Hugging Face's logo

spacy
/
en_core_web_sm

Token Classification
spaCy
English
Eval Results (legacy)
Model card Files
xet
Community
Omar Sanseviero commited on
Commit
22d7df0
·
1 Parent(s): 51059b6

Update spaCy pipeline

Browse files
Files changed (16) hide show
  1. README.md +23 -20
  2. accuracy.json +205 -202
  3. attribute_ruler/patterns +0 -0
  4. config.cfg +28 -30
  5. en_core_web_sm-any-py3-none-any.whl +2 -2
  6. meta.json +208 -205
  7. ner/model +2 -2
  8. parser/model +1 -1
  9. senter/cfg +1 -1
  10. senter/model +2 -2
  11. tagger/cfg +2 -1
  12. tagger/model +1 -1
  13. tok2vec/model +2 -2
  14. tokenizer +0 -0
  15. vocab/strings.json +2 -2
  16. vocab/vectors.cfg +3 -0
README.md CHANGED
@@ -14,47 +14,47 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8424355924
18
  - name: NER Recall
19
  type: recall
20
- value: 0.8335336538
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.8379609817
24
  - task:
25
  name: POS
26
  type: token-classification
27
  metrics:
28
  - name: POS Accuracy
29
  type: accuracy
30
- value: 0.9720712187
31
  - task:
32
  name: SENTER
33
  type: token-classification
34
  metrics:
35
  - name: SENTER Precision
36
  type: precision
37
- value: 0.9074955788
38
  - name: SENTER Recall
39
  type: recall
40
- value: 0.8801372122
41
  - name: SENTER F Score
42
  type: f_score
43
- value: 0.893607046
44
  - task:
45
  name: UNLABELED_DEPENDENCIES
46
  type: token-classification
47
  metrics:
48
  - name: Unlabeled Dependencies Accuracy
49
  type: accuracy
50
- value: 0.9185392711
51
  - task:
52
  name: LABELED_DEPENDENCIES
53
  type: token-classification
54
  metrics:
55
  - name: Labeled Dependencies Accuracy
56
  type: accuracy
57
- value: 0.9185392711
58
  ---
59
  ### Details: https://spacy.io/models/en#en_core_web_sm
60
 
@@ -63,8 +63,8 @@ English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
63
  | Feature | Description |
64
  | --- | --- |
65
  | **Name** | `en_core_web_sm` |
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** | 0 keys, 0 unique vectors (0 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` | 97.21 |
96
- | `DEP_UAS` | 91.85 |
97
- | `DEP_LAS` | 90.02 |
98
- | `ENTS_P` | 84.24 |
99
- | `ENTS_R` | 83.35 |
100
- | `ENTS_F` | 83.80 |
101
- | `SENTS_P` | 90.75 |
102
- | `SENTS_R` | 88.01 |
103
- | `SENTS_F` | 89.36 |
 
 
 
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8463095057
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.8377904647
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8420284384
24
  - task:
25
  name: POS
26
  type: token-classification
27
  metrics:
28
  - name: POS Accuracy
29
  type: accuracy
30
+ value: 0.9725066923
31
  - task:
32
  name: SENTER
33
  type: token-classification
34
  metrics:
35
  - name: SENTER Precision
36
  type: precision
37
+ value: 0.9205049471
38
  - name: SENTER Recall
39
  type: recall
40
+ value: 0.8899003892
41
  - name: SENTER F Score
42
  type: f_score
43
+ value: 0.904943986
44
  - task:
45
  name: UNLABELED_DEPENDENCIES
46
  type: token-classification
47
  metrics:
48
  - name: Unlabeled Dependencies Accuracy
49
  type: accuracy
50
+ value: 0.9166876131
51
  - task:
52
  name: LABELED_DEPENDENCIES
53
  type: token-classification
54
  metrics:
55
  - name: Labeled Dependencies Accuracy
56
  type: accuracy
57
+ value: 0.9166876131
58
  ---
59
  ### Details: https://spacy.io/models/en#en_core_web_sm
60
 
