EC2 Default User commited on
Commit
c653306
1 Parent(s): 39967f2

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -14,47 +14,41 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.7220589964
18
  - name: NER Recall
19
  type: recall
20
- value: 0.6751648352
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.6978249759
24
  - task:
25
- name: POS
26
  type: token-classification
27
  metrics:
28
- - name: POS Accuracy
29
  type: accuracy
30
- value: 0.9004973002
31
  - task:
32
- name: SENTER
33
  type: token-classification
34
  metrics:
35
- - name: SENTER Precision
36
- type: precision
37
- value: 0.7859447831
38
- - name: SENTER Recall
39
- type: recall
40
- value: 0.7298152156
41
- - name: SENTER F Score
42
  type: f_score
43
- value: 0.7568407423
44
  - task:
45
- name: UNLABELED_DEPENDENCIES
46
  type: token-classification
47
  metrics:
48
- - name: Unlabeled Dependencies Accuracy
49
- type: accuracy
50
- value: 0.7076909586
51
  - task:
52
- name: LABELED_DEPENDENCIES
53
  type: token-classification
54
  metrics:
55
- - name: Labeled Dependencies Accuracy
56
- type: accuracy
57
- value: 0.7076909586
58
  ---
59
  ### Details: https://spacy.io/models/zh#zh_core_web_md
60
 
@@ -63,8 +57,8 @@ Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
63
  | Feature | Description |
64
  | --- | --- |
65
  | **Name** | `zh_core_web_md` |
66
- | **Version** | `3.2.0` |
67
- | **spaCy** | `>=3.2.0,<3.3.0` |
68
  | **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `ner` |
69
  | **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `ner` |
70
  | **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
@@ -76,13 +70,12 @@ Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
76
 
77
  <details>
78
 
79
- <summary>View label scheme (101 labels for 4 components)</summary>
80
 
81
  | Component | Labels |
82
  | --- | --- |
83
  | **`tagger`** | `AD`, `AS`, `BA`, `CC`, `CD`, `CS`, `DEC`, `DEG`, `DER`, `DEV`, `DT`, `ETC`, `FW`, `IJ`, `INF`, `JJ`, `LB`, `LC`, `M`, `MSP`, `NN`, `NR`, `NT`, `OD`, `ON`, `P`, `PN`, `PU`, `SB`, `SP`, `URL`, `VA`, `VC`, `VE`, `VV`, `X` |
84
  | **`parser`** | `ROOT`, `acl`, `advcl:loc`, `advmod`, `advmod:dvp`, `advmod:loc`, `advmod:rcomp`, `amod`, `amod:ordmod`, `appos`, `aux:asp`, `aux:ba`, `aux:modal`, `aux:prtmod`, `auxpass`, `case`, `cc`, `ccomp`, `compound:nn`, `compound:vc`, `conj`, `cop`, `dep`, `det`, `discourse`, `dobj`, `etc`, `mark`, `mark:clf`, `name`, `neg`, `nmod`, `nmod:assmod`, `nmod:poss`, `nmod:prep`, `nmod:range`, `nmod:tmod`, `nmod:topic`, `nsubj`, `nsubj:xsubj`, `nsubjpass`, `nummod`, `parataxis:prnmod`, `punct`, `xcomp` |
85
- | **`senter`** | `I`, `S` |
86
  | **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `TIME`, `WORK_OF_ART` |
87
 
88
  </details>
@@ -95,12 +88,12 @@ Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
95
  | `TOKEN_P` | 94.58 |
96
  | `TOKEN_R` | 91.36 |
97
  | `TOKEN_F` | 92.94 |
98
- | `TAG_ACC` | 90.05 |
99
- | `SENTS_P` | 78.59 |
100
- | `SENTS_R` | 72.98 |
101
- | `SENTS_F` | 75.68 |
102
- | `DEP_UAS` | 70.77 |
103
- | `DEP_LAS` | 65.52 |
104
- | `ENTS_P` | 72.21 |
105
- | `ENTS_R` | 67.52 |
106
- | `ENTS_F` | 69.78 |
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.7214151828
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.6767032967
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.6983442958
24
  - task:
25
+ name: TAG
26
  type: token-classification
27
  metrics:
28
+ - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.8993969506
31
  - task:
32
+ name: UNLABELED_DEPENDENCIES
33
  type: token-classification
34
  metrics:
35
+ - name: Unlabeled Attachment Score (UAS)
 
 
 
 
 
 
36
  type: f_score
37
+ value: 0.7039979835
38
  - task:
39
+ name: LABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
+ - name: Labeled Attachment Score (LAS)
43
+ type: f_score
44
+ value: 0.6522146335
45
  - task:
46
+ name: SENTS
47
  type: token-classification
48
  metrics:
49
+ - name: Sentences F-Score
50
+ type: f_score
51
+ value: 0.7534931861
52
  ---
53
  ### Details: https://spacy.io/models/zh#zh_core_web_md
54
 
 
57
  | Feature | Description |
58
  | --- | --- |
59
  | **Name** | `zh_core_web_md` |
60
+ | **Version** | `3.3.0` |
61
+ | **spaCy** | `>=3.3.0.dev0,<3.4.0` |
62
  | **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `ner` |
63
  | **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `ner` |
64
  | **Vectors** | 500000 keys, 20000 unique vectors (300 dimensions) |
 
70
 
71
  <details>
72
 
73
+ <summary>View label scheme (99 labels for 3 components)</summary>
74
 
75
  | Component | Labels |
76
  | --- | --- |
77
  | **`tagger`** | `AD`, `AS`, `BA`, `CC`, `CD`, `CS`, `DEC`, `DEG`, `DER`, `DEV`, `DT`, `ETC`, `FW`, `IJ`, `INF`, `JJ`, `LB`, `LC`, `M`, `MSP`, `NN`, `NR`, `NT`, `OD`, `ON`, `P`, `PN`, `PU`, `SB`, `SP`, `URL`, `VA`, `VC`, `VE`, `VV`, `X` |
78
  | **`parser`** | `ROOT`, `acl`, `advcl:loc`, `advmod`, `advmod:dvp`, `advmod:loc`, `advmod:rcomp`, `amod`, `amod:ordmod`, `appos`, `aux:asp`, `aux:ba`, `aux:modal`, `aux:prtmod`, `auxpass`, `case`, `cc`, `ccomp`, `compound:nn`, `compound:vc`, `conj`, `cop`, `dep`, `det`, `discourse`, `dobj`, `etc`, `mark`, `mark:clf`, `name`, `neg`, `nmod`, `nmod:assmod`, `nmod:poss`, `nmod:prep`, `nmod:range`, `nmod:tmod`, `nmod:topic`, `nsubj`, `nsubj:xsubj`, `nsubjpass`, `nummod`, `parataxis:prnmod`, `punct`, `xcomp` |
 
79
  | **`ner`** | `CARDINAL`, `DATE`, `EVENT`, `FAC`, `GPE`, `LANGUAGE`, `LAW`, `LOC`, `MONEY`, `NORP`, `ORDINAL`, `ORG`, `PERCENT`, `PERSON`, `PRODUCT`, `QUANTITY`, `TIME`, `WORK_OF_ART` |
80
 
