Commit
·
582cb9c
1
Parent(s):
c0f7334
Update spaCy pipeline
Browse files- README.md +19 -19
- accuracy.json +201 -201
- attribute_ruler/patterns +0 -0
- config.cfg +5 -4
- en_core_web_sm-any-py3-none-any.whl +2 -2
- meta.json +204 -204
- ner/model +2 -2
- parser/model +1 -1
- senter/model +1 -1
- tagger/model +1 -1
- tok2vec/model +2 -2
- tokenizer +0 -0
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/en#en_core_web_sm
|
| 54 |
|
|
@@ -57,8 +57,8 @@ English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
|
|
| 57 |
| Feature | Description |
|
| 58 |
| --- | --- |
|
| 59 |
| **Name** | `en_core_web_sm` |
|
| 60 |
-
| **Version** | `3.
|
| 61 |
-
| **spaCy** | `>=3.
|
| 62 |
| **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
| 63 |
| **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
|
| 64 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
|
@@ -84,16 +84,16 @@ English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter,
|
|
| 84 |
|
| 85 |
| Type | Score |
|
| 86 |
| --- | --- |
|
| 87 |
-
| `TOKEN_ACC` | 99.
|
| 88 |
| `TOKEN_P` | 99.57 |
|
| 89 |
| `TOKEN_R` | 99.58 |
|
| 90 |
| `TOKEN_F` | 99.57 |
|
| 91 |
-
| `TAG_ACC` | 97.
|
| 92 |
-
| `SENTS_P` |
|
| 93 |
-
| `SENTS_R` |
|
| 94 |
-
| `SENTS_F` | 90.
|
| 95 |
-
| `DEP_UAS` | 91.
|
| 96 |
-
| `DEP_LAS` | 89.
|
| 97 |
-
| `ENTS_P` | 84.
|
| 98 |
-
| `ENTS_R` | 84.
|
| 99 |
-
| `ENTS_F` | 84.
|
|
|
|
| 14 |
metrics:
|
| 15 |
- name: NER Precision
|
| 16 |
type: precision
|
| 17 |
+
value: 0.8454836771
|
| 18 |
- name: NER Recall
|
| 19 |
type: recall
|
| 20 |
+
value: 0.8456530449
|
| 21 |
- name: NER F Score
|
| 22 |
type: f_score
|
| 23 |
+
value: 0.8455683525
|
| 24 |
- task:
|
| 25 |
name: TAG
|
| 26 |
type: token-classification
|
| 27 |
metrics:
|
| 28 |
- name: TAG (XPOS) Accuracy
|
| 29 |
type: accuracy
|
| 30 |
+
value: 0.97246532
|
| 31 |
- task:
|
| 32 |
name: UNLABELED_DEPENDENCIES
|
| 33 |
type: token-classification
|
| 34 |
metrics:
|
| 35 |
- name: Unlabeled Attachment Score (UAS)
|
| 36 |
type: f_score
|
| 37 |
+
value: 0.9175304332
|
| 38 |
- task:
|
| 39 |
name: LABELED_DEPENDENCIES
|
| 40 |
type: token-classification
|
| 41 |
metrics:
|
| 42 |
- name: Labeled Attachment Score (LAS)
|
| 43 |
type: f_score
|
| 44 |
+
value: 0.89874821
|
| 45 |
- task:
|
| 46 |
name: SENTS
|
| 47 |
type: token-classification
|
| 48 |
metrics:
|
| 49 |
- name: Sentences F-Score
|
| 50 |
type: f_score
|
| 51 |
+
value: 0.9059485531
|
| 52 |
---
|
| 53 |
### Details: https://spacy.io/models/en#en_core_web_sm
|
| 54 |
|
|
|
|
| 57 |
| Feature | Description |
|
| 58 |
| --- | --- |
|
| 59 |
| **Name** | `en_core_web_sm` |
|
| 60 |
+
| **Version** | `3.5.0` |
|
| 61 |
+
| **spaCy** | `>=3.5.0,<3.6.0` |
|
| 62 |
| **Default Pipeline** | `tok2vec`, `tagger`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
| 63 |
| **Components** | `tok2vec`, `tagger`, `parser`, `senter`, `attribute_ruler`, `lemmatizer`, `ner` |
|
| 64 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
|
|
|
| 84 |
|
| 85 |
| Type | Score |
|
| 86 |
| --- | --- |
|
| 87 |
+
| `TOKEN_ACC` | 99.86 |
|
| 88 |
| `TOKEN_P` | 99.57 |
|
| 89 |
| `TOKEN_R` | 99.58 |
|
| 90 |
| `TOKEN_F` | 99.57 |
|
| 91 |
+
| `TAG_ACC` | 97.25 |
|
| 92 |
+
| `SENTS_P` | 92.02 |
|
| 93 |
+
| `SENTS_R` | 89.21 |
|
| 94 |
+
| `SENTS_F` | 90.59 |
|
| 95 |
+
| `DEP_UAS` | 91.75 |
|
| 96 |
+
| `DEP_LAS` | 89.87 |
|
| 97 |
+
| `ENTS_P` | 84.55 |
|
| 98 |
+
| `ENTS_R` | 84.57 |
|
| 99 |
+
| `ENTS_F` | 84.56 |
|
accuracy.json
CHANGED
|
@@ -1,330 +1,330 @@
|
|
| 1 |
{
|
| 2 |
-
"token_acc": 0.
|
| 3 |
"token_p": 0.9956819193,
|
| 4 |
"token_r": 0.9957659295,
|
| 5 |
"token_f": 0.9957239226,
|
| 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 |
"prep": {
|
| 14 |
-
"p": 0.
|
| 15 |
-
"r": 0.
|
| 16 |
-
"f": 0.
|
| 17 |
},
|
| 18 |
"det": {
|
| 19 |
-
"p": 0.
|
| 20 |
"r": 0.9781048683,
|
| 21 |
-
"f": 0.
|
| 22 |
},
|
| 23 |
"pobj": {
|
| 24 |
-
"p": 0.
|
| 25 |
-
"r": 0.
|
| 26 |
-
"f": 0.
|
| 27 |
},
|
| 28 |
"nsubj": {
|
| 29 |
-
"p": 0.
|
| 30 |
-
"r": 0.
|
| 31 |
-
"f": 0.
|
| 32 |
},
|
| 33 |
"aux": {
|
| 34 |
-
"p": 0.
|
| 35 |
-
"r": 0.
|
| 36 |
-
"f": 0.
|
| 37 |
},
|
| 38 |
"advmod": {
|
| 39 |
-
"p": 0.
|
| 40 |
-
"r": 0.
|
| 41 |
-
"f": 0.
|
| 42 |
},
|
| 43 |
"relcl": {
|
| 44 |
-
"p": 0.
|
| 45 |
-
"r": 0.
|
| 46 |
-
"f": 0.
|
| 47 |
},
|
| 48 |
"root": {
|
| 49 |
-
"p": 0.
|
| 50 |
-
"r": 0.
|
| 51 |
-
"f": 0.
|
| 52 |
},
|
| 53 |
"xcomp": {
|
| 54 |
-
"p": 0.
|
| 55 |
-
"r": 0.
|
| 56 |
-
"f": 0.
|
| 57 |
},
|
| 58 |
"amod": {
|
| 59 |
-
"p": 0.
|
| 60 |
-
"r": 0.
|
| 61 |
-
"f": 0.
|
| 62 |
},
|
| 63 |
"compound": {
|
| 64 |
-
"p": 0.
|
| 65 |
-
"r": 0.
|
| 66 |
-
"f": 0.
|
| 67 |
},
|
| 68 |
"poss": {
|
| 69 |
-
"p": 0.
|
| 70 |
-
"r": 0.
|
| 71 |
-
"f": 0.
|
| 72 |
},
|
| 73 |
"ccomp": {
|
| 74 |
-
"p": 0.
|
| 75 |
-
"r": 0.
|
| 76 |
-
"f": 0.
