161
+ "f": 0.7252378288
162
  },
163
  "agent": {
164
+ "p": 0.8928571429,
165
  "r": 0.9408602151,
166
+ "f": 0.9162303665
167
  },
168
  "dative": {
169
+ "p": 0.7729591837,
170
+ "r": 0.6949541284,
171
+ "f": 0.731884058
172
  },
173
  "acomp": {
174
+ "p": 0.9102505695,
175
+ "r": 0.906122449,
176
+ "f": 0.9081818182
177
  },
178
  "dep": {
179
+ "p": 0.4491525424,
180
+ "r": 0.1720779221,
181
+ "f": 0.2488262911
182
  },
183
  "csubj": {
184
+ "p": 0.7243589744,
185
+ "r": 0.6686390533,
186
+ "f": 0.6953846154
187
  },
188
  "quantmod": {
189
+ "p": 0.8686779059,
190
+ "r": 0.7952883834,
191
+ "f": 0.8303647159
192
  },
193
  "nmod": {
194
+ "p": 0.76,
195
+ "r": 0.5789152956,
196
+ "f": 0.6572120374
197
  },
198
  "appos": {
199
+ "p": 0.7035040431,
200
+ "r": 0.6793926247,
201
+ "f": 0.6912381373
202
  },
203
  "predet": {
204
+ "p": 0.8300395257,
205
+ "r": 0.9012875536,
206
+ "f": 0.8641975309
207
  },
208
  "preconj": {
209
  "p": 0.5784313725,
 
211
  "f": 0.6276595745
212
  },
213
  "oprd": {
214
+ "p": 0.8379310345,
215
+ "r": 0.7253731343,
216
+ "f": 0.7776
217
  },
218
  "parataxis": {
219
+ "p": 0.6312849162,
220
+ "r": 0.4902386117,
221
+ "f": 0.5518925519
222
  },
223
  "meta": {
224
+ "p": 0.7647058824,
225
+ "r": 0.25,
226
+ "f": 0.3768115942
227
  },
228
  "csubjpass": {
229
  "p": 0.5555555556,
 
231
  "f": 0.6666666667
232
  }
233
  },
234
+ "ents_p": 0.8574246409,
235
+ "ents_r": 0.8490084135,
236
+ "ents_f": 0.8531957725,
237
  "ents_per_type": {
238
  "DATE": {
239
+ "p": 0.8695102686,
240
+ "r": 0.8736507937,
241
+ "f": 0.8715756136
242
  },
243
  "GPE": {
244
+ "p": 0.9231641622,
245
+ "r": 0.9082287308,
246
+ "f": 0.9156355456
247
  },
248
  "ORDINAL": {
249
+ "p": 0.7971428571,
250
  "r": 0.8664596273,
251
+ "f": 0.8303571429
252
  },
253
  "ORG": {
254
+ "p": 0.8194444444,
255
+ "r": 0.8290031813,
256
+ "f": 0.8241960991
257
  },
258
  "QUANTITY": {
259
+ "p": 0.7959183673,
260
+ "r": 0.6428571429,
261
+ "f": 0.7112462006
262
  },
263
  "CARDINAL": {
264
+ "p": 0.8221709007,
265
+ "r": 0.8466111772,
266
+ "f": 0.834212068
267
  },
268
  "PERSON": {
269
+ "p": 0.8823895457,
270
+ "r": 0.9255874674,
271
+ "f": 0.9034724435
272
  },
273
  "NORP": {
274
+ "p": 0.9027888446,
275
+ "r": 0.9064,
276
+ "f": 0.9045908184
277
+ },
278
+ "LOC": {
279
+ "p": 0.7185185185,
280
+ "r": 0.6178343949,
281
+ "f": 0.6643835616
282
  },
283
  "FAC": {
284
+ "p": 0.4263565891,
285
+ "r": 0.4230769231,
286
+ "f": 0.4247104247
287
  },
288
  "TIME": {
289
  "p": 0.7396825397,
290
  "r": 0.6812865497,
291
  "f": 0.7092846271
292
  },
293
+ "PRODUCT": {
294
+ "p": 0.6022727273,
295
+ "r": 0.2511848341,
296
+ "f": 0.3545150502
 
 
 
 
 