 
63
  | Feature | Description |
64
  | --- | --- |
65
  | **Name** | `en_core_web_sm` |
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** | 0 keys, 0 unique vectors (0 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` | 97.25 |
99
+ | `SENTS_P` | 92.05 |
100
+ | `SENTS_R` | 88.99 |
101
+ | `SENTS_F` | 90.49 |
102
+ | `DEP_UAS` | 91.67 |
103
+ | `DEP_LAS` | 89.80 |
104
+ | `ENTS_P` | 84.63 |
105
+ | `ENTS_R` | 83.78 |
106
+ | `ENTS_F` | 84.20 |
accuracy.json CHANGED
@@ -1,327 +1,330 @@
1
  {
2
  "token_acc": 0.9993053983,
3
- "tag_acc": 0.9720712187,
4
- "dep_uas": 0.9185392711,
5
- "dep_las": 0.9001546872,
6
- "ents_p": 0.8424355924,
7
- "ents_r": 0.8335336538,
8
- "ents_f": 0.8379609817,
9
- "sents_p": 0.9074955788,
10
- "sents_r": 0.8801372122,
11
- "sents_f": 0.893607046,
12
- "speed": 10426.0619939972,
13
  "dep_las_per_type": {
14
  "prep": {
15
- "p": 0.8554402587,
16
- "r": 0.8633276418,
17
- "f": 0.8593658527
18
  },
19
  "det": {
20
- "p": 0.9772329247,
21
- "r": 0.9783087336,
22
- "f": 0.9777705332
23
  },
24
  "pobj": {
25
- "p": 0.9603285837,
26
- "r": 0.9686628706,
27
- "f": 0.9644777228
28
  },
29
  "nsubj": {
30
- "p": 0.9598718747,
31
- "r": 0.945279299,
32
- "f": 0.9525197007
33
  },
34
  "aux": {
35
- "p": 0.9795737123,
36
- "r": 0.9819282471,
37
- "f": 0.9807495665
38
  },
39
  "advmod": {
40
- "p": 0.8538267452,
41
- "r": 0.8541140838,
42
- "f": 0.8539703903
43
  },
44
  "relcl": {
45
- "p": 0.764978602,
46
- "r": 0.7783018868,
47
- "f": 0.7715827338
48
  },
49
  "root": {
50
- "p": 0.9199754818,
51
- "r": 0.8910878026,
52
- "f": 0.9053012533
53
  },
54
  "xcomp": {
55
- "p": 0.8813440672,
56
- "r": 0.903804738,
57
- "f": 0.892433103
58
  },
59
  "amod": {
60
- "p": 0.9171875,
61
- "r": 0.9127308066,
62
- "f": 0.9149537263
63
  },
64
  "compound": {
65
- "p": 0.916057391,
66
- "r": 0.9280463355,
67
- "f": 0.9220128918
68
  },
69
  "poss": {
70
- "p": 0.9744672296,
71
- "r": 0.9756441224,
72
- "f": 0.9750553209
73
  },
74
  "ccomp": {
75
- "p": 0.7747747748,
76
- "r": 0.8407331976,
77
- "f": 0.8064075015
78
  },
79
  "attr": {
80
- "p": 0.8989490703,
81
- "r": 0.9352396972,
82
- "f": 0.9167353669
83
  },
84
  "case": {
85
- "p": 0.9801980198,
86
- "r": 0.990990991,
87
- "f": 0.9855649577
88
  },
89
  "mark": {
90
- "p": 0.9015392781,
91
- "r": 0.9001059883,
92
- "f": 0.9008220631
93
  },
94
  "intj": {
95
- "p": 0.6712856043,
96
- "r": 0.6388278388,
97
- "f": 0.6546546547
98
  },
99
  "advcl": {
100
- "p": 0.6687116564,
101
- "r": 0.6587761269,
102
- "f": 0.6637067106
103
  },
104
  "cc": {
105
- "p": 0.8426682692,
106
- "r": 0.8385360603,
107
- "f": 0.8405970865
108
  },
109
  "neg": {
110
- "p": 0.9461346633,
111
- "r": 0.9518314099,
112
- "f": 0.9489744872
113
  },
114
  "conj": {
115
- "p": 0.7715100422,
116
- "r": 0.7833585096,
117
- "f": 0.7773891318
118
  },
119
  "nsubjpass": {
120
- "p": 0.9296875,
121
- "r": 0.9153846154,
122
- "f": 0.9224806202
123
  },
124
  "auxpass": {
125
- "p": 0.9496883348,
126
- "r": 0.9717539863,
127
- "f": 0.9605944607
128
  },
129
  "dobj": {
130
- "p": 0.919667805,
131
- "r": 0.9442186628,
132
- "f": 0.9317815437
133
  },
134
  "nummod": {
135
- "p": 0.9341637011,
136
- "r": 0.928030303,
137
- "f": 0.9310869014
138
  },
139
  "npadvmod": {
140
- "p": 0.7723823976,
141
- "r": 0.723268206,
142
- "f": 0.7470188956
143
  },
144
  "prt": {
145
- "p": 0.8175842235,
146
- "r": 0.8915770609,
147
- "f": 0.852978997
148
  },
149
  "pcomp": {
150
- "p": 0.890625,
151
- "r": 0.8781512605,
152
- "f": 0.8843441467
153
  },
154
  "expl": {
155
- "p": 0.978858351,
156
- "r": 0.9914346895,
157
- "f": 0.985106383
158
  },
159
  "acl": {
160
- "p": 0.7473745624,
161
- "r": 0.6988543372,
162
- "f": 0.7223005357
163
  },
164
  "agent": {
165
- "p": 0.8937605396,
166
- "r": 0.9498207885,
167
- "f": 0.9209383145
168
  },
169
  "dative": {
170
- "p": 0.7608695652,
171
- "r": 0.7224770642,
172
- "f": 0.7411764706
173
  },
174
  "acomp": {
175
- "p": 0.91184573,
176
- "r": 0.9006802721,
177
- "f": 0.9062286105
178
  },
179
  "dep": {
180
- "p": 0.3689655172,
181
- "r": 0.1737012987,
182
- "f": 0.2362030905
183
  },
184
  "csubj": {
185
- "p": 0.6424242424,
186
- "r": 0.6272189349,
187
- "f": 0.6347305389
188
  },
189
  "quantmod": {
190
- "p": 0.8624667258,
191
- "r": 0.7896019496,
192
- "f": 0.8244274809
193
  },
194
  "nmod": {
195
- "p": 0.7359073359,
196
- "r": 0.5807434491,
197
- "f": 0.6491825613
198
  },
199
  "appos": {
200
- "p": 0.7011441648,
201
- "r": 0.6646420824,
202
- "f": 0.6824053452
203
  },
204
  "predet": {
205
- "p": 0.8514056225,
206
- "r": 0.9098712446,
207
- "f": 0.8796680498
208
  },
209
  "preconj": {
210
- "p": 0.476635514,
211
- "r": 0.5930232558,
212
- "f": 0.5284974093
213
  },
214
  "oprd": {
215
- "p": 0.8193979933,
216
- "r": 0.7313432836,
217
- "f": 0.7728706625
218
  },
219
  "parataxis": {
220
- "p": 0.6336088154,
221
- "r": 0.4989154013,
222
- "f": 0.5582524272
223
  },
224
  "meta": {
225
- "p": 0.7727272727,
226
  "r": 0.3269230769,
227
- "f": 0.4594594595
228
  },
229
  "csubjpass": {
230
- "p": 0.5,
231
- "r": 0.8333333333,
232
- "f": 0.625
233
  }
234
  },
 
