Commit
Β·
d156ba1
1
Parent(s):
caef619
Update spaCy pipeline
Browse files- README.md +19 -19
- accuracy.json +199 -199
- attribute_ruler/patterns +0 -0
- config.cfg +3 -2
- meta.json +202 -202
- ner/model +1 -1
- parser/model +1 -1
- senter/model +1 -1
- tagger/model +1 -1
- tok2vec/model +2 -2
- zh_core_web_md-any-py3-none-any.whl +2 -2
README.md
CHANGED
|
@@ -14,41 +14,41 @@ model-index:
|
|
| 14 |
metrics:
|
| 15 |
- name: NER Precision
|
| 16 |
type: precision
|
| 17 |
-
value: 0.
|
| 18 |
- name: NER Recall
|
| 19 |
type: recall
|
| 20 |
-
value: 0.
|
| 21 |
- name: NER F Score
|
| 22 |
type: f_score
|
| 23 |
-
value: 0.
|
| 24 |
- task:
|
| 25 |
name: TAG
|
| 26 |
type: token-classification
|
| 27 |
metrics:
|
| 28 |
- name: TAG (XPOS) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
-
value: 0.
|
| 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.
|
| 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.
|
| 45 |
- task:
|
| 46 |
name: SENTS
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Sentences F-Score
|
| 50 |
type: f_score
|
| 51 |
-
value: 0.
|
| 52 |
---
|
| 53 |
### Details: https://spacy.io/models/zh#zh_core_web_md
|
| 54 |
|
|
@@ -57,8 +57,8 @@ Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
|
|
| 57 |
| Feature | Description |
|
| 58 |
| --- | --- |
|
| 59 |
| **Name** | `zh_core_web_md` |
|
| 60 |
-
| **Version** | `3.
|
| 61 |
-
| **spaCy** | `>=3.
|
| 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) |
|
|
@@ -84,16 +84,16 @@ Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
|
|
| 84 |
|
| 85 |
| Type | Score |
|
| 86 |
| --- | --- |
|
| 87 |
-
| `TOKEN_ACC` |
|
| 88 |
| `TOKEN_P` | 94.58 |
|
| 89 |
| `TOKEN_R` | 91.36 |
|
| 90 |
| `TOKEN_F` | 92.94 |
|
| 91 |
-
| `TAG_ACC` | 90.
|
| 92 |
-
| `SENTS_P` | 78.
|
| 93 |
-
| `SENTS_R` | 72.
|
| 94 |
-
| `SENTS_F` | 75.
|
| 95 |
-
| `DEP_UAS` | 70.
|
| 96 |
-
| `DEP_LAS` | 65.
|
| 97 |
-
| `ENTS_P` |
|
| 98 |
-
| `ENTS_R` | 67.
|
| 99 |
-
| `ENTS_F` | 69.
|
|
|
|
| 14 |
metrics:
|
| 15 |
- name: NER Precision
|
| 16 |
type: precision
|
| 17 |
+
value: 0.7188227082
|
| 18 |
- name: NER Recall
|
| 19 |
type: recall
|
| 20 |
+
value: 0.679010989
|
| 21 |
- name: NER F Score
|
| 22 |
type: f_score
|
| 23 |
+
value: 0.6983499096
|
| 24 |
- task:
|
| 25 |
name: TAG
|
| 26 |
type: token-classification
|
| 27 |
metrics:
|
| 28 |
- name: TAG (XPOS) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
+
value: 0.9003849582
|
| 31 |
- task:
|
| 32 |
name: UNLABELED_DEPENDENCIES
|
| 33 |
type: token-classification
|
| 34 |
metrics:
|
| 35 |
- name: Unlabeled Attachment Score (UAS)
|
| 36 |
type: f_score
|
| 37 |
+
value: 0.7049895344
|
| 38 |
- task:
|
| 39 |
name: LABELED_DEPENDENCIES
|
| 40 |
type: token-classification
|
| 41 |
metrics:
|
| 42 |
- name: Labeled Attachment Score (LAS)
|
| 43 |
type: f_score
|
| 44 |
+
value: 0.652241773
|
| 45 |
- task:
|
| 46 |
name: SENTS
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Sentences F-Score
|
| 50 |
type: f_score
|
| 51 |
+
value: 0.7572294372
|
| 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** | `3.5.0` |
|
| 61 |
+
| **spaCy** | `>=3.5.0,<3.6.0` |
|
| 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) |
|
|
|
|
| 84 |
|
| 85 |
| Type | Score |
|
| 86 |
| --- | --- |
|
| 87 |
+
| `TOKEN_ACC` | 95.85 |
|
| 88 |
| `TOKEN_P` | 94.58 |
|
| 89 |
| `TOKEN_R` | 91.36 |
|
| 90 |
| `TOKEN_F` | 92.94 |
|
| 91 |
+
| `TAG_ACC` | 90.04 |
|
| 92 |
+
| `SENTS_P` | 78.89 |
|
| 93 |
+
| `SENTS_R` | 72.80 |
|
| 94 |
+
| `SENTS_F` | 75.72 |
|
| 95 |
+
| `DEP_UAS` | 70.50 |
|
| 96 |
+
| `DEP_LAS` | 65.22 |
|
| 97 |
+
| `ENTS_P` | 71.88 |
|
| 98 |
+
| `ENTS_R` | 67.90 |
|
| 99 |
+
| `ENTS_F` | 69.83 |
|
accuracy.json
CHANGED
|
@@ -1,229 +1,229 @@
|
|
| 1 |
{
|
| 2 |
-
"token_acc": 0.
|
| 3 |
"token_p": 0.9458325855,
|
| 4 |
"token_r": 0.9136060443,
|
| 5 |
"token_f": 0.9294400505,
|
| 6 |
-
"tag_acc": 0.
|
| 7 |
-
"sents_p": 0.
|
| 8 |
-
"sents_r": 0.
|
| 9 |
-
"sents_f": 0.
|
| 10 |
-
"dep_uas": 0.
|
| 11 |
-
"dep_las": 0.
|
| 12 |
"dep_las_per_type": {
|
| 13 |
"dep": {
|
| 14 |
-
"p": 0.
|
| 15 |
-
"r": 0.
|
| 16 |
-
"f": 0.
|
| 17 |
},
|
| 18 |
"case": {
|
| 19 |
-
"p": 0.
|
| 20 |
-
"r": 0.
|
| 21 |
-
"f": 0.
|
| 22 |
},
|
| 23 |
"nmod:tmod": {
|
| 24 |
-
"p": 0.
|
| 25 |
-
"r": 0.
|
| 26 |
-
"f": 0.
|
| 27 |
},
|
| 28 |
"nummod": {
|
| 29 |
-
"p": 0.
|
| 30 |
-
"r": 0.
|
| 31 |
-
"f": 0.
|
| 32 |
},
|
| 33 |
"mark:clf": {
|
| 34 |
-
"p": 0.
|
| 35 |
-
"r": 0.
|
| 36 |
-
"f": 0.
|
| 37 |
},
|
| 38 |
"auxpass": {
|
| 39 |
-
"p": 0.
|
| 40 |
-
"r": 0.
|
| 41 |
-
"f": 0.
|
| 42 |
},
|
| 43 |
"nsubj": {
|
| 44 |
-
"p": 0.
|
| 45 |
-
"r": 0.
|
| 46 |
-
"f": 0.
|
| 47 |
},
|
| 48 |
"acl": {
|
| 49 |
-
"p": 0.
|
| 50 |
-
"r": 0.
|
| 51 |
-
"f": 0.
|
| 52 |
},
|
| 53 |
"advmod": {
|
| 54 |
-
"p": 0.
|
| 55 |
-
"r": 0.
|
| 56 |
-
"f": 0.
|
| 57 |
},
|
| 58 |
"mark": {
|
| 59 |
-
"p": 0.
|
| 60 |
-
"r": 0.
|
| 61 |
-
"f": 0.
|
| 62 |
},
|
| 63 |
"xcomp": {
|
| 64 |
-
"p": 0.