297
  },
298
  "EVENT": {
299
+ "p": 0.5882352941,
300
+ "r": 0.2873563218,
301
+ "f": 0.3861003861
302
  },
303
  "WORK_OF_ART": {
304
+ "p": 0.4692307692,
305
+ "r": 0.3144329897,
306
+ "f": 0.3765432099
307
  },
308
  "LAW": {
309
+ "p": 0.5272727273,
310
+ "r": 0.453125,
311
+ "f": 0.487394958
312
  },
313
+ "MONEY": {
314
+ "p": 0.8990498812,
315
+ "r": 0.893742621,
316
+ "f": 0.8963883955
317
  },
318
+ "PERCENT": {
319
+ "p": 0.9202551834,
320
+ "r": 0.8836140888,
321
+ "f": 0.9015625
322
  },
323
  "LANGUAGE": {
324
+ "p": 0.8,
325
+ "r": 0.625,
326
+ "f": 0.701754386
327
  }
328
+ },
329
+ "speed": 7471.5995598921
330
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -1,10 +1,8 @@
1
  [paths]
2
- train = "corpus/en-core-web/train.spacy"
3
- dev = "corpus/en-core-web/dev.spacy"
4
- vectors = "corpus/en_vectors"
5
- raw = null
6
  init_tok2vec = null
7
- vocab_data = null
8
 
9
  [system]
10
  gpu_allocator = null
@@ -24,6 +22,7 @@ tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
24
 
25
  [components.attribute_ruler]
26
  factory = "attribute_ruler"
 
27
  validate = false
28
 
29
  [components.lemmatizer]
@@ -31,11 +30,13 @@ factory = "lemmatizer"
31
  mode = "rule"
32
  model = null
33
  overwrite = false
 
34
 
35
  [components.ner]
36
  factory = "ner"
37
  incorrect_spans_key = null
38
  moves = null
 
39
  update_with_oracle_cut_size = 100
40
 
41
  [components.ner.model]
@@ -53,8 +54,8 @@ nO = null
53
  [components.ner.model.tok2vec.embed]
54
  @architectures = "spacy.MultiHashEmbed.v2"
55
  width = 96
56
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
57
- rows = [5000,2500,2500,2500]
58
  include_static_vectors = true
59
 
60
  [components.ner.model.tok2vec.encode]
@@ -69,6 +70,7 @@ factory = "parser"
69
  learn_tokens = false
70
  min_action_freq = 30
71
  moves = null
 
72
  update_with_oracle_cut_size = 100
73
 
74
  [components.parser.model]
@@ -87,6 +89,8 @@ upstream = "tok2vec"
87
 
88
  [components.senter]
89
  factory = "senter"
 
 
90
 
91
  [components.senter.model]
92
  @architectures = "spacy.Tagger.v1"
@@ -98,8 +102,8 @@ nO = null
98
  [components.senter.model.tok2vec.embed]
99
  @architectures = "spacy.MultiHashEmbed.v2"
100
  width = 16
101
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
102
- rows = [1000,500,500,500]
103
  include_static_vectors = true
104
 
105
  [components.senter.model.tok2vec.encode]
@@ -111,6 +115,8 @@ maxout_pieces = 2
111
 
112
  [components.tagger]
113
  factory = "tagger"
 
 
114
 
115
  [components.tagger.model]
116
  @architectures = "spacy.Tagger.v1"
@@ -130,8 +136,8 @@ factory = "tok2vec"
130
  [components.tok2vec.model.embed]
131
  @architectures = "spacy.MultiHashEmbed.v2"
132
  width = ${components.tok2vec.model.encode:width}
133
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
134
- rows = [5000,2500,2500,2500]
135
  include_static_vectors = true
136
 
137
  [components.tok2vec.model.encode]
@@ -145,27 +151,19 @@ maxout_pieces = 3
145
 
146
  [corpora.dev]
147
  @readers = "spacy.Corpus.v1"
148
- limit = 0
149
- max_length = 0
150
- path = ${paths:dev}
151
  gold_preproc = false
 
 
152
  augmenter = null
153
 
154
  [corpora.train]
155
  @readers = "spacy.Corpus.v1"
156
- path = ${paths:train}
157
- max_length = 5000
158
  gold_preproc = false
 
159
  limit = 0
160
-
161
- [corpora.train.augmenter]
162
- @augmenters = "spacy.orth_variants.v1"
163
- level = 0.2
164
- lower = 0.5
165
-
166
- [corpora.train.augmenter.orth_variants]
167
- @readers = "srsly.read_json.v1"
168
- path = "assets/orth_variants.json"
169
 
170
  [training]
171
  train_corpus = "corpora.train"
@@ -196,9 +194,8 @@ compound = 1.001
196
  t = 0.0
197
 