 
 
235
  "ents_per_type": {
236
  "DATE": {
237
- "p": 0.8659955961,
238
- "r": 0.873968254,
239
- "f": 0.8699636593
240
  },
241
  "GPE": {
242
- "p": 0.9142529395,
243
- "r": 0.8892608089,
244
- "f": 0.9015837104
 
 
 
 
 
245
  },
246
  "ORG": {
247
- "p": 0.789707419,
248
- "r": 0.8014316013,
249
- "f": 0.7955263158
250
  },
251
  "FAC": {
252
- "p": 0.3679245283,
253
- "r": 0.3,
254
- "f": 0.3305084746
255
  },
256
  "CARDINAL": {
257
- "p": 0.8146892655,
258
- "r": 0.8573127229,
259
- "f": 0.8354577057
260
  },
261
  "PERSON": {
262
- "p": 0.8424487259,
263
- "r": 0.8847911227,
264
- "f": 0.8631009233
265
  },
266
  "NORP": {
267
- "p": 0.9078415521,
268
- "r": 0.8984,
269
- "f": 0.9030960997
270
- },
271
- "ORDINAL": {
272
- "p": 0.7787114846,
273
- "r": 0.8633540373,
274
- "f": 0.8188512518
275
  },
276
  "LOC": {
277
- "p": 0.713740458,
278
- "r": 0.5955414013,
279
- "f": 0.6493055556
280
  },
281
  "TIME": {
282
- "p": 0.712962963,
283
- "r": 0.6754385965,
284
- "f": 0.6936936937
285
- },
286
- "PRODUCT": {
287
- "p": 0.5510204082,
288
- "r": 0.2559241706,
289
- "f": 0.3495145631
290
  },
291
  "QUANTITY": {
292
- "p": 0.842519685,
293
- "r": 0.5879120879,
294
- "f": 0.6925566343
295
- },
296
- "WORK_OF_ART": {
297
- "p": 0.46875,
298
- "r": 0.3092783505,
299
- "f": 0.3726708075
300
  },
301
  "EVENT": {
302
- "p": 0.595959596,
303
- "r": 0.3390804598,
304
- "f": 0.4322344322
 
 
 
 
 
305
  },
306
  "MONEY": {
307
- "p": 0.9182692308,
308
- "r": 0.9020070838,
309
- "f": 0.9100655152
310
  },
311
  "LAW": {
312
- "p": 0.5555555556,
313
- "r": 0.46875,
314
- "f": 0.5084745763
315
  },
316
  "PERCENT": {
317
- "p": 0.92,
318
- "r": 0.8805513017,
319
- "f": 0.8998435055
 
 
 
 
 
320
  },
321
  "LANGUAGE": {
322
- "p": 0.7692307692,
323
- "r": 0.625,
324
- "f": 0.6896551724
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": 0.9725066923,
7
+ "sents_p": 0.9205049471,
8
+ "sents_r": 0.8899003892,
9
+ "sents_f": 0.904943986,
10
+ "dep_uas": 0.9166876131,
11
+ "dep_las": 0.8979960057,
 