|
| 65 |
"r": 0.6840390879,
|
| 66 |
-
"f": 0.
|
| 67 |
},
|
| 68 |
"nmod:assmod": {
|
| 69 |
-
"p": 0.
|
| 70 |
-
"r": 0.
|
| 71 |
-
"f": 0.
|
| 72 |
},
|
| 73 |
"det": {
|
| 74 |
-
"p": 0.
|
| 75 |
-
"r": 0.
|
| 76 |
-
"f": 0.
|
| 77 |
},
|
| 78 |
"amod": {
|
| 79 |
-
"p": 0.
|
| 80 |
-
"r": 0.
|
| 81 |
-
"f": 0.
|
| 82 |
},
|
| 83 |
"nmod:prep": {
|
| 84 |
-
"p": 0.
|
| 85 |
-
"r": 0.
|
| 86 |
-
"f": 0.
|
| 87 |
},
|
| 88 |
"root": {
|
| 89 |
-
"p": 0.
|
| 90 |
-
"r": 0.
|
| 91 |
-
"f": 0.
|
| 92 |
},
|
| 93 |
"aux:prtmod": {
|
| 94 |
-
"p": 0.
|
| 95 |
-
"r": 0.
|
| 96 |
-
"f": 0.
|
| 97 |
},
|
| 98 |
"compound:nn": {
|
| 99 |
-
"p": 0.
|
| 100 |
-
"r": 0.
|
| 101 |
-
"f": 0.
|
| 102 |
},
|
| 103 |
"dobj": {
|
| 104 |
-
"p": 0.
|
| 105 |
-
"r": 0.
|
| 106 |
-
"f": 0.
|
| 107 |
},
|
| 108 |
"ccomp": {
|
| 109 |
-
"p": 0.
|
| 110 |
-
"r": 0.
|
| 111 |
-
"f": 0.
|
| 112 |
},
|
| 113 |
"advmod:rcomp": {
|
| 114 |
-
"p": 0.
|
| 115 |
-
"r": 0.
|
| 116 |
-
"f": 0.
|
| 117 |
},
|
| 118 |
"nmod:topic": {
|
| 119 |
-
"p": 0.
|
| 120 |
"r": 0.2272727273,
|
| 121 |
-
"f": 0.
|
| 122 |
},
|
| 123 |
"cop": {
|
| 124 |
-
"p": 0.
|
| 125 |
-
"r": 0.
|
| 126 |
-
"f": 0.
|
| 127 |
},
|
| 128 |
"discourse": {
|
| 129 |
-
"p": 0.
|
| 130 |
-
"r": 0.
|
| 131 |
-
"f": 0.
|
| 132 |
},
|
| 133 |
"neg": {
|
| 134 |
-
"p": 0.
|
| 135 |
-
"r": 0.
|
| 136 |
-
"f": 0.
|
| 137 |
},
|
| 138 |
"aux:modal": {
|
| 139 |
-
"p": 0.
|
| 140 |
-
"r": 0.
|
| 141 |
-
"f": 0.
|
| 142 |
},
|
| 143 |
"nmod": {
|
| 144 |
-
"p": 0.
|
| 145 |
-
"r": 0.
|
| 146 |
-
"f": 0.
|
| 147 |
},
|
| 148 |
"aux:ba": {
|
| 149 |
-
"p": 0.
|
| 150 |
-
"r": 0.
|
| 151 |
-
"f": 0.
|
| 152 |
},
|
| 153 |
"advmod:loc": {
|
| 154 |
-
"p": 0.
|
| 155 |
-
"r": 0.
|
| 156 |
-
"f": 0.
|
| 157 |
},
|
| 158 |
"aux:asp": {
|
| 159 |
-
"p": 0.
|
| 160 |
-
"r": 0.
|
| 161 |
-
"f": 0.
|
| 162 |
},
|
| 163 |
"conj": {
|
| 164 |
-
"p": 0.
|
| 165 |
-
"r": 0.
|
| 166 |
-
"f": 0.
|
| 167 |
},
|
| 168 |
"nsubjpass": {
|
| 169 |
-
"p": 0.
|
| 170 |
-
"r": 0.
|
| 171 |
-
"f": 0.
|
| 172 |
},
|
| 173 |
"compound:vc": {
|
| 174 |
-
"p": 0.
|
| 175 |
-
"r": 0.
|
| 176 |
-
"f": 0.
|
| 177 |
},
|
| 178 |
"advcl:loc": {
|
| 179 |
-
"p": 0.
|
| 180 |
-
"r": 0.
|
| 181 |
-
"f": 0.
|
| 182 |
},
|
| 183 |
"cc": {
|
| 184 |
-
"p": 0.
|
| 185 |
-
"r": 0.
|
| 186 |
-
"f": 0.
|
| 187 |
},
|
| 188 |
"advmod:dvp": {
|
| 189 |
-
"p": 0.
|
| 190 |
-
"r": 0.
|
| 191 |
-
"f": 0.
|
| 192 |
},
|
| 193 |
-
"
|
| 194 |
-
"p": 0.
|
| 195 |
-
"r": 0.
|
| 196 |
-
"f": 0.
|
| 197 |
},
|
| 198 |
"appos": {
|
| 199 |
-
"p": 0.
|
| 200 |
-
"r": 0.
|
| 201 |
-
"f": 0.
|
| 202 |
},
|
| 203 |
"nmod:poss": {
|
| 204 |
-
"p": 0.
|
| 205 |
-
"r": 0.
|
| 206 |
-
"f": 0.
|
| 207 |
-
},
|
| 208 |
-
"name": {
|
| 209 |
-
"p": 0.6454545455,
|
| 210 |
-
"r": 0.5259259259,
|
| 211 |
-
"f": 0.5795918367
|
| 212 |
},
|
| 213 |
"nsubj:xsubj": {
|
| 214 |
"p": 0.0,
|
| 215 |
"r": 0.0,
|
| 216 |
"f": 0.0
|
| 217 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 218 |
"parataxis:prnmod": {
|
| 219 |
-
"p": 0.
|
| 220 |
-
"r": 0.
|
| 221 |
-
"f": 0.
|
| 222 |
},
|
| 223 |
"amod:ordmod": {
|
| 224 |
-
"p": 0.
|
| 225 |
"r": 0.578125,
|
| 226 |
-
"f": 0.
|
| 227 |
},
|
| 228 |
"erased": {
|
| 229 |
"p": 0.0,
|
|
@@ -231,105 +231,105 @@
|
|
| 231 |
"f": 0.0
|
| 232 |
},
|
| 233 |
"etc": {
|
| 234 |
-
"p": 0.
|
| 235 |
-
"r": 0.
|
| 236 |
-
"f": 0.
|
| 237 |
}
|
| 238 |
},
|
| 239 |
-
"ents_p": 0.
|
| 240 |
-
"ents_r": 0.
|
| 241 |
-
"ents_f": 0.
|
| 242 |
"ents_per_type": {
|
| 243 |
"DATE": {
|
| 244 |
-
"p": 0.
|
| 245 |
-
"r": 0.
|
| 246 |
-
"f": 0.
|
| 247 |
},
|
| 248 |
"GPE": {
|
| 249 |
-
"p": 0.
|
| 250 |
-
"r": 0.
|
| 251 |
-
"f": 0.
|
| 252 |
},
|
| 253 |
"ORDINAL": {
|
| 254 |
-
"p": 0.
|
| 255 |
-
"r": 0.
|
| 256 |
-
"f": 0.
|
| 257 |
},
|
| 258 |
"FAC": {
|
| 259 |
-
"p": 0.
|
| 260 |
-
"r": 0.
|
| 261 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 262 |
},
|
| 263 |
"ORG": {
|
| 264 |
-
"p": 0.
|
| 265 |
-
"r": 0.
|
| 266 |
-
"f": 0.
|
| 267 |
},
|
| 268 |
"LOC": {
|
| 269 |
-
"p": 0.
|
| 270 |
-
"r": 0.
|
| 271 |
-
"f": 0.
|
| 272 |
},
|
| 273 |
"QUANTITY": {
|
| 274 |
-
"p": 0.