81
  </details>
 
88
  | `TOKEN_P` | 94.58 |
89
  | `TOKEN_R` | 91.36 |
90
  | `TOKEN_F` | 92.94 |
91
+ | `TAG_ACC` | 89.94 |
92
+ | `SENTS_P` | 78.18 |
93
+ | `SENTS_R` | 72.72 |
94
+ | `SENTS_F` | 75.35 |
95
+ | `DEP_UAS` | 70.40 |
96
+ | `DEP_LAS` | 65.22 |
97
+ | `ENTS_P` | 72.14 |
98
+ | `ENTS_R` | 67.67 |
99
+ | `ENTS_F` | 69.83 |
accuracy.json CHANGED
@@ -3,212 +3,207 @@
3
  "token_p": 0.9458325855,
4
  "token_r": 0.9136060443,
5
  "token_f": 0.9294400505,
6
- "tag_acc": 0.9004973002,
7
- "sents_p": 0.7859447831,
8
- "sents_r": 0.7298152156,
9
- "sents_f": 0.7568407423,
10
- "dep_uas": 0.7076909586,
11
- "dep_las": 0.6551856356,
12
  "dep_las_per_type": {
13
  "dep": {
14
- "p": 0.4941927991,
15
- "r": 0.3439426089,
16
- "f": 0.4056002383
17
  },
18
  "case": {
19
- "p": 0.815348957,
20
- "r": 0.7677012609,
21
- "f": 0.790808043
22
  },
23
  "nmod:tmod": {
24
- "p": 0.7291941876,
25
  "r": 0.7510204082,
26
- "f": 0.7399463807
27
  },
28
  "nummod": {
29
- "p": 0.8324715615,
30
- "r": 0.5363091272,
31
- "f": 0.652350081
32
  },
33
  "mark:clf": {
34
- "p": 0.923958962,
35
- "r": 0.5710555763,
36
- "f": 0.7058552328
37
  },
38
  "auxpass": {
39
- "p": 0.8864864865,
40
- "r": 0.8864864865,
41
- "f": 0.8864864865
42
  },
43
  "nsubj": {
44
- "p": 0.7838943894,
45
- "r": 0.7293944233,
46
- "f": 0.7556630186
47
  },
48
  "acl": {
49
- "p": 0.7085714286,
50
- "r": 0.5501941209,
51
- "f": 0.6194192944
52
  },
53
  "advmod": {
54
- "p": 0.8221938776,
55
- "r": 0.7306733167,
56
- "f": 0.7737366463
57
  },
58
  "mark": {
59
- "p": 0.7447306792,
60
- "r": 0.6967572305,
61
- "f": 0.7199456645
62
  },
63
  "xcomp": {
64
- "p": 0.7822878229,
65
- "r": 0.6905537459,
66
- "f": 0.7335640138
67
  },
68
  "nmod:assmod": {
69
- "p": 0.7571008815,
70
- "r": 0.7217553688,
71
- "f": 0.7390057361
72
  },
73
  "det": {
74
- "p": 0.8367670365,
75
- "r": 0.618629174,
76
- "f": 0.7113506231
77
  },
78
  "amod": {
79
- "p": 0.7567811935,
80
- "r": 0.6575019639,
81
- "f": 0.7036569987
82
  },
83
  "nmod:prep": {
84
- "p": 0.6989096025,
85
- "r": 0.6010284332,
86
- "f": 0.6462839486
87
  },
88
  "root": {
89
- "p": 0.7426623746,
90
- "r": 0.6529049442,
91
- "f": 0.694897236
92
  },
93
  "aux:prtmod": {
94
- "p": 0.9058823529,
95
- "r": 0.825,
96
- "f": 0.8635514019
97
  },
98
  "compound:nn": {
99
- "p": 0.7339595888,
100
- "r": 0.700676819,
101
- "f": 0.716932133
102
  },
103
  "dobj": {
104
- "p": 0.802248996,
105
- "r": 0.7397422604,
106
- "f": 0.76972873
107
  },
108
  "ccomp": {
109
- "p": 0.6483430799,
110
- "r": 0.6465785381,
111
- "f": 0.6474596068
112
  },
113
  "advmod:rcomp": {
114
- "p": 0.8196202532,
115
- "r": 0.7174515235,
116
- "f": 0.765140325
117
  },
118
  "nmod:topic": {
119
- "p": 0.3596059113,
120
- "r": 0.237012987,
121
- "f": 0.2857142857
122
  },
123
  "cop": {
124
- "p": 0.7555739059,
125
- "r": 0.5888030888,
126
- "f": 0.6618444846
127
  },
128
  "discourse": {
129
- "p": 0.5577797998,
130
- "r": 0.5057755776,
131
- "f": 0.5305062743
132
  },
133
  "neg": {
134
- "p": 0.8365527489,
135
- "r": 0.6694411415,
136
- "f": 0.7437252312
137
  },
138
  "aux:modal": {
139
- "p": 0.8626198083,
140
- "r": 0.8376421923,
141
- "f": 0.8499475341
142
  },
143
  "nmod": {
144
- "p": 0.7152,
145
- "r": 0.6065128901,
146
- "f": 0.6563876652
147
  },
148
  "aux:ba": {
149
- "p": 0.8444444444,
150
- "r": 0.8085106383,
151
- "f": 0.8260869565
152
  },
153
  "advmod:loc": {
154
- "p": 0.6130268199,
155
- "r": 0.4747774481,
156
- "f": 0.5351170569
157
  },
158
  "aux:asp": {
159
- "p": 0.9095435685,
160
- "r": 0.8740031898,
161
- "f": 0.8914192761
162
  },
163
  "conj": {
164
- "p": 0.5032329577,
165
- "r": 0.5149338374,
166
- "f": 0.5090161637
167
  },
168
  "nsubjpass": {
169
- "p": 0.8292682927,
170
- "r": 0.68,
171
- "f": 0.7472527473
172
  },
173
  "compound:vc": {
174
- "p": 0.4486486486,
175
- "r": 0.4300518135,
176
- "f": 0.4391534392
177
  },
178
  "advcl:loc": {
179
- "p": 0.5945945946,
180
  "r": 0.4714285714,
181
- "f": 0.5258964143
182
  },
183
  "cc": {
184
- "p": 0.7013108614,
185
- "r": 0.6645962733,
186
- "f": 0.6824601367
187
  },
188
  "advmod:dvp": {
189
- "p": 0.8045112782,
190
  "r": 0.6645962733,
191
- "f": 0.7278911565
192
  },
193
  "appos": {
194
- "p": 0.8658536585,
195
- "r": 0.816091954,
196
- "f": 0.8402366864
197
- },
198
- "name": {
199
- "p": 0.5625,
200
- "r": 0.4666666667,
201
- "f": 0.5101214575
202
- },
203
- "parataxis:prnmod": {
204
- "p": 0.5,
205
- "r": 0.1278195489,
206
- "f": 0.2035928144
207
  },
208
  "nmod:poss": {
209
- "p": 0.6352941176,
210
- "r": 0.4,
211
- "f": 0.4909090909
 
 
 
 
 
212
  },
213
  "nsubj:xsubj": {
214
  "p": 0.0,
@@ -216,14 +211,19 @@
216
  "f": 0.0
217
  },
218
  "nmod:range": {
219
- "p": 0.7346153846,
220
- "r": 0.6409395973,
221
- "f": 0.6845878136
 