|
| 77 |
},
|
| 78 |
"attr": {
|
| 79 |
-
"p": 0.
|
| 80 |
-
"r": 0.
|
| 81 |
-
"f": 0.
|
| 82 |
},
|
| 83 |
"case": {
|
| 84 |
-
"p": 0.
|
| 85 |
"r": 0.9914914915,
|
| 86 |
-
"f": 0.
|
| 87 |
},
|
| 88 |
"mark": {
|
| 89 |
-
"p": 0.
|
| 90 |
-
"r": 0.
|
| 91 |
-
"f": 0.
|
| 92 |
},
|
| 93 |
"intj": {
|
| 94 |
-
"p": 0.
|
| 95 |
-
"r": 0.
|
| 96 |
-
"f": 0.
|
| 97 |
},
|
| 98 |
"advcl": {
|
| 99 |
-
"p": 0.
|
| 100 |
-
"r": 0.
|
| 101 |
-
"f": 0.
|
| 102 |
},
|
| 103 |
"cc": {
|
| 104 |
-
"p": 0.
|
| 105 |
-
"r": 0.
|
| 106 |
-
"f": 0.
|
| 107 |
},
|
| 108 |
"neg": {
|
| 109 |
-
"p": 0.
|
| 110 |
-
"r": 0.
|
| 111 |
-
"f": 0.
|
| 112 |
},
|
| 113 |
"conj": {
|
| 114 |
-
"p": 0.
|
| 115 |
-
"r": 0.
|
| 116 |
-
"f": 0.
|
| 117 |
},
|
| 118 |
"nsubjpass": {
|
| 119 |
-
"p": 0.
|
| 120 |
-
"r": 0.
|
| 121 |
-
"f": 0.
|
| 122 |
},
|
| 123 |
"auxpass": {
|
| 124 |
-
"p": 0.
|
| 125 |
-
"r": 0.
|
| 126 |
-
"f": 0.
|
| 127 |
},
|
| 128 |
"dobj": {
|
| 129 |
-
"p": 0.
|
| 130 |
-
"r": 0.
|
| 131 |
-
"f": 0.
|
| 132 |
},
|
| 133 |
"nummod": {
|
| 134 |
-
"p": 0.
|
| 135 |
-
"r": 0.
|
| 136 |
-
"f": 0.
|
| 137 |
},
|
| 138 |
"npadvmod": {
|
| 139 |
-
"p": 0.
|
| 140 |
-
"r": 0.
|
| 141 |
-
"f": 0.
|
| 142 |
},
|
| 143 |
"prt": {
|
| 144 |
-
"p": 0.
|
| 145 |
-
"r": 0.
|
| 146 |
-
"f": 0.
|
| 147 |
},
|
| 148 |
"pcomp": {
|
| 149 |
-
"p": 0.
|
| 150 |
-
"r": 0.
|
| 151 |
-
"f": 0.
|
| 152 |
},
|
| 153 |
"expl": {
|
| 154 |
-
"p": 0.
|
| 155 |
-
"r": 0.
|
| 156 |
-
"f": 0.
|
| 157 |
},
|
| 158 |
"acl": {
|
| 159 |
-
"p": 0.
|
| 160 |
-
"r": 0.
|
| 161 |
-
"f": 0.
|
| 162 |
},
|
| 163 |
"agent": {
|
| 164 |
-
"p": 0.
|
| 165 |
-
"r": 0.
|
| 166 |
-
"f": 0.
|
| 167 |
},
|
| 168 |
"dative": {
|
| 169 |
-
"p": 0.
|
| 170 |
-
"r": 0.
|
| 171 |
-
"f": 0.
|
| 172 |
},
|
| 173 |
"acomp": {
|
| 174 |
-
"p": 0.
|
| 175 |
-
"r": 0.
|
| 176 |
-
"f": 0.
|
| 177 |
},
|
| 178 |
"dep": {
|
| 179 |
-
"p": 0.
|
| 180 |
-
"r": 0.
|
| 181 |
-
"f": 0.
|
| 182 |
},
|
| 183 |
"csubj": {
|
| 184 |
-
"p": 0.
|
| 185 |
-
"r": 0.
|
| 186 |
-
"f": 0.
|
| 187 |
},
|
| 188 |
"quantmod": {
|
| 189 |
-
"p": 0.
|
| 190 |
-
"r": 0.
|
| 191 |
-
"f": 0.
|
| 192 |
},
|
| 193 |
"nmod": {
|
| 194 |
-
"p": 0.
|
| 195 |
-
"r": 0.
|
| 196 |
-
"f": 0.
|
| 197 |
},
|
| 198 |
"appos": {
|
| 199 |
-
"p": 0.
|
| 200 |
-
"r": 0.
|
| 201 |
-
"f": 0.
|
| 202 |
},
|
| 203 |
"predet": {
|
| 204 |
-
"p": 0.
|
| 205 |
-
"r": 0.
|
| 206 |
-
"f": 0.
|
| 207 |
},
|
| 208 |
"preconj": {
|
| 209 |
-
"p": 0.
|
| 210 |
-
"r": 0.
|
| 211 |
-
"f": 0.
|
| 212 |
},
|
| 213 |
"oprd": {
|
| 214 |
-
"p": 0.
|
| 215 |
-
"r": 0.
|
| 216 |
-
"f": 0.
|
| 217 |
},
|
| 218 |
"parataxis": {
|
| 219 |
-
"p": 0.
|
| 220 |
-
"r": 0.
|
| 221 |
-
"f": 0.
|
| 222 |
},
|
| 223 |
"meta": {
|
| 224 |
-
"p": 0.
|
| 225 |
-
"r": 0.
|
| 226 |
-
"f": 0.
|
| 227 |
},
|
| 228 |
"csubjpass": {
|
| 229 |
-
"p": 0.
|
| 230 |
-
"r": 0.
|
| 231 |
-
"f": 0.
|
| 232 |
}
|
| 233 |
},
|
| 234 |
-
"ents_p": 0.
|
| 235 |
-
"ents_r": 0.
|
| 236 |
-
"ents_f": 0.
|
| 237 |
"ents_per_type": {
|
| 238 |
"DATE": {
|
| 239 |
-
"p": 0.
|
| 240 |
-
"r": 0.
|
| 241 |
-
"f": 0.
|
| 242 |
},
|
| 243 |
"GPE": {
|
| 244 |
-
"p": 0.
|
| 245 |
-
"r": 0.
|
| 246 |
-
"f": 0.
|
| 247 |
-
},
|
| 248 |
-
"ORDINAL": {
|
| 249 |
-
"p": 0.7703081232,
|
| 250 |
-
"r": 0.8540372671,
|
| 251 |
-
"f": 0.8100147275
|
| 252 |
},
|
| 253 |
"ORG": {
|
| 254 |
-
"p": 0.
|
| 255 |
-
"r": 0.
|
| 256 |
-
"f": 0.
|
| 257 |
},
|
| 258 |
"CARDINAL": {
|
| 259 |
-
"p": 0.
|
| 260 |
-
"r": 0.
|
| 261 |
-
"f": 0.
|
| 262 |
-
},
|
| 263 |
-
"LOC": {
|
| 264 |
-
"p": 0.7148148148,
|
| 265 |
-
"r": 0.6146496815,
|
| 266 |
-
"f": 0.6609589041
|
| 267 |
},
|
| 268 |
"PERSON": {
|
| 269 |
-
"p": 0.
|
| 270 |
-
"r": 0.
|
| 271 |
-
"f": 0.
|
| 272 |
},
|
| 273 |
"NORP": {
|
| 274 |
-
"p": 0.
|
| 275 |
-
"r": 0.
|
| 276 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 277 |
},
|
| 278 |
"QUANTITY": {
|
| 279 |
-
"p": 0.
|
| 280 |
-
"r": 0.
|
| 281 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 282 |
},
|
| 283 |
"FAC": {
|
| 284 |
-
"p": 0.
|
| 285 |
-
"r": 0.
|
| 286 |
-
"f": 0.