|
| 275 |
-
"r": 0.
|
| 276 |
-
"f": 0.
|
| 277 |
},
|
| 278 |
"CARDINAL": {
|
| 279 |
-
"p": 0.
|
| 280 |
-
"r": 0.
|
| 281 |
-
"f": 0.
|
| 282 |
-
},
|
| 283 |
-
"PERSON": {
|
| 284 |
-
"p": 0.7744708995,
|
| 285 |
-
"r": 0.7545103093,
|
| 286 |
-
"f": 0.7643603133
|
| 287 |
},
|
| 288 |
"NORP": {
|
| 289 |
-
"p": 0.
|
| 290 |
-
"r": 0.
|
| 291 |
-
"f": 0.
|
| 292 |
-
},
|
| 293 |
-
"WORK_OF_ART": {
|
| 294 |
-
"p": 0.6075949367,
|
| 295 |
-
"r": 0.32,
|
| 296 |
-
"f": 0.4192139738
|
| 297 |
},
|
| 298 |
"TIME": {
|
| 299 |
-
"p": 0.
|
| 300 |
-
"r": 0.
|
| 301 |
-
"f": 0.
|
| 302 |
},
|
| 303 |
-
"
|
| 304 |
-
"p": 0.
|
| 305 |
-
"r": 0.
|
| 306 |
-
"f": 0.
|
| 307 |
},
|
| 308 |
-
"
|
| 309 |
-
"p": 0.
|
| 310 |
-
"r": 0.
|
| 311 |
-
"f": 0.
|
| 312 |
},
|
| 313 |
"EVENT": {
|
| 314 |
-
"p": 0.
|
| 315 |
-
"r": 0.
|
| 316 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 317 |
},
|
| 318 |
"PRODUCT": {
|
| 319 |
-
"p": 0.
|
| 320 |
-
"r": 0.
|
| 321 |
-
"f": 0.
|
| 322 |
},
|
| 323 |
"LAW": {
|
| 324 |
-
"p": 0.
|
| 325 |
-
"r": 0.
|
| 326 |
-
"f": 0.
|
| 327 |
},
|
| 328 |
"LANGUAGE": {
|
| 329 |
-
"p": 0.
|
| 330 |
"r": 0.7777777778,
|
| 331 |
-
"f": 0.
|
| 332 |
}
|
| 333 |
},
|
| 334 |
-
"speed":
|
| 335 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"token_acc": 0.9585384056,
|
| 3 |
"token_p": 0.9458325855,
|
| 4 |
"token_r": 0.9136060443,
|
| 5 |
"token_f": 0.9294400505,
|
| 6 |
+
"tag_acc": 0.9003849582,
|
| 7 |
+
"sents_p": 0.7889229659,
|
| 8 |
+
"sents_r": 0.7279840186,
|
| 9 |
+
"sents_f": 0.7572294372,
|
| 10 |
+
"dep_uas": 0.7049895344,
|
| 11 |
+
"dep_las": 0.652241773,
|
| 12 |
"dep_las_per_type": {
|
| 13 |
"dep": {
|
| 14 |
+
"p": 0.480506402,
|
| 15 |
+
"r": 0.3374760028,
|
| 16 |
+
"f": 0.3964862298
|
| 17 |
},
|
| 18 |
"case": {
|
| 19 |
+
"p": 0.8137318047,
|
| 20 |
+
"r": 0.7658826382,
|
| 21 |
+
"f": 0.7890825058
|
| 22 |
},
|
| 23 |
"nmod:tmod": {
|
| 24 |
+
"p": 0.7230971129,
|
| 25 |
+
"r": 0.7496598639,
|
| 26 |
+
"f": 0.7361389446
|
| 27 |
},
|
| 28 |
"nummod": {
|
| 29 |
+
"p": 0.8259067358,
|
| 30 |
+
"r": 0.5309793471,
|
| 31 |
+
"f": 0.6463909165
|
| 32 |
},
|
| 33 |
"mark:clf": {
|
| 34 |
+
"p": 0.9348494161,
|
| 35 |
+
"r": 0.5673256248,
|
| 36 |
+
"f": 0.7061281337
|
| 37 |
},
|
| 38 |
"auxpass": {
|
| 39 |
+
"p": 0.8641304348,
|
| 40 |
+
"r": 0.8594594595,
|
| 41 |
+
"f": 0.8617886179
|
| 42 |
},
|
| 43 |
"nsubj": {
|
| 44 |
+
"p": 0.7849376823,
|
| 45 |
+
"r": 0.7271833927,
|
| 46 |
+
"f": 0.7549575974
|
| 47 |
},
|
| 48 |
"acl": {
|
| 49 |
+
"p": 0.6644606221,
|
| 50 |
+
"r": 0.556849695,
|
| 51 |
+
"f": 0.605914303
|
| 52 |
},
|
| 53 |
"advmod": {
|
| 54 |
+
"p": 0.820278834,
|
| 55 |
+
"r": 0.7336204942,
|
| 56 |
+
"f": 0.7745332695
|
| 57 |
},
|
| 58 |
"mark": {
|
| 59 |
+
"p": 0.7400654511,
|
| 60 |
+
"r": 0.6936897458,
|
| 61 |
+
"f": 0.7161275729
|
| 62 |
},
|
| 63 |
"xcomp": {
|
| 64 |
+
"p": 0.7865168539,
|
| 65 |
"r": 0.6840390879,
|
| 66 |
+
"f": 0.7317073171
|
| 67 |
},
|
| 68 |
"nmod:assmod": {
|
| 69 |
+
"p": 0.7600130251,
|
| 70 |
+
"r": 0.7264239029,
|
| 71 |
+
"f": 0.7428389561
|
| 72 |
},
|
| 73 |
"det": {
|
| 74 |
+
"p": 0.8406148867,
|
| 75 |
+
"r": 0.6086701816,
|
| 76 |
+
"f": 0.706082229
|
| 77 |
},
|
| 78 |
"amod": {
|
| 79 |
+
"p": 0.7720254314,
|
| 80 |
+
"r": 0.6677140613,
|
| 81 |
+
"f": 0.7160909857
|
| 82 |
},
|
| 83 |
"nmod:prep": {
|
| 84 |
+
"p": 0.6991273997,
|
| 85 |
+
"r": 0.6058681186,
|
| 86 |
+
"f": 0.6491654513
|
| 87 |
},
|
| 88 |
"root": {
|
| 89 |
+
"p": 0.7380861609,
|
| 90 |
+
"r": 0.6445813218,
|
| 91 |
+
"f": 0.688172043
|
| 92 |
},
|
| 93 |
"aux:prtmod": {
|
| 94 |
+
"p": 0.9031007752,
|
| 95 |
+
"r": 0.8321428571,
|
| 96 |
+
"f": 0.8661710037
|
| 97 |
},
|
| 98 |
"compound:nn": {
|
| 99 |
+
"p": 0.733790195,
|
| 100 |
+
"r": 0.7065989848,
|
| 101 |
+
"f": 0.7199379364
|
| 102 |
},
|
| 103 |
"dobj": {
|
| 104 |
+
"p": 0.800386349,
|
| 105 |
+
"r": 0.7364834839,
|
| 106 |
+
"f": 0.7671063797
|
| 107 |
},
|
| 108 |
"ccomp": {
|
| 109 |
+
"p": 0.6472945892,
|
| 110 |
+
"r": 0.6279160187,
|
| 111 |
+
"f": 0.637458062
|
| 112 |
},
|
| 113 |
"advmod:rcomp": {
|
| 114 |
+
"p": 0.8140243902,
|
| 115 |
+
"r": 0.7396121884,
|
| 116 |
+
"f": 0.7750362845
|
| 117 |
},
|
| 118 |
"nmod:topic": {
|
| 119 |
+
"p": 0.351758794,
|
| 120 |
"r": 0.2272727273,
|
| 121 |
+
"f": 0.2761341223
|
| 122 |
},
|
| 123 |
"cop": {
|
| 124 |
+
"p": 0.7524429967,
|
| 125 |
+
"r": 0.5945945946,
|
| 126 |
+
"f": 0.6642703091
|
| 127 |
},
|
| 128 |
"discourse": {
|
| 129 |
+
"p": 0.5552434457,
|
| 130 |
+
"r": 0.4892739274,
|
| 131 |
+