 
 
 
 
222
  },
223
  "amod:ordmod": {
224
- "p": 0.6181818182,
225
- "r": 0.53125,
226
- "f": 0.5714285714
227
  },
228
  "erased": {
229
  "p": 0.0,
@@ -231,94 +231,94 @@
231
  "f": 0.0
232
  },
233
  "etc": {
234
- "p": 0.9268292683,
235
- "r": 0.9047619048,
236
- "f": 0.9156626506
237
  }
238
  },
239
- "ents_p": 0.7220589964,
240
- "ents_r": 0.6751648352,
241
- "ents_f": 0.6978249759,
242
  "ents_per_type": {
243
  "DATE": {
244
- "p": 0.758780037,
245
- "r": 0.8136769078,
246
- "f": 0.7852702056
247
  },
248
  "GPE": {
249
- "p": 0.7517889088,
250
- "r": 0.8216031281,
251
- "f": 0.7851471275
252
  },
253
  "ORDINAL": {
254
- "p": 0.8720930233,
255
- "r": 0.7894736842,
256
- "f": 0.8287292818
257
  },
258
  "FAC": {
259
- "p": 0.5076923077,
260
- "r": 0.3548387097,
261
- "f": 0.417721519
262
- },
263
- "PERSON": {
264
- "p": 0.7917511832,
265
- "r": 0.7545103093,
266
- "f": 0.7726822831
267
  },
268
  "ORG": {
269
- "p": 0.6896831844,
270
- "r": 0.6461187215,
271
- "f": 0.6671905697
 
 
 
 
 
272
  },
273
  "QUANTITY": {
274
- "p": 0.7706422018,
275
- "r": 0.6222222222,
276
- "f": 0.6885245902
 
 
 
 
 
277
  },
278
  "CARDINAL": {
279
- "p": 0.6181818182,
280
- "r": 0.5141129032,
281
- "f": 0.5613648872
282
  },
283
- "LOC": {
284
- "p": 0.5247148289,
285
- "r": 0.3709677419,
286
- "f": 0.4346456693
287
  },
288
  "NORP": {
289
- "p": 0.6646153846,
290
- "r": 0.4537815126,
291
- "f": 0.5393258427
292
  },
293
  "WORK_OF_ART": {
294
- "p": 0.5733333333,
295
- "r": 0.2866666667,
296
- "f": 0.3822222222
297
- },
298
- "TIME": {
299
- "p": 0.7209302326,
300
- "r": 0.7524271845,
301
- "f": 0.7363420428
302
- },
303
- "PRODUCT": {
304
- "p": 0.2,
305
- "r": 0.0612244898,
306
- "f": 0.09375
307
  },
308
  "MONEY": {
309
- "p": 0.9230769231,
310
- "r": 0.8,
311
- "f": 0.8571428571
312
  },
313
  "PERCENT": {
314
- "p": 0.7613636364,
315
- "r": 0.8072289157,
316
- "f": 0.783625731
317
  },
318
  "EVENT": {
319
- "p": 0.5688073394,
320
- "r": 0.4558823529,
321
- "f": 0.506122449
 
 
 
 
 
322
  },
323
  "LAW": {
324
  "p": 0.4814814815,
@@ -326,10 +326,10 @@
326
  "f": 0.2988505747
327
  },
328
  "LANGUAGE": {
329
- "p": 0.6363636364,
330
  "r": 0.7777777778,
331
- "f": 0.7
332
  }
333
  },
334
- "speed": 7391.1713592242
335
  }
 
3
  "token_p": 0.9458325855,
4
  "token_r": 0.9136060443,
5
  "token_f": 0.9294400505,
6
+ "tag_acc": 0.8993969506,
7
+ "sents_p": 0.7818149275,
8
+ "sents_r": 0.7271516564,
9
+ "sents_f": 0.7534931861,
10
+ "dep_uas": 0.7039979835,
11
+ "dep_las": 0.6522146335,
12
  "dep_las_per_type": {
13
  "dep": {
14
+ "p": 0.479214123,
15
+ "r": 0.3401030615,
16
+ "f": 0.3978488269
17
  },
18
  "case": {
19
+ "p": 0.81099213,
20
+ "r": 0.7621241513,
21
+ "f": 0.7857991124
22
  },
23
  "nmod:tmod": {
24
+ "p": 0.7311258278,
25
  "r": 0.7510204082,
26
+ "f": 0.7409395973
27
  },
28
  "nummod": {
29
+ "p": 0.8237704918,
30
+ "r": 0.5356429047,
31
+ "f": 0.649172386
32
  },
33
  "mark:clf": {
34
+ "p": 0.9305724726,
35
+ "r": 0.5699365908,
36
+ "f": 0.7069164932
37
  },
38
  "auxpass": {
39
+ "p": 0.8548387097,
40
+ "r": 0.8594594595,
41
+ "f": 0.8571428571
42
  },
43
  "nsubj": {
44
+ "p": 0.7813199842,
45
+ "r": 0.7285345781,
46
+ "f": 0.7540045767
47
  },
48
  "acl": {
49
+ "p": 0.6691324815,
50
+ "r": 0.5518580144,
51
+ "f": 0.6048632219
52
  },
53
  "advmod": {
54
+ "p": 0.8206363291,
55
+ "r": 0.7338472002,
56
+ "f": 0.7748189815
57
  },
58
  "mark": {
59
+ "p": 0.7307514984,
60
+ "r": 0.69456617,
61
+ "f": 0.7121995057
62
  },
63
  "xcomp": {
64
+ "p": 0.7686703097,
65
+ "r": 0.6872964169,
66
+ "f": 0.7257093723
67
  },
68
  "nmod:assmod": {
69
+ "p": 0.761548471,
70
+ "r": 0.7286025521,
71
+ "f": 0.7447113091
72
  },
73
  "det": {
74
+ "p": 0.8413848631,
75
+ "r": 0.6121851201,
76
+ "f": 0.7087148186
77
  },
78
  "amod": {
79
+ "p": 0.7721057429,
80
+ "r": 0.6653574234,
81
+ "f": 0.7147679325
82
  },
83
  "nmod:prep": {
84
+ "p": 0.6953619115,
85
+ "r": 0.5986085904,
86
+ "f": 0.6433680104
87
  },
88
  "root": {
89
+ "p": 0.7341652486,
90
+ "r": 0.6464125187,
91
+ "f": 0.6875
92
  },
93
  "aux:prtmod": {
94
+ "p": 0.9032258065,
95
+ "r": 0.8,
96
+ "f": 0.8484848485
97
  },
98
  "compound:nn": {
99
+ "p": 0.7426056338,
100
+ "r": 0.7137055838,
101
+ "f": 0.7278688525
102
  },
103
  "dobj": {
104
+ "p": 0.8030180107,
105
+ "r": 0.7330765812,
106
+ "f": 0.7664550101
107
  },
108
  "ccomp": {
109
+ "p": 0.6494183714,
110
+ "r": 0.6294712286,
111
+ "f": 0.6392892399
112
  },
113
  "advmod:rcomp": {
114
+ "p": 0.803125,
115
+ "r": 0.7119113573,
116
+ "f": 0.7547723935
117
  },
118
  "nmod:topic": {
119
+ "p": 0.3718592965,
120
+ "r": 0.2402597403,
121
+ "f": 0.291913215
122
  },
123
  "cop": {
124
+ "p": 0.7485806975,
125
+ "r": 0.593951094,
126
+ "f": 0.6623609616
127
  },
128
  "discourse": {
129
+ "p": 0.5652173913,
130
+ "r": 0.4933993399,
131
+ "f": 0.5268722467
132
  },
133
  "neg": {
134
+ "p": 0.8325859492,
135
+ "r": 0.6623067776,
136
+ "f": 0.7377483444
137
  },
138
  "aux:modal": {
139
+ "p": 0.8624733475,
140
+ "r": 0.8366080662,
141
+ "f": 0.849343832
142
  },
143
  "nmod": {
144
+ "p": 0.729468599,
145
+ "r": 0.6146540027,
146
+ "f": 0.6671575847
147
  },
148
  "aux:ba": {
149
+ "p": 0.8287292818,
150
+ "r": 0.7978723404,
151
+ "f": 0.8130081301
152
  },
153
  "advmod:loc": {
154
+ "p": 0.606741573,
155
+ "r": 0.4807121662,
156
+ "f": 0.5364238411
157
  },
158
  "aux:asp": {
159
+ "p": 0.9072249589,
160
+ "r": 0.8811802233,
161
+ "f": 0.894012945
162
  },
163
  "conj": {
164
+ "p": 0.4831861732,
165
+ "r": 0.4862003781,
166
+ "f": 0.4846885895
167
  },
168
  "nsubjpass": {
169
+ "p": 0.7674418605,
170
+ "r": 0.66,
171
+ "f": 0.7096774194
172
  },
173
  "compound:vc": {
174
+ "p": 0.4943181818,
175
+ "r": 0.4507772021,
176
+ "f": 0.4715447154
177
  },
178
  "advcl:loc": {
179
+ "p": 0.511627907,
180
  "r": 0.4714285714,
181
+ "f": 0.4907063197
182
  },
183
  "cc": {
184
+ "p": 0.7040913416,
185
+ "r": 0.6566104703,
186
+ "f": 0.6795224977
187
  },
188
  "advmod:dvp": {
189
+ "p": 0.842519685,
190
  "r": 0.6645962733,
191
+ "f": 0.7430555556
192
  },
193
  "appos": {
194
+ "p": 0.8796992481,
195
+ "r": 0.8068965517,
196
+ "f": 0.8417266187
 