|
| 287 |
},
|
| 288 |
"TIME": {
|
| 289 |
-
"p": 0.
|
| 290 |
-
"r": 0.
|
| 291 |
-
"f": 0.
|
| 292 |
},
|
| 293 |
-
"
|
| 294 |
-
"p": 0.
|
| 295 |
-
"r": 0.
|
| 296 |
-
"f": 0.
|
| 297 |
},
|
| 298 |
"WORK_OF_ART": {
|
| 299 |
-
"p": 0.
|
| 300 |
-
"r": 0.
|
| 301 |
-
"f": 0.
|
| 302 |
},
|
| 303 |
-
"
|
| 304 |
-
"p": 0.
|
| 305 |
-
"r": 0.
|
| 306 |
-
"f": 0.
|
| 307 |
},
|
| 308 |
"MONEY": {
|
| 309 |
-
"p": 0.
|
| 310 |
-
"r": 0.
|
| 311 |
-
"f": 0.
|
| 312 |
},
|
| 313 |
-
"
|
| 314 |
-
"p": 0.
|
| 315 |
-
"r": 0.
|
| 316 |
-
"f": 0.
|
| 317 |
},
|
| 318 |
"PERCENT": {
|
| 319 |
-
"p": 0.
|
| 320 |
"r": 0.8790199081,
|
| 321 |
-
"f": 0.
|
| 322 |
},
|
| 323 |
"LANGUAGE": {
|
| 324 |
-
"p": 0.
|
| 325 |
-
"r": 0.
|
| 326 |
-
"f": 0.
|
| 327 |
}
|
| 328 |
},
|
| 329 |
-
"speed":
|
| 330 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"token_acc": 0.9986194413,
|
| 3 |
"token_p": 0.9956819193,
|
| 4 |
"token_r": 0.9957659295,
|
| 5 |
"token_f": 0.9957239226,
|
| 6 |
+
"tag_acc": 0.97246532,
|
| 7 |
+
"sents_p": 0.9201877934,
|
| 8 |
+
"sents_r": 0.8921432812,
|
| 9 |
+
"sents_f": 0.9059485531,
|
| 10 |
+
"dep_uas": 0.9175304332,
|
| 11 |
+
"dep_las": 0.89874821,
|
| 12 |
"dep_las_per_type": {
|
| 13 |
"prep": {
|
| 14 |
+
"p": 0.853521338,
|
| 15 |
+
"r": 0.8635932461,
|
| 16 |
+
"f": 0.8585277532
|
| 17 |
},
|
| 18 |
"det": {
|
| 19 |
+
"p": 0.9763930156,
|
| 20 |
"r": 0.9781048683,
|
| 21 |
+
"f": 0.9772481923
|
| 22 |
},
|
| 23 |
"pobj": {
|
| 24 |
+
"p": 0.9613764045,
|
| 25 |
+
"r": 0.967681131,
|
| 26 |
+
"f": 0.9645184649
|
| 27 |
},
|
| 28 |
"nsubj": {
|
| 29 |
+
"p": 0.9565737052,
|
| 30 |
+
"r": 0.9467250821,
|
| 31 |
+
"f": 0.9516239128
|
| 32 |
},
|
| 33 |
"aux": {
|
| 34 |
+
"p": 0.9815061794,
|
| 35 |
+
"r": 0.9827294578,
|
| 36 |
+
"f": 0.9821174377
|
| 37 |
},
|
| 38 |
"advmod": {
|
| 39 |
+
"p": 0.8548033091,
|
| 40 |
+
"r": 0.8519266364,
|
| 41 |
+
"f": 0.8533625485
|
| 42 |
},
|
| 43 |
"relcl": {
|
| 44 |
+
"p": 0.7571736011,
|
| 45 |
+
"r": 0.7659651669,
|
| 46 |
+
"f": 0.7615440115
|
| 47 |
},
|
| 48 |
"root": {
|
| 49 |
+
"p": 0.9195942266,
|
| 50 |
+
"r": 0.8910218352,
|
| 51 |
+
"f": 0.9050825879
|
| 52 |
},
|
| 53 |
"xcomp": {
|
| 54 |
+
"p": 0.8836222144,
|
| 55 |
+
"r": 0.8966259871,
|
| 56 |
+
"f": 0.8900766079
|
| 57 |
},
|
| 58 |
"amod": {
|
| 59 |
+
"p": 0.9174389766,
|
| 60 |
+
"r": 0.9107223842,
|
| 61 |
+
"f": 0.9140683422
|
| 62 |
},
|
| 63 |
"compound": {
|
| 64 |
+
"p": 0.9126489559,
|
| 65 |
+
"r": 0.9298284696,
|
| 66 |
+
"f": 0.9211586207
|
| 67 |
},
|
| 68 |
"poss": {
|
| 69 |
+
"p": 0.9739583333,
|
| 70 |
+
"r": 0.9786634461,
|
| 71 |
+
"f": 0.9763052209
|
| 72 |
},
|
| 73 |
"ccomp": {
|
| 74 |
+
"p": 0.7671207315,
|
| 75 |
+
"r": 0.8372708758,
|
| 76 |
+
"f": 0.8006621872
|
| 77 |
},
|
| 78 |
"attr": {
|
| 79 |
+
"p": 0.899837794,
|
| 80 |
+
"r": 0.93313709,
|
| 81 |
+
"f": 0.9161849711
|
| 82 |
},
|
| 83 |
"case": {
|
| 84 |
+
"p": 0.9787549407,
|
| 85 |
"r": 0.9914914915,
|
| 86 |
+
"f": 0.9850820487
|
| 87 |
},
|
| 88 |
"mark": {
|
| 89 |
+
"p": 0.9068783069,
|
| 90 |
+
"r": 0.9083200848,
|
| 91 |
+
"f": 0.9075986232
|
| 92 |
},
|
| 93 |
"intj": {
|
| 94 |
+
"p": 0.6717131474,
|
| 95 |
+
"r": 0.6175824176,
|
| 96 |
+
"f": 0.6435114504
|
| 97 |
},
|
| 98 |
"advcl": {
|
| 99 |
+
"p": 0.6633986928,
|
| 100 |
+
"r": 0.6645681189,
|
| 101 |
+
"f": 0.6639828909
|
| 102 |
},
|
| 103 |
"cc": {
|
| 104 |
+
"p": 0.8323511726,
|
| 105 |
+
"r": 0.8277717976,
|
| 106 |
+
"f": 0.8300551691
|
| 107 |
},
|
| 108 |
"neg": {
|
| 109 |
+
"p": 0.9466865969,
|
| 110 |
+
"r": 0.9533366784,
|
| 111 |
+
"f": 0.95
|
| 112 |
},
|
| 113 |
"conj": {
|
| 114 |
+
"p": 0.7567333828,
|
| 115 |
+
"r": 0.7710221551,
|
| 116 |
+
"f": 0.763810949
|
| 117 |
},
|
| 118 |
"nsubjpass": {
|
| 119 |
+
"p": 0.9182939363,
|
| 120 |
+
"r": 0.9164102564,
|
| 121 |
+
"f": 0.9173511294
|
| 122 |
},
|
| 123 |
"auxpass": {
|
| 124 |
+
"p": 0.9501335708,
|
| 125 |
+
"r": 0.9722095672,
|
| 126 |
+
"f": 0.9610448097
|
| 127 |
},
|
| 128 |
"dobj": {
|
| 129 |
+
"p": 0.9229805886,
|
| 130 |
+
"r": 0.9396764682,
|
| 131 |
+
"f": 0.9312537019
|
| 132 |
},
|
| 133 |
"nummod": {
|
| 134 |
+
"p": 0.9379292801,
|
| 135 |
+
"r": 0.9310606061,
|
| 136 |
+
"f": 0.9344823216
|
| 137 |
},
|
| 138 |
"npadvmod": {
|
| 139 |
+
"p": 0.7629658087,
|
| 140 |
+
"r": 0.7055062167,
|
| 141 |
+
"f": 0.7331118494
|
| 142 |
},
|
| 143 |
"prt": {
|
| 144 |
+
"p": 0.8118323747,
|
| 145 |
+
"r": 0.8853046595,
|
| 146 |
+
"f": 0.8469781397
|
| 147 |
},
|
| 148 |
"pcomp": {
|
| 149 |
+
"p": 0.8835714286,
|
| 150 |
+
"r": 0.8662464986,
|
| 151 |
+
"f": 0.8748231966