"f": 0.5201754386
|
| 132 |
},
|
| 133 |
"neg": {
|
| 134 |
+
"p": 0.8400597907,
|
| 135 |
+
"r": 0.6682520809,
|
| 136 |
+
"f": 0.7443708609
|
| 137 |
},
|
| 138 |
"aux:modal": {
|
| 139 |
+
"p": 0.8646616541,
|
| 140 |
+
"r": 0.8324715615,
|
| 141 |
+
"f": 0.8482613277
|
| 142 |
},
|
| 143 |
"nmod": {
|
| 144 |
+
"p": 0.7028753994,
|
| 145 |
+
"r": 0.5970149254,
|
| 146 |
+
"f": 0.6456346295
|
| 147 |
},
|
| 148 |
"aux:ba": {
|
| 149 |
+
"p": 0.8453038674,
|
| 150 |
+
"r": 0.8138297872,
|
| 151 |
+
"f": 0.8292682927
|
| 152 |
},
|
| 153 |
"advmod:loc": {
|
| 154 |
+
"p": 0.577689243,
|
| 155 |
+
"r": 0.4302670623,
|
| 156 |
+
"f": 0.4931972789
|
| 157 |
},
|
| 158 |
"aux:asp": {
|
| 159 |
+
"p": 0.9067656766,
|
| 160 |
+
"r": 0.8763955343,
|
| 161 |
+
"f": 0.8913219789
|
| 162 |
},
|
| 163 |
"conj": {
|
| 164 |
+
"p": 0.4907251265,
|
| 165 |
+
"r": 0.4950850662,
|
| 166 |
+
"f": 0.492895455
|
| 167 |
},
|
| 168 |
"nsubjpass": {
|
| 169 |
+
"p": 0.7954545455,
|
| 170 |
+
"r": 0.7,
|
| 171 |
+
"f": 0.7446808511
|
| 172 |
},
|
| 173 |
"compound:vc": {
|
| 174 |
+
"p": 0.4725274725,
|
| 175 |
+
"r": 0.4455958549,
|
| 176 |
+
"f": 0.4586666667
|
| 177 |
},
|
| 178 |
"advcl:loc": {
|
| 179 |
+
"p": 0.4461538462,
|
| 180 |
+
"r": 0.4142857143,
|
| 181 |
+
"f": 0.4296296296
|
| 182 |
},
|
| 183 |
"cc": {
|
| 184 |
+
"p": 0.7127962085,
|
| 185 |
+
"r": 0.6672582076,
|
| 186 |
+
"f": 0.6892758937
|
| 187 |
},
|
| 188 |
"advmod:dvp": {
|
| 189 |
+
"p": 0.8307692308,
|
| 190 |
+
"r": 0.6708074534,
|
| 191 |
+
"f": 0.7422680412
|
| 192 |
},
|
| 193 |
+
"name": {
|
| 194 |
+
"p": 0.619047619,
|
| 195 |
+
"r": 0.4814814815,
|
| 196 |
+
"f": 0.5416666667
|
| 197 |
},
|
| 198 |
"appos": {
|
| 199 |
+
"p": 0.8877805486,
|
| 200 |
+
"r": 0.8183908046,
|
| 201 |
+
"f": 0.8516746411
|
| 202 |
},
|
| 203 |
"nmod:poss": {
|
| 204 |
+
"p": 0.65625,
|
| 205 |
+
"r": 0.4666666667,
|
| 206 |
+
"f": 0.5454545455
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 207 |
},
|
| 208 |
"nsubj:xsubj": {
|
| 209 |
"p": 0.0,
|
| 210 |
"r": 0.0,
|
| 211 |
"f": 0.0
|
| 212 |
},
|
| 213 |
+
"nmod:range": {
|
| 214 |
+
"p": 0.7480314961,
|
| 215 |
+
"r": 0.6375838926,
|
| 216 |
+
"f": 0.6884057971
|
| 217 |
+
},
|
| 218 |
"parataxis:prnmod": {
|
| 219 |
+
"p": 0.4857142857,
|
| 220 |
+
"r": 0.1278195489,
|
| 221 |
+
"f": 0.2023809524
|
| 222 |
},
|
| 223 |
"amod:ordmod": {
|
| 224 |
+
"p": 0.5606060606,
|
| 225 |
"r": 0.578125,
|
| 226 |
+
"f": 0.5692307692
|
| 227 |
},
|
| 228 |
"erased": {
|
| 229 |
"p": 0.0,
|
|
|
|
| 231 |
"f": 0.0
|
| 232 |
},
|
| 233 |
"etc": {
|
| 234 |
+
"p": 0.9285714286,
|
| 235 |
+
"r": 0.9285714286,
|
| 236 |
+
"f": 0.9285714286
|
| 237 |
}
|
| 238 |
},
|
| 239 |
+
"ents_p": 0.7188227082,
|
| 240 |
+
"ents_r": 0.679010989,
|
| 241 |
+
"ents_f": 0.6983499096,
|
| 242 |
"ents_per_type": {
|
| 243 |
"DATE": {
|
| 244 |
+
"p": 0.7758945386,
|
| 245 |
+
"r": 0.8166501487,
|
| 246 |
+
"f": 0.795750845
|
| 247 |
},
|
| 248 |
"GPE": {
|
| 249 |
+
"p": 0.7566351777,
|
| 250 |
+
"r": 0.8220918866,
|
| 251 |
+
"f": 0.7880065589
|
| 252 |
},
|
| 253 |
"ORDINAL": {
|
| 254 |
+
"p": 0.8764705882,
|
| 255 |
+
"r": 0.7842105263,
|
| 256 |
+
"f": 0.8277777778
|
| 257 |
},
|
| 258 |
"FAC": {
|
| 259 |
+
"p": 0.4353741497,
|
| 260 |
+
"r": 0.3440860215,
|
| 261 |
+
"f": 0.3843843844
|
| 262 |
+
},
|
| 263 |
+
"PERSON": {
|
| 264 |
+
"p": 0.7662082515,
|
| 265 |
+
"r": 0.7538659794,
|
| 266 |
+
"f": 0.7599870088
|
| 267 |
},
|
| 268 |
"ORG": {
|
| 269 |
+
"p": 0.6975409836,
|
| 270 |
+
"r": 0.6476407915,
|
| 271 |
+
"f": 0.6716653512
|
| 272 |
},
|
| 273 |
"LOC": {
|
| 274 |
+
"p": 0.4691780822,
|
| 275 |
+
"r": 0.3682795699,
|
| 276 |
+
"f": 0.4126506024
|
| 277 |
},
|
| 278 |
"QUANTITY": {
|
| 279 |
+
"p": 0.7543859649,
|
| 280 |
+
"r": 0.637037037,
|
| 281 |
+
"f": 0.6907630522
|
| 282 |
},
|
| 283 |
"CARDINAL": {
|
| 284 |
+
"p": 0.6059225513,
|
| 285 |
+
"r": 0.5362903226,
|
| 286 |
+
"f": 0.5689839572
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 287 |
},
|
| 288 |
"NORP": {
|
| 289 |
+
"p": 0.6955128205,
|
| 290 |
+
"r": 0.4558823529,
|
| 291 |
+
"f": 0.5507614213
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 292 |
},
|
| 293 |
"TIME": {
|
| 294 |
+
"p": 0.7452830189,
|
| 295 |
+
"r": 0.7669902913,
|
| 296 |
+
"f": 0.7559808612
|
| 297 |
},
|
| 298 |
+
"WORK_OF_ART": {
|
| 299 |
+
"p": 0.5921052632,
|
| 300 |
+
"r": 0.3,
|
| 301 |
+
"f": 0.3982300885
|
| 302 |
},
|
| 303 |
+
"MONEY": {
|
| 304 |
+
"p": 0.9322033898,
|
| 305 |
+
"r": 0.8148148148,
|
| 306 |
+
"f": 0.8695652174
|
| 307 |
},
|
| 308 |
"EVENT": {
|
| 309 |
