adrianeboyd commited on
Commit
0413247
β€’
1 Parent(s): 3270d9e

Update spaCy pipeline

Browse files
.gitattributes CHANGED
@@ -19,3 +19,4 @@
19
  *strings.json filter=lfs diff=lfs merge=lfs -text
20
  vectors filter=lfs diff=lfs merge=lfs -text
21
  model filter=lfs diff=lfs merge=lfs -text
 
19
  *strings.json filter=lfs diff=lfs merge=lfs -text
20
  vectors filter=lfs diff=lfs merge=lfs -text
21
  model filter=lfs diff=lfs merge=lfs -text
22
+ tokenizer/pkuseg_processors filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -14,41 +14,41 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.6942860106
18
  - name: NER Recall
19
  type: recall
20
- value: 0.7357142857
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.7144000427
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9235746441
31
  - task:
32
  name: UNLABELED_DEPENDENCIES
33
  type: token-classification
34
  metrics:
35
  - name: Unlabeled Attachment Score (UAS)
36
  type: f_score
37
- value: 0.7606435996
38
  - task:
39
  name: LABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Labeled Attachment Score (LAS)
43
  type: f_score
44
- value: 0.7210395809
45
  - task:
46
  name: SENTS
47
  type: token-classification
48
  metrics:
49
  - name: Sentences F-Score
50
  type: f_score
51
- value: 0.6541033435
52
  ---
53
  ### Details: https://spacy.io/models/zh#zh_core_web_trf
54
 
@@ -57,8 +57,8 @@ Chinese transformer pipeline (bert-base-chinese). Components: transformer, tagge
57
  | Feature | Description |
58
  | --- | --- |
59
  | **Name** | `zh_core_web_trf` |
60
- | **Version** | `3.3.0` |
61
- | **spaCy** | `>=3.3.0.dev0,<3.4.0` |
62
  | **Default Pipeline** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `ner` |
63
  | **Components** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `ner` |
64
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -88,12 +88,12 @@ Chinese transformer pipeline (bert-base-chinese). Components: transformer, tagge
88
  | `TOKEN_P` | 94.58 |
89
  | `TOKEN_R` | 91.36 |
90
  | `TOKEN_F` | 92.94 |
91
- | `TAG_ACC` | 92.36 |
92
- | `SENTS_P` | 68.37 |
93
- | `SENTS_R` | 62.69 |
94
- | `SENTS_F` | 65.41 |
95
- | `DEP_UAS` | 76.06 |
96
- | `DEP_LAS` | 72.10 |
97
- | `ENTS_P` | 69.43 |
98
- | `ENTS_R` | 73.57 |
99
- | `ENTS_F` | 71.44 |
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.6807715613
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.7407692308
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.7095042627
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9237103231
31
  - task:
32
  name: UNLABELED_DEPENDENCIES
33
  type: token-classification
34
  metrics:
35
  - name: Unlabeled Attachment Score (UAS)
36
  type: f_score
37
+ value: 0.7641386414
38
  - task:
39
  name: LABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Labeled Attachment Score (LAS)
43
  type: f_score
44
+ value: 0.724427042
45
  - task:
46
  name: SENTS
47
  type: token-classification
48
  metrics:
49
  - name: Sentences F-Score
50
  type: f_score
51
+ value: 0.6377692376
52
  ---
53
  ### Details: https://spacy.io/models/zh#zh_core_web_trf
54
 