12
  "dep_las_per_type": {
13
  "prep": {
14
+ "p": 0.8514792011,
15
+ "r": 0.8605577689,
16
+ "f": 0.8559944141
17
  },
18
  "det": {
19
+ "p": 0.9776402069,
20
+ "r": 0.9787164642,
21
+ "f": 0.9781780395
22
  },
23
  "pobj": {
24
+ "p": 0.9592170292,
25
+ "r": 0.9679560181,
26
+ "f": 0.9635667097
27
  },
28
  "nsubj": {
29
+ "p": 0.9562219157,
30
+ "r": 0.9416429354,
31
+ "f": 0.9488764293
32
  },
33
  "aux": {
34
+ "p": 0.9795809659,
35
+ "r": 0.9822843408,
36
+ "f": 0.9809307908
37
  },
38
  "advmod": {
39
+ "p": 0.8570825239,
40
+ "r": 0.8536934208,
41
+ "f": 0.8553846154
42
  },
43
  "relcl": {
44
+ "p": 0.7760869565,
45
+ "r": 0.7772133527,
46
+ "f": 0.7766497462
47
  },
48
  "root": {
49
+ "p": 0.9174912987,
50
+ "r": 0.8868658883,
51
+ "f": 0.9019186905
52
  },
53
  "xcomp": {
54
+ "p": 0.8794251665,
55
+ "r": 0.9005743001,
56
+ "f": 0.8898740912
57
  },
58
  "amod": {
59
+ "p": 0.9157270416,
60
+ "r": 0.9102688695,
61
+ "f": 0.9129897979
62
  },
63
  "compound": {
64
+ "p": 0.9140038367,
65
+ "r": 0.9287146358,
66
+ "f": 0.9213005166
67
  },
68
  "poss": {
69
+ "p": 0.9734779988,
70
+ "r": 0.9752415459,
71
+ "f": 0.9743589744
72
  },
73
  "ccomp": {
74
+ "p": 0.7639405204,
75
+ "r": 0.8370672098,
76
+ "f": 0.7988338192
77
  },
78
  "attr": {
79
+ "p": 0.8959421454,
80
+ "r": 0.9377628259,
81
+ "f": 0.9163755907
82
  },
83
  "case": {
84
+ "p": 0.9768015795,
85
+ "r": 0.9904904905,
86
+ "f": 0.9835984095
87
  },
88
  "mark": {
89
+ "p": 0.9027518034,
90
+ "r": 0.895336513,
91
+ "f": 0.8990288679
92
  },
93
  "intj": {
94
+ "p": 0.6757624398,
95
+ "r": 0.6168498168,
96
+ "f": 0.6449636155
97
  },
98
  "advcl": {
99
+ "p": 0.6617760618,
100
+ "r": 0.6474439688,
101
+ "f": 0.6545315682
102
  },
103
  "cc": {
104
+ "p": 0.8340149146,
105
+ "r": 0.8293266356,
106
+ "f": 0.8316641679
107
  },
108
  "neg": {
109
+ "p": 0.949127182,
110
+ "r": 0.9548419468,
111
+ "f": 0.951975988
112
  },
113
  "conj": {
114
+ "p": 0.7544115857,
115
+ "r": 0.7803373615,
116
+ "f": 0.7671554978
117
  },
118
  "nsubjpass": {
119
+ "p": 0.9232776618,
120
+ "r": 0.9071794872,
121
+ "f": 0.9151577858
122
  },
123
  "auxpass": {
124
+ "p": 0.9526362824,
125
+ "r": 0.9712984055,
126
+ "f": 0.9618768328
127
  },
128
  "dobj": {
129
+ "p": 0.9192971544,
130
+ "r": 0.9422264722,
131
+ "f": 0.9306205974
132
  },
133
  "nummod": {
134
+ "p": 0.9373881932,
135
+ "r": 0.9262626263,
136
+ "f": 0.9317922012
137
  },
138
  "npadvmod": {
139
+ "p": 0.7576675502,
140
+ "r": 0.7108348135,
141
+ "f": 0.7335043988
142
  },
143
  "prt": {
144
+ "p": 0.8091728092,
145
+ "r": 0.8853046595,
146
+ "f": 0.8455284553
147
  },
148
  "pcomp": {
149
+ "p": 0.871398454,
150
+ "r": 0.8683473389,
151
+ "f": 0.869870221
152
  },
153
  "expl": {
154
+ "p": 0.9808917197,
155
+ "r": 0.9892933619,
156
+ "f": 0.9850746269
157
  },
158
  "acl": {
159
+ "p": 0.7457627119,
160
+ "r": 0.6961265685,
161
+ "f": 0.7200902935
162
  },
163
  "agent": {
164
+ "p": 0.8868243243,
165
+ "r": 0.9408602151,
166
+ "f": 0.9130434783
167
  },
168
  "dative": {
169
+ "p": 0.7659033079,
170
+ "r": 0.6903669725,
171
+ "f": 0.7261761158
172
  },
173
  "acomp": {
174
+ "p": 0.9110499771,
175
+ "r": 0.9011337868,
176
+ "f": 0.9060647515
177
  },
178
  "dep": {
179
+ "p": 0.4232365145,
180
+ "r": 0.1655844156,
181
+ "f": 0.2380396733
182
  },
183
  "csubj": {
184
+ "p": 0.7077922078,
185
+ "r": 0.6449704142,
186
+ "f": 0.6749226006
187
  },
188
  "quantmod": {
189
+ "p": 0.8597883598,
190
+ "r": 0.7920389927,
191
+ "f": 0.8245243129
192
  },
193
  "nmod": {
194
+ "p": 0.7614091273,
195
+ "r": 0.5795246801,
196
+ "f": 0.6581314879
197
  },
198
  "appos": {
199
+ "p": 0.6951055231,
200
+ "r": 0.6715835141,
201
+ "f": 0.6831421006
202
  },
203
  "predet": {
204
+ "p": 0.8273092369,
205
+ "r": 0.8841201717,
206
+ "f": 0.8547717842
207
  },
208
  "preconj": {
209
+ "p": 0.5504587156,
210
+ "r": 0.6976744186,
211
+ "f": 0.6153846154
212
  },
213
  "oprd": {
214
+ "p": 0.821192053,
215
+ "r": 0.7402985075,
216
+ "f": 0.7786499215
217
  },
218
  "parataxis": {
219
+ "p": 0.6215469613,
220
+ "r": 0.4880694143,
221
+ "f": 0.5467800729
222
  },
223
  "meta": {
224
+ "p": 0.8095238095,
225
  "r": 0.3269230769,
226
+ "f": 0.4657534247
227
  },
228
  "csubjpass": {
229
+ "p": 0.6,
230
+ "r": 0.5,
231
+ "f": 0.5454545455
232
  }
233
  },
234
+ "ents_p": 0.8463095057,
235
+ "ents_r": 0.8377904647,
236
+ "ents_f": 0.8420284384,
237
  "ents_per_type": {
238
  "DATE": {
239
+ "p": 0.8653725736,
240
+ "r": 0.8774603175,
241
+ "f": 0.8713745271
242
  },
243
  "GPE": {
244
+ "p": 0.9126848692,
245
+ "r": 0.8951185495,
246
+ "f": 0.9038163639
247
+ },
248
+ "ORDINAL": {
249
+ "p": 0.7818696884,
250
+ "r": 0.8571428571,
251
+ "f": 0.8177777778
252
  },
253
  "ORG": {
254
+ "p": 0.8032096817,
255
+ "r": 0.8093849417,
256
+ "f": 0.8062854879
257
  },
258
  "FAC": {
259
+ "p": 0.412371134,
260
+ "r": 0.3076923077,
261
+ "f": 0.3524229075
262
  },
263
  "CARDINAL": {
264
+ "p": 0.8206857785,
265
+ "r": 0.8680142687,
266
+ "f": 0.8436867957
267
  },
268
  "PERSON": {
269
+ "p": 0.8429059298,
270
+ "r": 0.8860966057,
271
+ "f": 0.8639618138
272
  },
273
  "NORP": {
274
+ "p": 0.8995176849,
275
+ "r": 0.8952,
276
+ "f": 0.8973536488
 
 
 
 
 
277
  },
278
  "LOC": {
279
+ "p": 0.7210144928,
280
+ "r": 0.6337579618,
281
+ "f": 0.6745762712
282
  },
283
  "TIME": {
284
+ "p": 0.7492163009,
285
+ "r": 0.6988304094,
286
+ "f": 0.7231467474
 
