Hugging Face's logo

spacy
/
ru_core_news_md

Token Classification
spaCy
Russian
Eval Results
Model card Files Community
adrianeboyd commited on
Commit
741a806
•
1 Parent(s): 0476e6a

Update spaCy pipeline

Browse files
Files changed (13) hide show
  1. README.md +26 -26
  2. accuracy.json +181 -176
  3. attribute_ruler/patterns +0 -0
  4. config.cfg +6 -5
  5. meta.json +185 -180
  6. morphologizer/model +1 -1
  7. ner/model +2 -2
  8. parser/model +1 -1
  9. ru_core_news_md-any-py3-none-any.whl +2 -2
  10. senter/model +1 -1
  11. tok2vec/model +2 -2
  12. tokenizer +0 -0
  13. vocab/strings.json +2 -2
README.md CHANGED
@@ -14,62 +14,62 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.9442584533
18
  - name: NER Recall
19
  type: recall
20
- value: 0.9495034506
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.9468736886
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9882067028
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9882067028
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
- value: 0.971692281
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 2.15292e-05
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.9597537384
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.9477109237
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9980974125
73
  ---
74
  ### Details: https://spacy.io/models/ru#ru_core_news_md
75
 
@@ -78,8 +78,8 @@ Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `ru_core_news_md` |
81
- | **Version** | `3.4.0` |
82
- | **spaCy** | `>=3.4.0,<3.5.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
85
  | **Vectors** | 500002 keys, 20000 unique vectors (300 dimensions) |
@@ -105,22 +105,22 @@ Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
105
 
106
  | Type | Score |
107
  | --- | --- |
108
- | `TOKEN_ACC` | 99.84 |
109
  | `TOKEN_P` | 97.28 |
110
- | `TOKEN_R` | 98.32 |
111
  | `TOKEN_F` | 97.79 |
112
  | `POS_ACC` | 98.82 |
113
- | `MORPH_ACC` | 97.17 |
114
- | `MORPH_MICRO_P` | 98.80 |
115
- | `MORPH_MICRO_R` | 98.08 |
116
- | `MORPH_MICRO_F` | 98.44 |
117
- | `SENTS_P` | 99.81 |
118
- | `SENTS_R` | 99.81 |
119
- | `SENTS_F` | 99.81 |
120
- | `DEP_UAS` | 95.98 |
121
- | `DEP_LAS` | 94.77 |
122
  | `TAG_ACC` | 98.82 |
123
  | `LEMMA_ACC` | 0.00 |
124
- | `ENTS_P` | 94.43 |
125
- | `ENTS_R` | 94.95 |
126
- | `ENTS_F` | 94.69 |
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.9438296445
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.9474835886
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.9456530869
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9882061909
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9882061909
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
+ value: 0.972948348
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 2.15295e-05
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.9595456565
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.9474984155
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9985729236
73
  ---
74
  ### Details: https://spacy.io/models/ru#ru_core_news_md
75
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `ru_core_news_md` |
81
+ | **Version** | `3.5.0` |
82
+ | **spaCy** | `>=3.5.0,<3.6.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
85
  | **Vectors** | 500002 keys, 20000 unique vectors (300 dimensions) |
105
 