|
| 152 |
},
|
| 153 |
"expl": {
|
| 154 |
+
"p": 0.9851380042,
|
| 155 |
+
"r": 0.9935760171,
|
| 156 |
+
"f": 0.9893390192
|
| 157 |
},
|
| 158 |
"acl": {
|
| 159 |
+
"p": 0.742010459,
|
| 160 |
+
"r": 0.6966721222,
|
| 161 |
+
"f": 0.7186268993
|
| 162 |
},
|
| 163 |
"agent": {
|
| 164 |
+
"p": 0.9034482759,
|
| 165 |
+
"r": 0.9390681004,
|
| 166 |
+
"f": 0.920913884
|
| 167 |
},
|
| 168 |
"dative": {
|
| 169 |
+
"p": 0.8,
|
| 170 |
+
"r": 0.6972477064,
|
| 171 |
+
"f": 0.7450980392
|
| 172 |
},
|
| 173 |
"acomp": {
|
| 174 |
+
"p": 0.9020594966,
|
| 175 |
+
"r": 0.893877551,
|
| 176 |
+
"f": 0.8979498861
|
| 177 |
},
|
| 178 |
"dep": {
|
| 179 |
+
"p": 0.4147286822,
|
| 180 |
+
"r": 0.1737012987,
|
| 181 |
+
"f": 0.2448512586
|
| 182 |
},
|
| 183 |
"csubj": {
|
| 184 |
+
"p": 0.6983240223,
|
| 185 |
+
"r": 0.7396449704,
|
| 186 |
+
"f": 0.7183908046
|
| 187 |
},
|
| 188 |
"quantmod": {
|
| 189 |
+
"p": 0.8727436823,
|
| 190 |
+
"r": 0.7855402112,
|
| 191 |
+
"f": 0.8268490808
|
| 192 |
},
|
| 193 |
"nmod": {
|
| 194 |
+
"p": 0.7498033045,
|
| 195 |
+
"r": 0.5807434491,
|
| 196 |
+
"f": 0.654532967
|
| 197 |
},
|
| 198 |
"appos": {
|
| 199 |
+
"p": 0.7048498845,
|
| 200 |
+
"r": 0.6620390456,
|
| 201 |
+
"f": 0.6827740492
|
| 202 |
},
|
| 203 |
"predet": {
|
| 204 |
+
"p": 0.8299595142,
|
| 205 |
+
"r": 0.8798283262,
|
| 206 |
+
"f": 0.8541666667
|
| 207 |
},
|
| 208 |
"preconj": {
|
| 209 |
+
"p": 0.5544554455,
|
| 210 |
+
"r": 0.6511627907,
|
| 211 |
+
"f": 0.5989304813
|
| 212 |
},
|
| 213 |
"oprd": {
|
| 214 |
+
"p": 0.8013245033,
|
| 215 |
+
"r": 0.7223880597,
|
| 216 |
+
"f": 0.759811617
|
| 217 |
},
|
| 218 |
"parataxis": {
|
| 219 |
+
"p": 0.6428571429,
|
| 220 |
+
"r": 0.4880694143,
|
| 221 |
+
"f": 0.5548705302
|
| 222 |
},
|
| 223 |
"meta": {
|
| 224 |
+
"p": 0.3770491803,
|
| 225 |
+
"r": 0.4423076923,
|
| 226 |
+
"f": 0.407079646
|
| 227 |
},
|
| 228 |
"csubjpass": {
|
| 229 |
+
"p": 0.5555555556,
|
| 230 |
+
"r": 0.8333333333,
|
| 231 |
+
"f": 0.6666666667
|
| 232 |
}
|
| 233 |
},
|
| 234 |
+
"ents_p": 0.8454836771,
|
| 235 |
+
"ents_r": 0.8456530449,
|
| 236 |
+
"ents_f": 0.8455683525,
|
| 237 |
"ents_per_type": {
|
| 238 |
"DATE": {
|
| 239 |
+
"p": 0.8603213844,
|
| 240 |
+
"r": 0.8838095238,
|
| 241 |
+
"f": 0.8719072972
|
| 242 |
},
|
| 243 |
"GPE": {
|
| 244 |
+
"p": 0.9146932953,
|
| 245 |
+
"r": 0.8942817294,
|
| 246 |
+
"f": 0.9043723554
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 247 |
},
|
| 248 |
"ORG": {
|
| 249 |
+
"p": 0.7955942623,
|
| 250 |
+
"r": 0.8234358431,
|
| 251 |
+
"f": 0.8092756644
|
| 252 |
},
|
| 253 |
"CARDINAL": {
|
| 254 |
+
"p": 0.8149171271,
|
| 255 |
+
"r": 0.8769322235,
|
| 256 |
+
"f": 0.8447880871
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 257 |
},
|
| 258 |
"PERSON": {
|
| 259 |
+
"p": 0.8617758186,
|
| 260 |
+
"r": 0.8932767624,
|
| 261 |
+
"f": 0.8772435897
|
| 262 |
},
|
| 263 |
"NORP": {
|
| 264 |
+
"p": 0.8957006369,
|
| 265 |
+
"r": 0.9,
|
| 266 |
+
"f": 0.8978451716
|
| 267 |
+
},
|
| 268 |
+
"ORDINAL": {
|
| 269 |
+
"p": 0.7844827586,
|
| 270 |
+
"r": 0.847826087,
|
| 271 |
+
"f": 0.8149253731
|
| 272 |
},
|
| 273 |
"QUANTITY": {
|
| 274 |
+
"p": 0.8529411765,
|
| 275 |
+
"r": 0.6373626374,
|
| 276 |
+
"f": 0.7295597484
|
| 277 |
+
},
|
| 278 |
+
"LOC": {
|
| 279 |
+
"p": 0.7210884354,
|
| 280 |
+
"r": 0.6751592357,
|
| 281 |
+
"f": 0.6973684211
|
| 282 |
},
|
| 283 |
"FAC": {
|
| 284 |
+
"p": 0.358490566,
|
| 285 |
+
"r": 0.2923076923,
|
| 286 |
+
"f": 0.3220338983
|
| 287 |
},
|
| 288 |
"TIME": {
|
| 289 |
+
"p": 0.7413793103,
|
| 290 |
+
"r": 0.7543859649,
|
| 291 |
+
"f": 0.747826087
|
| 292 |
},
|
| 293 |
+
"PRODUCT": {
|
| 294 |
+
"p": 0.5591397849,
|
| 295 |
+
"r": 0.2464454976,
|
| 296 |
+
"f": 0.3421052632
|
| 297 |
},
|
| 298 |
"WORK_OF_ART": {
|
| 299 |
+
"p": 0.4885496183,
|
| 300 |
+
"r": 0.3298969072,
|
| 301 |
+
"f": 0.3938461538
|
| 302 |
},
|
| 303 |
+
"EVENT": {
|
| 304 |
+
"p": 0.6428571429,
|
| 305 |
+
"r": 0.3103448276,
|
| 306 |
+
"f": 0.4186046512
|
| 307 |
},
|
| 308 |
"MONEY": {
|
| 309 |
+
"p": 0.9071428571,
|
| 310 |
+
"r": 0.8996458087,
|
| 311 |
+
"f": 0.9033787789
|
| 312 |
},
|
| 313 |
+
"LAW": {
|
| 314 |
+
"p": 0.5454545455,
|
| 315 |
+
"r": 0.46875,
|
| 316 |
+
"f": 0.5042016807
|
| 317 |
},
|
| 318 |
"PERCENT": {
|
| 319 |
+
"p": 0.9184,
|
| 320 |
"r": 0.8790199081,
|
| 321 |
+
"f": 0.8982785603
|
| 322 |
},
|
| 323 |
"LANGUAGE": {
|
| 324 |
+
"p": 0.8,
|
| 325 |
+
"r": 0.625,
|
| 326 |
+
"f": 0.701754386
|
| 327 |
}
|
| 328 |
},
|
| 329 |
+
"speed": 9611.7804215009
|
| 330 |
}
|
attribute_ruler/patterns
CHANGED
|