 
 
 
 
 
 
 
 
 
197
  },
198
  "nmod:poss": {
199
+ "p": 0.6904761905,
200
+ "r": 0.4296296296,
201
+ "f": 0.5296803653
202
+ },
203
+ "name": {
204
+ "p": 0.6285714286,
205
+ "r": 0.4888888889,
206
+ "f": 0.55
207
  },
208
  "nsubj:xsubj": {
209
  "p": 0.0,
 
211
  "f": 0.0
212
  },
213
  "nmod:range": {
214
+ "p": 0.7366412214,
215
+ "r": 0.6476510067,
216
+ "f": 0.6892857143
217
+ },
218
+ "parataxis:prnmod": {
219
+ "p": 0.53125,
220
+ "r": 0.1278195489,
221
+ "f": 0.2060606061
222
  },
223
  "amod:ordmod": {
224
+ "p": 0.6037735849,
225
+ "r": 0.5,
226
+ "f": 0.547008547
227
  },
228
  "erased": {
229
  "p": 0.0,
 
231
  "f": 0.0
232
  },
233
  "etc": {
234
+ "p": 0.9277108434,
235
+ "r": 0.9166666667,
236
+ "f": 0.9221556886
237
  }
238
  },
239
+ "ents_p": 0.7214151828,
240
+ "ents_r": 0.6767032967,
241
+ "ents_f": 0.6983442958,
242
  "ents_per_type": {
243
  "DATE": {
244
+ "p": 0.7714016933,
245
+ "r": 0.8126858276,
246
+ "f": 0.7915057915
247
  },
248
  "GPE": {
249
+ "p": 0.7518863737,
250
+ "r": 0.8279569892,
251
+ "f": 0.7880902535
252
  },
253
  "ORDINAL": {
254
+ "p": 0.8934911243,
255
+ "r": 0.7947368421,
256
+ "f": 0.8412256267
257
  },
258
  "FAC": {
259
+ "p": 0.4609375,
260
+ "r": 0.3172043011,
261
+ "f": 0.3757961783
 
 
 
 
 
262
  },
263
  "ORG": {
264
+ "p": 0.6854646545,
265
+ "r": 0.6567732116,
266
+ "f": 0.6708122814
267
+ },
268
+ "LOC": {
269
+ "p": 0.528,
270
+ "r": 0.3548387097,
271
+ "f": 0.424437299
272
  },
273
  "QUANTITY": {
274
+ "p": 0.7619047619,
275
+ "r": 0.5925925926,
276
+ "f": 0.6666666667
277
+ },
278
+ "PERSON": {
279
+ "p": 0.7750841751,
280
+ "r": 0.7416237113,
281
+ "f": 0.7579848535
282
  },
283
  "CARDINAL": {
284
+ "p": 0.606271777,
285
+ "r": 0.5262096774,
286
+ "f": 0.5634106854
287
  },
288
+ "TIME": {
289
+ "p": 0.7512195122,
290
+ "r": 0.7475728155,
291
+ "f": 0.7493917275
292
  },
293
  "NORP": {
294
+ "p": 0.6772151899,
295
+ "r": 0.4495798319,
296
+ "f": 0.5404040404
297
  },
298
  "WORK_OF_ART": {
299
+ "p": 0.6419753086,
300
+ "r": 0.3466666667,
301
+ "f": 0.4502164502
 
 
 
 
 
 
 
 
 
 
302
  },
303
  "MONEY": {
304
+ "p": 0.9565217391,
305
+ "r": 0.8148148148,
306
+ "f": 0.88
307
  },
308
  "PERCENT": {
309
+ "p": 0.8117647059,
310
+ "r": 0.8313253012,
311
+ "f": 0.8214285714
312
  },
313
  "EVENT": {
314
+ "p": 0.6037735849,
315
+ "r": 0.4705882353,
316
+ "f": 0.5289256198
317
+ },
318
+ "PRODUCT": {
319
+ "p": 0.2142857143,
320
+ "r": 0.0612244898,
321
+ "f": 0.0952380952
322
  },
323
  "LAW": {
324
  "p": 0.4814814815,
 
326
  "f": 0.2988505747
327
  },
328
  "LANGUAGE": {
329
+ "p": 0.5,
330
  "r": 0.7777777778,
331
+ "f": 0.6086956522
332
  }
333
  },
334
+ "speed": 7209.1977233502
335
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -51,7 +51,7 @@ nO = null
51
  @architectures = "spacy.MultiHashEmbed.v2"
52
  width = 96
53
  attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
54
- rows = [5000,2500,2500,2500]
55
  include_static_vectors = true
56
 