57
  | Feature | Description |
58
  | --- | --- |
59
  | **Name** | `zh_core_web_trf` |
60
+ | **Version** | `3.4.0` |
61
+ | **spaCy** | `>=3.4.0,<3.5.0` |
62
  | **Default Pipeline** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `ner` |
63
  | **Components** | `transformer`, `tagger`, `parser`, `attribute_ruler`, `ner` |
64
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
88
  | `TOKEN_P` | 94.58 |
89
  | `TOKEN_R` | 91.36 |
90
  | `TOKEN_F` | 92.94 |
91
+ | `TAG_ACC` | 92.37 |
92
+ | `SENTS_P` | 68.85 |
93
+ | `SENTS_R` | 59.40 |
94
+ | `SENTS_F` | 63.78 |
95
+ | `DEP_UAS` | 76.41 |
96
+ | `DEP_LAS` | 72.44 |
97
+ | `ENTS_P` | 68.08 |
98
+ | `ENTS_R` | 74.08 |
99
+ | `ENTS_F` | 70.95 |
accuracy.json CHANGED
@@ -3,212 +3,212 @@
3
  "token_p": 0.9458325855,
4
  "token_r": 0.9136060443,
5
  "token_f": 0.9294400505,
6
- "tag_acc": 0.9235746441,
7
- "sents_p": 0.6837327524,
8
- "sents_r": 0.6269352422,
9
- "sents_f": 0.6541033435,
10
- "dep_uas": 0.7606435996,
11
- "dep_las": 0.7210395809,
12
  "dep_las_per_type": {
13
  "dep": {
14
- "p": 0.5599170698,
15
- "r": 0.4093159543,
16
- "f": 0.4729161802
17
  },
18
  "case": {
19
- "p": 0.907999478,
20
- "r": 0.8435984481,
21
- "f": 0.8746150462
22
  },
23
  "nmod:tmod": {
24
- "p": 0.7767624021,
25
- "r": 0.8095238095,
26
- "f": 0.7928047968
27
  },
28
  "nummod": {
29
- "p": 0.888776542,
30
- "r": 0.5856095936,
31
- "f": 0.7060240964
32
  },
33
  "mark:clf": {
34
- "p": 0.9469463294,
35
- "r": 0.5725475569,
36
- "f": 0.7136215714
37
  },
38
  "auxpass": {
39
- "p": 0.9144385027,
40
  "r": 0.9243243243,
41
- "f": 0.9193548387
42
  },
43
  "nsubj": {
44
- "p": 0.8656656388,
45
- "r": 0.7931458052,
46
- "f": 0.8278205128
47
  },
48
  "acl": {
49
- "p": 0.8174404015,
50
- "r": 0.7226844149,
51
- "f": 0.7671474831
52
  },
53
  "advmod": {
54
- "p": 0.8674004864,
55
- "r": 0.7681931535,
56
- "f": 0.8147880974
57
  },
58
  "mark": {
59
- "p": 0.855269109,
60
- "r": 0.828659071,
61
- "f": 0.8417538393
62
  },
63
  "xcomp": {
64
- "p": 0.8389662028,
65
- "r": 0.6872964169,
66
- "f": 0.7555953447
67
  },
68
  "nmod:assmod": {
69
- "p": 0.8584937521,
70
- "r": 0.7911609088,
71
- "f": 0.8234531908
72
  },
73
  "det": {
74
- "p": 0.8737254902,
75
- "r": 0.6526069127,
76
- "f": 0.7471495641
77
  },
78
  "amod": {
79
- "p": 0.8251533742,
80
- "r": 0.7395915161,
81
- "f": 0.78003314
82
  },
83
  "nmod:prep": {
84
- "p": 0.8231932773,
85
- "r": 0.7407743497,
86
- "f": 0.7798121318
87
  },
88
  "root": {
89
- "p": 0.7630277672,
90
- "r": 0.6678874646,
91
- "f": 0.7122947182
92
  },
93
  "aux:prtmod": {
94
- "p": 0.932,
95
- "r": 0.8321428571,
96
- "f": 0.879245283
97
  },
98
  "compound:nn": {
99
- "p": 0.8085642317,
100
- "r": 0.7604060914,
101
- "f": 0.783746076
102
  },
103
  "dobj": {
104
- "p": 0.9031158715,
105
- "r": 0.8243223226,
106
- "f": 0.861922094
107
  },
108
  "ccomp": {
109
- "p": 0.769519833,
110
- "r": 0.716562986,
111
- "f": 0.7420978458
112
  },
113
  "advmod:rcomp": {
114
- "p": 0.8643533123,
115
- "r": 0.7590027701,
116
- "f": 0.808259587
117
  },
118
  "nmod:topic": {
119
- "p": 0.4703703704,
120
- "r": 0.4123376623,
121
- "f": 0.4394463668
122
  },
123
  "cop": {
124
- "p": 0.8237738986,
125
- "r": 0.6377091377,
126
- "f": 0.7188973522
127
  },
128
  "discourse": {
129
- "p": 0.5715539947,
130
- "r": 0.5371287129,
131
- "f": 0.5538068907
132
  },
133
  "neg": {
134
- "p": 0.8788819876,
135
- "r": 0.6730083234,
136
- "f": 0.7622895623
137
  },
138
  "aux:modal": {
139
- "p": 0.9065628476,
140
- "r": 0.8428128232,
141
- "f": 0.8735262594
142
  },
143
  "nmod": {
144
- "p": 0.7727272727,
145
- "r": 0.7611940299,
146
- "f": 0.7669172932
147
  },
148
  "aux:ba": {
149
- "p": 0.9333333333,
150
- "r": 0.8936170213,
151
- "f": 0.9130434783
152
  },
153
  "advmod:loc": {
154
- "p": 0.7860082305,
155
- "r": 0.5667655786,
156
- "f": 0.6586206897
157
  },
158
  "aux:asp": {
159
- "p": 0.9312714777,
160
- "r": 0.8644338118,
161
- "f": 0.8966087676
162
  },
163
  "conj": {
164
- "p": 0.5976989815,
165
- "r": 0.5990548204,
166
- "f": 0.5983761329
167
  },
168
  "nsubjpass": {
169
- "p": 0.8409090909,
170
- "r": 0.74,
171
- "f": 0.7872340426
172
  },
173
  "compound:vc": {
174
- "p": 0.5,
175
- "r": 0.5544041451,
176
- "f": 0.5257985258
177
  },
178
  "advcl:loc": {
179
- "p": 0.7317073171,
180
- "r": 0.6428571429,
181
- "f": 0.6844106464
182
  },
183
  "cc": {
184
- "p": 0.8057692308,
185
- "r": 0.743566992,
186
- "f": 0.7734194739
187
  },
188
  "advmod:dvp": {
189
- "p": 0.8863636364,
190
- "r": 0.7267080745,
191
- "f": 0.7986348123
192
  },
193
  "amod:ordmod": {
194
- "p": 0.671641791,
195
  "r": 0.703125,
196
- "f": 0.6870229008
197
  },
198
  "appos": {
199
- "p": 0.9394673123,
200
  "r": 0.891954023,
201
- "f": 0.9150943396
202
  },
203
  "nmod:poss": {
204
- "p": 0.7981651376,
205
- "r": 0.6444444444,
206
- "f": 0.7131147541
207
  },
208
  "name": {
209
- "p": 0.5954198473,
210
- "r": 0.5777777778,
211
- "f": 0.5864661654
212
  },
213
  "nsubj:xsubj": {
214
  "p": 0.0,
@@ -216,14 +216,14 @@
216
  "f": 0.0
217
  },
218
  "nmod:range": {
219
- "p": 0.82,
220
- "r": 0.6879194631,
221
- "f": 0.7481751825
222
  },
223
  "parataxis:prnmod": {
224
- "p": 0.3333333333,
225
- "r": 0.1729323308,
226
- "f": 0.2277227723
227
  },
228
  "erased": {
229
  "p": 0.0,
@@ -231,105 +231,105 @@
231
  "f": 0.0
232
  },
233
  "etc": {
234
- "p": 0.8555555556,
235
- "r": 0.9166666667,
236
- "f": 0.8850574713
237
  }
238
  },
239
- "ents_p": 0.6942860106,
240
- "ents_r": 0.7357142857,
241
- "ents_f": 0.7144000427,
242
  "ents_per_type": {
243
  "DATE": {
244
- "p": 0.7094017094,
245
- "r": 0.8225966303,
246
- "f": 0.7618173474
247
  },
248
  "GPE": {
249
- "p": 0.8088372093,
250
- "r": 0.8499511241,
251
- "f": 0.828884652
252
- },
253
- "CARDINAL": {
254
- "p": 0.5852631579,
255
- "r": 0.560483871,
256
- "f": 0.5726055613
257
  },
258
  "ORDINAL": {
259
- "p": 0.8703703704,
260
- "r": 0.7421052632,
261
- "f": 0.8011363636
262
  },
263
  "FAC": {
264
- "p": 0.4449541284,
265
- "r": 0.5215053763,
266
- "f": 0.4801980198
267
  },
268
  "ORG": {
269
- "p": 0.749412686,
270
- "r": 0.7283105023,
271
- "f": 0.7387109224
272
  },
273
  "LOC": {
274
- "p": 0.187,
275
- "r": 0.502688172,
276
- "f": 0.2725947522
 
