Jacobo commited on
Commit
45e47b8
1 Parent(s): 754fbe9

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -13,14 +13,14 @@ model-index:
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
- value: 0.9871174426
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
- value: 0.9861631791
24
  - task:
25
  name: MORPH
26
  type: token-classification
@@ -34,34 +34,34 @@ model-index:
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
- value: 0.9644196033
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
- value: 0.8906547532
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
- value: 0.8569649919
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
- value: 0.9960822723
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
62
  | **Name** | `grc_proiel_trf` |
63
  | **Version** | `3.7.5` |
64
- | **spaCy** | `>=3.7.5,<3.8.0` |
65
  | **Default Pipeline** | `transformer`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
66
  | **Components** | `transformer`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
67
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -87,16 +87,16 @@ model-index:
87
 
88
  | Type | Score |
89
  | --- | --- |
90
- | `POS_ACC` | 98.62 |
91
  | `MORPH_ACC` | 94.61 |
92
- | `TAG_ACC` | 98.71 |
93
- | `DEP_UAS` | 89.07 |
94
- | `DEP_LAS` | 85.70 |
95
- | `SENTS_P` | 99.41 |
96
- | `SENTS_R` | 99.80 |
97
- | `SENTS_F` | 99.61 |
98
- | `LEMMA_ACC` | 96.44 |
99
- | `TRANSFORMER_LOSS` | 112503.24 |
100
- | `MORPHOLOGIZER_LOSS` | 1176.78 |
101
- | `TAGGER_LOSS` | 622.42 |
102
- | `PARSER_LOSS` | 9969849.86 |
 
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
+ value: 0.9870492809
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
+ value: 0.9865039875
24
  - task:
25
  name: MORPH
26
  type: token-classification
 
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
+ value: 0.9655101902
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
+ value: 0.8870743317
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
+ value: 0.8555840352
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
+ value: 0.9941234084
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
62
  | **Name** | `grc_proiel_trf` |
63
  | **Version** | `3.7.5` |
64
+ | **spaCy** | `>=3.8.2,<3.9.0` |
65
  | **Default Pipeline** | `transformer`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
66
  | **Components** | `transformer`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
67
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
 
87
 
88
  | Type | Score |
89
  | --- | --- |
90
+ | `POS_ACC` | 98.65 |
91
  | `MORPH_ACC` | 94.61 |
92
+ | `TAG_ACC` | 98.70 |
93
+ | `DEP_UAS` | 88.71 |
94
+ | `DEP_LAS` | 85.56 |
95
+ | `SENTS_P` | 99.22 |
96
+ | `SENTS_R` | 99.61 |
97
+ | `SENTS_F` | 99.41 |
98
+ | `LEMMA_ACC` | 96.55 |
99
+ | `TRANSFORMER_LOSS` | 121398.42 |
100
+ | `MORPHOLOGIZER_LOSS` | 1526.60 |
101
+ | `TAGGER_LOSS` | 208.68 |
102
+ | `PARSER_LOSS` | 9990298.44 |
grc_proiel_trf-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e5c1a5d5d2d405f71bc48fcc0e7120339ed0f0c8c31d73001b9a07880aa99eea
3
- size 497456659
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a81c6fc3875d9799a75d4b845d92d564983b5b41d2c6a8d00027d6e8715658d
3
+ size 497457150
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:becf7d37bd570f1a89a157da3184d2710dccc79804ec6f0ad3cae090aafe5c2a
3
  size 29215702
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a16cafd4cbc7aa11d3fb22e11674b2eceb1cdd54f633ede1359da290a71192c4
3
  size 29215702
meta.json CHANGED
@@ -7,8 +7,8 @@
7
  "email":"",
8
  "url":"",
9
  "license":"",
10
- "spacy_version":">=3.7.5,<3.8.0",
11
- "spacy_git_version":"a6d0fc360",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -1136,33 +1136,33 @@
1136
 