57
  [components.ner.model.tok2vec.encode]
@@ -89,8 +89,9 @@ overwrite = false
89
  scorer = {"@scorers":"spacy.senter_scorer.v1"}
90
 
91
  [components.senter.model]
92
- @architectures = "spacy.Tagger.v1"
93
  nO = null
 
94
 
95
  [components.senter.model.tok2vec]
96
  @architectures = "spacy.Tok2Vec.v2"
@@ -111,12 +112,14 @@ maxout_pieces = 2
111
 
112
  [components.tagger]
113
  factory = "tagger"
 
114
  overwrite = false
115
  scorer = {"@scorers":"spacy.tagger_scorer.v1"}
116
 
117
  [components.tagger.model]
118
- @architectures = "spacy.Tagger.v1"
119
  nO = null
 
120
 
121
  [components.tagger.model.tok2vec]
122
  @architectures = "spacy.Tok2VecListener.v1"
@@ -133,7 +136,7 @@ factory = "tok2vec"
133
  @architectures = "spacy.MultiHashEmbed.v2"
134
  width = ${components.tok2vec.model.encode:width}
135
  attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
136
- rows = [5000,2500,2500,2500]
137
  include_static_vectors = true
138
 
139
  [components.tok2vec.model.encode]
@@ -170,7 +173,7 @@ dropout = 0.1
170
  accumulate_gradient = 1
171
  patience = 5000
172
  max_epochs = 0
173
- max_steps = 0
174
  eval_frequency = 1000
175
  frozen_components = []
176
  before_to_disk = null
 
51
  @architectures = "spacy.MultiHashEmbed.v2"
52
  width = 96
53
  attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
54
+ rows = [5000,1000,2500,2500]
55
  include_static_vectors = true
56
 
57
  [components.ner.model.tok2vec.encode]
 
89
  scorer = {"@scorers":"spacy.senter_scorer.v1"}
90
 
91
  [components.senter.model]
92
+ @architectures = "spacy.Tagger.v2"
93
  nO = null
94
+ normalize = false
95
 
96
  [components.senter.model.tok2vec]
97
  @architectures = "spacy.Tok2Vec.v2"
 
112
 
113
  [components.tagger]
114
  factory = "tagger"
115
+ neg_prefix = "!"
116
  overwrite = false
117
  scorer = {"@scorers":"spacy.tagger_scorer.v1"}
118
 
119
  [components.tagger.model]
120
+ @architectures = "spacy.Tagger.v2"
121
  nO = null
122
+ normalize = false
123
 
124
  [components.tagger.model.tok2vec]
125
  @architectures = "spacy.Tok2VecListener.v1"
 
136
  @architectures = "spacy.MultiHashEmbed.v2"
137
  width = ${components.tok2vec.model.encode:width}
138
  attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
139
+ rows = [5000,1000,2500,2500]
140
  include_static_vectors = true
141
 
142
  [components.tok2vec.model.encode]
 
173
  accumulate_gradient = 1
174
  patience = 5000
175
  max_epochs = 0
176
+ max_steps = 100000
177
  eval_frequency = 1000
178
  frozen_components = []
179
  before_to_disk = null
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"zh",
3
  "name":"core_web_md",
4
- "version":"3.2.0",
5
  "description":"Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.",
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":300,
14
  "vectors":20000,
@@ -104,10 +104,6 @@
104
  "punct",
105
  "xcomp"
106
  ],
107
- "senter":[
108
- "I",
109
- "S"
110
- ],
111
  "attribute_ruler":[
112
 
113
  ],
@@ -155,212 +151,207 @@
155
  "token_p":0.9458325855,
156
  "token_r":0.9136060443,
157
  "token_f":0.9294400505,
158
- "tag_acc":0.9004973002,
159
- "sents_p":0.7859447831,
160
- "sents_r":0.7298152156,
161
- "sents_f":0.7568407423,
162
- "dep_uas":0.7076909586,
163
- "dep_las":0.6551856356,
164
  "dep_las_per_type":{
165
  "dep":{
166
- "p":0.4941927991,
167
- "r":0.3439426089,
168
- "f":0.4056002383
169
  },
170
  "case":{
171
- "p":0.815348957,
172
- "r":0.7677012609,
173
- "f":0.790808043
174
  },
175
  "nmod:tmod":{
176
- "p":0.7291941876,
177
  "r":0.7510204082,
178
- "f":0.7399463807
179
  },
180
  "nummod":{
181
- "p":0.8324715615,
182
- "r":0.5363091272,
183
- "f":0.652350081
184
  },
185
  "mark:clf":{
186
- "p":0.923958962,
187
- "r":0.5710555763,
188
- "f":0.7058552328
189
  },
190
  "auxpass":{
191
- "p":0.8864864865,
192
- "r":0.8864864865,
193
- "f":0.8864864865
194
  },
195
  "nsubj":{
196
- "p":0.7838943894,
197
- "r":0.7293944233,
198
- "f":0.7556630186
199
  },
200
  "acl":{
201
- "p":0.7085714286,
202
- "r":0.5501941209,
203
- "f":0.6194192944
204
  },
205
  "advmod":{
206
- "p":0.8221938776,
207
- "r":0.7306733167,
208
- "f":0.7737366463
209
  },
210
  "mark":{
211
- "p":0.7447306792,
212
- "r":0.6967572305,
213
- "f":0.7199456645
214
  },
215
  "xcomp":{
216
- "p":0.7822878229,
217
- "r":0.6905537459,
218
- "f":0.7335640138
219
  },
220
  "nmod:assmod":{
221
- "p":0.7571008815,
222
- "r":0.7217553688,
223
- "f":0.7390057361
224
  },
225
  "det":{
226
- "p":0.8367670365,
227
- "r":0.618629174,
228
- "f":0.7113506231
229
  },
230
  "amod":{
231
- "p":0.7567811935,
232
- "r":0.6575019639,
233
- "f":0.7036569987
234
  },
235
  "nmod:prep":{
236
- "p":0.6989096025,
237
- "r":0.6010284332,
238
- "f":0.6462839486
239
  },
240
  "root":{
241
- "p":0.7426623746,
242
- "r":0.6529049442,
243
- "f":0.694897236
244
  },
245
  "aux:prtmod":{
246
- "p":0.9058823529,
247
- "r":0.825,
248
- "f":0.8635514019
249
  },
250
  "compound:nn":{
251
- "p":0.7339595888,
252
- "r":0.700676819,
253
- "f":0.716932133
254
  },
255
  "dobj":{
256
- "p":0.802248996,
257
- "r":0.7397422604,
258
- "f":0.76972873
259
  },
260
  "ccomp":{
261
- "p":0.6483430799,
262
- "r":0.6465785381,
263
- "f":0.6474596068
264
  },
265
  "advmod:rcomp":{
266
- "p":0.8196202532,
267
- "r":0.7174515235,
268
- "f":0.765140325
269
  },
270
  "nmod:topic":{
271
- "p":0.3596059113,
272
- "r":0.237012987,
273
- "f":0.2857142857
274
  },
275
  "cop":{
276
- "p":0.7555739059,
277
- "r":0.5888030888,
278
- "f":0.6618444846
279
  },
280
  "discourse":{
281
- "p":0.5577797998,
282
- "r":0.5057755776,
283
- "f":0.5305062743
284
  },
285
  "neg":{
286
- "p":0.8365527489,
287
- "r":0.6694411415,
288
- "f":0.7437252312
289
  },
290
  "aux:modal":{
291
- "p":0.8626198083,
292
- "r":0.8376421923,
293
- "f":0.8499475341
294
  },
295
  "nmod":{
296
- "p":0.7152,
297
- "r":0.6065128901,
298
- "f":0.6563876652
299
  },
300
  "aux:ba":{
301
- "p":0.8444444444,
302
- "r":0.8085106383,
303
- "f":0.8260869565
304
  },
305
  "advmod:loc":{
306
- "p":0.6130268199,
307
- "r":0.4747774481,
308
- "f":0.5351170569
309
  },
310
  "aux:asp":{
311
- "p":0.9095435685,
312
- "r":0.8740031898,
313
- "f":0.8914192761
314
  },
315
  "conj":{
316
- "p":0.5032329577,
317
- "r":0.5149338374,
318
- "f":0.5090161637
319
  },
320
  "nsubjpass":{
321
- "p":0.8292682927,
322
- "r":0.68,
323
- "f":0.7472527473
324
  },
325
  "compound:vc":{
326
- "p":0.4486486486,
327
- "r":0.4300518135,
328
- "f":0.4391534392
329
  },
330
  "advcl:loc":{
331
- "p":0.5945945946,
332
  "r":0.4714285714,
333
- "f":0.5258964143
334
  },
335
  "cc":{
336
- "p":0.7013108614,
337
- "r":0.6645962733,
338
- "f":0.6824601367
339
  },
340
  "advmod:dvp":{
341
- "p":0.8045112782,
342
  "r":0.6645962733,
343
- "f":0.7278911565
344
  },
345
  "appos":{
346
- "p":0.8658536585,
347
- "r":0.816091954,
348
- "f":0.8402366864
349
- },
350
- "name":{
351
- "p":0.5625,
352
- "r":0.4666666667,
353
- "f":0.5101214575
354
- },
355
- "parataxis:prnmod":{
356
- "p":0.5,
357
- "r":0.1278195489,
358
- "f":0.2035928144
359
  },
360
  "nmod:poss":{
361
- "p":0.6352941176,
362
- "r":0.4,
363
- "f":0.4909090909
 