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
|
|
|
config.cfg
CHANGED
|
@@ -54,8 +54,8 @@ nO = null
|
|
| 54 |
[components.ner.model.tok2vec.embed]
|
| 55 |
@architectures = "spacy.MultiHashEmbed.v2"
|
| 56 |
width = 96
|
| 57 |
-
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"
|
| 58 |
-
rows = [5000,1000,2500,2500
|
| 59 |
include_static_vectors = false
|
| 60 |
|
| 61 |
[components.ner.model.tok2vec.encode]
|
|
@@ -139,8 +139,8 @@ factory = "tok2vec"
|
|
| 139 |
[components.tok2vec.model.embed]
|
| 140 |
@architectures = "spacy.MultiHashEmbed.v2"
|
| 141 |
width = ${components.tok2vec.model.encode:width}
|
| 142 |
-
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY"]
|
| 143 |
-
rows = [5000,1000,2500,2500,50]
|
| 144 |
include_static_vectors = false
|
| 145 |
|
| 146 |
[components.tok2vec.model.encode]
|
|
@@ -182,6 +182,7 @@ eval_frequency = 1000
|
|
| 182 |
frozen_components = []
|
| 183 |
before_to_disk = null
|
| 184 |
annotating_components = []
|
|
|
|
| 185 |
|
| 186 |
[training.batcher]
|
| 187 |
@batchers = "spacy.batch_by_words.v1"
|
|
|
|
| 54 |
[components.ner.model.tok2vec.embed]
|
| 55 |
@architectures = "spacy.MultiHashEmbed.v2"
|
| 56 |
width = 96
|
| 57 |
+
attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
|
| 58 |
+
rows = [5000,1000,2500,2500]
|
| 59 |
include_static_vectors = false
|
| 60 |
|
| 61 |
[components.ner.model.tok2vec.encode]
|
|
|
|
| 139 |
[components.tok2vec.model.embed]
|
| 140 |
@architectures = "spacy.MultiHashEmbed.v2"
|
| 141 |
width = ${components.tok2vec.model.encode:width}
|
| 142 |
+
attrs = ["NORM","PREFIX","SUFFIX","SHAPE","SPACY","IS_SPACE"]
|
| 143 |
+
rows = [5000,1000,2500,2500,50,50]
|
| 144 |
include_static_vectors = false
|
| 145 |
|
| 146 |
[components.tok2vec.model.encode]
|
|
|
|
| 182 |
frozen_components = []
|
| 183 |
before_to_disk = null
|
| 184 |
annotating_components = []
|
| 185 |
+
before_update = null
|
| 186 |
|
| 187 |
[training.batcher]
|
| 188 |
@batchers = "spacy.batch_by_words.v1"
|
en_core_web_sm-any-py3-none-any.whl
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0964370218b7e1672a30ac50d72cdc6b16f7c867496f1d60925691188f4d2510
|
| 3 |
+
size 12803284
|
meta.json
CHANGED
|
@@ -1,14 +1,14 @@
|
|
| 1 |
{
|
| 2 |
"lang":"en",
|
| 3 |
"name":"core_web_sm",
|
| 4 |
-
"version":"3.
|
| 5 |
"description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
|
| 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":0,
|
| 14 |
"vectors":0,
|
|
@@ -166,334 +166,334 @@
|
|
| 166 |
"senter"
|
| 167 |
],
|
| 168 |
"performance":{
|
| 169 |
-
"token_acc":0.
|
| 170 |
"token_p":0.9956819193,
|
| 171 |
"token_r":0.9957659295,
|
| 172 |
"token_f":0.9957239226,
|
| 173 |
-
"tag_acc":0.
|
| 174 |
-
"sents_p":0.
|
| 175 |
-
"sents_r":0.
|
| 176 |
-
"sents_f":0.
|
| 177 |
-
"dep_uas":0.
|
| 178 |
-
"dep_las":0.
|
| 179 |
"dep_las_per_type":{
|
| 180 |
"prep":{
|
| 181 |
-
"p":0.
|
| 182 |
-
"r":0.
|
| 183 |
-
"f":0.
|
| 184 |
},
|
| 185 |
"det":{
|
| 186 |
-
"p":0.
|
| 187 |
"r":0.9781048683,
|
| 188 |
-
"f":0.
|
| 189 |
},
|
| 190 |
"pobj":{
|
| 191 |
-
"p":0.
|
| 192 |
-
"r":0.
|
| 193 |
-
"f":0.
|
| 194 |
},
|
| 195 |
"nsubj":{
|
| 196 |
-
"p":0.
|
| 197 |
-
"r":0.
|
| 198 |
-
"f":0.
|
| 199 |
},
|
| 200 |
"aux":{
|
| 201 |
-
"p":0.
|
| 202 |
-
"r":0.
|
| 203 |
-
"f":0.
|
| 204 |
},
|
| 205 |
"advmod":{
|
| 206 |
-
"p":0.
|
| 207 |
-
"r":0.
|
| 208 |
-
"f":0.
|
| 209 |
},
|
| 210 |
"relcl":{
|
| 211 |
-
"p":0.
|
| 212 |
-
"r":0.
|
| 213 |
-
"f":0.
|
| 214 |
},
|
| 215 |
"root":{
|
| 216 |
-
"p":0.
|
| 217 |
-
"r":0.
|
| 218 |
-
"f":0.
|
| 219 |
},
|
| 220 |
"xcomp":{
|
| 221 |
-
"p":0.
|
| 222 |
-
"r":0.
|
| 223 |
-
"f":0.
|
| 224 |
},
|
| 225 |
"amod":{
|
| 226 |
-
"p":0.
|
| 227 |
-
"r":0.
|
| 228 |
-
"f":0.
|
| 229 |
},
|
| 230 |
"compound":{
|
| 231 |
-
"p":0.
|
| 232 |
-
"r":0.
|
| 233 |
-
"f":0.
|
| 234 |
},
|
| 235 |
"poss":{
|
| 236 |
-
"p":0.
|
| 237 |
-
"r":0.
|
| 238 |
-
"f":0.
|
| 239 |
},
|
| 240 |
"ccomp":{
|
| 241 |
-
"p":0.
|
| 242 |
-
"r":0.
|
| 243 |
-
"f":0.
|
| 244 |
},
|
| 245 |
"attr":{
|
| 246 |
-
"p":0.
|
| 247 |
-
"r":0.
|
| 248 |
-
"f":0.
|
| 249 |
},
|
| 250 |
"case":{
|
| 251 |
-
"p":0.
|
| 252 |
"r":0.9914914915,
|
| 253 |
-
"f":0.
|
| 254 |
},
|
| 255 |
"mark":{
|
| 256 |
-
"p":0.
|
| 257 |
-
"r":0.
|
| 258 |
-
"f":0.
|
| 259 |
},
|
| 260 |
"intj":{
|
| 261 |
-
"p":0.
|
| 262 |
-
"r":0.
|
| 263 |
-
"f":0.
|
| 264 |
},
|
| 265 |
"advcl":{
|
| 266 |
-
"p":0.
|
| 267 |
-
"r":0.
|
| 268 |
-
"f":0.
|
| 269 |
},
|
| 270 |
"cc":{
|
| 271 |
-
"p":0.
|
| 272 |
-
"r":0.
|
| 273 |
-
"f":0.
|
| 274 |
},
|
| 275 |
"neg":{
|
| 276 |
-
"p":0.