198
  [training.logger]
199
- @loggers = "spacy.WandbLogger.v1"
200
- project_name = "spacy-v3.0.0a2"
201
- remove_config_values = []
202
 
203
  [training.optimizer]
204
  @optimizers = "Adam.v1"
@@ -219,16 +216,17 @@ dep_las_per_type = null
219
  sents_p = null
220
  sents_r = null
221
  sents_f = 0.02
222
- lemma_acc = 0.33
223
- ents_f = 0.33
224
  ents_p = 0.0
225
  ents_r = 0.0
226
  ents_per_type = null
 
227
 
228
  [pretraining]
229
 
230
  [initialize]
231
- vocab_data = ${paths.vocab_data}
232
  vectors = ${paths.vectors}
233
  init_tok2vec = ${paths.init_tok2vec}
234
  before_init = null
 
1
  [paths]
2
+ train = null
3
+ dev = null
4
+ vectors = null
 
5
  init_tok2vec = null
 
6
 
7
  [system]
8
  gpu_allocator = null
 
22
 
23
  [components.attribute_ruler]
24
  factory = "attribute_ruler"
25
+ scorer = {"@scorers":"spacy.attribute_ruler_scorer.v1"}
26
  validate = false
27
 
28
  [components.lemmatizer]
 
30
  mode = "rule"
31
  model = null
32
  overwrite = false
33
+ scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
34
 
35
  [components.ner]
36
  factory = "ner"
37
  incorrect_spans_key = null
38
  moves = null
39
+ scorer = {"@scorers":"spacy.ner_scorer.v1"}
40
  update_with_oracle_cut_size = 100
41
 
42
  [components.ner.model]
 
54
  [components.ner.model.tok2vec.embed]
55
  @architectures = "spacy.MultiHashEmbed.v2"
56
  width = 96
57
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
58
+ rows = [5000,2500,2500,2500,100]
59
  include_static_vectors = true
60
 
61
  [components.ner.model.tok2vec.encode]
 
70
  learn_tokens = false
71
  min_action_freq = 30
72
  moves = null
73
+ scorer = {"@scorers":"spacy.parser_scorer.v1"}
74
  update_with_oracle_cut_size = 100
75
 
76
  [components.parser.model]
 
89
 
90
  [components.senter]
91
  factory = "senter"
92
+ overwrite = false
93
+ scorer = {"@scorers":"spacy.senter_scorer.v1"}
94
 
95
  [components.senter.model]
96
  @architectures = "spacy.Tagger.v1"
 
102
  [components.senter.model.tok2vec.embed]
103
  @architectures = "spacy.MultiHashEmbed.v2"
104
  width = 16
105
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
106
+ rows = [1000,500,500,500,50]
107
  include_static_vectors = true
108
 
109
  [components.senter.model.tok2vec.encode]
 
115
 
116
  [components.tagger]
117
  factory = "tagger"
118
+ overwrite = false
119
+ scorer = {"@scorers":"spacy.tagger_scorer.v1"}
120
 
121
  [components.tagger.model]
122
  @architectures = "spacy.Tagger.v1"
 
136
  [components.tok2vec.model.embed]
137
  @architectures = "spacy.MultiHashEmbed.v2"
138
  width = ${components.tok2vec.model.encode:width}
139
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
140
+ rows = [5000,2500,2500,2500,100]
141
  include_static_vectors = true
142
 
143
  [components.tok2vec.model.encode]
 
151
 
152
  [corpora.dev]
153
  @readers = "spacy.Corpus.v1"
154
+ path = ${paths.dev}
 
 
155
  gold_preproc = false
156
+ max_length = 0
157
+ limit = 0
158
  augmenter = null
159
 
160
  [corpora.train]
161
  @readers = "spacy.Corpus.v1"
162
+ path = ${paths.train}
 
163
  gold_preproc = false
164
+ max_length = 0
165
  limit = 0
166
+ augmenter = null
 
 
 
 
 
 
 
 
167
 
168
  [training]
169
  train_corpus = "corpora.train"
 
194
  t = 0.0
195
 
196
  [training.logger]
197
+ @loggers = "spacy.ConsoleLogger.v1"
198
+ progress_bar = false
 
199
 
200
  [training.optimizer]
201
  @optimizers = "Adam.v1"
 