 
 
 
 
364
  },
365
  "nsubj:xsubj":{
366
  "p":0.0,
@@ -368,14 +359,19 @@
368
  "f":0.0
369
  },
370
  "nmod:range":{
371
- "p":0.7346153846,
372
- "r":0.6409395973,
373
- "f":0.6845878136
 
 
 
 
 
374
  },
375
  "amod:ordmod":{
376
- "p":0.6181818182,
377
- "r":0.53125,
378
- "f":0.5714285714
379
  },
380
  "erased":{
381
  "p":0.0,
@@ -383,94 +379,94 @@
383
  "f":0.0
384
  },
385
  "etc":{
386
- "p":0.9268292683,
387
- "r":0.9047619048,
388
- "f":0.9156626506
389
  }
390
  },
391
- "ents_p":0.7220589964,
392
- "ents_r":0.6751648352,
393
- "ents_f":0.6978249759,
394
  "ents_per_type":{
395
  "DATE":{
396
- "p":0.758780037,
397
- "r":0.8136769078,
398
- "f":0.7852702056
399
  },
400
  "GPE":{
401
- "p":0.7517889088,
402
- "r":0.8216031281,
403
- "f":0.7851471275
404
  },
405
  "ORDINAL":{
406
- "p":0.8720930233,
407
- "r":0.7894736842,
408
- "f":0.8287292818
409
  },
410
  "FAC":{
411
- "p":0.5076923077,
412
- "r":0.3548387097,
413
- "f":0.417721519
414
- },
415
- "PERSON":{
416
- "p":0.7917511832,
417
- "r":0.7545103093,
418
- "f":0.7726822831
419
  },
420
  "ORG":{
421
- "p":0.6896831844,
422
- "r":0.6461187215,
423
- "f":0.6671905697
 
 
 
 
 
424
  },
425
  "QUANTITY":{
426
- "p":0.7706422018,
427
- "r":0.6222222222,
428
- "f":0.6885245902
 
 
 
 
 
429
  },
430
  "CARDINAL":{
431
- "p":0.6181818182,
432
- "r":0.5141129032,
433
- "f":0.5613648872
434
  },
435
- "LOC":{
436
- "p":0.5247148289,
437
- "r":0.3709677419,
438
- "f":0.4346456693
439
  },
440
  "NORP":{
441
- "p":0.6646153846,
442
- "r":0.4537815126,
443
- "f":0.5393258427
444
  },
445
  "WORK_OF_ART":{
446
- "p":0.5733333333,
447
- "r":0.2866666667,
448
- "f":0.3822222222
449
- },
450
- "TIME":{
451
- "p":0.7209302326,
452
- "r":0.7524271845,
453
- "f":0.7363420428
454
- },
455
- "PRODUCT":{
456
- "p":0.2,
457
- "r":0.0612244898,
458
- "f":0.09375
459
  },
460
  "MONEY":{
461
- "p":0.9230769231,
462
- "r":0.8,
463
- "f":0.8571428571
464
  },
465
  "PERCENT":{
466
- "p":0.7613636364,
467
- "r":0.8072289157,
468
- "f":0.783625731
469
  },
470
  "EVENT":{
471
- "p":0.5688073394,
472
- "r":0.4558823529,
473
- "f":0.506122449
 
 
 
 
 
474
  },
475
  "LAW":{
476
  "p":0.4814814815,
@@ -478,12 +474,12 @@
478
  "f":0.2988505747
479
  },
480
  "LANGUAGE":{
481
- "p":0.6363636364,
482
  "r":0.7777777778,
483
- "f":0.7
484
  }
485
  },
486
- "speed":7391.1713592242
487
  },
488
  "sources":[
489
  {
 
1
  {
2
  "lang":"zh",
3
  "name":"core_web_md",
4
+ "version":"3.3.0",
5
  "description":"Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"MIT",
10
+ "spacy_version":">=3.3.0.dev0,<3.4.0",
11
+ "spacy_git_version":"849bef2de",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
 
104
  "punct",
105
  "xcomp"
106
  ],
 
 
 