106
  | Type | Score |
107
  | --- | --- |
108
+ | `TOKEN_ACC` | 99.68 |
109
  | `TOKEN_P` | 97.28 |
110
+ | `TOKEN_R` | 98.31 |
111
  | `TOKEN_F` | 97.79 |
112
  | `POS_ACC` | 98.82 |
113
+ | `MORPH_ACC` | 97.29 |
114
+ | `MORPH_MICRO_P` | 98.88 |
115
+ | `MORPH_MICRO_R` | 98.17 |
116
+ | `MORPH_MICRO_F` | 98.52 |
117
+ | `SENTS_P` | 99.87 |
118
+ | `SENTS_R` | 99.85 |
119
+ | `SENTS_F` | 99.86 |
120
+ | `DEP_UAS` | 95.95 |
121
+ | `DEP_LAS` | 94.75 |
122
  | `TAG_ACC` | 98.82 |
123
  | `LEMMA_ACC` | 0.00 |
124
+ | `ENTS_P` | 94.38 |
125
+ | `ENTS_R` | 94.75 |
126
+ | `ENTS_F` | 94.57 |
accuracy.json CHANGED
@@ -1,68 +1,68 @@
1
  {
2
- "token_acc": 0.9984047451,
3
- "token_p": 0.9727635194,
4
- "token_r": 0.9831678569,
5
- "token_f": 0.9779380158,
6
- "pos_acc": 0.9882067028,
7
- "morph_acc": 0.971692281,
8
- "morph_micro_p": 0.9880271418,
9
- "morph_micro_r": 0.98081327,
10
- "morph_micro_f": 0.98440699,
11
  "morph_per_feat": {
12
  "Animacy": {
13
- "p": 0.9880564604,
14
- "r": 0.9787221673,
15
- "f": 0.9833671637
16
  },
17
  "Case": {
18
- "p": 0.9757604349,
19
- "r": 0.9691202392,
20
- "f": 0.9724290016
21
  },
22
  "Gender": {
23
- "p": 0.9874913906,
24
- "r": 0.980996314,
25
- "f": 0.984233137
26
  },
27
  "Number": {
28
- "p": 0.995280605,
29
- "r": 0.9890383094,
30
- "f": 0.9921496387
31
  },
32
  "Degree": {
33
- "p": 0.9833145665,
34
- "r": 0.9862422998,
35
- "f": 0.9847762571
36
  },
37
  "Aspect": {
38
- "p": 0.985580847,
39
- "r": 0.9768988764,
40
- "f": 0.9812206573
41
  },
42
  "Mood": {
43
- "p": 0.9983858952,
44
- "r": 0.9969005703,
45
- "f": 0.9976426799
46
  },
47
  "Tense": {
48
- "p": 0.9919120697,
49
- "r": 0.9825390304,
50
- "f": 0.9872033024
51
  },
52
  "VerbForm": {
53
- "p": 0.9951029292,
54
- "r": 0.9863370787,
55
- "f": 0.9907006139
56
  },
57
  "Voice": {
58
- "p": 0.9894803664,
59
- "r": 0.9807640449,
60
- "f": 0.9851029252
61
  },
62
  "StyleVariant": {
63
- "p": 0.9920713578,
64
- "r": 0.9871794872,
65
- "f": 0.9896193772
66
  },
67
  "Polarity": {
68
  "p": 1.0,
@@ -70,14 +70,14 @@
70
  "f": 1.0
71
  },
72
  "Person": {
73
- "p": 0.9986376022,
74
- "r": 0.9921046695,
75
- "f": 0.9953604164
76
  },
77
  "Foreign": {
78
- "p": 0.9737098345,
79
- "r": 0.8650519031,
80
- "f": 0.9161704077
81
  },
82
  "Hyph": {
83
  "p": 0.0,
@@ -85,196 +85,196 @@
85
  "f": 0.0
86
  }
87
  },
88
- "sents_p": 0.9980974125,
89
- "sents_r": 0.9980974125,
90
- "sents_f": 0.9980974125,
91
- "dep_uas": 0.9597537384,
92
- "dep_las": 0.9477109237,
93
  "dep_las_per_type": {
94
  "case": {
95
- "p": 0.9933018868,
96
- "r": 0.9892887344,
97
- "f": 0.9912912489
98
  },
99
  "parataxis": {
100
- "p": 0.8817204301,
101
- "r": 0.8486416559,
102
- "f": 0.8648648649
103
  },
104
  "nmod": {
105
- "p": 0.9244423792,
106
- "r": 0.9238413671,
107
- "f": 0.9241417754
108
  },
109
  "advmod": {
110
- "p": 0.9561373682,
111
- "r": 0.9503210544,
112
- "f": 0.953220339
113
  },
114
  "obl": {
115
- "p": 0.9407174151,
116
- "r": 0.929895791,
117
- "f": 0.9352753012
118
  },
119
  "amod": {
120
- "p": 0.9880613985,
121
- "r": 0.9830316742,
122
- "f": 0.9855401191
123
  },
124
  "nsubj": {
125
- "p": 0.966192733,
126
- "r": 0.9657350387,
127
- "f": 0.9659638316
128
  },
129
  "root": {
130
- "p": 0.9870500857,
131
- "r": 0.9861111111,
132
- "f": 0.986580375
133
  },
134
  "xcomp": {
135
- "p": 0.9547511312,
136
- "r": 0.962006079,
137
- "f": 0.9583648751
138
  },
139
  "conj": {
140
- "p": 0.8786653185,
141
- "r": 0.894646534,
142
- "f": 0.8865839143
143
  },
144
  "cc": {
145
- "p": 0.9715086408,
146
- "r": 0.9728718428,
147
- "f": 0.972189764
148
  },
149
  "fixed": {
150
- "p": 0.9872611465,
151
- "r": 0.9860050891,
152
- "f": 0.986632718
153
  },
154
  "mark": {
155
- "p": 0.9687703318,
156
- "r": 0.9719321149,
157
- "f": 0.9703486478
158
  },
159
  "ccomp": {
160
- "p": 0.9790356394,
161
- "r": 0.9769874477,
162
- "f": 0.9780104712
163
  },
164
  "nummod:gov": {
165
- "p": 0.9705263158,
166
- "r": 0.9604166667,
167
- "f": 0.9654450262
168
  },
169
  "nummod": {
170
- "p": 0.9695652174,
171
- "r": 0.9465195246,
172
- "f": 0.9579037801
173
  },
174
  "obj": {
175
- "p": 0.9645799012,
176
- "r": 0.9598360656,
177
- "f": 0.9622021364
178
  },
179
  "det": {
180
- "p": 0.9675792507,
181
- "r": 0.9703757225,
182
- "f": 0.968975469
183
  },
184
  "appos": {
185
- "p": 0.885659838,
186
- "r": 0.7985395189,
187
- "f": 0.8398463971
188
  },
189
  "aux": {
190
- "p": 0.9716981132,
191
- "r": 0.980952381,
192
- "f": 0.9763033175
193
  },
194
  "flat": {
195
- "p": 0.9906323185,
196
- "r": 0.9635535308,
197
- "f": 0.9769053118
198
  },
199
  "flat:name": {
200
- "p": 0.9637305699,
201
- "r": 0.9607438017,
202
- "f": 0.9622348681
203
  },
204
  "iobj": {
205
- "p": 0.9167822469,
206
- "r": 0.8304020101,
207
- "f": 0.8714568227
208
  },
209
  "acl": {
210
- "p": 0.9178617992,
211
- "r": 0.8789013733,
212
- "f": 0.8979591837
213
  },
214
  "obl:agent": {
215
- "p": 0.7837837838,
216
- "r": 0.7631578947,
217
- "f": 0.7733333333
218
  },
219
  "advcl": {
220
- "p": 0.8497757848,
221
- "r": 0.8652968037,
222
- "f": 0.8574660633
223
  },
224
  "cop": {
225
- "p": 0.9103448276,
226
- "r": 0.9166666667,
227
- "f": 0.9134948097
228
  },
229
  "flat:foreign": {
230
- "p": 0.9653333333,
231
- "r": 0.8227272727,
232
- "f": 0.8883435583
233
  },
234
  "aux:pass": {
235
- "p": 0.9913043478,
236
- "r": 0.9799426934,
237
- "f": 0.9855907781
238
  },
239
  "nsubj:pass": {
240
- "p": 0.951754386,
241
  "r": 0.9503649635,
242
- "f": 0.9510591673
243
  },
244
  "acl:relcl": {
245
- "p": 0.7974413646,
246
- "r": 0.7679671458,
247
- "f": 0.7824267782
248
  },
249
  "orphan": {
250
- "p": 0.7878787879,
251
- "r": 0.7222222222,
252
- "f": 0.7536231884
253
  },
254
  "discourse": {
255
- "p": 0.8676470588,
256
- "r": 0.9076923077,
257
- "f": 0.8872180451
258
  },
259
  "csubj": {
260
- "p": 0.9473684211,
261
- "r": 0.8873239437,
262
- "f": 0.9163636364
263
  },
264
  "expl": {
265
- "p": 0.7894736842,
266
  "r": 0.7894736842,
267
- "f": 0.7894736842
268
  },
269
  "compound": {
270
  "p": 1.0,
271
- "r": 0.4,
272
- "f": 0.5714285714
273
  },
274
  "csubj:pass": {
275
- "p": 0.75,
276
- "r": 0.8181818182,
277
- "f": 0.7826086957
278
  },
279
  "nummod:entity": {
280
  "p": 1.0,
@@ -285,29 +285,34 @@
285
  "p": 0.0,
286
  "r": 0.0,
287
  "f": 0.0
 