|
| 277 |
-
"r":0.
|
| 278 |
-
"f":0.
|
| 279 |
},
|
| 280 |
"conj":{
|
| 281 |
-
"p":0.
|
| 282 |
-
"r":0.
|
| 283 |
-
"f":0.
|
| 284 |
},
|
| 285 |
"nsubjpass":{
|
| 286 |
-
"p":0.
|
| 287 |
-
"r":0.
|
| 288 |
-
"f":0.
|
| 289 |
},
|
| 290 |
"auxpass":{
|
| 291 |
-
"p":0.
|
| 292 |
-
"r":0.
|
| 293 |
-
"f":0.
|
| 294 |
},
|
| 295 |
"dobj":{
|
| 296 |
-
"p":0.
|
| 297 |
-
"r":0.
|
| 298 |
-
"f":0.
|
| 299 |
},
|
| 300 |
"nummod":{
|
| 301 |
-
"p":0.
|
| 302 |
-
"r":0.
|
| 303 |
-
"f":0.
|
| 304 |
},
|
| 305 |
"npadvmod":{
|
| 306 |
-
"p":0.
|
| 307 |
-
"r":0.
|
| 308 |
-
"f":0.
|
| 309 |
},
|
| 310 |
"prt":{
|
| 311 |
-
"p":0.
|
| 312 |
-
"r":0.
|
| 313 |
-
"f":0.
|
| 314 |
},
|
| 315 |
"pcomp":{
|
| 316 |
-
"p":0.
|
| 317 |
-
"r":0.
|
| 318 |
-
"f":0.
|
| 319 |
},
|
| 320 |
"expl":{
|
| 321 |
-
"p":0.
|
| 322 |
-
"r":0.
|
| 323 |
-
"f":0.
|
| 324 |
},
|
| 325 |
"acl":{
|
| 326 |
-
"p":0.
|
| 327 |
-
"r":0.
|
| 328 |
-
"f":0.
|
| 329 |
},
|
| 330 |
"agent":{
|
| 331 |
-
"p":0.
|
| 332 |
-
"r":0.
|
| 333 |
-
"f":0.
|
| 334 |
},
|
| 335 |
"dative":{
|
| 336 |
-
"p":0.
|
| 337 |
-
"r":0.
|
| 338 |
-
"f":0.
|
| 339 |
},
|
| 340 |
"acomp":{
|
| 341 |
-
"p":0.
|
| 342 |
-
"r":0.
|
| 343 |
-
"f":0.
|
| 344 |
},
|
| 345 |
"dep":{
|
| 346 |
-
"p":0.
|
| 347 |
-
"r":0.
|
| 348 |
-
"f":0.
|
| 349 |
},
|
| 350 |
"csubj":{
|
| 351 |
-
"p":0.
|
| 352 |
-
"r":0.
|
| 353 |
-
"f":0.
|
| 354 |
},
|
| 355 |
"quantmod":{
|
| 356 |
-
"p":0.
|
| 357 |
-
"r":0.
|
| 358 |
-
"f":0.
|
| 359 |
},
|
| 360 |
"nmod":{
|
| 361 |
-
"p":0.
|
| 362 |
-
"r":0.
|
| 363 |
-
"f":0.
|
| 364 |
},
|
| 365 |
"appos":{
|
| 366 |
-
"p":0.
|
| 367 |
-
"r":0.
|
| 368 |
-
"f":0.
|
| 369 |
},
|
| 370 |
"predet":{
|
| 371 |
-
"p":0.
|
| 372 |
-
"r":0.
|
| 373 |
-
"f":0.
|
| 374 |
},
|
| 375 |
"preconj":{
|
| 376 |
-
"p":0.
|
| 377 |
-
"r":0.
|
| 378 |
-
"f":0.
|
| 379 |
},
|
| 380 |
"oprd":{
|
| 381 |
-
"p":0.
|
| 382 |
-
"r":0.
|
| 383 |
-
"f":0.
|
| 384 |
},
|
| 385 |
"parataxis":{
|
| 386 |
-
"p":0.
|
| 387 |
-
"r":0.
|
| 388 |
-
"f":0.
|
| 389 |
},
|
| 390 |
"meta":{
|
| 391 |
-
"p":0.
|
| 392 |
-
"r":0.
|
| 393 |
-
"f":0.
|
| 394 |
},
|
| 395 |
"csubjpass":{
|
| 396 |
-
"p":0.
|
| 397 |
-
"r":0.
|
| 398 |
-
"f":0.
|
| 399 |
}
|
| 400 |
},
|
| 401 |
-
"ents_p":0.
|
| 402 |
-
"ents_r":0.
|
| 403 |
-
"ents_f":0.
|
| 404 |
"ents_per_type":{
|
| 405 |
"DATE":{
|
| 406 |
-
"p":0.
|
| 407 |
-
"r":0.
|
| 408 |
-
"f":0.
|
| 409 |
},
|
| 410 |
"GPE":{
|
| 411 |
-
"p":0.
|
| 412 |
-
"r":0.
|
| 413 |
-
"f":0.
|
| 414 |
-
},
|
| 415 |
-
"ORDINAL":{
|
| 416 |
-
"p":0.7703081232,
|
| 417 |
-
"r":0.8540372671,
|
| 418 |
-
"f":0.8100147275
|
| 419 |
},
|
| 420 |
"ORG":{
|
| 421 |
-
"p":0.
|
| 422 |
-
"r":0.
|
| 423 |
-
"f":0.
|
| 424 |
},
|
| 425 |
"CARDINAL":{
|
| 426 |
-
"p":0.
|
| 427 |
-
"r":0.
|
| 428 |
-
"f":0.
|
| 429 |
-
},
|
| 430 |
-
"LOC":{
|
| 431 |
-
"p":0.7148148148,
|
| 432 |
-
"r":0.6146496815,
|
| 433 |
-
"f":0.6609589041
|
| 434 |
},
|
| 435 |
"PERSON":{
|
| 436 |
-
"p":0.
|
| 437 |
-
"r":0.
|
| 438 |
-
"f":0.
|
| 439 |
},
|
| 440 |
"NORP":{
|
| 441 |
-
"p":0.
|
| 442 |
-
"r":0.
|
| 443 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 444 |
},
|
| 445 |
"QUANTITY":{
|
| 446 |
-
"p":0.
|
| 447 |
-
"r":0.
|
| 448 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 449 |
},
|
| 450 |
"FAC":{
|
| 451 |
-
"p":0.
|
| 452 |
-
"r":0.
|
| 453 |
-
"f":0.
|
| 454 |
},
|
| 455 |
"TIME":{
|
| 456 |
-
"p":0.
|
| 457 |
-
"r":0.
|
| 458 |
-
"f":0.
|
| 459 |
},
|
| 460 |
-
"
|
| 461 |
-
"p":0.
|
| 462 |
-
"r":0.
|
| 463 |
-
"f":0.
|
| 464 |
},
|
| 465 |
"WORK_OF_ART":{
|
| 466 |
-
"p":0.
|
| 467 |
-
"r":0.
|
| 468 |
-
"f":0.
|
| 469 |
},
|
| 470 |
-
"
|
| 471 |
-
"p":0.
|
| 472 |
-
"r":0.
|
| 473 |
-
"f":0.
|
| 474 |
},
|
| 475 |
"MONEY":{
|
| 476 |
-
"p":0.
|
| 477 |
-
"r":0.
|
| 478 |
-
"f":0.
|
| 479 |
},
|
| 480 |
-
"
|
| 481 |
-
"p":0.
|
| 482 |
-
"r":0.
|
| 483 |
-
"f":0.
|
| 484 |
},
|
| 485 |
"PERCENT":{
|
| 486 |
-
"p":0.
|
| 487 |
"r":0.8790199081,
|
| 488 |
-
"f":0.
|
| 489 |
},
|
| 490 |
"LANGUAGE":{
|
| 491 |
-
"p":0.
|
| 492 |
-
"r":0.
|
| 493 |
-
"f":0.