1137
  ],
1138
  "performance":{
1139
- "pos_acc":0.9861631791,
1140
  "morph_acc":0.9460841115,
1141
  "morph_per_feat":{
1142
  "Case":{
1143
- "p":0.9864864865,
1144
- "r":0.9857395255,
1145
- "f":0.9861128645
1146
  },
1147
  "Gender":{
1148
- "p":0.9443880142,
1149
- "r":0.9490876611,
1150
- "f":0.9467320053
1151
  },
1152
  "Number":{
1153
- "p":0.9961709614,
1154
  "r":0.9953469135,
1155
- "f":0.9957587669
1156
  },
1157
  "Person":{
1158
- "p":0.9922451994,
1159
- "r":0.9918789221,
1160
- "f":0.992062027
1161
  },
1162
  "PronType":{
1163
- "p":0.9938050212,
1164
- "r":0.9896103896,
1165
- "f":0.9917032699
1166
  },
1167
  "Polarity":{
1168
  "p":1.0,
@@ -1170,9 +1170,9 @@
1170
  "f":0.9895287958
1171
  },
1172
  "Aspect":{
1173
- "p":0.9868871152,
1174
- "r":0.9824063564,
1175
- "f":0.9846416382
1176
  },
1177
  "Mood":{
1178
  "p":0.9919770774,
@@ -1180,29 +1180,29 @@
1180
  "f":0.9914089347
1181
  },
1182
  "Tense":{
1183
- "p":0.9855769231,
1184
- "r":0.985915493,
1185
- "f":0.9857461789
1186
  },
1187
  "VerbForm":{
1188
- "p":0.9975969791,
1189
- "r":0.9975969791,
1190
- "f":0.9975969791
1191
  },
1192
  "Voice":{
1193
- "p":0.978021978,
1194
- "r":0.9783579526,
1195
- "f":0.9781899365
1196
  },
1197
  "Degree":{
1198
- "p":0.9529569892,
1199
  "r":0.9529569892,
1200
- "f":0.9529569892
1201
  },
1202
  "Definite":{
1203
- "p":0.9967672414,
1204
  "r":0.9994597515,
1205
- "f":0.9981116806
1206
  },
1207
  "Reflex":{
1208
  "p":1.0,
@@ -1215,44 +1215,44 @@
1215
  "f":0.972972973
1216
  }
1217
  },
1218
- "tag_acc":0.9871174426,
1219
- "dep_uas":0.8906547532,
1220
- "dep_las":0.8569649919,
1221
  "dep_las_per_type":{
1222
  "nsubj":{
1223
- "p":0.8571428571,
1224
- "r":0.8515709642,
1225
- "f":0.8543478261
1226
  },
1227
  "discourse":{
1228
- "p":0.8546195652,
1229
- "r":0.864010989,
1230
- "f":0.8592896175
1231
  },
1232
  "mark":{
1233
- "p":0.9130434783,
1234
- "r":0.9314516129,
1235
- "f":0.9221556886
1236
  },
1237
  "advmod":{
1238
- "p":0.8140243902,
1239
- "r":0.79346211,
1240
- "f":0.8036117381
1241
  },
1242
  "advcl":{
1243
- "p":0.8096514745,
1244
- "r":0.825136612,
1245
- "f":0.8173207037
1246
  },
1247
  "xcomp":{
1248
- "p":0.7261904762,
1249
- "r":0.732,
1250
- "f":0.7290836653
1251
  },
1252
  "cop":{
1253
- "p":0.8348623853,
1254
- "r":0.8504672897,
1255
- "f":0.8425925926
1256
  },
1257
  "root":{
1258
  "p":0.954056696,
@@ -1265,64 +1265,64 @@
1265
  "f":0.9540130152
1266
  },
1267
  "nmod":{
1268