216
  sents_p = null
217
  sents_r = null
218
  sents_f = 0.02
219
+ lemma_acc = 0.5
220
+ ents_f = 0.16
221
  ents_p = 0.0
222
  ents_r = 0.0
223
  ents_per_type = null
224
+ speed = 0.0
225
 
226
  [pretraining]
227
 
228
  [initialize]
229
+ vocab_data = null
230
  vectors = ${paths.vectors}
231
  init_tok2vec = ${paths.init_tok2vec}
232
  before_init = null
en_core_web_lg-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:57f57f20bc91bca79bd42c22f4f137eb728914553027bce88b616f4eeabd5d8c
3
- size 777079810
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae37a39df924099ea9e9d9d4d2912bbed9c534089c9f5f3ac0a3564ca7815521
3
+ size 777382778
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"en",
3
  "name":"core_web_lg",
4
- "version":"3.1.0",
5
  "description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"[email protected]",
8
  "url":"https://explosion.ai",
9
  "license":"MIT",
10
- "spacy_version":">=3.1.0,<3.2.0",
11
- "spacy_git_version":"caba63b74",
12
  "vectors":{
13
  "width":300,
14
  "vectors":684830,
@@ -170,146 +170,145 @@
170
  ],
171
  "performance":{
172
  "token_acc":0.9993053983,
173
- "tag_acc":0.9728657496,
174
- "dep_uas":0.9184566079,
175
- "dep_las":0.9001671544,
176
- "ents_p":0.8537926165,
177
- "ents_r":0.8478064904,
178
- "ents_f":0.850789024,
179
- "sents_p":0.9029447521,
180
- "sents_r":0.8819183323,
181
- "sents_f":0.8923076923,
182
- "speed":9380.6157273927,
183
  "dep_las_per_type":{
184
  "prep":{
185
- "p":0.8554759314,
186
- "r":0.8651489281,
187
- "f":0.86028524
188
  },
189
  "det":{
190
- "p":0.9781155758,
191
- "r":0.978594145,
192
- "f":0.9783548019
193
  },
194
  "pobj":{
195
- "p":0.9612475634,
196
- "r":0.9682309052,
197
- "f":0.9647265969
198
  },
199
  "nsubj":{
200
- "p":0.9584851987,
201
- "r":0.9447535597,
202
- "f":0.9515698431
203
  },
204
  "aux":{
205
- "p":0.9797459359,
206
- "r":0.9818392237,
207
- "f":0.9807914629
208
  },
209
  "advmod":{
210
- "p":0.8577342232,
211
- "r":0.8541982164,
212
- "f":0.855962568
213
  },
214
  "relcl":{
215
- "p":0.7635782748,
216
- "r":0.780478955,
217
- "f":0.7719361206
218
  },
219
  "root":{
220
- "p":0.9167794317,
221
- "r":0.8938584339,
222
- "f":0.9051738535
223
  },
224
  "xcomp":{
225
- "p":0.8808435852,
226
- "r":0.8994974874,
227
- "f":0.8900728112
228
  },
229
  "amod":{
230
- "p":0.9213768825,
231
- "r":0.9156462585,
232
- "f":0.9185026321
233
  },
234
  "compound":{
235
- "p":0.9190853122,
236
- "r":0.9311650702,
237
- "f":0.9250857585
238
  },
239
  "poss":{
240
- "p":0.9742661842,
241
- "r":0.9754428341,
242
- "f":0.9748541541
243
  },
244
  "ccomp":{
245
- "p":0.7662144583,
246
- "r":0.8397148676,
247
- "f":0.8012826742
248
  },
249
  "attr":{
250
- "p":0.8953068592,
251
- "r":0.9386038688,
252
- "f":0.916444262
253
  },
254
  "case":{
255
- "p":0.9777337952,