 
 
 
 
288
  }
289
  },
290
- "tag_acc": 0.9882067028,
291
- "lemma_acc": 2.15292e-05,
292
- "ents_p": 0.9442584533,
293
- "ents_r": 0.9495034506,
294
- "ents_f": 0.9468736886,
295
  "ents_per_type": {
296
  "PER": {
297
- "p": 0.9582392777,
298
- "r": 0.953396968,
299
- "f": 0.9558119899
300
  },
301
  "LOC": {
302
- "p": 0.972667295,
303
- "r": 0.9749645725,
304
- "f": 0.9738145789
305
  },
306
  "ORG": {
307
- "p": 0.9033653846,
308
- "r": 0.9197258933,
309
- "f": 0.911472229
310
  }
311
  },
312
- "speed": 2063.9072523376
313
  }
1
  {
2
+ "token_acc": 0.9968038482,
3
+ "token_p": 0.9727525387,
4
+ "token_r": 0.9831462495,
5
+ "token_f": 0.9779217779,
6
+ "pos_acc": 0.9882061909,
7
+ "morph_acc": 0.972948348,
8
+ "morph_micro_p": 0.9887788671,
9
+ "morph_micro_r": 0.9817244058,
10
+ "morph_micro_f": 0.9852390089,
11
  "morph_per_feat": {
12
  "Animacy": {
13
+ "p": 0.9891058582,
14
+ "r": 0.9791291204,
15
+ "f": 0.9840922039
16
  },
17
  "Case": {
18
+ "p": 0.9780733285,
19
+ "r": 0.9713737477,
20
+ "f": 0.9747120261
21
  },
22
  "Gender": {
23
+ "p": 0.9878032525,
24
+ "r": 0.981371532,
25
+ "f": 0.9845768886
26
  },
27
  "Number": {
28
+ "p": 0.9957918681,
29
+ "r": 0.9894338343,
30
+ "f": 0.9926026698
31
  },
32
  "Degree": {
33
+ "p": 0.9841188525,
34
+ "r": 0.9861396304,
35
+ "f": 0.9851282051
36
  },
37
  "Aspect": {
38
+ "p": 0.9848772978,
39
+ "r": 0.9776179775,
40
+ "f": 0.9812342115
41
  },
42
  "Mood": {
43
+ "p": 0.9986343886,
44
+ "r": 0.9972725019,
45
+ "f": 0.9979529806
46
  },
47
  "Tense": {
48
+ "p": 0.9914043082,
49
+ "r": 0.9832580115,
50
+ "f": 0.9873143564
51
  },
52
  "VerbForm": {
53
+ "p": 0.9953816898,
54
+ "r": 0.9880449438,
55
+ "f": 0.9916997474
56
  },
57
  "Voice": {
58
+ "p": 0.9898578285,
59
+ "r": 0.9825617978,
60
+ "f": 0.986196319
61
  },
62
  "StyleVariant": {
63
+ "p": 0.9911417323,
64
+ "r": 0.9930966469,
65
+ "f": 0.9921182266
66
  },
67
  "Polarity": {
68
  "p": 1.0,
70
  "f": 1.0
71
  },
72
  "Person": {
73
+ "p": 0.9993192648,
74
+ "r": 0.9934581547,
75
+ "f": 0.9963800905
76
  },
77
  "Foreign": {
78
+ "p": 0.9709583737,
79
+ "r": 0.8676470588,
80
+ "f": 0.9164001827
81
  },
82
  "Hyph": {
83
  "p": 0.0,
85
  "f": 0.0
86
  }
87
  },
88
+ "sents_p": 0.9986679353,
89
+ "sents_r": 0.99847793,
90
+ "sents_f": 0.9985729236,
91
+ "dep_uas": 0.9595456565,
92
+ "dep_las": 0.9474984155,
93
  "dep_las_per_type": {
94
  "case": {
95
+ "p": 0.9915126367,
96
+ "r": 0.9878793573,
97
+ "f": 0.9896926625
98
  },
99
  "parataxis": {
100
+ "p": 0.8791357191,
101
+ "r": 0.8421733506,
102
+ "f": 0.8602576809
103
  },
104
  "nmod": {
105
+ "p": 0.9247812325,
106
+ "r": 0.9226339742,
107
+ "f": 0.9237063555
108
  },
109
  "advmod": {
110
+ "p": 0.9616306954,
111
+ "r": 0.9486312944,
112
+ "f": 0.9550867642
113
  },
114
  "obl": {
115
+ "p": 0.9385497747,
116
+ "r": 0.9301664637,
117
+ "f": 0.9343393148
118
  },
119
  "amod": {
120
+ "p": 0.9875070982,
121
+ "r": 0.9835972851,
122
+ "f": 0.985548314
123
  },
124
  "nsubj": {
125
+ "p": 0.9686460808,
126
+ "r": 0.9658929417,
127
+ "f": 0.9672675522
128
  },
129
  "root": {
130
+ "p": 0.9891387195,
131
+ "r": 0.9876331811,
132
+ "f": 0.988385377
133
  },
134
  "xcomp": {
135
+ "p": 0.9539622642,
136
+ "r": 0.9604863222,
137
+ "f": 0.9572131768
138
  },
139
  "conj": {
140
+ "p": 0.8889264011,
141
+ "r": 0.9035689774,
142
+ "f": 0.8961878829
143
  },
144
  "cc": {
145
+ "p": 0.9695264885,
146
+ "r": 0.9672591207,
147
+ "f": 0.9683914774
148
  },
149
  "fixed": {
150
+ "p": 0.987244898,
151
+ "r": 0.9847328244,
152
+ "f": 0.9859872611
153
  },
154
  "mark": {
155
+ "p": 0.9660574413,
156
+ "r": 0.9660574413,
157
+ "f": 0.9660574413