 
 
 
 
277
  },
278
  "QUANTITY": {
279
- "p": 0.6564885496,
280
- "r": 0.637037037,
281
- "f": 0.6466165414
282
  },
283
  "PERSON": {
284
- "p": 0.8925081433,
285
- "r": 0.8827319588,
286
- "f": 0.8875931325
287
  },
288
- "NORP": {
289
- "p": 0.7124010554,
290
- "r": 0.5672268908,
291
- "f": 0.6315789474
292
  },
293
  "TIME": {
294
- "p": 0.7323943662,
295
- "r": 0.7572815534,
296
- "f": 0.7446300716
297
  },
298
  "WORK_OF_ART": {
299
- "p": 0.402173913,
300
- "r": 0.2466666667,
301
- "f": 0.305785124
302
  },
303
  "MONEY": {
304
- "p": 0.8549618321,
305
- "r": 0.8296296296,
306
- "f": 0.8421052632
307
  },
308
  "EVENT": {
309
- "p": 0.5966386555,
310
- "r": 0.5220588235,
311
- "f": 0.5568627451
312
- },
313
- "PERCENT": {
314
- "p": 0.8414634146,
315
- "r": 0.8313253012,
316
- "f": 0.8363636364
317
  },
318
  "PRODUCT": {
319
- "p": 1.0,
320
- "r": 0.0612244898,
321
- "f": 0.1153846154
 
 
 
 
 