|
| 494 |
}
|
| 495 |
},
|
| 496 |
-
"speed":
|
| 497 |
},
|
| 498 |
"sources":[
|
| 499 |
{
|
|
|
|
| 1 |
{
|
| 2 |
"lang":"en",
|
| 3 |
"name":"core_web_sm",
|
| 4 |
+
"version":"3.5.0",
|
| 5 |
"description":"English pipeline optimized for CPU. Components: tok2vec, tagger, parser, senter, ner, attribute_ruler, lemmatizer.",
|
| 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":0,
|
| 14 |
"vectors":0,
|
|
|
|
| 166 |
"senter"
|
| 167 |
],
|
| 168 |
"performance":{
|
| 169 |
+
"token_acc":0.9986194413,
|
| 170 |
"token_p":0.9956819193,
|
| 171 |
"token_r":0.9957659295,
|
| 172 |
"token_f":0.9957239226,
|
| 173 |
+
"tag_acc":0.97246532,
|
| 174 |
+
"sents_p":0.9201877934,
|
| 175 |
+
"sents_r":0.8921432812,
|
| 176 |
+
"sents_f":0.9059485531,
|
| 177 |
+
"dep_uas":0.9175304332,
|
| 178 |
+
"dep_las":0.89874821,
|
| 179 |
"dep_las_per_type":{
|
| 180 |
"prep":{
|
| 181 |
+
"p":0.853521338,
|
| 182 |
+
"r":0.8635932461,
|
| 183 |
+
"f":0.8585277532
|
| 184 |
},
|
| 185 |
"det":{
|
| 186 |
+
"p":0.9763930156,
|
| 187 |
"r":0.9781048683,
|
| 188 |
+
"f":0.9772481923
|
| 189 |
},
|
| 190 |
"pobj":{
|
| 191 |
+
"p":0.9613764045,
|
| 192 |
+
"r":0.967681131,
|
| 193 |
+
"f":0.9645184649
|
| 194 |
},
|
| 195 |
"nsubj":{
|
| 196 |
+
"p":0.9565737052,
|
| 197 |
+
"r":0.9467250821,
|
| 198 |
+
"f":0.9516239128
|
| 199 |
},
|
| 200 |
"aux":{
|
| 201 |
+
"p":0.9815061794,
|
| 202 |
+
"r":0.9827294578,
|
| 203 |
+
"f":0.9821174377
|
| 204 |
},
|
| 205 |
"advmod":{
|
| 206 |
+
"p":0.8548033091,
|
| 207 |
+
"r":0.8519266364,
|
| 208 |
+
"f":0.8533625485
|
| 209 |
},
|
| 210 |
"relcl":{
|
| 211 |
+
"p":0.7571736011,
|
| 212 |
+
"r":0.7659651669,
|
| 213 |
+
"f":0.7615440115
|
| 214 |
},
|
| 215 |
"root":{
|
| 216 |
+
"p":0.9195942266,
|
| 217 |
+
"r":0.8910218352,
|
| 218 |
+
"f":0.9050825879
|
| 219 |
},
|
| 220 |
"xcomp":{
|
| 221 |
+
"p":0.8836222144,
|
| 222 |
+
"r":0.8966259871,
|
| 223 |
+
"f":0.8900766079
|
| 224 |
},
|
| 225 |
"amod":{
|
| 226 |
+
"p":0.9174389766,
|
| 227 |
+
"r":0.9107223842,
|
| 228 |
+
"f":0.9140683422
|
| 229 |
},
|
| 230 |
"compound":{
|
| 231 |
+
"p":0.9126489559,
|
| 232 |
+
"r":0.9298284696,
|
| 233 |
+
"f":0.9211586207
|
| 234 |
},
|
| 235 |
"poss":{
|
| 236 |
+
"p":0.9739583333,
|
| 237 |
+
"r":0.9786634461,
|
| 238 |
+
"f":0.9763052209
|
| 239 |
},
|
| 240 |
"ccomp":{
|
| 241 |
+
"p":0.7671207315,
|
| 242 |
+
"r":0.8372708758,
|
| 243 |
+
"f":0.8006621872
|
| 244 |
},
|
| 245 |
"attr":{
|
| 246 |
+
"p":0.899837794,
|
| 247 |
+
"r":0.93313709,
|
| 248 |
+
"f":0.9161849711
|
| 249 |
},
|
| 250 |
"case":{
|
| 251 |
+
"p":0.9787549407,
|
| 252 |
"r":0.9914914915,
|
| 253 |
+
"f":0.9850820487
|
| 254 |
},
|
| 255 |
"mark":{
|
| 256 |
+
"p":0.9068783069,
|
| 257 |
+
"r":0.9083200848,
|
| 258 |
+
"f":0.9075986232
|
| 259 |
},
|
| 260 |
"intj":{
|
| 261 |
+
"p":0.6717131474,
|
| 262 |
+
"r":0.6175824176,
|
| 263 |
+
"f":0.6435114504
|
| 264 |
},
|
| 265 |
"advcl":{
|
| 266 |
+
"p":0.6633986928,
|
| 267 |
+
"r":0.6645681189,
|
| 268 |
+
"f":0.6639828909
|
| 269 |
},
|
| 270 |
"cc":{
|
| 271 |
+
"p":0.8323511726,
|
| 272 |
+
"r":0.8277717976,
|
| 273 |
+
"f":0.8300551691
|
| 274 |
},
|
| 275 |
"neg":{
|
| 276 |
+
"p":0.9466865969,
|
| 277 |
+
"r":0.9533366784,
|
| 278 |
+
"f":0.95
|
| 279 |
},
|
| 280 |
"conj":{
|
| 281 |
+
"p":0.7567333828,
|
| 282 |
+
"r":0.7710221551,
|
| 283 |
+
"f":0.763810949
|
| 284 |
},
|
| 285 |
"nsubjpass":{
|
| 286 |
+
"p":0.9182939363,
|
| 287 |
+
"r":0.9164102564,
|
| 288 |
+
"f":0.9173511294
|
| 289 |
},
|
| 290 |
"auxpass":{
|
| 291 |
+
"p":0.9501335708,
|
| 292 |
+
"r":0.9722095672,
|
| 293 |
+
"f":0.9610448097
|
| 294 |
},
|
| 295 |
"dobj":{
|
| 296 |
+
"p":0.9229805886,
|
| 297 |
+
"r":0.9396764682,
|
| 298 |
+
"f":0.9312537019
|
| 299 |
},
|
| 300 |
"nummod":{
|
| 301 |
+
"p":0.9379292801,
|
| 302 |
+
"r":0.9310606061,
|
| 303 |
+
"f":0.9344823216
|
| 304 |
},
|
| 305 |
"npadvmod":{
|
| 306 |
+
"p":0.7629658087,
|
| 307 |
+
"r":0.7055062167,
|
| 308 |
+
"f":0.7331118494
|
| 309 |
},
|
| 310 |
"prt":{
|
| 311 |
+
"p":0.8118323747,
|
| 312 |
+
"r":0.8853046595,
|
| 313 |
+
"f":0.8469781397
|
| 314 |
},
|
| 315 |
"pcomp":{
|
| 316 |
+
"p":0.8835714286,
|
| 317 |
+
"r":0.8662464986,
|
| 318 |
+
"f":0.8748231966
|
| 319 |
},
|
| 320 |
"expl":{
|
| 321 |
+
"p":0.9851380042,
|
| 322 |
+
"r":0.9935760171,
|
| 323 |
+
"f":0.9893390192
|
| 324 |
},
|
| 325 |
"acl":{
|
| 326 |
+
"p":0.742010459,
|
| 327 |
+
"r":0.6966721222,
|
| 328 |
+
"f":0.7186268993
|
| 329 |
},
|
| 330 |
"agent":{
|
| 331 |
+
"p":0.9034482759,
|
| 332 |
+
"r":0.9390681004,
|
| 333 |
+
"f":0.920913884
|
| 334 |
},
|
| 335 |
"dative":{
|
| 336 |
+
"p":0.8,
|
| 337 |
+
"r":0.6972477064,
|
| 338 |
+
"f":0.7450980392
|
| 339 |
},
|
| 340 |
"acomp":{
|
| 341 |
+
"p":0.9020594966,
|
| 342 |
+
"r":0.893877551,
|
| 343 |
+
"f":0.8979498861
|
| 344 |
},
|
| 345 |