158
  },
159
  "ccomp": {
160
+ "p": 0.976016684,
161
+ "r": 0.9790794979,
162
+ "f": 0.9775456919
163
  },
164
  "nummod:gov": {
165
+ "p": 0.9704016913,
166
+ "r": 0.95625,
167
+ "f": 0.963273872
168
  },
169
  "nummod": {
170
+ "p": 0.9653078925,
171
+ "r": 0.9448217317,
172
+ "f": 0.954954955
173
  },
174
  "obj": {
175
+ "p": 0.9662273476,
176
+ "r": 0.9614754098,
177
+ "f": 0.9638455218
178
  },
179
  "det": {
180
+ "p": 0.9595959596,
181
+ "r": 0.960982659,
182
+ "f": 0.9602888087
183
  },
184
  "appos": {
185
+ "p": 0.8813799622,
186
+ "r": 0.8011168385,
187
+ "f": 0.8393339334
188
  },
189
  "aux": {
190
+ "p": 0.9433962264,
191
+ "r": 0.9523809524,
192
+ "f": 0.9478672986
193
  },
194
  "flat": {
195
+ "p": 0.9952606635,
196
+ "r": 0.9567198178,
197
+ "f": 0.9756097561
198
  },
199
  "flat:name": {
200
+ "p": 0.966873706,
201
+ "r": 0.9648760331,
202
+ "f": 0.9658738366
203
  },
204
  "iobj": {
205
+ "p": 0.9123783032,
206
+ "r": 0.824120603,
207
+ "f": 0.8660066007
208
  },
209
  "acl": {
210
+ "p": 0.9166666667,
211
+ "r": 0.8651685393,
212
+ "f": 0.8901734104
213
  },
214
  "obl:agent": {
215
+ "p": 0.7215189873,
216
+ "r": 0.75,
217
+ "f": 0.735483871
218
  },
219
  "advcl": {
220
+ "p": 0.8716216216,
221
+ "r": 0.8835616438,
222
+ "f": 0.8775510204
223
  },
224
  "cop": {
225
+ "p": 0.9178082192,
226
+ "r": 0.9305555556,
227
+ "f": 0.924137931
228
  },
229
  "flat:foreign": {
230
+ "p": 0.9625668449,
231
+ "r": 0.8181818182,
232
+ "f": 0.8845208845
233
  },
234
  "aux:pass": {
235
+ "p": 0.9942028986,
236
+ "r": 0.9828080229,
237
+ "f": 0.9884726225
238
  },
239
  "nsubj:pass": {
240
+ "p": 0.9448476052,
241
  "r": 0.9503649635,
242
+ "f": 0.9475982533
243
  },
244
  "acl:relcl": {
245
+ "p": 0.8008385744,
246
+ "r": 0.7843942505,
247
+ "f": 0.7925311203
248
  },
249
  "orphan": {
250
+ "p": 0.7352941176,
251
+ "r": 0.6944444444,
252
+ "f": 0.7142857143
253
  },
254
  "discourse": {
255
+ "p": 0.8219178082,
256
+ "r": 0.9230769231,
257
+ "f": 0.8695652174
258
  },
259
  "csubj": {
260
+ "p": 0.9710144928,
261
+ "r": 0.9436619718,
262
+ "f": 0.9571428571
263
  },
264
  "expl": {
265
+ "p": 0.8333333333,
266
  "r": 0.7894736842,
267
+ "f": 0.8108108108
268
  },
269
  "compound": {
270
  "p": 1.0,
271
+ "r": 0.5,
272
+ "f": 0.6666666667
273
  },
274
  "csubj:pass": {
275
+ "p": 0.8333333333,
276
+ "r": 0.9090909091,
277
+ "f": 0.8695652174
278
  },
279
  "nummod:entity": {
280
  "p": 1.0,
285
  "p": 0.0,
286
  "r": 0.0,
287
  "f": 0.0
288
+ },
289
+ "dep": {
290
+ "p": 0.0,
291
+ "r": 0.0,
292
+ "f": 0.0
293
  }
294
  },
295
+ "tag_acc": 0.9882061909,
296
+ "lemma_acc": 2.15295e-05,
297
+ "ents_p": 0.9438296445,
298
+ "ents_r": 0.9474835886,
299
+ "ents_f": 0.9456530869,
300
  "ents_per_type": {
301
  "PER": {
302
+ "p": 0.9598870056,
303
+ "r": 0.9539584503,
304
+ "f": 0.9569135455
305
  },
306
  "LOC": {
307
+ "p": 0.9717247879,
308
+ "r": 0.9740198394,
309
+ "f": 0.9728709601
310
  },
311
  "ORG": {
312
+ "p": 0.9015444015,
313
+ "r": 0.9143416544,
314
+ "f": 0.9078979344
315
  }
316
  },
317
+ "speed": 2419.855983662
318
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
config.cfg CHANGED
@@ -27,7 +27,7 @@ validate = false
27
 
28
  [components.lemmatizer]
29
  factory = "lemmatizer"
30
- mode = "pymorphy2"
31
  model = null
32
  overwrite = false
33
  scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
@@ -70,8 +70,8 @@ nO = null
70
  [components.ner.model.tok2vec.embed]
71
  @architectures = "spacy.MultiHashEmbed.v2"
72
  width = 96
73
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
74
- rows = [5000,1000,2500,2500,50]
75
  include_static_vectors = true
76
 