- "p":0.814953271,
1269
- "r":0.7676056338,
1270
- "f":0.7905711695
1271
  },
1272
  "obj":{
1273
- "p":0.8968008256,
1274
- "r":0.9023883697,
1275
- "f":0.8995859213
1276
  },
1277
  "case":{
1278
- "p":0.9736842105,
1279
- "r":0.9736842105,
1280
- "f":0.9736842105
1281
  },
1282
  "obl":{
1283
- "p":0.8043742406,
1284
- "r":0.8083028083,
1285
- "f":0.8063337393
1286
  },
1287
  "cc":{
1288
- "p":0.8488612836,
1289
- "r":0.8436213992,
1290
- "f":0.8462332301
1291
  },
1292
  "conj":{
1293
- "p":0.7872340426,
1294
- "r":0.7769028871,
1295
- "f":0.7820343461
1296
  },
1297
  "obl:agent":{
1298
- "p":0.7575757576,
1299
- "r":0.6756756757,
1300
- "f":0.7142857143
1301
  },
1302
  "ccomp":{
1303
- "p":0.7357512953,
1304
- "r":0.7064676617,
1305
- "f":0.7208121827
1306
  },
1307
  "nsubj:pass":{
1308
- "p":0.7258064516,
1309
- "r":0.8411214953,
1310
- "f":0.7792207792
1311
  },
1312
  "amod":{
1313
- "p":0.819047619,
1314
- "r":0.8075117371,
1315
- "f":0.8132387707
1316
  },
1317
  "acl":{
1318
- "p":0.5806451613,
1319
- "r":0.5454545455,
1320
- "f":0.5625
1321
  },
1322
  "iobj":{
1323
- "p":0.8239277652,
1324
  "r":0.8429561201,
1325
- "f":0.8333333333
1326
  },
1327
  "nummod":{
1328
  "p":0.9,
@@ -1330,19 +1330,19 @@
1330
  "f":0.84375
1331
  },
1332
  "vocative":{
1333
- "p":0.8805970149,
1334
- "r":0.8550724638,
1335
- "f":0.8676470588
1336
  },
1337
  "orphan":{
1338
- "p":0.4615384615,
1339
- "r":0.2790697674,
1340
- "f":0.347826087
1341
  },
1342
  "appos":{
1343
- "p":0.5267175573,
1344
- "r":0.4893617021,
1345
- "f":0.5073529412
1346
  },
1347
  "dep":{
1348
  "p":0.0,
@@ -1350,24 +1350,24 @@
1350
  "f":0.0
1351
  },
1352
  "parataxis":{
1353
- "p":0.5,
1354
  "r":0.15,
1355
- "f":0.2307692308
1356
  },
1357
  "dislocated":{
1358
- "p":0.5,
1359
  "r":0.3076923077,
1360
- "f":0.380952381
1361
  },
1362
  "csubj:pass":{
1363
- "p":0.5,
1364
- "r":0.2,
1365
- "f":0.2857142857
1366
  },
1367
  "flat:name":{
1368
- "p":0.9285714286,
1369
  "r":0.5909090909,
1370
- "f":0.7222222222
1371
  },
1372
  "aux:pass":{
1373
  "p":0.0,
@@ -1385,16 +1385,17 @@
1385
  "f":0.0
1386
  }
1387
  },
1388
- "sents_p":0.9941348974,
1389
- "sents_r":0.9980372915,
1390
- "sents_f":0.9960822723,
1391
- "lemma_acc":0.9644196033,
1392
- "transformer_loss":1125.0324298582,
1393
- "morphologizer_loss":11.7678151131,
1394
- "tagger_loss":6.2242061632,
1395
- "parser_loss":99698.4986075311
1396
  },
1397
  "requirements":[
1398
- "spacy-transformers>=1.3.5,<1.4.0"
 