322
  },
323
  "LAW": {
324
- "p": 0.3,
325
- "r": 0.1,
326
- "f": 0.15
327
  },
328
  "LANGUAGE": {
329
- "p": 0.7272727273,
330
- "r": 0.8888888889,
331
- "f": 0.8
332
  }
333
  },
334
- "speed": 2802.8382367834
335
  }
3
  "token_p": 0.9458325855,
4
  "token_r": 0.9136060443,
5
  "token_f": 0.9294400505,
6
+ "tag_acc": 0.9237103231,
7
+ "sents_p": 0.6885372443,
8
+ "sents_r": 0.5939736974,
9
+ "sents_f": 0.6377692376,
10
+ "dep_uas": 0.7641386414,
11
+ "dep_las": 0.724427042,
12
  "dep_las_per_type": {
13
  "dep": {
14
+ "p": 0.556125806,
15
+ "r": 0.4269980802,
16
+ "f": 0.4830818473
17
  },
18
  "case": {
19
+ "p": 0.9095206829,
20
+ "r": 0.8397187197,
21
+ "f": 0.8732270062
22
  },
23
  "nmod:tmod": {
24
+ "p": 0.801082544,
25
+ "r": 0.8054421769,
26
+ "f": 0.803256445
27
  },
28
  "nummod": {
29
+ "p": 0.8936170213,
30
+ "r": 0.5876082612,
31
+ "f": 0.7090032154
32
  },
33
  "mark:clf": {
34
+ "p": 0.9504950495,
35
+ "r": 0.572920552,
36
+ "f": 0.7149173842
37
  },
38
  "auxpass": {
39
+ "p": 0.9293478261,
40
  "r": 0.9243243243,
41
+ "f": 0.9268292683
42
  },
43
  "nsubj": {
44
+ "p": 0.8697112156,
45
+ "r": 0.7953568358,
46
+ "f": 0.8308738612
47
  },
48
  "acl": {
49
+ "p": 0.8118811881,
50
+ "r": 0.7276760954,
51
+ "f": 0.7674758701
52
  },
53
  "advmod": {
54
+ "p": 0.8822219311,
55
+ "r": 0.7633189753,
56
+ "f": 0.8184746278
57
  },
58
  "mark": {
59
+ "p": 0.8395604396,
60
+ "r": 0.8369851008,
61
+ "f": 0.8382707922
62
  },
63
  "xcomp": {
64
+ "p": 0.8200757576,
65
+ "r": 0.7052117264,
66
+ "f": 0.7583187391
67
  },
68
  "nmod:assmod": {
69
+ "p": 0.8556113903,
70
+ "r": 0.7948957361,
71
+ "f": 0.8241368183
72
  },
73
  "det": {
74
+ "p": 0.8923076923,
75
+ "r": 0.6455770357,
76
+ "f": 0.7491502379
77
  },
78
  "amod": {
79
+ "p": 0.8492438563,
80
+ "r": 0.7058130401,
81
+ "f": 0.7709137709
82
  },
83
  "nmod:prep": {
84
+ "p": 0.8267821452,
85
+ "r": 0.7507562008,
86
+ "f": 0.7869372226
87
  },
88
  "root": {
89
+ "p": 0.7861788618,
90
+ "r": 0.643915432,
91
+ "f": 0.7079710808
92
  },
93
  "aux:prtmod": {
94
+ "p": 0.9291338583,
95
+ "r": 0.8428571429,
96
+ "f": 0.8838951311
97
  },
98
  "compound:nn": {
99
+ "p": 0.8028863076,
100
+ "r": 0.7719120135,
101
+ "f": 0.787094548
102
  },
103
  "dobj": {
104
+ "p": 0.9105064743,
105
+ "r": 0.8228410606,
106
+ "f": 0.8644568939
107
  },
108
  "ccomp": {
109
+ "p": 0.783817952,
110
+ "r": 0.7231726283,
111
+ "f": 0.7522750253
112
  },
113
  "advmod:rcomp": {
114
+ "p": 0.8445747801,
115
+ "r": 0.7977839335,
116
+ "f": 0.8205128205
117
  },
118
  "nmod:topic": {
119
+ "p": 0.4741641337,
120
+ "r": 0.5064935065,
121
+ "f": 0.4897959184
122
  },
123
  "cop": {
124
+ "p": 0.8486672399,
125
+ "r": 0.6351351351,
126
+ "f": 0.7265366213
127
  },
128
  "discourse": {
129
+ "p": 0.5922939068,
130
+ "r": 0.545379538,
131
+ "f": 0.5678694158
132
  },
133
  "neg": {
134
+ "p": 0.8825347759,
135
+ "r": 0.6789536266,
136
+ "f": 0.7674731183
137
  },
138
  "aux:modal": {
139
+ "p": 0.8969631236,
140
+ "r": 0.8552223371,
141
+ "f": 0.8755955532
142
  },
143
  "nmod": {
144
+ "p": 0.8,
145
+ "r": 0.7598371777,
146
+ "f": 0.779401531
147
  },
148
  "aux:ba": {
149
+ "p": 0.9162011173,
150
+ "r": 0.8723404255,
151
+ "f": 0.89373297
152
  },
153
  "advmod:loc": {
154
+ "p": 0.792,
155
+ "r": 0.587537092,
156
+ "f": 0.6746166951
157
  },
158
  "aux:asp": {
159
+ "p": 0.9298986486,
160
+ "r": 0.8779904306,
161
+ "f": 0.9031993437
162
  },
163
  "conj": {
164
+ "p": 0.615168012,
165
+ "r": 0.6194706994,
166
+ "f": 0.6173118583
167
  },
168
  "nsubjpass": {
169
+ "p": 0.8723404255,
170
+ "r": 0.82,
171
+ "f": 0.8453608247
172
  },
173
  "compound:vc": {
174
+ "p": 0.5339805825,
175
+ "r": 0.5699481865,
176
+ "f": 0.5513784461
177
  },
178
  "advcl:loc": {
179
+ "p": 0.6567164179,
180
+ "r": 0.6285714286,
181
+ "f": 0.6423357664
182
  },
183
  "cc": {
184
+ "p": 0.7996306556,
185
+ "r": 0.7684117125,
186
+ "f": 0.7837104072
187
  },
188
  "advmod:dvp": {
189
+ "p": 0.8518518519,
190
+ "r": 0.7142857143,
191
+ "f": 0.777027027
192
  },
193
  "amod:ordmod": {
194
+ "p": 0.703125,
195
  "r": 0.703125,
196
+ "f": 0.703125
197
  },
198
  "appos": {
199
+ "p": 0.9509803922,
200
  "r": 0.891954023,
201
+ "f": 0.9205219454
202
  },
203
  "nmod:poss": {
204
+ "p": 0.8230088496,
205
+ "r": 0.6888888889,
206
+ "f": 0.75
207
  },
208
  "name": {
209
+ "p": 0.6513761468,
210
+ "r": 0.5259259259,
211
+ "f": 0.5819672131
212
  },
213
  "nsubj:xsubj": {
214
  "p": 0.0,
216
  "f": 0.0
217
  },
218
  "nmod:range": {
219
+ "p": 0.8264150943,
220
+ "r": 0.7348993289,
221
+ "f": 0.7779751332
222
  },
223
  "parataxis:prnmod": {
224
+ "p": 0.2475247525,
225
+ "r": 0.1879699248,
226
+ "f": 0.2136752137
227
  },
228
  "erased": {
229
  "p": 0.0,
231
  "f": 0.0
232
  },
233
  "etc": {
234
+ "p": 0.8965517241,
235
+ "r": 0.9285714286,
236
+ "f": 0.9122807018
237
  }
238
  },
239
+ "ents_p": 0.6807715613,
240
+ "ents_r": 0.7407692308,
241
+ "ents_f": 0.7095042627,
242
  "ents_per_type": {
243
  "DATE": {
244
+ "p": 0.7026116259,
245
+ "r": 0.8265609514,
246
+ "f": 0.7595628415
247
  },
248
  "GPE": {
249
+ "p": 0.8069756331,
250
+ "r": 0.8255131965,
251
+ "f": 0.816139164
 
 
 
 
 
252
  },
253
  "ORDINAL": {
254
+ "p": 0.8514285714,
255
+ "r": 0.7842105263,
256
+ "f": 0.8164383562
257
  },
258
  "FAC": {
259
+ "p": 0.4751381215,
260
+ "r": 0.4623655914,
261
+ "f": 0.4686648501
262
  },
263
  "ORG": {
264
+ "p": 0.7506033789,
265
+ "r": 0.7100456621,
266
+ "f": 0.7297614392
267
  },
268
  "LOC": {
269
+ "p": 0.1955867603,
270
+ "r": 0.5241935484,
271
+ "f": 0.2848794741
272
+ },
273
+ "NORP": {
274
+ "p": 0.6170212766,
275
+ "r": 0.6092436975,
276
+ "f": 0.6131078224
277
  },
278
  "QUANTITY": {
279
+ "p": 0.615942029,
280
+ "r": 0.6296296296,
281
+ "f": 0.6227106227
282
  },
283
  "PERSON": {
284
+ "p": 0.8742783836,
285
+ "r": 0.8782216495,
286
+ "f": 0.8762455802
287
  },
288
+ "CARDINAL": {
289
+ "p": 0.560111836,
290
+ "r": 0.6058467742,
291
+ "f": 0.5820823245
292
  },
293
  "TIME": {
294
+ "p": 0.7314814815,
295
+ "r": 0.7669902913,
296
+ "f": 0.7488151659
297
  },
298
  "WORK_OF_ART": {
299
+ "p": 0.4108527132,
300
+ "r": 0.3533333333,
301
+ "f": 0.3799283154
302
  },
303
  "MONEY": {
304
+ "p": 0.873015873,
305
+ "r": 0.8148148148,
306
+ "f": 0.8429118774
307
  },
308
  "EVENT": {
309
+ "p": 0.5945945946,
310
+ "r": 0.6470588235,
311
+ "f": 0.6197183099
 