+
"p": 0.5625,
|
| 310 |
+
"r": 0.4632352941,
|
| 311 |
+
"f": 0.5080645161
|
| 312 |
+
},
|
| 313 |
+
"PERCENT": {
|
| 314 |
+
"p": 0.8313253012,
|
| 315 |
+
"r": 0.8313253012,
|
| 316 |
+
"f": 0.8313253012
|
| 317 |
},
|
| 318 |
"PRODUCT": {
|
| 319 |
+
"p": 0.125,
|
| 320 |
+
"r": 0.0204081633,
|
| 321 |
+
"f": 0.0350877193
|
| 322 |
},
|
| 323 |
"LAW": {
|
| 324 |
+
"p": 0.5,
|
| 325 |
+
"r": 0.2333333333,
|
| 326 |
+
"f": 0.3181818182
|
| 327 |
},
|
| 328 |
"LANGUAGE": {
|
| 329 |
+
"p": 0.5,
|
| 330 |
"r": 0.7777777778,
|
| 331 |
+
"f": 0.6086956522
|
| 332 |
}
|
| 333 |
},
|
| 334 |
+
"speed": 7528.4602636561
|
| 335 |
}
|
attribute_ruler/patterns
CHANGED
|
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
|
|
|
config.cfg
CHANGED
|
@@ -135,8 +135,8 @@ factory = "tok2vec"
|
|
| 135 |
[components.tok2vec.model.embed]
|
| 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]
|
|
@@ -178,6 +178,7 @@ eval_frequency = 1000
|
|
| 178 |
frozen_components = []
|
| 179 |
before_to_disk = null
|
| 180 |
annotating_components = []
|
|
|
|
| 181 |
|
| 182 |
[training.batcher]
|
| 183 |
@batchers = "spacy.batch_by_words.v1"
|
|
|
|
| 135 |
[components.tok2vec.model.embed]
|
| 136 |
@architectures = "spacy.MultiHashEmbed.v2"
|
| 137 |
width = ${components.tok2vec.model.encode:width}
|
| 138 |
+
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","IS_SPACE"]
|
| 139 |
+
rows = [5000,1000,2500,2500,50]
|
| 140 |
include_static_vectors = true
|
| 141 |
|
| 142 |
[components.tok2vec.model.encode]
|
|
|
|
| 178 |
frozen_components = []
|
| 179 |
before_to_disk = null
|
| 180 |
annotating_components = []
|
| 181 |
+
before_update = null
|
| 182 |
|
| 183 |
[training.batcher]
|
| 184 |
@batchers = "spacy.batch_by_words.v1"
|
meta.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"lang":"zh",
|
| 3 |
"name":"core_web_md",
|
| 4 |
-
"version":"3.
|
| 5 |
"description":"Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.",
|
| 6 |
"author":"Explosion",
|
| 7 |
"email":"[email protected]",
|
| 8 |
"url":"https://explosion.ai",
|
| 9 |
"license":"MIT",
|
| 10 |
-
"spacy_version":">=3.
|
| 11 |
-
"spacy_git_version":"
|
| 12 |
"vectors":{
|
| 13 |
"width":300,
|
| 14 |
"vectors":20000,
|
|
@@ -148,231 +148,231 @@
|
|
| 148 |
"senter"
|
| 149 |
],
|
| 150 |
"performance":{
|
| 151 |
-
"token_acc":0.
|
| 152 |
"token_p":0.9458325855,
|
| 153 |
"token_r":0.9136060443,
|
| 154 |
"token_f":0.9294400505,
|
| 155 |
-
"tag_acc":0.
|
| 156 |
-
"sents_p":0.
|
| 157 |
-
"sents_r":0.
|
| 158 |
-
"sents_f":0.
|
| 159 |
-
"dep_uas":0.
|
| 160 |
-
"dep_las":0.
|
| 161 |
"dep_las_per_type":{
|
| 162 |
"dep":{
|
| 163 |
-
"p":0.
|
| 164 |
-
"r":0.
|
| 165 |
-
"f":0.
|
| 166 |
},
|
| 167 |
"case":{
|
| 168 |
-
"p":0.
|
| 169 |
-
"r":0.
|
| 170 |
-
"f":0.
|
| 171 |
},
|
| 172 |
"nmod:tmod":{
|
| 173 |
-
"p":0.
|
| 174 |
-
"r":0.
|
| 175 |
-
"f":0.
|
| 176 |
},
|
| 177 |
"nummod":{
|
| 178 |
-
"p":0.
|
| 179 |
-
"r":0.
|
| 180 |
-
"f":0.
|
| 181 |
},
|
| 182 |
"mark:clf":{
|
| 183 |
-
"p":0.
|
| 184 |
-
"r":0.
|
| 185 |
-
"f":0.
|
| 186 |
},
|
| 187 |
"auxpass":{
|
| 188 |
-
"p":0.
|
| 189 |
-
"r":0.
|
| 190 |
-
"f":0.
|
| 191 |
},
|
| 192 |
"nsubj":{
|
| 193 |
-
"p":0.
|
| 194 |
-
"r":0.
|
| 195 |
-
"f":0.
|
| 196 |
},
|
| 197 |
"acl":{
|
| 198 |
-
"p":0.
|
| 199 |
-
"r":0.
|
| 200 |
-
"f":0.
|
| 201 |
},
|
| 202 |
"advmod":{
|
| 203 |
-
"p":0.
|
| 204 |
-
"r":0.
|
| 205 |
-
"f":0.
|
| 206 |
},
|
| 207 |
"mark":{
|
| 208 |
-
"p":0.
|
| 209 |
-
"r":0.
|
| 210 |
-
"f":0.
|
| 211 |
},
|
| 212 |
"xcomp":{
|
| 213 |
-
"p":0.
|
| 214 |
"r":0.6840390879,
|
| 215 |
-
"f":0.
|
| 216 |
},
|
| 217 |
"nmod:assmod":{
|
| 218 |
-
"p":0.
|
| 219 |
-
"r":0.
|
| 220 |
-
"f":0.
|
| 221 |
},
|
| 222 |
"det":{
|
| 223 |
-
"p":0.
|
| 224 |
-
"r":0.
|
| 225 |
-
"f":0.
|
| 226 |
},
|
| 227 |
"amod":{
|
| 228 |
-
"p":0.
|
| 229 |
-
"r":0.
|
| 230 |
-
"f":0.
|
| 231 |
},
|
| 232 |
"nmod:prep":{
|
| 233 |
-
"p":0.
|
| 234 |
-
"r":0.
|
| 235 |
-
"f":0.
|
| 236 |
},
|
| 237 |
"root":{
|
| 238 |
-
"p":0.
|
| 239 |
-
"r":0.
|
| 240 |
-
"f":0.
|
| 241 |
},
|
| 242 |
"aux:prtmod":{
|
| 243 |
-
"p":0.
|
| 244 |
-
"r":0.
|
| 245 |
-
"f":0.
|
| 246 |
},
|
| 247 |
"compound:nn":{
|
| 248 |
-
"p":0.
|
| 249 |
-
"r":0.
|
| 250 |
-
"f":0.
|
| 251 |
},
|
| 252 |
"dobj":{
|
| 253 |
-
"p":0.
|
| 254 |
-
"r":0.
|
| 255 |
-
"f":0.
|
| 256 |
},
|
| 257 |
"ccomp":{
|
| 258 |
-
"p":0.
|
| 259 |
-
"r":0.
|
| 260 |
-
"f":0.
|
| 261 |
},
|
| 262 |
"advmod:rcomp":{
|
| 263 |
-
"p":0.
|
| 264 |
-
"r":0.
|
| 265 |
-
"f":0.
|
| 266 |
},
|
| 267 |
"nmod:topic":{
|
| 268 |
-
"p":0.