77
  [components.ner.model.tok2vec.encode]
@@ -139,8 +139,8 @@ factory = "tok2vec"
139
  [components.tok2vec.model.embed]
140
  @architectures = "spacy.MultiHashEmbed.v2"
141
  width = ${components.tok2vec.model.encode:width}
142
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
143
- rows = [5000,1000,2500,2500,50]
144
  include_static_vectors = true
145
 
146
  [components.tok2vec.model.encode]
@@ -182,6 +182,7 @@ eval_frequency = 1000
182
  frozen_components = []
183
  before_to_disk = null
184
  annotating_components = []
 
185
 
186
  [training.batcher]
187
  @batchers = "spacy.batch_by_words.v1"
27
 
28
  [components.lemmatizer]
29
  factory = "lemmatizer"
30
+ mode = "pymorphy3"
31
  model = null
32
  overwrite = false
33
  scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
70
  [components.ner.model.tok2vec.embed]
71
  @architectures = "spacy.MultiHashEmbed.v2"
72
  width = 96
73
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
74
+ rows = [5000,1000,2500,2500]
75
  include_static_vectors = true
76
 
77
  [components.ner.model.tok2vec.encode]
139
  [components.tok2vec.model.embed]
140
  @architectures = "spacy.MultiHashEmbed.v2"
141
  width = ${components.tok2vec.model.encode:width}
142
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
143
+ rows = [5000,1000,2500,2500,50,50]
144
  include_static_vectors = true
145
 
146
  [components.tok2vec.model.encode]
182
  frozen_components = []
183
  before_to_disk = null
184
  annotating_components = []
185
+ before_update = null
186
 