 
 
 
 
312
  },
313
  "PRODUCT": {
314
+ "p": 0.375,
315
+ "r": 0.1836734694,
316
+ "f": 0.2465753425
317
+ },
318
+ "PERCENT": {
319
+ "p": 0.843373494,
320
+ "r": 0.843373494,
321
+ "f": 0.843373494
322
  },
323
  "LAW": {
324
+ "p": 0.3958333333,
325
+ "r": 0.3166666667,
326
+ "f": 0.3518518519
327
  },
328
  "LANGUAGE": {
329
+ "p": 0.75,
330
+ "r": 1.0,
331
+ "f": 0.8571428571
332
  }
333
  },
334
+ "speed": 4551.3152436145
335
  }
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"zh",
3
  "name":"core_web_trf",
4
- "version":"3.3.0",
5
  "description":"Chinese transformer pipeline (bert-base-chinese). Components: transformer, tagger, parser, 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":0,
14
  "vectors":0,
@@ -150,212 +150,212 @@
150
  "token_p":0.9458325855,
151
  "token_r":0.9136060443,
152
  "token_f":0.9294400505,
153
- "tag_acc":0.9235746441,
154
- "sents_p":0.6837327524,
155
- "sents_r":0.6269352422,
156
- "sents_f":0.6541033435,
157
- "dep_uas":0.7606435996,
158
- "dep_las":0.7210395809,
159
  "dep_las_per_type":{
160
  "dep":{
161
- "p":0.5599170698,
162
- "r":0.4093159543,
163
- "f":0.4729161802
164
  },
165
  "case":{
166
- "p":0.907999478,
167
- "r":0.8435984481,
168
- "f":0.8746150462
169
  },
170
  "nmod:tmod":{
171
- "p":0.7767624021,
172
- "r":0.8095238095,
173
- "f":0.7928047968
174
  },
175
  "nummod":{
176
- "p":0.888776542,
177
- "r":0.5856095936,
178
- "f":0.7060240964
179
  },
180
  "mark:clf":{
181
- "p":0.9469463294,
182
- "r":0.5725475569,
183
- "f":0.7136215714
184
  },
185
  "auxpass":{
186
- "p":0.9144385027,
187
  "r":0.9243243243,
188
- "f":0.9193548387
189
  },
190
  "nsubj":{
191
- "p":0.8656656388,
192
- "r":0.7931458052,
193
- "f":0.8278205128
194
  },
195
  "acl":{
196
- "p":0.8174404015,
197
- "r":0.7226844149,
198
- "f":0.7671474831
199
  },
200
  "advmod":{
201
- "p":0.8674004864,
202
- "r":0.7681931535,
203
- "f":0.8147880974
204
  },
205
  "mark":{
206
- "p":0.855269109,
207
- "r":0.828659071,
208
- "f":0.8417538393
209
  },
210
  "xcomp":{
211
- "p":0.8389662028,
212
- "r":0.6872964169,
213
- "f":0.7555953447
214
  },
215
  "nmod:assmod":{
216
- "p":0.8584937521,
217
- "r":0.7911609088,
218
- "f":0.8234531908
219
  },
220
  "det":{
221
- "p":0.8737254902,
222
- "r":0.6526069127,
223
- "f":0.7471495641
224
  },
225
  "amod":{
226
- "p":0.8251533742,
227
- "r":0.7395915161,
228
- "f":0.78003314
229
  },
230
  "nmod:prep":{
231
- "p":0.8231932773,
232
- "r":0.7407743497,
233
- "f":0.7798121318
234
  },
235
  "root":{
236
- "p":0.7630277672,
237
- "r":0.6678874646,
238
- "f":0.7122947182
239
  },
240
  "aux:prtmod":{
241
- "p":0.932,
242
- "r":0.8321428571,
243
- "f":0.879245283
244
  },
245
  "compound:nn":{
246
- "p":0.8085642317,
247
- "r":0.7604060914,
248
- "f":0.783746076
249
  },
250
  "dobj":{
251
- "p":0.9031158715,
252
- "r":0.8243223226,
253
- "f":0.861922094
254
  },
255
  "ccomp":{
256
- "p":0.769519833,
257
- "r":0.716562986,
258
- "f":0.7420978458
259
  },
260
  "advmod:rcomp":{
261
- "p":0.8643533123,
262
- "r":0.7590027701,
263
- "f":0.808259587
264
  },
265
  "nmod:topic":{
266
- "p":0.4703703704,
267
- "r":0.4123376623,
268
- "f":0.4394463668
269
  },
270
  "cop":{
271
- "p":0.8237738986,
272
- "r":0.6377091377,
273
- "f":0.7188973522
274
  },
275
  "discourse":{
276
- "p":0.5715539947,
277
- "r":0.5371287129,
278
- "f":0.5538068907
279
  },
280
  "neg":{
281
- "p":0.8788819876,
282
- "r":0.6730083234,
283
- "f":0.7622895623
284
  },
285
  "aux:modal":{
286
- "p":0.9065628476,
287
- "r":0.8428128232,
288
- "f":0.8735262594
289
  },
290
  "nmod":{
291
- "p":0.7727272727,
292
- "r":0.7611940299,
293
- "f":0.7669172932
294
  },
295
  "aux:ba":{
296
- "p":0.9333333333,
297
- "r":0.8936170213,
298
- "f":0.9130434783
299
  },
300
  "advmod:loc":{
301
- "p":0.7860082305,
302
- "r":0.5667655786,
303
- "f":0.6586206897
304
  },
305
  "aux:asp":{
306
- "p":0.9312714777,
307
- "r":0.8644338118,
308
- "f":0.8966087676
309
  },
310
  "conj":{
311
- "p":0.5976989815,
312
- "r":0.5990548204,
313
- "f":0.5983761329
314
  },
315
  "nsubjpass":{
316
- "p":0.8409090909,
317
- "r":0.74,
318
- "f":0.7872340426
319
  },
320
  "compound:vc":{
321
- "p":0.5,
322
- "r":0.5544041451,
323
- "f":0.5257985258
324
  },
325
  "advcl:loc":{
326
- "p":0.7317073171,
327
- "r":0.6428571429,
328
- "f":0.6844106464
329
  },
330
  "cc":{
331
- "p":0.8057692308,
332
- "r":0.743566992,
333
- "f":0.7734194739
334
  },
335
  "advmod:dvp":{
336
- "p":0.8863636364,
337
- "r":0.7267080745,
338
- "f":0.7986348123
339
  },
340
  "amod:ordmod":{
341
- "p":0.671641791,
342
  "r":0.703125,
343
- "f":0.6870229008
344
  },
345
  "appos":{
346
- "p":0.9394673123,
347
  "r":0.891954023,
348
- "f":0.9150943396
349
  },
350
  "nmod:poss":{
351
- "p":0.7981651376,
352
- "r":0.6444444444,
353
- "f":0.7131147541
354
  },
355
  "name":{
356
- "p":0.5954198473,
357
- "r":0.5777777778,
358
- "f":0.5864661654
359
  },
360
  "nsubj:xsubj":{
361
  "p":0.0,
@@ -363,14 +363,14 @@
363
  "f":0.0
364
  },
365
  "nmod:range":{
366
- "p":0.82,
367
- "r":0.6879194631,
368
- "f":0.7481751825
369
  },
370
  "parataxis:prnmod":{
371
- "p":0.3333333333,
372
- "r":0.1729323308,
373
- "f":0.2277227723
374
  },
375
  "erased":{
376
  "p":0.0,
@@ -378,107 +378,107 @@
378
  "f":0.0
379
  },
380
  "etc":{
381
- "p":0.8555555556,
382
- "r":0.9166666667,
383
- "f":0.8850574713
384
  }
385
  },
386
- "ents_p":0.6942860106,
387
- "ents_r":0.7357142857,
388
- "ents_f":0.7144000427,
389
  "ents_per_type":{
390
  "DATE":{
391
- "p":0.7094017094,
392
- "r":0.8225966303,
393
- "f":0.7618173474
394
  },
395
  "GPE":{
396
- "p":0.8088372093,
397
- "r":0.8499511241,
398
- "f":0.828884652
399
- },
400
- "CARDINAL":{
401
- "p":0.5852631579,
402
- "r":0.560483871,
403
- "f":0.5726055613
404
  },
405
  "ORDINAL":{
406
- "p":0.8703703704,
407
- "r":0.7421052632,
408
- "f":0.8011363636
409
  },
410
  "FAC":{
411
- "p":0.4449541284,
412
- "r":0.5215053763,
413
- "f":0.4801980198
414
  },
415
  "ORG":{
416
- "p":0.749412686,
417
- "r":0.7283105023,
418
- "f":0.7387109224
419
  },
420
  "LOC":{
421
- "p":0.187,
422
- "r":0.502688172,
423
- "f":0.2725947522
 