|
| 269 |
"r":0.2272727273,
|
| 270 |
-
"f":0.
|
| 271 |
},
|
| 272 |
"cop":{
|
| 273 |
-
"p":0.
|
| 274 |
-
"r":0.
|
| 275 |
-
"f":0.
|
| 276 |
},
|
| 277 |
"discourse":{
|
| 278 |
-
"p":0.
|
| 279 |
-
"r":0.
|
| 280 |
-
"f":0.
|
| 281 |
},
|
| 282 |
"neg":{
|
| 283 |
-
"p":0.
|
| 284 |
-
"r":0.
|
| 285 |
-
"f":0.
|
| 286 |
},
|
| 287 |
"aux:modal":{
|
| 288 |
-
"p":0.
|
| 289 |
-
"r":0.
|
| 290 |
-
"f":0.
|
| 291 |
},
|
| 292 |
"nmod":{
|
| 293 |
-
"p":0.
|
| 294 |
-
"r":0.
|
| 295 |
-
"f":0.
|
| 296 |
},
|
| 297 |
"aux:ba":{
|
| 298 |
-
"p":0.
|
| 299 |
-
"r":0.
|
| 300 |
-
"f":0.
|
| 301 |
},
|
| 302 |
"advmod:loc":{
|
| 303 |
-
"p":0.
|
| 304 |
-
"r":0.
|
| 305 |
-
"f":0.
|
| 306 |
},
|
| 307 |
"aux:asp":{
|
| 308 |
-
"p":0.
|
| 309 |
-
"r":0.
|
| 310 |
-
"f":0.
|
| 311 |
},
|
| 312 |
"conj":{
|
| 313 |
-
"p":0.
|
| 314 |
-
"r":0.
|
| 315 |
-
"f":0.
|
| 316 |
},
|
| 317 |
"nsubjpass":{
|
| 318 |
-
"p":0.
|
| 319 |
-
"r":0.
|
| 320 |
-
"f":0.
|
| 321 |
},
|
| 322 |
"compound:vc":{
|
| 323 |
-
"p":0.
|
| 324 |
-
"r":0.
|
| 325 |
-
"f":0.
|
| 326 |
},
|
| 327 |
"advcl:loc":{
|
| 328 |
-
"p":0.
|
| 329 |
-
"r":0.
|
| 330 |
-
"f":0.
|
| 331 |
},
|
| 332 |
"cc":{
|
| 333 |
-
"p":0.
|
| 334 |
-
"r":0.
|
| 335 |
-
"f":0.
|
| 336 |
},
|
| 337 |
"advmod:dvp":{
|
| 338 |
-
"p":0.
|
| 339 |
-
"r":0.
|
| 340 |
-
"f":0.
|
| 341 |
},
|
| 342 |
-
"
|
| 343 |
-
"p":0.
|
| 344 |
-
"r":0.
|
| 345 |
-
"f":0.
|
| 346 |
},
|
| 347 |
"appos":{
|
| 348 |
-
"p":0.
|
| 349 |
-
"r":0.
|
| 350 |
-
"f":0.
|
| 351 |
},
|
| 352 |
"nmod:poss":{
|
| 353 |
-
"p":0.
|
| 354 |
-
"r":0.
|
| 355 |
-
"f":0.
|
| 356 |
-
},
|
| 357 |
-
"name":{
|
| 358 |
-
"p":0.6454545455,
|
| 359 |
-
"r":0.5259259259,
|
| 360 |
-
"f":0.5795918367
|
| 361 |
},
|
| 362 |
"nsubj:xsubj":{
|
| 363 |
"p":0.0,
|
| 364 |
"r":0.0,
|
| 365 |
"f":0.0
|
| 366 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 367 |
"parataxis:prnmod":{
|
| 368 |
-
"p":0.
|
| 369 |
-
"r":0.
|
| 370 |
-
"f":0.
|
| 371 |
},
|
| 372 |
"amod:ordmod":{
|
| 373 |
-
"p":0.
|
| 374 |
"r":0.578125,
|
| 375 |
-
"f":0.
|
| 376 |
},
|
| 377 |
"erased":{
|
| 378 |
"p":0.0,
|
|
@@ -380,107 +380,107 @@
|
|
| 380 |
"f":0.0
|
| 381 |
},
|
| 382 |
"etc":{
|
| 383 |
-
"p":0.
|
| 384 |
-
"r":0.
|
| 385 |
-
"f":0.
|
| 386 |
}
|
| 387 |
},
|
| 388 |
-
"ents_p":0.
|
| 389 |
-
"ents_r":0.
|
| 390 |
-
"ents_f":0.
|
| 391 |
"ents_per_type":{
|
| 392 |
"DATE":{
|
| 393 |
-
"p":0.
|
| 394 |
-
"r":0.
|
| 395 |
-
"f":0.
|
| 396 |
},
|
| 397 |
"GPE":{
|
| 398 |
-
"p":0.
|
| 399 |
-
"r":0.
|
| 400 |
-
"f":0.
|
| 401 |
},
|
| 402 |
"ORDINAL":{
|
| 403 |
-
"p":0.
|
| 404 |
-
"r":0.
|
| 405 |
-
"f":0.
|
| 406 |
},
|
| 407 |
"FAC":{
|
| 408 |
-
"p":0.
|
| 409 |
-
"r":0.
|
| 410 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 411 |
},
|
| 412 |
"ORG":{
|
| 413 |
-
"p":0.
|
| 414 |
-
"r":0.
|
| 415 |
-
"f":0.
|
| 416 |
},
|
| 417 |
"LOC":{
|
| 418 |
-
"p":0.
|
| 419 |
-
"r":0.
|
| 420 |
-
"f":0.
|
| 421 |
},
|
| 422 |
"QUANTITY":{
|
| 423 |
-
"p":0.
|
| 424 |
-
"r":0.
|
| 425 |
-
"f":0.
|
| 426 |
},
|
| 427 |
"CARDINAL":{
|
| 428 |
-
"p":0.
|
| 429 |
-
"r":0.
|
| 430 |
-
"f":0.
|
| 431 |
-
},
|
| 432 |
-
"PERSON":{
|
| 433 |
-
"p":0.7744708995,
|
| 434 |
-
"r":0.7545103093,
|
| 435 |
-
"f":0.7643603133
|
| 436 |
},
|
| 437 |
"NORP":{
|
| 438 |
-
"p":0.
|
| 439 |
-
"r":0.
|
| 440 |
-
"f":0.
|
| 441 |
-
},
|
| 442 |
-
"WORK_OF_ART":{
|
| 443 |
-
"p":0.6075949367,
|
| 444 |
-
"r":0.32,
|
| 445 |
-
"f":0.4192139738
|
| 446 |
},
|
| 447 |
"TIME":{
|
| 448 |
-
"p":0.
|
| 449 |
-
"r":0.
|
| 450 |
-
"f":0.
|
| 451 |
},
|
| 452 |
-
"
|
| 453 |
-
"p":0.
|
| 454 |
-
"r":0.
|
| 455 |
-
"f":0.
|
| 456 |
},
|
| 457 |
-
"
|
| 458 |
-
"p":0.
|
| 459 |
-
"r":0.
|
| 460 |
-
"f":0.
|
| 461 |
},
|
| 462 |
"EVENT":{
|
| 463 |
-
"p":0.
|
| 464 |
-
"r":0.
|
| 465 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 466 |
},
|
| 467 |
"PRODUCT":{
|
| 468 |
-
"p":0.
|
| 469 |
-
"r":0.
|
| 470 |
-
"f":0.
|
| 471 |
},
|
| 472 |
"LAW":{
|
| 473 |
-
"p":0.
|
| 474 |
-
"r":0.
|
| 475 |
-
"f":0.
|
| 476 |
},
|
| 477 |
"LANGUAGE":{
|
| 478 |
-
"p":0.
|
| 479 |
"r":0.7777777778,
|
| 480 |
-
"f":0.