256
- "r":0.988988989,
257
- "f":0.9833291864
258
  },
259
  "mark":{
260
- "p":0.9056,
261
- "r":0.8998410175,
262
- "f":0.9027113238
263
  },
264
  "intj":{
265
- "p":0.6828872668,
266
- "r":0.6168498168,
267
- "f":0.6481909161
268
  },
269
  "advcl":{
270
- "p":0.6682631712,
271
- "r":0.6675900277,
272
- "f":0.6679264298
273
  },
274
  "cc":{
275
- "p":0.8339341504,
276
- "r":0.8300442531,
277
- "f":0.831984655
278
  },
279
  "neg":{
280
- "p":0.9440838742,
281
- "r":0.9488208731,
282
- "f":0.9464464464
283
  },
284
  "conj":{
285
- "p":0.7651796778,
286
- "r":0.7773162135,
287
- "f":0.7712001998
288
  },
289
  "nsubjpass":{
290
- "p":0.9289074752,
291
- "r":0.9112820513,
292
- "f":0.9200103546
293
  },
294
  "auxpass":{
295
- "p":0.9491298527,
296
- "r":0.9690205011,
297
- "f":0.9589720469
298
  },
299
  "dobj":{
300
- "p":0.9230350195,
301
- "r":0.9451749143,
302
- "f":0.9339737785
303
  },
304
  "nummod":{
305
- "p":0.9318642351,
306
- "r":0.929040404,
307
- "f":0.930450177
308
  },
309
  "npadvmod":{
310
- "p":0.7657013915,
311
- "r":0.723268206,
312
- "f":0.7438801608
313
  },
314
  "prt":{
315
  "p":0.8190082645,
@@ -317,64 +316,64 @@
317
  "f":0.8521066208
318
  },
319
  "pcomp":{
320
- "p":0.8813202247,
321
- "r":0.8788515406,
322
- "f":0.8800841515
323
  },
324
  "expl":{
325
- "p":0.983014862,
326
- "r":0.9914346895,
327
- "f":0.987206823
328
  },
329
  "acl":{
330
- "p":0.7536148062,
331
- "r":0.7108565194,
332
- "f":0.7316114542
333
  },
334
  "agent":{
335
- "p":0.8974358974,
336
  "r":0.9408602151,
337
- "f":0.9186351706
338
  },
339
  "dative":{
340
- "p":0.7647058824,
341
- "r":0.6857798165,
342
- "f":0.723095526
343
  },
344
  "acomp":{
345
- "p":0.9172413793,
346
- "r":0.9047619048,
347
- "f":0.9109589041
348
  },
349
  "dep":{
350
- "p":0.3886792453,
351
- "r":0.1672077922,
352
- "f":0.2338251986
353
  },
354
  "csubj":{
355
- "p":0.7133333333,
356
- "r":0.6331360947,
357
- "f":0.670846395
358
  },
359
  "quantmod":{
360
- "p":0.8654545455,
361
- "r":0.7733549959,
362
- "f":0.8168168168
363
  },
364
  "nmod":{
365
- "p":0.7545526524,
366
- "r":0.5807434491,
367
- "f":0.6563360882
368
  },
369
  "appos":{
370
- "p":0.6708074534,
371
- "r":0.6559652928,
372
- "f":0.663303356
373
  },
374
  "predet":{
375
- "p":0.828685259,
376
- "r":0.8927038627,
377
- "f":0.8595041322
378
  },
379
  "preconj":{
380
  "p":0.5784313725,
@@ -382,19 +381,19 @@
382
  "f":0.6276595745
383
  },
384
  "oprd":{
385
- "p":0.8758865248,
386
- "r":0.7373134328,
387
- "f":0.8006482982
388
  },
389
  "parataxis":{
390
- "p":0.6073446328,
391
- "r":0.4663774403,
392
- "f":0.527607362
393
  },
394
  "meta":{
395
- "p":0.95,
396
- "r":0.3653846154,
397
- "f":0.5277777778
398
  },
399
  "csubjpass":{
400
  "p":0.5555555556,
@@ -402,98 +401,102 @@
402
  "f":0.6666666667
403
  }
404
  },
 