187
  [training.batcher]
188
  @batchers = "spacy.batch_by_words.v1"
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"ru",
3
  "name":"core_news_md",
4
- "version":"3.4.0",
5
  "description":"Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, 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":">=3.4.0,<3.5.0",
11
- "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
@@ -953,70 +953,70 @@
953
  "senter"
954
  ],
955
  "performance":{
956
- "token_acc":0.9984047451,
957
- "token_p":0.9727635194,
958
- "token_r":0.9831678569,
959
- "token_f":0.9779380158,
960
- "pos_acc":0.9882067028,
961
- "morph_acc":0.971692281,
962
- "morph_micro_p":0.9880271418,
963
- "morph_micro_r":0.98081327,
964
- "morph_micro_f":0.98440699,
965
  "morph_per_feat":{
966
  "Animacy":{
967
- "p":0.9880564604,
968
- "r":0.9787221673,
969
- "f":0.9833671637
970
  },
971
  "Case":{
972
- "p":0.9757604349,
973
- "r":0.9691202392,
974
- "f":0.9724290016
975
  },
976
  "Gender":{
977
- "p":0.9874913906,
978
- "r":0.980996314,
979
- "f":0.984233137
980
  },
981
  "Number":{
982
- "p":0.995280605,
983
- "r":0.9890383094,
984
- "f":0.9921496387
985
  },
986
  "Degree":{
987
- "p":0.9833145665,
988
- "r":0.9862422998,
989
- "f":0.9847762571
990
  },
991
  "Aspect":{
992
- "p":0.985580847,
993
- "r":0.9768988764,
994
- "f":0.9812206573
995
  },
996
  "Mood":{
997
- "p":0.9983858952,
998
- "r":0.9969005703,
999
- "f":0.9976426799
1000
  },
1001
  "Tense":{
1002
- "p":0.9919120697,
1003
- "r":0.9825390304,
1004
- "f":0.9872033024
1005
  },
1006
  "VerbForm":{
1007
- "p":0.9951029292,
1008
- "r":0.9863370787,
1009
- "f":0.9907006139
1010
  },
1011
  "Voice":{
1012
- "p":0.9894803664,
1013
- "r":0.9807640449,
1014
- "f":0.9851029252
1015
  },
1016
  "StyleVariant":{
1017
- "p":0.9920713578,
1018
- "r":0.9871794872,
1019
- "f":0.9896193772
1020
  },
1021
  "Polarity":{
1022
  "p":1.0,
@@ -1024,14 +1024,14 @@
1024
  "f":1.0
1025
  },
1026
  "Person":{
1027
- "p":0.9986376022,
1028
- "r":0.9921046695,
1029
- "f":0.9953604164
1030
  },
1031
  "Foreign":{
1032
- "p":0.9737098345,
1033
- "r":0.8650519031,
1034
- "f":0.9161704077
1035
  },
1036
  "Hyph":{
1037
  "p":0.0,
@@ -1039,196 +1039,196 @@
1039
  "f":0.0
1040
  }
1041
  },
1042
- "sents_p":0.9980974125,
1043
- "sents_r":0.9980974125,
1044
- "sents_f":0.9980974125,
1045
- "dep_uas":0.9597537384,
1046
- "dep_las":0.9477109237,
1047
  "dep_las_per_type":{
1048
  "case":{
1049
- "p":0.9933018868,
1050
- "r":0.9892887344,
1051
- "f":0.9912912489
1052
  },
1053
  "parataxis":{
1054
- "p":0.8817204301,
1055
- "r":0.8486416559,
1056
- "f":0.8648648649
1057
  },
1058
  "nmod":{
1059
- "p":0.9244423792,
1060
- "r":0.9238413671,
1061
- "f":0.9241417754
1062
  },
1063
  "advmod":{
1064
- "p":0.9561373682,
1065
- "r":0.9503210544,
1066
- "f":0.953220339
1067
  },
1068
  "obl":{
1069
- "p":0.9407174151,
1070
- "r":0.929895791,
1071
- "f":0.9352753012
1072
  },
1073
  "amod":{
1074
- "p":0.9880613985,
1075
- "r":0.9830316742,
1076
- "f":0.9855401191
1077
  },
1078
  "nsubj":{
1079
- "p":0.966192733,
1080
- "r":0.9657350387,
1081
- "f":0.9659638316
1082
  },
1083
  "root":{
1084
- "p":0.9870500857,
1085
- "r":0.9861111111,
1086
- "f":0.986580375
1087
  },
1088
  "xcomp":{
1089
- "p":0.9547511312,
1090
- "r":0.962006079,
1091
- "f":0.9583648751
1092
  },
1093
  "conj":{
1094
- "p":0.8786653185,
1095
- "r":0.894646534,
1096
- "f":0.8865839143
1097
  },
1098
  "cc":{
1099
- "p":0.9715086408,
1100
- "r":0.9728718428,
1101
- "f":0.972189764
1102
  },
1103
  "fixed":{
1104
- "p":0.9872611465,
1105
- "r":0.9860050891,
1106
- "f":0.986632718
1107
  },
1108
  "mark":{
1109
- "p":0.9687703318,
1110
- "r":0.9719321149,
1111
- "f":0.9703486478
1112
  },
1113
  "ccomp":{
1114
- "p":0.9790356394,
1115
- "r":0.9769874477,
1116
- "f":0.9780104712
1117
  },
1118
  "nummod:gov":{
1119
- "p":0.9705263158,
1120
- "r":0.9604166667,
1121
- "f":0.9654450262
1122
  },
1123
  "nummod":{
1124
- "p":0.9695652174,
1125
- "r":0.9465195246,
1126
- "f":0.9579037801
1127
  },
1128
  "obj":{
1129
- "p":0.9645799012,
1130
- "r":0.9598360656,
1131
- "f":0.9622021364
1132
  },
1133
  "det":{
1134
- "p":0.9675792507,
1135
- "r":0.9703757225,
1136
- "f":0.968975469
1137
  },
1138
  "appos":{
1139
- "p":0.885659838,
1140
- "r":0.7985395189,
1141
- "f":0.8398463971
1142
  },
1143
  "aux":{
1144
- "p":0.9716981132,
1145
- "r":0.980952381,
1146
- "f":0.9763033175
1147
  },
1148
  "flat":{
1149
- "p":0.9906323185,
1150
- "r":0.9635535308,
1151
- "f":0.9769053118
1152
  },
1153
  "flat:name":{
1154
- "p":0.9637305699,
1155
- "r":0.9607438017,
1156
- "f":0.9622348681
1157
  },
1158
  "iobj":{
1159
- "p":0.9167822469,
1160
- "r":0.8304020101,
1161
- "f":0.8714568227
1162
  },
1163
  "acl":{
1164
- "p":0.9178617992,
1165
- "r":0.8789013733,
1166
- "f":0.8979591837
1167
  },
1168
  "obl:agent":{
1169
- "p":0.7837837838,
1170
- "r":0.7631578947,
1171
- "f":0.7733333333
1172
  },
1173
  "advcl":{
1174
- "p":0.8497757848,
1175
- "r":0.8652968037,
1176
- "f":0.8574660633
1177
  },
1178
  "cop":{
1179
- "p":0.9103448276,
1180
- "r":0.9166666667,
1181
- "f":0.9134948097
1182
  },
1183
  "flat:foreign":{
1184
- "p":0.9653333333,
1185
- "r":0.8227272727,
1186
- "f":0.8883435583
1187
  },
1188
  "aux:pass":{
1189
- "p":0.9913043478,
1190
- "r":0.9799426934,
1191
- "f":0.9855907781
1192
  },
1193
  "nsubj:pass":{
1194
- "p":0.951754386,
1195
  "r":0.9503649635,
1196
- "f":0.9510591673
1197
  },
1198
  "acl:relcl":{
1199
- "p":0.7974413646,
1200
- "r":0.7679671458,
1201
- "f":0.7824267782
1202
  },
1203
  "orphan":{
1204
- "p":0.7878787879,
1205
- "r":0.7222222222,
1206
- "f":0.7536231884
1207
  },
1208
  "discourse":{
1209
- "p":0.8676470588,
1210
- "r":0.9076923077,
1211
- "f":0.8872180451
1212
  },
1213
  "csubj":{
1214
- "p":0.9473684211,
1215
- "r":0.8873239437,
1216
- "f":0.9163636364
1217
  },
1218
  "expl":{
1219
- "p":0.7894736842,
1220
  "r":0.7894736842,
1221
- "f":0.7894736842
1222
  },
1223
  "compound":{
1224
  "p":1.0,
1225
- "r":0.4,
1226
- "f":0.5714285714
1227
  },
1228
  "csubj:pass":{
1229
- "p":0.75,
1230
- "r":0.8181818182,
1231
- "f":0.7826086957
1232
  },
1233
  "nummod:entity":{
1234
  "p":1.0,
@@ -1239,31 +1239,36 @@
1239
  "p":0.0,
1240
  "r":0.0,
1241
  "f":0.0
 
 
 
 
 