1399
  ]
1400
  }
 
7
  "email":"",
8
  "url":"",
9
  "license":"",
10
+ "spacy_version":">=3.8.2,<3.9.0",
11
+ "spacy_git_version":"63f1b53",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
 
1136
 
1137
  ],
1138
  "performance":{
1139
+ "pos_acc":0.9865039875,
1140
  "morph_acc":0.9460841115,
1141
  "morph_per_feat":{
1142
  "Case":{
1143
+ "p":0.9871212121,
1144
+ "r":0.9866229177,
1145
+ "f":0.986872002
1146
  },
1147
  "Gender":{
1148
+ "p":0.9440213252,
1149
+ "r":0.9489600612,
1150
+ "f":0.9464842507
1151
  },
1152
  "Number":{
1153
+ "p":0.9959648215,
1154
  "r":0.9953469135,
1155
+ "f":0.9956557716
1156
  },
1157
  "Person":{
1158
+ "p":0.99298116,
1159
+ "r":0.992248062,
1160
+ "f":0.9926144756
1161
  },
1162
  "PronType":{
1163
+ "p":0.9925130208,
1164
+ "r":0.9899350649,
1165
+ "f":0.9912223667
1166
  },
1167
  "Polarity":{
1168
  "p":1.0,
 
1170
  "f":0.9895287958
1171
  },
1172
  "Aspect":{
1173
+ "p":0.9885844749,
1174
+ "r":0.9829738933,
1175
+ "f":0.9857712009
1176
  },
1177
  "Mood":{
1178
  "p":0.9919770774,
 
1180
  "f":0.9914089347
1181
  },
1182
  "Tense":{
1183
+ "p":0.9859203297,
1184
+ "r":0.9862590175,
1185
+ "f":0.9860896445
1186
  },
1187
  "VerbForm":{
1188
+ "p":0.9972536904,
1189
+ "r":0.9972536904,
1190
+ "f":0.9972536904
1191
  },
1192
  "Voice":{
1193
+ "p":0.9766483516,
1194
+ "r":0.9769838543,
1195
+ "f":0.9768160742
1196
  },
1197
  "Degree":{
1198
+ "p":0.9516778523,
1199
  "r":0.9529569892,
1200
+ "f":0.9523169913
1201
  },
1202
  "Definite":{
1203
+ "p":0.9962304793,
1204
  "r":0.9994597515,
1205
+ "f":0.9978425027
1206
  },
1207
  "Reflex":{
1208
  "p":1.0,
 
1215
  "f":0.972972973
1216
  }
1217
  },
1218
+ "tag_acc":0.9870492809,
1219
+ "dep_uas":0.8870743317,
1220
+ "dep_las":0.8555840352,
1221
  "dep_las_per_type":{
1222
  "nsubj":{
1223
+ "p":0.8608414239,
1224
+ "r":0.8645720477,
1225
+ "f":0.8627027027
1226
  },
1227
  "discourse":{
1228
+ "p":0.8610354223,
1229
+ "r":0.8681318681,
1230
+ "f":0.8645690834
1231
  },
1232
  "mark":{
1233
+ "p":0.9090909091,
1234
+ "r":0.9274193548,
1235
+ "f":0.9181636727
1236
  },
1237
  "advmod":{
1238
+ "p":0.8052550232,
1239
+ "r":0.7741456166,
1240
+ "f":0.7893939394
1241
  },
1242
  "advcl":{
1243
+ "p":0.8186666667,
1244
+ "r":0.8387978142,
1245
+ "f":0.8286099865
1246
  },
1247
  "xcomp":{
1248
+ "p":0.7081712062,
1249
+ "r":0.728,
1250
+ "f":0.7179487179
1251
  },
1252
  "cop":{
1253
+ "p":0.8571428571,
1254
+ "r":0.8691588785,
1255
+ "f":0.8631090487
1256
  },
1257
  "root":{
1258
  "p":0.954056696,
 
1265
  "f":0.9540130152
1266
  },
1267
  "nmod":{
1268
+ "p":0.8215613383,
1269
+ "r":0.7781690141,
1270
+ "f":0.7992766727
1271
  },
1272
  "obj":{
1273
+ "p":0.8873966942,
1274
+ "r":0.8920041537,
1275
+ "f":0.8896944588
1276
  },
1277
  "case":{
1278
+ "p":0.9650655022,
1279
+ "r":0.9692982456,
1280
+ "f":0.9671772429
1281
  },
1282
  "obl":{
1283
+ "p":0.7961165049,
1284
+ "r":0.800976801,
1285
+ "f":0.7985392575
1286
  },
1287
  "cc":{
1288
+ "p":0.8455200824,
1289
+ "r":0.8446502058,
1290
+ "f":0.8450849202
1291
  },
1292
  "conj":{
1293
+ "p":0.7801324503,
1294
+ "r":0.7729658793,
1295
+ "f":0.7765326302
1296
  },
1297
  "obl:agent":{
1298
+ "p":0.8,
1299
+ "r":0.6486486486,
1300
+ "f":0.7164179104
1301
  },
1302
  "ccomp":{
1303
+ "p":0.75,
1304
+ "r":0.7014925373,
1305
+ "f":0.7249357326
1306
  },
1307
  "nsubj:pass":{
1308
+ "p":0.7739130435,
1309
+ "r":0.8317757009,
1310
+ "f":0.8018018018
1311
  },
1312
  "amod":{
1313
+ "p":0.7962085308,
1314
+ "r":0.7887323944,
1315
+ "f":0.7924528302
1316
  },
1317
  "acl":{
1318
+ "p":0.5548387097,
1319
+ "r":0.5212121212,
1320
+ "f":0.5375
1321
  },
1322
  "iobj":{
1323
+ "p":0.8220720721,
1324
  "r":0.8429561201,
1325
+ "f":0.8323831243
1326
  },
1327
  "nummod":{
1328
  "p":0.9,
 