|
| 481 |
}
|
| 482 |
},
|
| 483 |
-
"speed":
|
| 484 |
},
|
| 485 |
"sources":[
|
| 486 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"lang":"zh",
|
| 3 |
"name":"core_web_md",
|
| 4 |
+
"version":"3.5.0",
|
| 5 |
"description":"Chinese pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler.",
|
| 6 |
"author":"Explosion",
|
| 7 |
"email":"[email protected]",
|
| 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,
|
|
|
|
| 148 |
"senter"
|
| 149 |
],
|
| 150 |
"performance":{
|
| 151 |
+
"token_acc":0.9585384056,
|
| 152 |
"token_p":0.9458325855,
|
| 153 |
"token_r":0.9136060443,
|
| 154 |
"token_f":0.9294400505,
|
| 155 |
+
"tag_acc":0.9003849582,
|
| 156 |
+
"sents_p":0.7889229659,
|
| 157 |
+
"sents_r":0.7279840186,
|
| 158 |
+
"sents_f":0.7572294372,
|
| 159 |
+
"dep_uas":0.7049895344,
|
| 160 |
+
"dep_las":0.652241773,
|
| 161 |
"dep_las_per_type":{
|
| 162 |
"dep":{
|
| 163 |
+
"p":0.480506402,
|
| 164 |
+
"r":0.3374760028,
|
| 165 |
+
"f":0.3964862298
|
| 166 |
},
|
| 167 |
"case":{
|
| 168 |
+
"p":0.8137318047,
|
| 169 |
+
"r":0.7658826382,
|
| 170 |
+
"f":0.7890825058
|
| 171 |
},
|
| 172 |
"nmod:tmod":{
|
| 173 |
+
"p":0.7230971129,
|
| 174 |
+
"r":0.7496598639,
|
| 175 |
+
"f":0.7361389446
|
| 176 |
},
|
| 177 |
"nummod":{
|
| 178 |
+
"p":0.8259067358,
|
| 179 |
+
"r":0.5309793471,
|
| 180 |
+
"f":0.6463909165
|
| 181 |
},
|
| 182 |
"mark:clf":{
|
| 183 |
+
"p":0.9348494161,
|
| 184 |
+
"r":0.5673256248,
|
| 185 |
+
"f":0.7061281337
|
| 186 |
},
|
| 187 |
"auxpass":{
|
| 188 |
+
"p":0.8641304348,
|
| 189 |
+
"r":0.8594594595,
|
| 190 |
+
"f":0.8617886179
|
| 191 |
},
|
| 192 |
"nsubj":{
|
| 193 |
+
"p":0.7849376823,
|
| 194 |
+
"r":0.7271833927,
|
| 195 |
+
"f":0.7549575974
|
| 196 |
},
|
| 197 |
"acl":{
|
| 198 |
+
"p":0.6644606221,
|
| 199 |
+
"r":0.556849695,
|
| 200 |
+
"f":0.605914303
|
| 201 |
},
|
| 202 |
"advmod":{
|
| 203 |
+
"p":0.820278834,
|
| 204 |
+
"r":0.7336204942,
|
| 205 |
+
"f":0.7745332695
|
| 206 |
},
|
| 207 |
"mark":{
|
| 208 |
+
"p":0.7400654511,
|
| 209 |
+
"r":0.6936897458,
|
| 210 |
+
"f":0.7161275729
|
| 211 |
},
|
| 212 |
"xcomp":{
|
| 213 |
+
"p":0.7865168539,
|
| 214 |
"r":0.6840390879,
|
| 215 |
+
"f":0.7317073171
|
| 216 |
},
|
| 217 |
"nmod:assmod":{
|
| 218 |
+
"p":0.7600130251,
|
| 219 |
+
"r":0.7264239029,
|
| 220 |
+
"f":0.7428389561
|
| 221 |
},
|
| 222 |
"det":{
|
| 223 |
+
"p":0.8406148867,
|
| 224 |
+
"r":0.6086701816,
|
| 225 |
+
"f":0.706082229
|
| 226 |
},
|
| 227 |
"amod":{
|
| 228 |
+
"p":0.7720254314,
|
| 229 |
+
"r":0.6677140613,
|
| 230 |
+
"f":0.7160909857
|
| 231 |
},
|
| 232 |
"nmod:prep":{
|
| 233 |
+
"p":0.6991273997,
|
| 234 |
+
"r":0.6058681186,
|
| 235 |
+
"f":0.6491654513
|
| 236 |
},
|
| 237 |
"root":{
|
| 238 |
+
"p":0.7380861609,
|
| 239 |
+
"r":0.6445813218,
|
| 240 |
+
"f":0.688172043
|
| 241 |
},
|
| 242 |
"aux:prtmod":{
|
| 243 |
+
"p":0.9031007752,
|
| 244 |
+
"r":0.8321428571,
|
| 245 |
+
"f":0.8661710037
|
| 246 |
},
|
| 247 |
"compound:nn":{
|
| 248 |
+
"p":0.733790195,
|
| 249 |
+
"r":0.7065989848,
|
| 250 |
+
"f":0.7199379364
|
| 251 |
},
|
| 252 |
"dobj":{
|
| 253 |
+
"p":0.800386349,
|
| 254 |
+
"r":0.7364834839,
|
| 255 |
+
"f":0.7671063797
|
| 256 |
},
|
| 257 |
"ccomp":{
|
| 258 |
+
"p":0.6472945892,
|
| 259 |
+
"r":0.6279160187,
|
| 260 |
+
"f":0.637458062
|
| 261 |
},
|
| 262 |
"advmod:rcomp":{
|
| 263 |
+
"p":0.8140243902,
|
| 264 |
+
"r":0.7396121884,
|
| 265 |
+
"f":0.7750362845
|
| 266 |
},
|
| 267 |
"nmod:topic":{
|
| 268 |
+
"p":0.351758794,
|
| 269 |
"r":0.2272727273,
|
| 270 |
+
"f":0.2761341223
|
| 271 |
},
|
| 272 |
"cop":{
|
| 273 |
+
"p":0.7524429967,
|
| 274 |
+
"r":0.5945945946,
|
| 275 |
+
"f":0.6642703091
|
| 276 |
},
|
| 277 |
"discourse":{
|
| 278 |
+
"p":0.5552434457,
|
| 279 |
+
"r":0.4892739274,
|
| 280 |
+
"f":0.5201754386
|
| 281 |
},
|
| 282 |
"neg":{
|
| 283 |
+
"p":0.8400597907,
|
| 284 |
+
"r":0.6682520809,
|
| 285 |
+
"f":0.7443708609
|
| 286 |
},
|
| 287 |
"aux:modal":{
|
| 288 |
+
"p":0.8646616541,
|
| 289 |
+
"r":0.8324715615,
|
| 290 |
+
"f":0.8482613277
|
| 291 |
},
|
| 292 |
"nmod":{
|
| 293 |
+
"p":0.7028753994,
|
| 294 |
+
"r":0.5970149254,
|
| 295 |
+
"f":0.6456346295
|
| 296 |
},
|
| 297 |
"aux:ba":{
|
| 298 |
+
"p":0.8453038674,
|
| 299 |
+
"r":0.8138297872,
|
| 300 |
+
"f":0.8292682927
|
| 301 |
},
|
| 302 |
"advmod:loc":{
|
| 303 |
+
"p":0.577689243,
|
| 304 |
+
"r":0.4302670623,
|
| 305 |
+
"f":0.4931972789
|
| 306 |
},
|
| 307 |
"aux:asp":{
|
| 308 |
+
"p":0.9067656766,
|
| 309 |
+
"r":0.8763955343,
|
| 310 |
+
"f":0.8913219789
|
| 311 |
},
|
| 312 |
"conj":{
|
| 313 |
+
"p":0.4907251265,
|
| 314 |
+
"r":0.4950850662,
|
| 315 |
+
"f":0.492895455
|
| 316 |
},
|
| 317 |
"nsubjpass":{
|
| 318 |
+
"p":0.7954545455,
|
| 319 |
+
"r":0.7,
|
| 320 |
+
"f":0.7446808511
|
| 321 |
},
|
| 322 |
"compound:vc":{
|
| 323 |
+
"p":0.4725274725,
|
| 324 |
+
"r":0.4455958549,
|
| 325 |
+
"f":0.4586666667
|
| 326 |
},
|
| 327 |
"advcl:loc":{
|
| 328 |
+
"p":0.4461538462,
|
| 329 |
+
"r":0.4142857143,
|
| 330 |
+
"f":0.4296296296