 
 
405
  "ents_per_type":{
406
  "DATE":{
407
- "p":0.8650594865,
408
- "r":0.8771428571,
409
- "f":0.8710592686
410
  },
411
  "GPE":{
412
- "p":0.916572717,
413
- "r":0.9071129707,
414
- "f":0.9118183093
415
  },
416
  "ORDINAL":{
417
- "p":0.785915493,
418
  "r":0.8664596273,
419
- "f":0.8242245199
420
  },
421
  "ORG":{
422
- "p":0.8143681175,
423
- "r":0.8234358431,
424
- "f":0.8188768785
425
  },
426
  "QUANTITY":{
427
- "p":0.7769784173,
428
- "r":0.5934065934,
429
- "f":0.6728971963
430
  },
431
  "CARDINAL":{
432
- "p":0.8160403814,
433
- "r":0.8650416171,
434
- "f":0.8398268398
435
  },
436
  "PERSON":{
437
- "p":0.8838289963,
438
- "r":0.9311357702,
439
- "f":0.9068658614
440
  },
441
  "NORP":{
442
- "p":0.8933969769,
443
- "r":0.8984,
444
- "f":0.8958915038
 
 
 
 
 
445
  },
446
  "FAC":{
447
- "p":0.4141414141,
448
- "r":0.3153846154,
449
- "f":0.3580786026
450
  },
451
  "TIME":{
452
  "p":0.7396825397,
453
  "r":0.6812865497,
454
  "f":0.7092846271
455
  },
456
- "LOC":{
457
- "p":0.6937269373,
458
- "r":0.5987261146,
459
- "f":0.6427350427
460
- },
461
- "MONEY":{
462
- "p":0.9008363202,
463
- "r":0.8902007084,
464
- "f":0.8954869359
465
  },
466
  "EVENT":{
467
- "p":0.597826087,
468
- "r":0.316091954,
469
- "f":0.4135338346
470
  },
471
  "WORK_OF_ART":{
472
- "p":0.4827586207,
473
- "r":0.2886597938,
474
- "f":0.3612903226
475
  },
476
  "LAW":{
477
- "p":0.5,
478
- "r":0.3125,
479
- "f":0.3846153846
480
  },
481
- "PERCENT":{
482
- "p":0.9089456869,
483
- "r":0.8713629403,
484
- "f":0.8897576231
485
  },
486
- "PRODUCT":{
487
- "p":0.6195652174,
488
- "r":0.2701421801,
489
- "f":0.3762376238
490
  },
491
  "LANGUAGE":{
492
- "p":0.7727272727,
493
- "r":0.53125,
494
- "f":0.6296296296
495
  }
496
- }
 
497
  },
498
  "sources":[
499
  {
 
1
  {
2
  "lang":"en",
3
  "name":"core_web_lg",
4
+ "version":"3.2.0",
5
  "description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"[email protected]",
8
  "url":"https://explosion.ai",
9
  "license":"MIT",
10
+ "spacy_version":">=3.2.0,<3.3.0",
11
+ "spacy_git_version":"bb26550e2",
12
  "vectors":{
13
  "width":300,
14
  "vectors":684830,
 
170
  ],
171
  "performance":{
172
  "token_acc":0.9993053983,
173
+ "token_p":0.9956742163,
174
+ "token_r":0.9957505887,
175
+ "token_f":0.9957124011,
176
+ "tag_acc":0.9741780493,
177
+ "sents_p":0.9179358172,
178
+ "sents_r":0.8906260307,
179
+ "sents_f":0.9040747313,
180
+ "dep_uas":0.9200593914,
181
+ "dep_las":0.9021556352,
 