1330
  "f":0.84375
1331
  },
1332
  "vocative":{
1333
+ "p":0.8970588235,
1334
+ "r":0.884057971,
1335
+ "f":0.8905109489
1336
  },
1337
  "orphan":{
1338
+ "p":0.3333333333,
1339
+ "r":0.2093023256,
1340
+ "f":0.2571428571
1341
  },
1342
  "appos":{
1343
+ "p":0.5689655172,
1344
+ "r":0.4680851064,
1345
+ "f":0.513618677
1346
  },
1347
  "dep":{
1348
  "p":0.0,
 
1350
  "f":0.0
1351
  },
1352
  "parataxis":{
1353
+ "p":0.2727272727,
1354
  "r":0.15,
1355
+ "f":0.1935483871
1356
  },
1357
  "dislocated":{
1358
+ "p":0.6153846154,
1359
  "r":0.3076923077,
1360
+ "f":0.4102564103
1361
  },
1362
  "csubj:pass":{
1363
+ "p":0.0,
1364
+ "r":0.0,
1365
+ "f":0.0
1366
  },
1367
  "flat:name":{
1368
+ "p":1.0,
1369
  "r":0.5909090909,
1370
+ "f":0.7428571429
1371
  },
1372
  "aux:pass":{
1373
  "p":0.0,
 
1385
  "f":0.0
1386
  }
1387
  },
1388
+ "sents_p":0.9921798631,
1389
+ "sents_r":0.9960745829,
1390
+ "sents_f":0.9941234084,
1391
+ "lemma_acc":0.9655101902,
1392
+ "transformer_loss":1213.9841676582,
1393
+ "morphologizer_loss":15.2659904288,
1394
+ "tagger_loss":2.0868166378,
1395
+ "parser_loss":99902.984375
1396
  },
1397
  "requirements":[
1398
+ "spacy-transformers>=1.1.9,<1.2.0",
1399
+ "spacy>=3.8.2,<3.9.0"
1400
  ]
1401
  }
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc5ed89813c9c693cfbb75a3b1d4672f73a544c211e3233b80a1ac56bf6dba5b
3
  size 3172009
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:123f9d7a0d073c947a7c32c759e39ec264d0c1536f94d2e8a2a148351529f1b0
3
  size 3172009
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5188d9d60a45b0eb8fb3cb69dd05bf6ddda53073e4ed89e25f713c12c4ad074
3
  size 1919319
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:390850c90f69dbaa7ea2d603bcfa07899f1221f2a0e24e6d099222f9fdc3d411
3
  size 1919319
tagger/model CHANGED
Binary files a/tagger/model and b/tagger/model differ
 
transformer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40c1052a4c0a121833d15cab3165d902abea2d51b589b8fc7229e13908f1464f
3
- size 500074867
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:733e02d8461c635d4368d459c30fab554e90472c35cea9f1b6bea02883bda15b
3
+ size 500078692
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ad0af38cd28c4908f5ca4a8fcd4ba0d5af1e332eeeb300359884635bd39d0d07
3
- size 22420276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:365eb9e7f7f1fa13525aaa02f708349cc3ac44bc0fafdfa1a83734d3af28f108
3
+ size 22453502