 
107
  "attribute_ruler":[
108
 
109
  ],
 
151
  "token_p":0.9458325855,
152
  "token_r":0.9136060443,
153
  "token_f":0.9294400505,
154
+ "tag_acc":0.8993969506,
155
+ "sents_p":0.7818149275,
156
+ "sents_r":0.7271516564,
157
+ "sents_f":0.7534931861,
158
+ "dep_uas":0.7039979835,
159
+ "dep_las":0.6522146335,
160
  "dep_las_per_type":{
161
  "dep":{
162
+ "p":0.479214123,
163
+ "r":0.3401030615,
164
+ "f":0.3978488269
165
  },
166
  "case":{
167
+ "p":0.81099213,
168
+ "r":0.7621241513,
169
+ "f":0.7857991124
170
  },
171
  "nmod:tmod":{
172
+ "p":0.7311258278,
173
  "r":0.7510204082,
174
+ "f":0.7409395973
175
  },
176
  "nummod":{
177
+ "p":0.8237704918,
178
+ "r":0.5356429047,
179
+ "f":0.649172386
180
  },
181
  "mark:clf":{
182
+ "p":0.9305724726,
183
+ "r":0.5699365908,
184
+ "f":0.7069164932
185
  },
186
  "auxpass":{
187
+ "p":0.8548387097,
188
+ "r":0.8594594595,
189
+ "f":0.8571428571
190
  },
191
  "nsubj":{
192
+ "p":0.7813199842,
193
+ "r":0.7285345781,
194
+ "f":0.7540045767
195
  },
196
  "acl":{
197
+ "p":0.6691324815,
198
+ "r":0.5518580144,
199
+ "f":0.6048632219
200
  },
201
  "advmod":{
202
+ "p":0.8206363291,
203
+ "r":0.7338472002,
204
+ "f":0.7748189815
205
  },
206
  "mark":{
207
+ "p":0.7307514984,
208
+ "r":0.69456617,
209
+ "f":0.7121995057
210
  },
211
  "xcomp":{
212
+ "p":0.7686703097,
213
+ "r":0.6872964169,
214
+ "f":0.7257093723
215
  },
216
  "nmod:assmod":{
217
+ "p":0.761548471,
218
+ "r":0.7286025521,
219
+ "f":0.7447113091
220
  },
221
  "det":{
222
+ "p":0.8413848631,
223
+ "r":0.6121851201,
224
+ "f":0.7087148186
225
  },
226
  "amod":{
227
+ "p":0.7721057429,
228
+ "r":0.6653574234,
229
+ "f":0.7147679325
230
  },
231
  "nmod:prep":{
232
+ "p":0.6953619115,
233
+ "r":0.5986085904,
234
+ "f":0.6433680104
235
  },
236
  "root":{
237
+ "p":0.7341652486,
238
+ "r":0.6464125187,
239
+ "f":0.6875
240
  },
241
  "aux:prtmod":{
242
+ "p":0.9032258065,
243
+ "r":0.8,
244
+ "f":0.8484848485
245
  },
246
  "compound:nn":{
247
+ "p":0.7426056338,
248
+ "r":0.7137055838,
249
+ "f":0.7278688525
250
  },
251
  "dobj":{
252
+ "p":0.8030180107,
253
+ "r":0.7330765812,
254
+ "f":0.7664550101
255
  },
256
  "ccomp":{
257
+ "p":0.6494183714,
258
+ "r":0.6294712286,
259
+ "f":0.6392892399
260
  },
261
  "advmod:rcomp":{
262
+ "p":0.803125,
263
+ "r":0.7119113573,
264
+ "f":0.7547723935
265
  },
266
  "nmod:topic":{
267
+ "p":0.3718592965,
268
+ "r":0.2402597403,
269
+ "f":0.291913215
270
  },
271
  "cop":{
272
+ "p":0.7485806975,
273
+ "r":0.593951094,
274
+ "f":0.6623609616
275
  },
276
  "discourse":{
277
+ "p":0.5652173913,
278
+ "r":0.4933993399,
279
+ "f":0.5268722467
280
  },
281
  "neg":{
282
+ "p":0.8325859492,
283
+ "r":0.6623067776,
284
+ "f":0.7377483444
285
  },
286
  "aux:modal":{
287
+ "p":0.8624733475,
288
+ "r":0.8366080662,
289
+ "f":0.849343832
290
  },
291
  "nmod":{
292
+ "p":0.729468599,
293
+ "r":0.6146540027,
294
+ "f":0.6671575847
295
  },
296
  "aux:ba":{
297
+ "p":0.8287292818,
298
+ "r":0.7978723404,
299
+ "f":0.8130081301
300
  },
301
  "advmod:loc":{
302
+ "p":0.606741573,
303
+ "r":0.4807121662,
304
+ "f":0.5364238411
305
  },
306
  "aux:asp":{
307
+ "p":0.9072249589,
308
+ "r":0.8811802233,
309
+ "f":0.894012945
310
  },
311
  "conj":{
312
+ "p":0.4831861732,
313
+ "r":0.4862003781,
314
+ "f":0.4846885895
315
  },
316
  "nsubjpass":{
317
+ "p":0.7674418605,
318
+ "r":0.66,
319
+ "f":0.7096774194
320
  },
321
  "compound:vc":{
322
+ "p":0.4943181818,
323
+ "r":0.4507772021,
324
+ "f":0.4715447154
325
  },
326
  "advcl:loc":{
327
+ "p":0.511627907,
328
  "r":0.4714285714,
329
+ "f":0.4907063197
330
  },
331
  "cc":{
332
+ "p":0.7040913416,
333
+ "r":0.6566104703,
334
+ "f":0.6795224977
335
  },
336
  "advmod:dvp":{
337
+ "p":0.842519685,
338
  "r":0.6645962733,
339
+ "f":0.7430555556
340
  },
341
  "appos":{
342
+ "p":0.8796992481,
343
+ "r":0.8068965517,
344
+ "f":0.8417266187
 
 
 
 
 
 
 
 
 
 
345
  },
346
  "nmod:poss":{
347
+ "p":0.6904761905,
348
+ "r":0.4296296296,
349
+ "f":0.5296803653
350
+ },
351
+ "name":{
352
+ "p":0.6285714286,
353
+ "r":0.4888888889,
354
+ "f":0.55
355
  },
356
  "nsubj:xsubj":{
357
  "p":0.0,
 
359
  "f":0.0
360
  },
361
  "nmod:range":{
362
+ "p":0.7366412214,
363
+ "r":0.6476510067,
364
+ "f":0.6892857143
365
+ },
366
+ "parataxis:prnmod":{
367
+ "p":0.53125,
368
+ "r":0.1278195489,
369
+ "f":0.2060606061
370
  },
371
  "amod:ordmod":{
372
+ "p":0.6037735849,
373
+ "r":0.5,
374
+ "f":0.547008547
375
  },
376
  "erased":{
377
  "p":0.0,
 
379
  "f":0.0
380
  },
381
  "etc":{
382
+ "p":0.9277108434,
383
+ "r":0.9166666667,
384
+ "f":0.9221556886
385
  }
386
  },
387
+ "ents_p":0.7214151828,
388
+ "ents_r":0.6767032967,
389
+ "ents_f":0.6983442958,
390
  "ents_per_type":{
391
  "DATE":{
392
+ "p":0.7714016933,
393
+ "r":0.8126858276,
394
+ "f":0.7915057915
395
  },
396
  "GPE":{
397
+ "p":0.7518863737,
398
+ "r":0.8279569892,
399
+ "f":0.7880902535
400
  },
401
  "ORDINAL":{
402
+ "p":0.8934911243,
403
+ "r":0.7947368421,
404
+ "f":0.8412256267
405
  },
406
  "FAC":{
407
+ "p":0.4609375,
408
+ "r":0.3172043011,
409
+ "f":0.3757961783
 
 
 
 
 