 
 
 
 
287
  },
288
  "QUANTITY": {
289
+ "p": 0.8273381295,
290
+ "r": 0.6318681319,
291
+ "f": 0.7165109034
 
 
 
 
 
292
  },
293
  "EVENT": {
294
+ "p": 0.5604395604,
295
+ "r": 0.2931034483,
296
+ "f": 0.3849056604
297
+ },
298
+ "WORK_OF_ART": {
299
+ "p": 0.5151515152,
300
+ "r": 0.3505154639,
301
+ "f": 0.4171779141
302
  },
303
  "MONEY": {
304
+ "p": 0.9178743961,
305
+ "r": 0.8972845336,
306
+ "f": 0.9074626866
307
  },
308
  "LAW": {
309
+ "p": 0.5102040816,
310
+ "r": 0.390625,
311
+ "f": 0.4424778761
312
  },
313
  "PERCENT": {
314
+ "p": 0.9230769231,
315
+ "r": 0.8820826953,
316
+ "f": 0.9021143305
317
+ },
318
+ "PRODUCT": {
319
+ "p": 0.5185185185,
320
+ "r": 0.1990521327,
321
+ "f": 0.2876712329
322
  },
323
  "LANGUAGE": {
324
+ "p": 0.7826086957,
325
+ "r": 0.5625,
326
+ "f": 0.6545454545
327
  }
328
+ },
329
+ "speed": 8030.19594793
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 = null
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 = false
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 = false
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 = false
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 = false
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 = false
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 = false
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_sm-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:82bc8de1e7fa6609f0ff481af519c18291d0204044580df0813461608ae2d00c
3
- size 13622633
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e02939fb7fbae6dbcc9c5a1355f5e4e02939b649a1f0846ee844ac1d479bbeb
3
+ size 13900196
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"en",
3
  "name":"core_web_sm",
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":"contact@explosion.ai",
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":0,
14
  "vectors":0,
@@ -170,330 +170,333 @@
170
  ],
171
  "performance":{
172
  "token_acc":0.9993053983,
173
- "tag_acc":0.9720712187,
174
- "dep_uas":0.9185392711,
175
- "dep_las":0.9001546872,
176
- "ents_p":0.8424355924,
177
- "ents_r":0.8335336538,
178
- "ents_f":0.8379609817,
179
- "sents_p":0.9074955788,
180
- "sents_r":0.8801372122,
181
- "sents_f":0.893607046,
182
- "speed":10426.0619939972,
183
  "dep_las_per_type":{
184
  "prep":{
185
- "p":0.8554402587,
186
- "r":0.8633276418,
187
- "f":0.8593658527
188
  },
189
  "det":{
190
- "p":0.9772329247,
191
- "r":0.9783087336,
192
- "f":0.9777705332
193
  },
194
  "pobj":{
195
- "p":0.9603285837,
196
- "r":0.9686628706,
197
- "f":0.9644777228
198
  },
199
  "nsubj":{
200
- "p":0.9598718747,
201
- "r":0.945279299,
202
- "f":0.9525197007
203
  },
204
  "aux":{
205
- "p":0.9795737123,
206
- "r":0.9819282471,
207
- "f":0.9807495665
208
  },
209
  "advmod":{
210
- "p":0.8538267452,
211
- "r":0.8541140838,
212
- "f":0.8539703903
213
  },
214
  "relcl":{
215
- "p":0.764978602,
216
- "r":0.7783018868,
217
- "f":0.7715827338
218
  },
219
  "root":{
220
- "p":0.9199754818,
221
- "r":0.8910878026,
222
- "f":0.9053012533
223
  },
224
  "xcomp":{
225
- "p":0.8813440672,
226
- "r":0.903804738,
227
- "f":0.892433103
228
  },
229
  "amod":{
230
- "p":0.9171875,
231
- "r":0.9127308066,
232
- "f":0.9149537263
233
  },
234
  "compound":{
235
- "p":0.916057391,
236
- "r":0.9280463355,
237
- "f":0.9220128918
238
  },
239
  "poss":{
240
- "p":0.9744672296,
241
- "r":0.9756441224,
242
- "f":0.9750553209
243
  },
244
  "ccomp":{
245
- "p":0.7747747748,
246
- "r":0.8407331976,
247
- "f":0.8064075015
248
  },
249
  "attr":{
250
- "p":0.8989490703,
251
- "r":0.9352396972,
252
- "f":0.9167353669
253
  },
254
  "case":{
255
- "p":0.9801980198,
256
- "r":0.990990991,
257
- "f":0.9855649577
258
  },
259
  "mark":{
260
- "p":0.9015392781,
261
- "r":0.9001059883,
262
- "f":0.9008220631
263
  },
264
  "intj":{
265
- "p":0.6712856043,
266
- "r":0.6388278388,
267
- "f":0.6546546547
268
  },
269
  "advcl":{
270
- "p":0.6687116564,
271
- "r":0.6587761269,
272
- "f":0.6637067106
273
  },
274
  "cc":{
275
- "p":0.8426682692,
276
- "r":0.8385360603,
277
- "f":0.8405970865
278
  },
279
  "neg":{
280
- "p":0.9461346633,
281
- "r":0.9518314099,
282
- "f":0.9489744872
283
  },
284
  "conj":{
285
- "p":0.7715100422,
286
- "r":0.7833585096,
287
- "f":0.7773891318
288
  },
289
  "nsubjpass":{
290
- "p":0.9296875,
291
- "r":0.9153846154,
292
- "f":0.9224806202
293
  },
294
  "auxpass":{
295
- "p":0.9496883348,
296
- "r":0.9717539863,
297
- "f":0.9605944607
298
  },
299
  "dobj":{
300
- "p":0.919667805,
301
- "r":0.9442186628,
302
- "f":0.9317815437
303
  },
304
  "nummod":{
305
- "p":0.9341637011,
306
- "r":0.928030303,
307
- "f":0.9310869014
308
  },
309
  "npadvmod":{
310
- "p":0.7723823976,
311
- "r":0.723268206,
312
- "f":0.7470188956
313
  },
314
  "prt":{
315
- "p":0.8175842235,
316
- "r":0.8915770609,
317
- "f":0.852978997
318
  },
319
  "pcomp":{
320
- "p":0.890625,
321
- "r":0.8781512605,
322
- "f":0.8843441467
323
  },
324
  "expl":{
325
- "p":0.978858351,
326
- "r":0.9914346895,
327
- "f":0.985106383
328
  },
329
  "acl":{
330
- "p":0.7473745624,
331
- "r":0.6988543372,
332
- "f":0.7223005357
333
  },
334
  "agent":{
335
- "p":0.8937605396,
336
- "r":0.9498207885,
337
- "f":0.9209383145
338
  },
339
  "dative":{
340
- "p":0.7608695652,
341
- "r":0.7224770642,
342
- "f":0.7411764706
343
  },
344
  "acomp":{
345
- "p":0.91184573,
346
- "r":0.9006802721,
347
- "f":0.9062286105
348
  },
349
  "dep":{
350
- "p":0.3689655172,
351
- "r":0.1737012987,
352
- "f":0.2362030905
353
  },
354
  "csubj":{
355
- "p":0.6424242424,
356
- "r":0.6272189349,
357
- "f":0.6347305389
358
  },
359
  "quantmod":{
360
- "p":0.8624667258,
361
- "r":0.7896019496,
362
- "f":0.8244274809
363
  },
364
  "nmod":{
365
- "p":0.7359073359,
366
- "r":0.5807434491,
367
- "f":0.6491825613
368
  },
369
  "appos":{
370
- "p":0.7011441648,
371
- "r":0.6646420824,
372
- "f":0.6824053452
373
  },
374
  "predet":{
375
- "p":0.8514056225,
376
- "r":0.9098712446,
377
- "f":0.8796680498
378
  },
379
  "preconj":{
380
- "p":0.476635514,
381
- "r":0.5930232558,
382
- "f":0.5284974093
383
  },
384
  "oprd":{
385
- "p":0.8193979933,
386
- "r":0.7313432836,
387
- "f":0.7728706625
388
  },
389
  "parataxis":{
390
- "p":0.6336088154,
391
- "r":0.4989154013,
392
- "f":0.5582524272
393
  },
394
  "meta":{
395
- "p":0.7727272727,
396
  "r":0.3269230769,
397
- "f":0.4594594595
398
  },
399
  "csubjpass":{
400
- "p":0.5,
401
- "r":0.8333333333,
402
- "f":0.625
403
  }
404
  },
 