1242
  }
1243
  },
1244
- "tag_acc":0.9882067028,
1245
- "lemma_acc":0.0000215292,
1246
- "ents_p":0.9442584533,
1247
- "ents_r":0.9495034506,
1248
- "ents_f":0.9468736886,
1249
  "ents_per_type":{
1250
  "PER":{
1251
- "p":0.9582392777,
1252
- "r":0.953396968,
1253
- "f":0.9558119899
1254
  },
1255
  "LOC":{
1256
- "p":0.972667295,
1257
- "r":0.9749645725,
1258
- "f":0.9738145789
1259
  },
1260
  "ORG":{
1261
- "p":0.9033653846,
1262
- "r":0.9197258933,
1263
- "f":0.911472229
1264
  }
1265
  },
1266
- "speed":2063.9072523376
1267
  },
1268
  "sources":[
1269
  {
@@ -1280,6 +1285,6 @@
1280
  }
1281
  ],
1282
  "requirements":[
1283
- "pymorphy2>=0.9"
1284
  ]
1285
  }
1
  {
2
  "lang":"ru",
3
  "name":"core_news_md",
4
+ "version":"3.5.0",
5
  "description":"Russian pipeline optimized for CPU. Components: tok2vec, morphologizer, 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":">=3.5.0,<3.6.0",
11
+ "spacy_git_version":"9e0322de1",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
953
  "senter"
954
  ],
955
  "performance":{
956
+ "token_acc":0.9968038482,
957
+ "token_p":0.9727525387,
958
+ "token_r":0.9831462495,
959
+ "token_f":0.9779217779,
960
+ "pos_acc":0.9882061909,
961
+ "morph_acc":0.972948348,
962
+ "morph_micro_p":0.9887788671,
963
+ "morph_micro_r":0.9817244058,
964
+ "morph_micro_f":0.9852390089,
965
  "morph_per_feat":{
966
  "Animacy":{
967
+ "p":0.9891058582,
968
+ "r":0.9791291204,
969
+ "f":0.9840922039
970
  },
971
  "Case":{
972
+ "p":0.9780733285,
973
+ "r":0.9713737477,
974
+ "f":0.9747120261
975
  },
976
  "Gender":{
977
+ "p":0.9878032525,
978
+ "r":0.981371532,
979
+ "f":0.9845768886
980
  },
981
  "Number":{
982
+ "p":0.9957918681,
983
+ "r":0.9894338343,
984
+ "f":0.9926026698
985
  },
986
  "Degree":{
987
+ "p":0.9841188525,
988
+ "r":0.9861396304,
989
+ "f":0.9851282051
990
  },
991
  "Aspect":{
992
+ "p":0.9848772978,
993
+ "r":0.9776179775,
994
+ "f":0.9812342115
995
  },
996
  "Mood":{
997
+ "p":0.9986343886,
998
+ "r":0.9972725019,
999
+ "f":0.9979529806
1000
  },
1001
  "Tense":{
1002
+ "p":0.9914043082,
1003
+ "r":0.9832580115,
1004
+ "f":0.9873143564
1005
  },
1006
  "VerbForm":{
1007
+ "p":0.9953816898,
1008
+ "r":0.9880449438,
1009
+ "f":0.9916997474
1010
  },
1011
  "Voice":{
1012
+ "p":0.9898578285,
1013
+ "r":0.9825617978,
1014
+ "f":0.986196319
1015
  },
1016
  "StyleVariant":{
1017
+ "p":0.9911417323,
1018
+ "r":0.9930966469,
1019
+ "f":0.9921182266
1020
  },
1021
  "Polarity":{
1022
  "p":1.0,
1024
  "f":1.0
1025
  },
1026
  "Person":{
1027
+ "p":0.9993192648,
1028
+ "r":0.9934581547,
1029
+ "f":0.9963800905
1030
  },
1031
  "Foreign":{
1032
+ "p":0.9709583737,
1033
+ "r":0.8676470588,
1034
+ "f":0.9164001827
1035
  },
1036
  "Hyph":{
1037
  "p":0.0,
1039
  "f":0.0
1040
  }
1041
  },
1042
+ "sents_p":0.9986679353,
1043
+ "sents_r":0.99847793,
1044
+ "sents_f":0.9985729236,
1045
+ "dep_uas":0.9595456565,
1046
+ "dep_las":0.9474984155,
1047
  "dep_las_per_type":{
1048
  "case":{
1049
+ "p":0.9915126367,
1050
+ "r":0.9878793573,
1051
+ "f":0.9896926625
1052
  },
1053
  "parataxis":{
1054
+ "p":0.8791357191,
1055
+ "r":0.8421733506,
1056
+ "f":0.8602576809
1057
  },
1058
  "nmod":{
1059
+ "p":0.9247812325,
1060
+ "r":0.9226339742,
1061
+ "f":0.9237063555
1062
  },
1063
  "advmod":{
1064
+ "p":0.9616306954,
1065
+ "r":0.9486312944,
1066
+ "f":0.9550867642
1067
  },
1068
  "obl":{
1069
+ "p":0.9385497747,
1070
+ "r":0.9301664637,
1071
+ "f":0.9343393148
1072
  },
1073
  "amod":{
1074
+ "p":0.9875070982,
1075
+ "r":0.9835972851,
1076
+ "f":0.985548314
1077
  },
1078
  "nsubj":{
1079
+ "p":0.9686460808,
1080
+ "r":0.9658929417,
1081
+ "f":0.9672675522
1082
  },
1083
  "root":{
1084
+ "p":0.9891387195,
1085
+ "r":0.9876331811,
1086
+ "f":0.988385377
1087
  },
1088
  "xcomp":{
1089
+ "p":0.9539622642,
1090
+ "r":0.9604863222,
1091
+ "f":0.9572131768
1092
  },
1093
  "conj":{
1094
+ "p":0.8889264011,
1095
+ "r":0.9035689774,
1096
+ "f":0.8961878829
1097
  },
1098
  "cc":{
1099
+ "p":0.9695264885,
1100
+ "r":0.9672591207,
1101
+ "f":0.9683914774
1102
  },
1103
  "fixed":{
1104
+ "p":0.987244898,
1105
+ "r":0.9847328244,
1106
+ "f":0.9859872611
1107
  },
1108
  "mark":{
1109
+ "p":0.9660574413,
1110
+ "r":0.9660574413,
1111
+ "f":0.9660574413
1112
  },
1113
  "ccomp":{
1114
+ "p":0.976016684,
1115
+ "r":0.9790794979,
1116
+ "f":0.9775456919
1117
  },
1118
  "nummod:gov":{
1119
+ "p":0.9704016913,
1120
+ "r":0.95625,
1121
+ "f":0.963273872
1122
  },
1123
  "nummod":{
1124
+ "p":0.9653078925,
1125
+ "r":0.9448217317,
1126
+ "f":0.954954955
1127
  },
1128
  "obj":{
1129
+ "p":0.9662273476,
1130
+ "r":0.9614754098,
1131
+ "f":0.9638455218
1132
  },
1133
  "det":{
1134
+ "p":0.9595959596,