 
 
 
 
424
  },
425
  "QUANTITY":{
426
- "p":0.6564885496,
427
- "r":0.637037037,
428
- "f":0.6466165414
429
  },
430
  "PERSON":{
431
- "p":0.8925081433,
432
- "r":0.8827319588,
433
- "f":0.8875931325
434
  },
435
- "NORP":{
436
- "p":0.7124010554,
437
- "r":0.5672268908,
438
- "f":0.6315789474
439
  },
440
  "TIME":{
441
- "p":0.7323943662,
442
- "r":0.7572815534,
443
- "f":0.7446300716
444
  },
445
  "WORK_OF_ART":{
446
- "p":0.402173913,
447
- "r":0.2466666667,
448
- "f":0.305785124
449
  },
450
  "MONEY":{
451
- "p":0.8549618321,
452
- "r":0.8296296296,
453
- "f":0.8421052632
454
  },
455
  "EVENT":{
456
- "p":0.5966386555,
457
- "r":0.5220588235,
458
- "f":0.5568627451
459
- },
460
- "PERCENT":{
461
- "p":0.8414634146,
462
- "r":0.8313253012,
463
- "f":0.8363636364
464
  },
465
  "PRODUCT":{
466
- "p":1.0,
467
- "r":0.0612244898,
468
- "f":0.1153846154
 
 
 
 
 