 
 
405
  "ents_per_type":{
406
  "DATE":{
407
- "p":0.8659955961,
408
- "r":0.873968254,
409
- "f":0.8699636593
410
  },
411
  "GPE":{
412
- "p":0.9142529395,
413
- "r":0.8892608089,
414
- "f":0.9015837104
 
 
 
 
 
415
  },
416
  "ORG":{
417
- "p":0.789707419,
418
- "r":0.8014316013,
419
- "f":0.7955263158
420
  },
421
  "FAC":{
422
- "p":0.3679245283,
423
- "r":0.3,
424
- "f":0.3305084746
425
  },
426
  "CARDINAL":{
427
- "p":0.8146892655,
428
- "r":0.8573127229,
429
- "f":0.8354577057
430
  },
431
  "PERSON":{
432
- "p":0.8424487259,
433
- "r":0.8847911227,
434
- "f":0.8631009233
435
  },
436
  "NORP":{
437
- "p":0.9078415521,
438
- "r":0.8984,
439
- "f":0.9030960997
440
- },
441
- "ORDINAL":{
442
- "p":0.7787114846,
443
- "r":0.8633540373,
444
- "f":0.8188512518
445
  },
446
  "LOC":{
447
- "p":0.713740458,
448
- "r":0.5955414013,
449
- "f":0.6493055556
450
  },
451
  "TIME":{
452
- "p":0.712962963,
453
- "r":0.6754385965,
454
- "f":0.6936936937
455
- },
456
- "PRODUCT":{
457
- "p":0.5510204082,
458
- "r":0.2559241706,
459
- "f":0.3495145631
460
  },
461
  "QUANTITY":{
462
- "p":0.842519685,
463
- "r":0.5879120879,
464
- "f":0.6925566343
465
- },
466
- "WORK_OF_ART":{
467
- "p":0.46875,
468
- "r":0.3092783505,
469
- "f":0.3726708075
470
  },
471
  "EVENT":{
472
- "p":0.595959596,
473
- "r":0.3390804598,
474
- "f":0.4322344322
 
 
 
 
 
475
  },
476
  "MONEY":{
477
- "p":0.9182692308,
478
- "r":0.9020070838,
479
- "f":0.9100655152
480
  },
481
  "LAW":{
482
- "p":0.5555555556,
483
- "r":0.46875,
484
- "f":0.5084745763
485
  },
486
  "PERCENT":{
487
- "p":0.92,
488
- "r":0.8805513017,
489
- "f":0.8998435055
 
 
 
 
 
490
  },
491
  "LANGUAGE":{
492
- "p":0.7692307692,
493
- "r":0.625,
494
- "f":0.6896551724
495
  }
496
- }
 
497
  },
498
  "sources":[
499
  {
 
1
  {
2
  "lang":"en",
3
  "name":"core_web_sm",
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":"contact@explosion.ai",
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":0,
14
  "vectors":0,
 