410
  },
411
  "ORG":{
412
+ "p":0.6854646545,
413
+ "r":0.6567732116,
414
+ "f":0.6708122814
415
+ },
416
+ "LOC":{
417
+ "p":0.528,
418
+ "r":0.3548387097,
419
+ "f":0.424437299
420
  },
421
  "QUANTITY":{
422
+ "p":0.7619047619,
423
+ "r":0.5925925926,
424
+ "f":0.6666666667
425
+ },
426
+ "PERSON":{
427
+ "p":0.7750841751,
428
+ "r":0.7416237113,
429
+ "f":0.7579848535
430
  },
431
  "CARDINAL":{
432
+ "p":0.606271777,
433
+ "r":0.5262096774,
434
+ "f":0.5634106854
435
  },
436
+ "TIME":{
437
+ "p":0.7512195122,
438
+ "r":0.7475728155,
439
+ "f":0.7493917275
440
  },
441
  "NORP":{
442
+ "p":0.6772151899,
443
+ "r":0.4495798319,
444
+ "f":0.5404040404
445
  },
446
  "WORK_OF_ART":{
447
+ "p":0.6419753086,
448
+ "r":0.3466666667,
449
+ "f":0.4502164502
 
 
 
 
 
 
 
 
 
 
450
  },
451
  "MONEY":{
452
+ "p":0.9565217391,
453
+ "r":0.8148148148,
454
+ "f":0.88
455
  },
456
  "PERCENT":{
457
+ "p":0.8117647059,
458
+ "r":0.8313253012,
459
+ "f":0.8214285714
460
  },
461
  "EVENT":{
462
+ "p":0.6037735849,
463
+ "r":0.4705882353,
464
+ "f":0.5289256198
465
+ },
466
+ "PRODUCT":{
467
+ "p":0.2142857143,
468
+ "r":0.0612244898,
469
+ "f":0.0952380952
470
  },
471
  "LAW":{
472
  "p":0.4814814815,
 
474
  "f":0.2988505747
475
  },
476
  "LANGUAGE":{
477
+ "p":0.5,
478
  "r":0.7777777778,
479
+ "f":0.6086956522
480
  }
481
  },
482
+ "speed":7209.1977233502
483
  },
484
  "sources":[
485
  {
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e07704cf381c439dc5b3ca939d540cdb9fdbaf322430c94c3bb2b6157eb66c0d
3
- size 6956943
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5314160296d6340eb155b5e9f46ee350a19b3dbae04c59e70b5e58ac06861783
3
+ size 6380943
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:af450b5a78a5939ad7c7731017209ecb7db6b1d376e0072fbbd7b2e1b37dae93
3
  size 308728
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:133ddb06357a6c8d63008118357b3b8100b540df0fdeb020f22bcbe067e87c86
3
  size 308728
parser/moves CHANGED
@@ -1 +1 @@
1
- ��moves��{"0":{"":406716},"1":{"":267231},"2":{"advmod":56960,"nsubj":53520,"compound:nn":43919,"dep":40111,"punct":36035,"case":23986,"nmod:assmod":21599,"nmod:prep":20098,"amod":16922,"acl":11979,"conj":10687,"cop":7238,"det":7210,"nummod":6994,"cc":6235,"aux:modal":5566,"nmod:tmod":5335,"nmod":4915,"neg":4363,"xcomp":3881,"appos":2955,"nmod:topic":2410,"discourse":2163,"advmod:loc":1591,"aux:prtmod":1539,"aux:ba":1311,"auxpass":1220,"advmod:dvp":1142,"advcl:loc":1046,"name":1032,"compound:vc":830,"nmod:poss":560,"amod:ordmod":511,"dobj":406,"nsubjpass":263,"nsubj:xsubj||ccomp":62,"parataxis:prnmod":34,"nsubj:xsubj":32},"3":{"punct":74006,"dobj":45383,"conj":30040,"case":30024,"dep":18660,"ccomp":17216,"mark":16600,"mark:clf":11551,"aux:asp":7896,"discourse":3998,"advmod:rcomp":2387,"nmod:range":1885,"cc":1675,"nmod:prep":1595,"advmod":1116,"etc":941,"compound:vc":790,"parataxis:prnmod":693,"advmod:loc":522,"neg":69,"advcl:loc":39,"acl":39},"4":{"ROOT":34525}}�cfg��neg_key�
 
1
+ ��moves��{"0":{"":436297},"1":{"":282750},"2":{"advmod":61142,"nsubj":55539,"compound:nn":45994,"dep":43937,"punct":36396,"case":24751,"nmod:assmod":22308,"nmod:prep":21037,"amod":18609,"acl":12438,"conj":10993,"det":10371,"nummod":9922,"cop":9515,"cc":6289,"aux:modal":6003,"neg":5955,"nmod:tmod":5338,"nmod":5049,"xcomp":4333,"appos":2988,"nmod:topic":2532,"discourse":2283,"advmod:loc":1902,"aux:prtmod":1724,"aux:ba":1323,"auxpass":1240,"advmod:dvp":1193,"name":1117,"advcl:loc":1072,"compound:vc":834,"nmod:poss":657,"amod:ordmod":601,"dobj":441,"nsubjpass":276,"nsubj:xsubj||ccomp":64,"parataxis:prnmod":36,"nsubj:xsubj":32},"3":{"punct":74587,"dobj":46958,"conj":31352,"case":31222,"dep":20953,"mark:clf":18377,"ccomp":17748,"mark":16793,"aux:asp":8130,"discourse":4187,"advmod:rcomp":2519,"nmod:range":2021,"cc":1715,"nmod:prep":1690,"advmod":1162,"etc":943,"compound:vc":828,"parataxis:prnmod":724,"advmod:loc":571,"neg":70,"acl":43,"advcl:loc":42},"4":{"ROOT":36097}}�cfg��neg_key�
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:34739b32c9d0b5380fbee01ff5ed35d540e381d0a46886173895327884e4ee5e
3
- size 213211
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7fe184649e10a94fa13802dc861c959ddc83b38ee6f509fb2eae365be8120bb
3
+ size 213263
tagger/cfg CHANGED
@@ -37,5 +37,6 @@
37
  "VV",
38
  "X"
39
  ],
 
40
  "overwrite":false
41
  }
 
37
  "VV",
38
  "X"
39
  ],
40
+ "neg_prefix":"!",
41
  "overwrite":false
42
  }
tagger/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:feff2c434b6bc2373d6dc60bbdc595e50a73d93e29717afd52aa45478e33838f
3
- size 14345
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8fe2a9e6ff681944753e2d43c44dc3392a85641f1e023e810a5a77f3cb9458
3
+ size 14397
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bd834abdcb36589c68c219f892ec0fe34323d6d5a3f5d58f9567a7a82168ebb
3
- size 6811418
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14dedbd7b9257827229ff2175bd49415a94a3fc14b253c6a3ea0f5327274be8c
3
+ size 6235418
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9860bff8f8b50d10c77f43b97e932359ecb16be487fab650fd5e7ae3895101fc
3
- size 10513704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f13a0f49d0066b44d02ec1356ec80b6a93560a7be4138dc1c533945094dadf3
3
+ size 10514537
zh_core_web_md-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:911a182dd8f81287df1b8b48fe62e8468d76a337ab28bbe0c7f5321875cc9eb2
3
- size 78965830
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4b3cfdf7de2ed404d28b4c64bdebfcee0c7916d03a6bf11d152120594cc78d
3
+ size 77896549