|
| 331 |
},
|
| 332 |
"cc":{
|
| 333 |
+
"p":0.7127962085,
|
| 334 |
+
"r":0.6672582076,
|
| 335 |
+
"f":0.6892758937
|
| 336 |
},
|
| 337 |
"advmod:dvp":{
|
| 338 |
+
"p":0.8307692308,
|
| 339 |
+
"r":0.6708074534,
|
| 340 |
+
"f":0.7422680412
|
| 341 |
},
|
| 342 |
+
"name":{
|
| 343 |
+
"p":0.619047619,
|
| 344 |
+
"r":0.4814814815,
|
| 345 |
+
"f":0.5416666667
|
| 346 |
},
|
| 347 |
"appos":{
|
| 348 |
+
"p":0.8877805486,
|
| 349 |
+
"r":0.8183908046,
|
| 350 |
+
"f":0.8516746411
|
| 351 |
},
|
| 352 |
"nmod:poss":{
|
| 353 |
+
"p":0.65625,
|
| 354 |
+
"r":0.4666666667,
|
| 355 |
+
"f":0.5454545455
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 356 |
},
|
| 357 |
"nsubj:xsubj":{
|
| 358 |
"p":0.0,
|
| 359 |
"r":0.0,
|
| 360 |
"f":0.0
|
| 361 |
},
|
| 362 |
+
"nmod:range":{
|
| 363 |
+
"p":0.7480314961,
|
| 364 |
+
"r":0.6375838926,
|
| 365 |
+
"f":0.6884057971
|
| 366 |
+
},
|
| 367 |
"parataxis:prnmod":{
|
| 368 |
+
"p":0.4857142857,
|
| 369 |
+
"r":0.1278195489,
|
| 370 |
+
"f":0.2023809524
|
| 371 |
},
|
| 372 |
"amod:ordmod":{
|
| 373 |
+
"p":0.5606060606,
|
| 374 |
"r":0.578125,
|
| 375 |
+
"f":0.5692307692
|
| 376 |
},
|
| 377 |
"erased":{
|
| 378 |
"p":0.0,
|
|
|
|
| 380 |
"f":0.0
|
| 381 |
},
|
| 382 |
"etc":{
|
| 383 |
+
"p":0.9285714286,
|
| 384 |
+
"r":0.9285714286,
|
| 385 |
+
"f":0.9285714286
|
| 386 |
}
|
| 387 |
},
|
| 388 |
+
"ents_p":0.7188227082,
|
| 389 |
+
"ents_r":0.679010989,
|
| 390 |
+
"ents_f":0.6983499096,
|
| 391 |
"ents_per_type":{
|
| 392 |
"DATE":{
|
| 393 |
+
"p":0.7758945386,
|
| 394 |
+
"r":0.8166501487,
|
| 395 |
+
"f":0.795750845
|
| 396 |
},
|
| 397 |
"GPE":{
|
| 398 |
+
"p":0.7566351777,
|
| 399 |
+
"r":0.8220918866,
|
| 400 |
+
"f":0.7880065589
|
| 401 |
},
|
| 402 |
"ORDINAL":{
|
| 403 |
+
"p":0.8764705882,
|
| 404 |
+
"r":0.7842105263,
|
| 405 |
+
"f":0.8277777778
|
| 406 |
},
|
| 407 |
"FAC":{
|
| 408 |
+
"p":0.4353741497,
|
| 409 |
+
"r":0.3440860215,
|
| 410 |
+
"f":0.3843843844
|
| 411 |
+
},
|
| 412 |
+
"PERSON":{
|
| 413 |
+
"p":0.7662082515,
|
| 414 |
+
"r":0.7538659794,
|
| 415 |
+
"f":0.7599870088
|
| 416 |
},
|
| 417 |
"ORG":{
|
| 418 |
+
"p":0.6975409836,
|
| 419 |
+
"r":0.6476407915,
|
| 420 |
+
"f":0.6716653512
|
| 421 |
},
|
| 422 |
"LOC":{
|
| 423 |
+
"p":0.4691780822,
|
| 424 |
+
"r":0.3682795699,
|
| 425 |
+
"f":0.4126506024
|
| 426 |
},
|
| 427 |
"QUANTITY":{
|
| 428 |
+
"p":0.7543859649,
|
| 429 |
+
"r":0.637037037,
|
| 430 |
+
"f":0.6907630522
|
| 431 |
},
|
| 432 |
"CARDINAL":{
|
| 433 |
+
"p":0.6059225513,
|
| 434 |
+
"r":0.5362903226,
|
| 435 |
+
"f":0.5689839572
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 436 |
},
|
| 437 |
"NORP":{
|
| 438 |
+
"p":0.6955128205,
|
| 439 |
+
"r":0.4558823529,
|
| 440 |
+
"f":0.5507614213
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 441 |
},
|
| 442 |
"TIME":{
|
| 443 |
+
"p":0.7452830189,
|
| 444 |
+
"r":0.7669902913,
|
| 445 |
+
"f":0.7559808612
|
| 446 |
},
|
| 447 |
+
"WORK_OF_ART":{
|
| 448 |
+
"p":0.5921052632,
|
| 449 |
+
"r":0.3,
|
| 450 |
+
"f":0.3982300885
|
| 451 |
},
|
| 452 |
+
"MONEY":{
|
| 453 |
+
"p":0.9322033898,
|
| 454 |
+
"r":0.8148148148,
|
| 455 |
+
"f":0.8695652174
|
| 456 |
},
|
| 457 |
"EVENT":{
|
| 458 |
+
"p":0.5625,
|
| 459 |
+
"r":0.4632352941,
|
| 460 |
+
"f":0.5080645161
|
| 461 |
+
},
|
| 462 |
+
"PERCENT":{
|
| 463 |
+
"p":0.8313253012,
|
| 464 |
+
"r":0.8313253012,
|
| 465 |
+
"f":0.8313253012
|
| 466 |
},
|
| 467 |
"PRODUCT":{
|
| 468 |
+
"p":0.125,
|
| 469 |
+
"r":0.0204081633,
|
| 470 |
+
"f":0.0350877193
|
| 471 |
},
|
| 472 |
"LAW":{
|
| 473 |
+
"p":0.5,
|
| 474 |
+
"r":0.2333333333,
|
| 475 |
+
"f":0.3181818182
|
| 476 |
},
|
| 477 |
"LANGUAGE":{
|
| 478 |
+
"p":0.5,
|
| 479 |
"r":0.7777777778,
|
| 480 |
+
"f":0.6086956522
|
| 481 |
}
|
| 482 |
},
|
| 483 |
+
"speed":7528.4602636561
|
| 484 |
},
|
| 485 |
"sources":[
|
| 486 |
{
|
ner/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 6380943
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:224290effa2168204cdcbdf9c7da73c8aa997e7047c1d0f23c460947789e2e9c
|
| 3 |
size 6380943
|
parser/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 308728
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8ca3ba63825c8bcf001ed54bbed5550d66389fc609995852645955b453c96ebd
|
| 3 |
size 308728
|
senter/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 213263
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45be269d1191ed595b2d41641469125d7cf75b1d9b7869299bfc951a0730cc0d
|
| 3 |
size 213263
|
tagger/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14785
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6007429942e26dcf377e11cc5e696d1f37af038509c81522fb5d31a9d79b77a
|
| 3 |
size 14785
|
tok2vec/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89728c92c19c93e2db07e658ddb533cdd56cd87063b5da43f03b0736e9afe9cd
|
| 3 |
+
size 6365607
|
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:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9daae015e8a5be9e4914cd9ac722d5f9a0d1d41b6f19c5b1c961cc576582103a
|
| 3 |
+
size 78020947
|