182
  "dep_las_per_type":{
183
  "prep":{
184
+ "p":0.8578239976,
185
+ "r":0.8669702144,
186
+ "f":0.8623728558
187
  },
188
  "det":{
189
+ "p":0.9798012706,
190
+ "r":0.9809997554,
191
+ "f":0.9804001467
192
  },
193
  "pobj":{
194
+ "p":0.9617211838,
195
+ "r":0.9698409582,
196
+ "f":0.9657640043
197
  },
198
  "nsubj":{
199
+ "p":0.9608471258,
200
+ "r":0.9461555312,
201
+ "f":0.9534447363
202
  },
203
  "aux":{
204
+ "p":0.9807231056,
205
+ "r":0.9828184813,
206
+ "f":0.9817696754
207
  },
208
  "advmod":{
209
+ "p":0.8600169779,
210
+ "r":0.8523472993,
211
+ "f":0.8561649624
212
  },
213
  "relcl":{
214
+ "p":0.755259467,
215
+ "r":0.7815674891,
216
+ "f":0.7681883024
217
  },
218
  "root":{
219
+ "p":0.9196325281,
220
+ "r":0.8914836071,
221
+ "f":0.905339318
222
  },
223
  "xcomp":{
224
+ "p":0.8886906885,
225
+ "r":0.8941134243,
226
+ "f":0.8913938093
227
  },
228
  "amod":{
229
+ "p":0.9216490817,
230
+ "r":0.9168124393,
231
+ "f":0.9192243983
232
  },
233
  "compound":{
234
+ "p":0.9188224309,
235
+ "r":0.9316662954,
236
+ "f":0.9251997898
237
  },
238
  "poss":{
239
+ "p":0.9760755931,
240
+ "r":0.9772544283,
241
+ "f":0.976664655
242
  },
243
  "ccomp":{
244
+ "p":0.7797340326,
245
+ "r":0.8478615071,
246
+ "f":0.8123719387
247
  },
248
  "attr":{
249
+ "p":0.8931845357,
250
+ "r":0.9423885618,
251
+ "f":0.9171270718
252
  },
253
  "case":{
254
+ "p":0.9782823297,
255
+ "r":0.991991992,
256
+ "f":0.9850894632
257
  },
258
  "mark":{
259
+ "p":0.9105669417,
260
+ "r":0.9064652888,
261
+ "f":0.9085114859
262
  },
263
  "intj":{
264
+ "p":0.6737089202,
265
+ "r":0.6307692308,
266
+ "f":0.6515323496
267
  },
268
  "advcl":{
269
+ "p":0.67003282,
270
+ "r":0.6683455049,
271
+ "f":0.6691880988
272
  },
273
  "cc":{
274
+ "p":0.8372232916,
275
+ "r":0.8323167085,
276
+ "f":0.8347627901
277
  },
278
  "neg":{
279
+ "p":0.9408548708,
280
+ "r":0.9498243853,
281
+ "f":0.9453183521
282
  },
283
  "conj":{
284
+ "p":0.7653624433,
285
+ "r":0.7854984894,
286
+ "f":0.7752997453
287
  },
288
  "nsubjpass":{
289
+ "p":0.9327377824,
290
+ "r":0.9102564103,
291
+ "f":0.9213599792
292
  },
293
  "auxpass":{
294
+ "p":0.9543624161,
295
+ "r":0.9717539863,
296
+ "f":0.962979684
297
  },
298
  "dobj":{
299
+ "p":0.9222826087,
300
+ "r":0.9466092916,
301
+ "f":0.9342876244
302
  },
303
  "nummod":{
304
+ "p":0.9430395913,
305
+ "r":0.9323232323,
306
+ "f":0.9376507937
307
  },
308
  "npadvmod":{
309
+ "p":0.7866254349,
310
+ "r":0.7229129663,
311
+ "f":0.7534246575
312
  },
313
  "prt":{
314
  "p":0.8190082645,
 
316
  "f":0.8521066208
317
  },
318
  "pcomp":{
319
+ "p":0.879020979,
320
+ "r":0.8802521008,
321
+ "f":0.8796361092
322
  },
323
  "expl":{
324
+ "p":0.9809725159,
325
+ "r":0.9935760171,
326
+ "f":0.9872340426
327
  },
328
  "acl":{
329
+ "p":0.7443997702,
330
+ "r":0.7070376432,
331
+ "f":0.7252378288
332
  },
333
  "agent":{
334
+ "p":0.8928571429,
335
  "r":0.9408602151,
336
+ "f":0.9162303665
337
  },
338
  "dative":{
339
+ "p":0.7729591837,
340
+ "r":0.6949541284,
341
+ "f":0.731884058
342
  },
343
  "acomp":{
344
+ "p":0.9102505695,
345
+ "r":0.906122449,
346
+ "f":0.9081818182
347
  },
348
  "dep":{
349
+ "p":0.4491525424,
350
+ "r":0.1720779221,
351
+ "f":0.2488262911
352
  },
353
  "csubj":{
354
+ "p":0.7243589744,
355
+ "r":0.6686390533,
356
+ "f":0.6953846154
357
  },
358
  "quantmod":{
359
+ "p":0.8686779059,
360
+ "r":0.7952883834,
361
+ "f":0.8303647159
362
  },
363
  "nmod":{
364
+ "p":0.76,
365
+ "r":0.5789152956,
366
+ "f":0.6572120374
367
  },
368
  "appos":{
369
+ "p":0.7035040431,
370
+ "r":0.6793926247,
371
+ "f":0.6912381373
372
  },
373
  "predet":{
374
+ "p":0.8300395257,
375
+ "r":0.9012875536,
376
+ "f":0.8641975309
377
  },
378
  "preconj":{
379
  "p":0.5784313725,
 
381
  "f":0.6276595745
382
  },
383
  "oprd":{
384
+ "p":0.8379310345,
385
+ "r":0.7253731343,
386
+ "f":0.7776
387
  },
388
  "parataxis":{
389
+ "p":0.6312849162,
390
+ "r":0.4902386117,
391
+ "f":0.5518925519
392
  },
393
  "meta":{
394
+ "p":0.7647058824,
395
+ "r":0.25,
396
+ "f":0.3768115942
397
  },
398
  "csubjpass":{
399
  "p":0.5555555556,
 