469
  },
470
  "LAW":{
471
- "p":0.3,
472
- "r":0.1,
473
- "f":0.15
474
  },
475
  "LANGUAGE":{
476
- "p":0.7272727273,
477
- "r":0.8888888889,
478
- "f":0.8
479
  }
480
  },
481
- "speed":2802.8382367834
482
  },
483
  "sources":[
484
  {
1
  {
2
  "lang":"zh",
3
  "name":"core_web_trf",
4
+ "version":"3.4.0",
5
  "description":"Chinese transformer pipeline (bert-base-chinese). Components: transformer, tagger, parser, ner, attribute_ruler.",
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":0,
14
  "vectors":0,
150
  "token_p":0.9458325855,
151
  "token_r":0.9136060443,
152
  "token_f":0.9294400505,
153
+ "tag_acc":0.9237103231,
154
+ "sents_p":0.6885372443,
155
+ "sents_r":0.5939736974,
156
+ "sents_f":0.6377692376,
157
+ "dep_uas":0.7641386414,
158
+ "dep_las":0.724427042,
159
  "dep_las_per_type":{
160
  "dep":{
161
+ "p":0.556125806,
162
+ "r":0.4269980802,
163
+ "f":0.4830818473
164
  },
165
  "case":{
166
+ "p":0.9095206829,
167
+ "r":0.8397187197,
168
+ "f":0.8732270062
169
  },
170
  "nmod:tmod":{
171
+ "p":0.801082544,
172
+ "r":0.8054421769,
173
+ "f":0.803256445
174
  },
175
  "nummod":{
176
+ "p":0.8936170213,
177
+ "r":0.5876082612,
178
+ "f":0.7090032154
179
  },
180
  "mark:clf":{
181
+ "p":0.9504950495,
182
+ "r":0.572920552,
183
+ "f":0.7149173842
184
  },
185
  "auxpass":{
186
+ "p":0.9293478261,
187
  "r":0.9243243243,
188
+ "f":0.9268292683
189
  },
190
  "nsubj":{
191
+ "p":0.8697112156,
192
+ "r":0.7953568358,
193
+ "f":0.8308738612
194
  },
195
  "acl":{
196
+ "p":0.8118811881,
197
+ "r":0.7276760954,
198
+ "f":0.7674758701
199
  },
200
  "advmod":{
201
+ "p":0.8822219311,
202
+ "r":0.7633189753,
203
+ "f":0.8184746278
204
  },
205
  "mark":{
206
+ "p":0.8395604396,
207
+ "r":0.8369851008,
208
+ "f":0.8382707922
209
  },
210
  "xcomp":{
211
+ "p":0.8200757576,
212
+ "r":0.7052117264,
213
+ "f":0.7583187391
214
  },
215
  "nmod:assmod":{
216
+ "p":0.8556113903,
217
+ "r":0.7948957361,
218
+ "f":0.8241368183
219
  },
220
  "det":{
221
+ "p":0.8923076923,
222
+ "r":0.6455770357,
223
+ "f":0.7491502379
224
  },
225
  "amod":{
226
+ "p":0.8492438563,
227
+ "r":0.7058130401,
228
+ "f":0.7709137709
229
  },
230
  "nmod:prep":{
231
+ "p":0.8267821452,
232
+ "r":0.7507562008,
233
+ "f":0.7869372226
234
  },
235
  "root":{
236
+ "p":0.7861788618,
237
+ "r":0.643915432,
238
+ "f":0.7079710808
239
  },
240
  "aux:prtmod":{
241
+ "p":0.9291338583,
242
+ "r":0.8428571429,
243
+ "f":0.8838951311
244
  },
245
  "compound:nn":{
246
+ "p":0.8028863076,
247
+ "r":0.7719120135,
248
+ "f":0.787094548
249
  },
250
  "dobj":{
251
+ "p":0.9105064743,
252
+ "r":0.8228410606,
253
+ "f":0.8644568939
254
  },
255
  "ccomp":{
256
+ "p":0.783817952,
257
+ "r":0.7231726283,
258
+ "f":0.7522750253
259
  },
260
  "advmod:rcomp":{
261
+ "p":0.8445747801,
262
+ "r":0.7977839335,
263
+ "f":0.8205128205
264
  },
265
  "nmod:topic":{
266
+ "p":0.4741641337,
267
+ "r":0.5064935065,
268
+ "f":0.4897959184
269
  },
270
  "cop":{
271
+ "p":0.8486672399,
272
+ "r":0.6351351351,
273
+ "f":0.7265366213
274
  },
275
  "discourse":{
276
+ "p":0.5922939068,
277
+ "r":0.545379538,
278
+ "f":0.5678694158
279
  },
280
  "neg":{
281
+ "p":0.8825347759,
282
+ "r":0.6789536266,
283
+ "f":0.7674731183
284
  },
285
  "aux:modal":{
286
+ "p":0.8969631236,
287
+ "r":0.8552223371,
288
+ "f":0.8755955532
289
  },
290
  "nmod":{
291
+ "p":0.8,
292
+ "r":0.7598371777,
293
+ "f":0.779401531
294
  },
295
  "aux:ba":{
296
+ "p":0.9162011173,
297
+ "r":0.8723404255,
298
+ "f":0.89373297
299
  },
300
  "advmod:loc":{
301
+ "p":0.792,
302
+ "r":0.587537092,
303
+ "f":0.6746166951
304
  },
305
  "aux:asp":{
306
+ "p":0.9298986486,
307
+ "r":0.8779904306,
308
+ "f":0.9031993437
309
  },
310
  "conj":{
311
+ "p":0.615168012,
312
+ "r":0.6194706994,
313
+ "f":0.6173118583
314
  },
315
  "nsubjpass":{
316
+ "p":0.8723404255,
317
+ "r":0.82,
318
+ "f":0.8453608247
319
  },
320
  "compound:vc":{
321
+ "p":0.5339805825,
322
+ "r":0.5699481865,
323
+ "f":0.5513784461
324
  },
325
  "advcl:loc":{
326
+ "p":0.6567164179,
327
+ "r":0.6285714286,
328
+ "f":0.6423357664
329
  },
330
  "cc":{
331
+ "p":0.7996306556,
332
+ "r":0.7684117125,
333
+ "f":0.7837104072
334
  },
335
  "advmod:dvp":{
336
+ "p":0.8518518519,
337
+ "r":0.7142857143,
338
+ "f":0.777027027
339
  },
340
  "amod:ordmod":{
341
+ "p":0.703125,
342
  "r":0.703125,
343
+ "f":0.703125
344
  },
345
  "appos":{
346
+ "p":0.9509803922,
347
  "r":0.891954023,
348
+ "f":0.9205219454
349
  },
350
  "nmod:poss":{
351
+ "p":0.8230088496,
352
+ "r":0.6888888889,
353
+ "f":0.75
354
  },
355
  "name":{
356
+ "p":0.6513761468,
357
+ "r":0.5259259259,
358
+ "f":0.5819672131
359
  },
360
  "nsubj:xsubj":{
361
  "p":0.0,
363
  "f":0.0
364
  },
365
  "nmod:range":{
366
+ "p":0.8264150943,
367
+ "r":0.7348993289,
368
+ "f":0.7779751332
369
  },
370
  "parataxis:prnmod":{
371
+ "p":0.2475247525,
372
+ "r":0.1879699248,
373
+ "f":0.2136752137
374
  },
375
  "erased":{
376
  "p":0.0,
378
  "f":0.0
379
  },
380
  "etc":{
381
+ "p":0.8965517241,
382
+ "r":0.9285714286,
383
+ "f":0.9122807018
384
  }
385
  },
386
+ "ents_p":0.6807715613,
387
+ "ents_r":0.7407692308,
388
+ "ents_f":0.7095042627,
389
  "ents_per_type":{
390
  "DATE":{
391
+ "p":0.7026116259,
392
+ "r":0.8265609514,
393
+ "f":0.7595628415
394
  },
395
  "GPE":{
396
+ "p":0.8069756331,
397
+ "r":0.8255131965,
398
+ "f":0.816139164
 