"dep":{
|
| 346 |
+
"p":0.4147286822,
|
| 347 |
+
"r":0.1737012987,
|
| 348 |
+
"f":0.2448512586
|
| 349 |
},
|
| 350 |
"csubj":{
|
| 351 |
+
"p":0.6983240223,
|
| 352 |
+
"r":0.7396449704,
|
| 353 |
+
"f":0.7183908046
|
| 354 |
},
|
| 355 |
"quantmod":{
|
| 356 |
+
"p":0.8727436823,
|
| 357 |
+
"r":0.7855402112,
|
| 358 |
+
"f":0.8268490808
|
| 359 |
},
|
| 360 |
"nmod":{
|
| 361 |
+
"p":0.7498033045,
|
| 362 |
+
"r":0.5807434491,
|
| 363 |
+
"f":0.654532967
|
| 364 |
},
|
| 365 |
"appos":{
|
| 366 |
+
"p":0.7048498845,
|
| 367 |
+
"r":0.6620390456,
|
| 368 |
+
"f":0.6827740492
|
| 369 |
},
|
| 370 |
"predet":{
|
| 371 |
+
"p":0.8299595142,
|
| 372 |
+
"r":0.8798283262,
|
| 373 |
+
"f":0.8541666667
|
| 374 |
},
|
| 375 |
"preconj":{
|
| 376 |
+
"p":0.5544554455,
|
| 377 |
+
"r":0.6511627907,
|
| 378 |
+
"f":0.5989304813
|
| 379 |
},
|
| 380 |
"oprd":{
|
| 381 |
+
"p":0.8013245033,
|
| 382 |
+
"r":0.7223880597,
|
| 383 |
+
"f":0.759811617
|
| 384 |
},
|
| 385 |
"parataxis":{
|
| 386 |
+
"p":0.6428571429,
|
| 387 |
+
"r":0.4880694143,
|
| 388 |
+
"f":0.5548705302
|
| 389 |
},
|
| 390 |
"meta":{
|
| 391 |
+
"p":0.3770491803,
|
| 392 |
+
"r":0.4423076923,
|
| 393 |
+
"f":0.407079646
|
| 394 |
},
|
| 395 |
"csubjpass":{
|
| 396 |
+
"p":0.5555555556,
|
| 397 |
+
"r":0.8333333333,
|
| 398 |
+
"f":0.6666666667
|
| 399 |
}
|
| 400 |
},
|
| 401 |
+
"ents_p":0.8454836771,
|
| 402 |
+
"ents_r":0.8456530449,
|
| 403 |
+
"ents_f":0.8455683525,
|
| 404 |
"ents_per_type":{
|
| 405 |
"DATE":{
|
| 406 |
+
"p":0.8603213844,
|
| 407 |
+
"r":0.8838095238,
|
| 408 |
+
"f":0.8719072972
|
| 409 |
},
|
| 410 |
"GPE":{
|
| 411 |
+
"p":0.9146932953,
|
| 412 |
+
"r":0.8942817294,
|
| 413 |
+
"f":0.9043723554
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 414 |
},
|
| 415 |
"ORG":{
|
| 416 |
+
"p":0.7955942623,
|
| 417 |
+
"r":0.8234358431,
|
| 418 |
+
"f":0.8092756644
|
| 419 |
},
|
| 420 |
"CARDINAL":{
|
| 421 |
+
"p":0.8149171271,
|
| 422 |
+
"r":0.8769322235,
|
| 423 |
+
"f":0.8447880871
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 424 |
},
|
| 425 |
"PERSON":{
|
| 426 |
+
"p":0.8617758186,
|
| 427 |
+
"r":0.8932767624,
|
| 428 |
+
"f":0.8772435897
|
| 429 |
},
|
| 430 |
"NORP":{
|
| 431 |
+
"p":0.8957006369,
|
| 432 |
+
"r":0.9,
|
| 433 |
+
"f":0.8978451716
|
| 434 |
+
},
|
| 435 |
+
"ORDINAL":{
|
| 436 |
+
"p":0.7844827586,
|
| 437 |
+
"r":0.847826087,
|
| 438 |
+
"f":0.8149253731
|
| 439 |
},
|
| 440 |
"QUANTITY":{
|
| 441 |
+
"p":0.8529411765,
|
| 442 |
+
"r":0.6373626374,
|
| 443 |
+
"f":0.7295597484
|
| 444 |
+
},
|
| 445 |
+
"LOC":{
|
| 446 |
+
"p":0.7210884354,
|
| 447 |
+
"r":0.6751592357,
|
| 448 |
+
"f":0.6973684211
|
| 449 |
},
|
| 450 |
"FAC":{
|
| 451 |
+
"p":0.358490566,
|
| 452 |
+
"r":0.2923076923,
|
| 453 |
+
"f":0.3220338983
|
| 454 |
},
|
| 455 |
"TIME":{
|
| 456 |
+
"p":0.7413793103,
|
| 457 |
+
"r":0.7543859649,
|
| 458 |
+
"f":0.747826087
|
| 459 |
},
|
| 460 |
+
"PRODUCT":{
|
| 461 |
+
"p":0.5591397849,
|
| 462 |
+
"r":0.2464454976,
|
| 463 |
+
"f":0.3421052632
|
| 464 |
},
|
| 465 |
"WORK_OF_ART":{
|
| 466 |
+
"p":0.4885496183,
|
| 467 |
+
"r":0.3298969072,
|
| 468 |
+
"f":0.3938461538
|
| 469 |
},
|
| 470 |
+
"EVENT":{
|
| 471 |
+
"p":0.6428571429,
|
| 472 |
+
"r":0.3103448276,
|
| 473 |
+
"f":0.4186046512
|
| 474 |
},
|
| 475 |
"MONEY":{
|
| 476 |
+
"p":0.9071428571,
|
| 477 |
+
"r":0.8996458087,
|
| 478 |
+
"f":0.9033787789
|
| 479 |
},
|
| 480 |
+
"LAW":{
|
| 481 |
+
"p":0.5454545455,
|
| 482 |
+
"r":0.46875,
|
| 483 |
+
"f":0.5042016807
|
| 484 |
},
|
| 485 |
"PERCENT":{
|
| 486 |
+
"p":0.9184,
|
| 487 |
"r":0.8790199081,
|
| 488 |
+
"f":0.8982785603
|
| 489 |
},
|
| 490 |
"LANGUAGE":{
|
| 491 |
+
"p":0.8,
|
| 492 |
+
"r":0.625,
|
| 493 |
+
"f":0.701754386
|
| 494 |
}
|
| 495 |
},
|
| 496 |
+
"speed":9611.7804215009
|
| 497 |
},
|
| 498 |
"sources":[
|
| 499 |
{
|
ner/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 sha256:6f47ca062eb419c8ffb7d3023e6fbc4b2eb21dab14c5d49aa5e5586228b87405
|
| 3 |
+
size 6154601
|
parser/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 319909
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1836fbc02b3924b2fd5f65325c58ae852ff112db1090ca724e5a801e68b85fd
|
| 3 |
size 319909
|
senter/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 197089
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e62c2504dcdc66144b30c048100af05f12207f933f6d669982b947ae71ffdeef
|
| 3 |
size 197089
|
tagger/model
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 19829
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb00ef592a2a464d95dd889ce424952ae7fd64e095153054c310345198cc0fc4
|
| 3 |
size 19829
|
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 sha256:42d8414521eaf75f817bd1b351b26039a22a912bb2617f95ead305420f2ebffd
|
| 3 |
+
size 6269370
|
tokenizer
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|