401
  "f":0.6666666667
402
  }
403
  },
404
+ "ents_p":0.8574246409,
405
+ "ents_r":0.8490084135,
406
+ "ents_f":0.8531957725,
407
  "ents_per_type":{
408
  "DATE":{
409
+ "p":0.8695102686,
410
+ "r":0.8736507937,
411
+ "f":0.8715756136
412
  },
413
  "GPE":{
414
+ "p":0.9231641622,
415
+ "r":0.9082287308,
416
+ "f":0.9156355456
417
  },
418
  "ORDINAL":{
419
+ "p":0.7971428571,
420
  "r":0.8664596273,
421
+ "f":0.8303571429
422
  },
423
  "ORG":{
424
+ "p":0.8194444444,
425
+ "r":0.8290031813,
426
+ "f":0.8241960991
427
  },
428
  "QUANTITY":{
429
+ "p":0.7959183673,
430
+ "r":0.6428571429,
431
+ "f":0.7112462006
432
  },
433
  "CARDINAL":{
434
+ "p":0.8221709007,
435
+ "r":0.8466111772,
436
+ "f":0.834212068
437
  },
438
  "PERSON":{
439
+ "p":0.8823895457,
440
+ "r":0.9255874674,
441
+ "f":0.9034724435
442
  },
443
  "NORP":{
444
+ "p":0.9027888446,
445
+ "r":0.9064,
446
+ "f":0.9045908184
447
+ },
448
+ "LOC":{
449
+ "p":0.7185185185,
450
+ "r":0.6178343949,
451
+ "f":0.6643835616
452
  },
453
  "FAC":{
454
+ "p":0.4263565891,
455
+ "r":0.4230769231,
456
+ "f":0.4247104247
457
  },
458
  "TIME":{
459
  "p":0.7396825397,
460
  "r":0.6812865497,
461
  "f":0.7092846271
462
  },
463
+ "PRODUCT":{
464
+ "p":0.6022727273,
465
+ "r":0.2511848341,
466
+ "f":0.3545150502
 
 
 
 
 
467
  },
468
  "EVENT":{
469
+ "p":0.5882352941,
470
+ "r":0.2873563218,
471
+ "f":0.3861003861
472
  },
473
  "WORK_OF_ART":{
474
+ "p":0.4692307692,
475
+ "r":0.3144329897,
476
+ "f":0.3765432099
477
  },
478
  "LAW":{
479
+ "p":0.5272727273,
480
+ "r":0.453125,
481
+ "f":0.487394958
482
  },
483
+ "MONEY":{
484
+ "p":0.8990498812,
485
+ "r":0.893742621,
486
+ "f":0.8963883955
487
  },
488
+ "PERCENT":{
489
+ "p":0.9202551834,
490
+ "r":0.8836140888,
491
+ "f":0.9015625
492
  },
493
  "LANGUAGE":{
494
+ "p":0.8,
495
+ "r":0.625,
496
+ "f":0.701754386
497
  }
498
+ },
499
+ "speed":7471.5995598921
500
  },
501
  "sources":[
502
  {
ner/model CHANGED
Binary files a/ner/model and b/ner/model differ
 
parser/model CHANGED
Binary files a/parser/model and b/parser/model differ
 
senter/cfg CHANGED
@@ -1,3 +1,3 @@
1
  {
2
-
3
  }
 
1
  {
2
+ "overwrite":false
3
  }
senter/model CHANGED
Binary files a/senter/model and b/senter/model differ
 
tagger/cfg CHANGED
@@ -49,5 +49,6 @@
49
  "WRB",
50
  "XX",
51
  "``"
52
- ]
 
53
  }
 
49
  "WRB",
50
  "XX",
51
  "``"
52
+ ],
53
+ "overwrite":false
54
  }
tagger/model CHANGED
Binary files a/tagger/model and b/tagger/model differ
 
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ecd96d0b8b113acc0c42d7cb1202dabcd4af74ee3c8ef4b4c2cac7ceb30f51c0
3
- size 6811418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e0c6b29d6d78255e764d45f99bb4d4d594fd6e5709bf3cd62c3df00e702c442c
3
+ size 6960804
tokenizer CHANGED
The diff for this file is too large to render. See raw diff
 
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af36b391672464e41eba46c48bd91ffc9cc5587b67f2122d70ac68c68f1a56fb
3
- size 9622332
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:266477264a21daaabda7d6b1200598290e20aaf2c72ebaf6e2a671f282f5e2bc
3
+ size 9695169
vocab/vectors.cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "mode":"default"
3
+ }