 
 
 
 
399
  },
400
  "ORDINAL":{
401
+ "p":0.8514285714,
402
+ "r":0.7842105263,
403
+ "f":0.8164383562
404
  },
405
  "FAC":{
406
+ "p":0.4751381215,
407
+ "r":0.4623655914,
408
+ "f":0.4686648501
409
  },
410
  "ORG":{
411
+ "p":0.7506033789,
412
+ "r":0.7100456621,
413
+ "f":0.7297614392
414
  },
415
  "LOC":{
416
+ "p":0.1955867603,
417
+ "r":0.5241935484,
418
+ "f":0.2848794741
419
+ },
420
+ "NORP":{
421
+ "p":0.6170212766,
422
+ "r":0.6092436975,
423
+ "f":0.6131078224
424
  },
425
  "QUANTITY":{
426
+ "p":0.615942029,
427
+ "r":0.6296296296,
428
+ "f":0.6227106227
429
  },
430
  "PERSON":{
431
+ "p":0.8742783836,
432
+ "r":0.8782216495,
433
+ "f":0.8762455802
434
  },
435
+ "CARDINAL":{
436
+ "p":0.560111836,
437
+ "r":0.6058467742,
438
+ "f":0.5820823245
439
  },
440
  "TIME":{
441
+ "p":0.7314814815,
442
+ "r":0.7669902913,
443
+ "f":0.7488151659
444
  },
445
  "WORK_OF_ART":{
446
+ "p":0.4108527132,
447
+ "r":0.3533333333,
448
+ "f":0.3799283154
449
  },
450
  "MONEY":{
451
+ "p":0.873015873,
452
+ "r":0.8148148148,
453
+ "f":0.8429118774
454
  },
455
  "EVENT":{
456
+ "p":0.5945945946,
457
+ "r":0.6470588235,
458
+ "f":0.6197183099
 
 
 
 
 
459
  },
460
  "PRODUCT":{
461
+ "p":0.375,
462
+ "r":0.1836734694,
463
+ "f":0.2465753425
464
+ },
465
+ "PERCENT":{
466
+ "p":0.843373494,
467
+ "r":0.843373494,
468
+ "f":0.843373494
469
  },
470
  "LAW":{
471
+ "p":0.3958333333,
472
+ "r":0.3166666667,
473
+ "f":0.3518518519
474
  },
475
  "LANGUAGE":{
476
+ "p":0.75,
477
+ "r":1.0,
478
+ "f":0.8571428571
479
  }
480
  },
481
+ "speed":4551.3152436145
482
  },
483
  "sources":[
484
  {
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0a8c31dd0292ac4611636c97d27f3154d9ad22f80036635baa639189c9efae8e
3
  size 313773
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a5007872178b99a75c136823a0659c35a45a4fb1fd25f34e494217417116357
3
  size 313773
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31e8a1938e9b83803fa019871a130be976494768838bb3edd9c291cd6bc3152b
3
  size 460325
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a37ce5e63e93b4f1e1ed8d5914e25a6cd954f1d25323426d4709de629c47b0a
3
  size 460325
tagger/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7484ad41424567aeb4c9c08521e264afc07156b38e8c989a47b0cf3c96d27f0
3
  size 111378
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8a1b2530c9738b46b468a6d1dd5c09e1469229cf7c5436c91a6414aea60459
3
  size 111378
tokenizer/pkuseg_processors CHANGED
Binary files a/tokenizer/pkuseg_processors and b/tokenizer/pkuseg_processors differ
transformer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3269ad370be2065cbd80eb27f032ebcff9c037330f01c26fa88954b8d5dd39e
3
- size 409701204
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e06885b15719bc16076db0e3a79fba274fd52897ec8bca1a0834aae6271f7775
3
+ size 409701239
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33a091fd24337b44ec904f92aa1eb044cc3e23ec9816ec73fa84698079c49ec3
3
- size 1217133
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:089a4a19967ed4a806708237b48bc8f2feca537e47cf4b50a282e59285094077
3
+ size 1217019
zh_core_web_trf-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21604cb2a0f4b3b80477160ed52d090b704d47365f4aa3903a13bdc2668a9e73
3
- size 417448162
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f067dcbaa07b9a198d82f824ca195b2fc8d5e26f2aefa2d8090ccc9d16fce673
3
+ size 417448829