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":0.9725066923,
177
+ "sents_p":0.9205049471,
178
+ "sents_r":0.8899003892,
179
+ "sents_f":0.904943986,
180
+ "dep_uas":0.9166876131,
181
+ "dep_las":0.8979960057,
 
182
  "dep_las_per_type":{
183
  "prep":{
184
+ "p":0.8514792011,
185
+ "r":0.8605577689,
186
+ "f":0.8559944141
187
  },
188
  "det":{
189
+ "p":0.9776402069,
190
+ "r":0.9787164642,
191
+ "f":0.9781780395
192
  },
193
  "pobj":{
194
+ "p":0.9592170292,
195
+ "r":0.9679560181,
196
+ "f":0.9635667097
197
  },
198
  "nsubj":{
199
+ "p":0.9562219157,
200
+ "r":0.9416429354,
201
+ "f":0.9488764293
202
  },
203
  "aux":{
204
+ "p":0.9795809659,
205
+ "r":0.9822843408,
206
+ "f":0.9809307908
207
  },
208
  "advmod":{
209
+ "p":0.8570825239,
210
+ "r":0.8536934208,
211
+ "f":0.8553846154
212
  },
213
  "relcl":{
214
+ "p":0.7760869565,
215
+ "r":0.7772133527,
216
+ "f":0.7766497462
217
  },
218
  "root":{
219
+ "p":0.9174912987,
220
+ "r":0.8868658883,
221
+ "f":0.9019186905
222
  },
223
  "xcomp":{
224
+ "p":0.8794251665,
225
+ "r":0.9005743001,
226
+ "f":0.8898740912
227
  },
228
  "amod":{
229
+ "p":0.9157270416,
230
+ "r":0.9102688695,
231
+ "f":0.9129897979
232
  },
233
  "compound":{
234
+ "p":0.9140038367,
235
+ "r":0.9287146358,
236
+ "f":0.9213005166
237
  },
238
  "poss":{
239
+ "p":0.9734779988,
240
+ "r":0.9752415459,
241
+ "f":0.9743589744
242
  },
243
  "ccomp":{
244
+ "p":0.7639405204,
245
+ "r":0.8370672098,
246
+ "f":0.7988338192
247
  },
248
  "attr":{
249
+ "p":0.8959421454,
250
+ "r":0.9377628259,
251
+ "f":0.9163755907
252
  },
253
  "case":{
254
+ "p":0.9768015795,
255
+ "r":0.9904904905,
256
+ "f":0.9835984095
257
  },
258
  "mark":{
259
+ "p":0.9027518034,
260
+ "r":0.895336513,
261
+ "f":0.8990288679
262
  },
263
  "intj":{
264
+ "p":0.6757624398,
265
+ "r":0.6168498168,
266
+ "f":0.6449636155
267
  },
268
  "advcl":{
269
+ "p":0.6617760618,
270
+ "r":0.6474439688,
271
+ "f":0.6545315682
272
  },
273
  "cc":{
274
+ "p":0.8340149146,
275
+ "r":0.8293266356,
276
+ "f":0.8316641679
277
  },
278
  "neg":{
279
+ "p":0.949127182,
280
+ "r":0.9548419468,
281
+ "f":0.951975988
282
  },
283
  "conj":{
284
+ "p":0.7544115857,
285
+ "r":0.7803373615,
286
+ "f":0.7671554978
287
  },
288
  "nsubjpass":{
289
+ "p":0.9232776618,
290
+ "r":0.9071794872,
291
+ "f":0.9151577858
292
  },
293
  "auxpass":{
294
+ "p":0.9526362824,
295
+ "r":0.9712984055,
296
+ "f":0.9618768328
297
  },
298
  "dobj":{
299
+ "p":0.9192971544,
300
+ "r":0.9422264722,
301
+ "f":0.9306205974
302
  },
303
  "nummod":{
304
+ "p":0.9373881932,
305
+ "r":0.9262626263,
306
+ "f":0.9317922012
307
  },
308
  "npadvmod":{
309
+ "p":0.7576675502,
310
+ "r":0.7108348135,
311
+ "f":0.7335043988
312
  },
313
  "prt":{
314
+ "p":0.8091728092,
315
+ "r":0.8853046595,
316
+ "f":0.8455284553
317
  },
318
  "pcomp":{
319
+ "p":0.871398454,
320
+ "r":0.8683473389,
321
+ "f":0.869870221
322
  },
323
  "expl":{
324
+ "p":0.9808917197,
325
+ "r":0.9892933619,
326
+ "f":0.9850746269
327
  },
328
  "acl":{
329
+ "p":0.7457627119,
330
+ "r":0.6961265685,
331
+ "f":0.7200902935
332
  },
333
  "agent":{
334
+ "p":0.8868243243,
335
+ "r":0.9408602151,
336
+ "f":0.9130434783
337
  },
338
  "dative":{
339
+ "p":0.7659033079,
340
+ "r":0.6903669725,
341
+ "f":0.7261761158
342
  },
343
  "acomp":{
344
+ "p":0.9110499771,
345
+ "r":0.9011337868,
346
+ "f":0.9060647515
347
  },
348
  "dep":{
349
+ "p":0.4232365145,
350
+ "r":0.1655844156,
351
+ "f":0.2380396733
352
  },
353
  "csubj":{
354
+ "p":0.7077922078,
355
+ "r":0.6449704142,
356
+ "f":0.6749226006
357
  },
358
  "quantmod":{
359
+ "p":0.8597883598,
360
+ "r":0.7920389927,
361
+ "f":0.8245243129
362
  },
363
  "nmod":{
364
+ "p":0.7614091273,
365
+ "r":0.5795246801,
366
+ "f":0.6581314879
367
  },
368
  "appos":{
369
+ "p":0.6951055231,
370
+ "r":0.6715835141,
371
+ "f":0.6831421006
372
  },
373
  "predet":{
374
+ "p":0.8273092369,
375
+ "r":0.8841201717,
376
+ "f":0.8547717842
377
  },
378
  "preconj":{
379
+ "p":0.5504587156,
380
+ "r":0.6976744186,
381
+ "f":0.6153846154
382
  },
383
  "oprd":{
384
+ "p":0.821192053,
385
+ "r":0.7402985075,
386
+ "f":0.7786499215
387
  },
388
  "parataxis":{
389
+ "p":0.6215469613,
390
+ "r":0.4880694143,
391
+ "f":0.5467800729
392
  },
393
  "meta":{
394
+ "p":0.8095238095,
395
  "r":0.3269230769,
396
+ "f":0.4657534247
397
  },
398
  "csubjpass":{
399
+ "p":0.6,
400
+ "r":0.5,
401
+ "f":0.5454545455
402
  }
403
  },
404
+ "ents_p":0.8463095057,
405
+ "ents_r":0.8377904647,
406
+ "ents_f":0.8420284384,
407
  "ents_per_type":{
408
  "DATE":{
409
+ "p":0.8653725736,
410
+ "r":0.8774603175,
411
+ "f":0.8713745271
412
  },
413
  "GPE":{
414
+ "p":0.9126848692,
415
+ "r":0.8951185495,
416
+ "f":0.9038163639
417
+ },
418
+ "ORDINAL":{
419
+ "p":0.7818696884,
420
+ "r":0.8571428571,
421
+ "f":0.8177777778
422
  },
423
  "ORG":{
424
+ "p":0.8032096817,
425
+ "r":0.8093849417,
426
+ "f":0.8062854879
427
  },
428
  "FAC":{
429
+ "p":0.412371134,
430
+ "r":0.3076923077,
431
+ "f":0.3524229075
432
  },
433
  "CARDINAL":{
434
+ "p":0.8206857785,
435
+ "r":0.8680142687,
436
+ "f":0.8436867957
437
  },
438
  "PERSON":{
439
+ "p":0.8429059298,
440
+ "r":0.8860966057,
441
+ "f":0.8639618138
442
  },
443
  "NORP":{
444
+ "p":0.8995176849,
445
+ "r":0.8952,
446
+ "f":0.8973536488
 