1135
+ "r":0.960982659,
1136
+ "f":0.9602888087
1137
  },
1138
  "appos":{
1139
+ "p":0.8813799622,
1140
+ "r":0.8011168385,
1141
+ "f":0.8393339334
1142
  },
1143
  "aux":{
1144
+ "p":0.9433962264,
1145
+ "r":0.9523809524,
1146
+ "f":0.9478672986
1147
  },
1148
  "flat":{
1149
+ "p":0.9952606635,
1150
+ "r":0.9567198178,
1151
+ "f":0.9756097561
1152
  },
1153
  "flat:name":{
1154
+ "p":0.966873706,
1155
+ "r":0.9648760331,
1156
+ "f":0.9658738366
1157
  },
1158
  "iobj":{
1159
+ "p":0.9123783032,
1160
+ "r":0.824120603,
1161
+ "f":0.8660066007
1162
  },
1163
  "acl":{
1164
+ "p":0.9166666667,
1165
+ "r":0.8651685393,
1166
+ "f":0.8901734104
1167
  },
1168
  "obl:agent":{
1169
+ "p":0.7215189873,
1170
+ "r":0.75,
1171
+ "f":0.735483871
1172
  },
1173
  "advcl":{
1174
+ "p":0.8716216216,
1175
+ "r":0.8835616438,
1176
+ "f":0.8775510204
1177
  },
1178
  "cop":{
1179
+ "p":0.9178082192,
1180
+ "r":0.9305555556,
1181
+ "f":0.924137931
1182
  },
1183
  "flat:foreign":{
1184
+ "p":0.9625668449,
1185
+ "r":0.8181818182,
1186
+ "f":0.8845208845
1187
  },
1188
  "aux:pass":{
1189
+ "p":0.9942028986,
1190
+ "r":0.9828080229,
1191
+ "f":0.9884726225
1192
  },
1193
  "nsubj:pass":{
1194
+ "p":0.9448476052,
1195
  "r":0.9503649635,
1196
+ "f":0.9475982533
1197
  },
1198
  "acl:relcl":{
1199
+ "p":0.8008385744,
1200
+ "r":0.7843942505,
1201
+ "f":0.7925311203
1202
  },
1203
  "orphan":{
1204
+ "p":0.7352941176,
1205
+ "r":0.6944444444,
1206
+ "f":0.7142857143
1207
  },
1208
  "discourse":{
1209
+ "p":0.8219178082,
1210
+ "r":0.9230769231,
1211
+ "f":0.8695652174
1212
  },
1213
  "csubj":{
1214
+ "p":0.9710144928,
1215
+ "r":0.9436619718,
1216
+ "f":0.9571428571
1217
  },
1218
  "expl":{
1219
+ "p":0.8333333333,
1220
  "r":0.7894736842,
1221
+ "f":0.8108108108
1222
  },
1223
  "compound":{
1224
  "p":1.0,
1225
+ "r":0.5,
1226
+ "f":0.6666666667
1227
  },
1228
  "csubj:pass":{
1229
+ "p":0.8333333333,
1230
+ "r":0.9090909091,
1231
+ "f":0.8695652174
1232
  },
1233
  "nummod:entity":{
1234
  "p":1.0,
1239
  "p":0.0,
1240
  "r":0.0,
1241
  "f":0.0
1242
+ },
1243
+ "dep":{
1244
+ "p":0.0,
1245
+ "r":0.0,
1246
+ "f":0.0
1247
  }
1248
  },
1249
+ "tag_acc":0.9882061909,
1250
+ "lemma_acc":0.0000215295,
1251
+ "ents_p":0.9438296445,
1252
+ "ents_r":0.9474835886,
1253
+ "ents_f":0.9456530869,
1254
  "ents_per_type":{
1255
  "PER":{
1256
+ "p":0.9598870056,
1257
+ "r":0.9539584503,
1258
+ "f":0.9569135455
1259
  },
1260
  "LOC":{
1261
+ "p":0.9717247879,
1262
+ "r":0.9740198394,
1263
+ "f":0.9728709601
1264
  },
1265
  "ORG":{
1266
+ "p":0.9015444015,
1267
+ "r":0.9143416544,
1268
+ "f":0.9078979344
1269
  }
1270
  },
1271
+ "speed":2419.855983662
1272
  },
1273
  "sources":[
1274
  {
1285
  }
1286
  ],
1287
  "requirements":[
1288
+ "pymorphy3>=1.0.0"
1289
  ]
1290
  }
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:35390094a1baba496fefa7c2901d2620614d68cbbfd81c48b2a3cc06c18d5e79
3
  size 332570
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c36092621041b7473b9a114e3f243a971c3974a337e5ce76c2bb6c40d0d5be3
3
  size 332570
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f971e8f3e93fdd8607e9f37d49c0214d76c16195ebe4d138275dc8aef293f013
3
- size 6495552
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0b4573855d6fd4b9e82211721a344471c5ba5ca6546d019b0639917d84cda31d
3
+ size 6365342
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:006fb1da70fc2fd1584ed2c844809b105588fb5495b13cbce8d6cc3ebee5fc88
3
  size 312369
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfa55f89f7bea9488fbedf2bce98d1ca1e1ad22d8a6306c4aae6c31900f51bfc
3
  size 312369
ru_core_news_md-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d44831ef205ff8eeaea5c05404f02edce96502b99930e0c25c2978c5b0949c36
3
- size 41885781
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:446d6667f7f178bb3100d3af66574fda4da86dd5732239f044dde8182e3dd4ad
3
+ size 41888569
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aba4067d17fc4cee82c5d6b2eb054e5ecef8fa2a67fa5103a9f2061272f6934a
3
  size 219953
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5ae19c6d3f8928a2bd734c0c8d324722ac214d07bd35088e68295a4834da9cf9
3
  size 219953
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c02ba59113163b4dd5bdef5d5b4f2fafb66a6e45a133b5a7bb609823a0cf10e2
3
- size 6365604
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c70cbc5b6ed3a0b69aa358a381adfbbde3398d8e6ec36f9d5a15cc4d313c6f0b
3
+ size 6495793
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 sha256:80a194c976452ce9e08dcbb3e0cc44dbe4e3e55b9306749dd798b9396e9ab477
3
- size 49011229
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:967899b299d4c01affbceff241c8c8546b171c66d05a57fe8dc078c192759284
3
+ size 49011292