 
 
 
 
447
  },
448
  "LOC":{
449
+ "p":0.7210144928,
450
+ "r":0.6337579618,
451
+ "f":0.6745762712
452
  },
453
  "TIME":{
454
+ "p":0.7492163009,
455
+ "r":0.6988304094,
456
+ "f":0.7231467474
 
 
 
 
 
457
  },
458
  "QUANTITY":{
459
+ "p":0.8273381295,
460
+ "r":0.6318681319,
461
+ "f":0.7165109034
 
 
 
 
 
462
  },
463
  "EVENT":{
464
+ "p":0.5604395604,
465
+ "r":0.2931034483,
466
+ "f":0.3849056604
467
+ },
468
+ "WORK_OF_ART":{
469
+ "p":0.5151515152,
470
+ "r":0.3505154639,
471
+ "f":0.4171779141
472
  },
473
  "MONEY":{
474
+ "p":0.9178743961,
475
+ "r":0.8972845336,
476
+ "f":0.9074626866
477
  },
478
  "LAW":{
479
+ "p":0.5102040816,
480
+ "r":0.390625,
481
+ "f":0.4424778761
482
  },
483
  "PERCENT":{
484
+ "p":0.9230769231,
485
+ "r":0.8820826953,
486
+ "f":0.9021143305
487
+ },
488
+ "PRODUCT":{
489
+ "p":0.5185185185,
490
+ "r":0.1990521327,
491
+ "f":0.2876712329
492
  },
493
  "LANGUAGE":{
494
+ "p":0.7826086957,
495
+ "r":0.5625,
496
+ "f":0.6545454545
497
  }
498
+ },
499
+ "speed":8030.19594793
500
  },
501
  "sources":[
502
  {
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20b7d17b21c63fcef7ae4c3c3fb96dd7303d9c1af7679730c17526188b556952
3
- size 6730601
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efcd16e914096ec260996fcaeb38eb3831898ab11c956e9463ab94b5593649dd
3
+ size 6879963
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:86de5c9df77f4e1b7f943a9bbe03597f247958f1c9d6cb4c2319028b855e4b8f
3
  size 319909
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b59392116d91c4703c8f57d775d471c14a788104c0491b0364ee00c1ed3dc906
3
  size 319909
senter/cfg CHANGED
@@ -1,3 +1,3 @@
1
  {
2
-
3
  }
 
1
  {
2
+ "overwrite":false
3
  }
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b08f7b005a60e60a5ef7bfccf7688a43b827589b25bb00870a579b3b4fb3e448
3
- size 190395
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f2013511610eaacb41a853d504a56e983b0a3d395061d29f25c103e9e683976
3
+ size 197037
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
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e44dee97269622028054bed3a2afe95fe262a4c0a29d03cd27bb97132e789c5
3
  size 19389
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba998456472a6669d24e643e1924f24daeb15da1b5eb985abae8c3e787162364
3
  size 19389
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3d5333dfc0da3b6a1732d4f797d937fbf44b971d9145572d1b295cfa8d52e26
3
- size 6585091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8f529c77a3dd14a7d13e59bf848a8606f40a5d45928e324b8e3a1ecca98d14ce
3
+ size 6734429
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:ec3430fd196b03ddec50540d84444e463e40f4b0a6423a411a04ac81ef601739
3
- size 1089529
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3754cf655a9b96170f5f2626b663b9899a7a5a1dcbf52470db10c9213bd0c7d
3
+ size 1089556
vocab/vectors.cfg ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ {
2
+ "mode":"default"
3
+ }