Hugging Face's logo

spacy
/
da_core_news_trf

Token Classification
spaCy
Danish
Eval Results
Model card Files Community
adrianeboyd commited on
Commit
eca5c8a
•
1 Parent(s): c2cc21c

Update spaCy pipeline

Browse files
Files changed (15) hide show
  1. README.md +25 -25
  2. accuracy.json +159 -159
  3. attribute_ruler/patterns +0 -0
  4. config.cfg +2 -1
  5. da_core_news_trf-any-py3-none-any.whl +2 -2
  6. lemmatizer/cfg +149 -149
  7. lemmatizer/model +1 -1
  8. lemmatizer/trees +0 -0
  9. meta.json +163 -163
  10. morphologizer/model +1 -1
  11. ner/model +1 -1
  12. parser/model +1 -1
  13. tokenizer +0 -0
  14. transformer/model +2 -2
  15. vocab/strings.json +2 -2
README.md CHANGED
@@ -14,62 +14,62 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.8118609407
18
  - name: NER Recall
19
  type: recall
20
  value: 0.8270833333
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.8194014448
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9746222394
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9746222394
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
- value: 0.971716389
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 0.9459564165
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.8596491228
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.8301675978
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.832319722
73
  ---
74
  ### Details: https://spacy.io/models/da#da_core_news_trf
75
 
@@ -78,8 +78,8 @@ Danish transformer pipeline (Maltehb/danish-bert-botxo). Components: transformer
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `da_core_news_trf` |
81
- | **Version** | `3.4.0` |
82
- | **spaCy** | `>=3.4.0,<3.5.0` |
83
  | **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
84
  | **Components** | `transformer`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -105,22 +105,22 @@ Danish transformer pipeline (Maltehb/danish-bert-botxo). Components: transformer
105
 
106
  | Type | Score |
107
  | --- | --- |
108
- | `TOKEN_ACC` | 99.95 |
109
  | `TOKEN_P` | 99.78 |
110
  | `TOKEN_R` | 99.75 |
111
  | `TOKEN_F` | 99.76 |
112
- | `POS_ACC` | 97.46 |
113
- | `MORPH_ACC` | 97.17 |
114
  | `MORPH_MICRO_P` | 98.72 |
115
- | `MORPH_MICRO_R` | 97.61 |
116
- | `MORPH_MICRO_F` | 98.16 |
117
- | `SENTS_P` | 81.60 |
118
- | `SENTS_R` | 84.93 |
119
- | `SENTS_F` | 83.23 |
120
- | `DEP_UAS` | 85.96 |
121
- | `DEP_LAS` | 83.02 |
122
- | `LEMMA_ACC` | 94.60 |
123
- | `TAG_ACC` | 97.46 |
124
- | `ENTS_P` | 81.19 |
125
  | `ENTS_R` | 82.71 |
126
- | `ENTS_F` | 81.94 |
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.8236514523
18
  - name: NER Recall
19
  type: recall
20
  value: 0.8270833333
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.8253638254
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9767058937
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9767058937
38
  - task:
39
  name: MORPH
40
  type: token-classification
41
  metrics:
42
  - name: Morph (UFeats) Accuracy
43
  type: accuracy
44
+ value: 0.97360647
45
  - task:
46
  name: LEMMA
47
  type: token-classification
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9471186441
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.8648950424
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.8355942612
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.8591674048
73
  ---
74
  ### Details: https://spacy.io/models/da#da_core_news_trf
75
 
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `da_core_news_trf` |
81
+ | **Version** | `3.5.0` |
82
+ | **spaCy** | `>=3.5.0,<3.6.0` |
83
  | **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
84
  | **Components** | `transformer`, `morphologizer`, `parser`, `lemmatizer`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
 
105
 
106
  | Type | Score |
107
  | --- | --- |
108
+ | `TOKEN_ACC` | 99.89 |
109
  | `TOKEN_P` | 99.78 |
110
  | `TOKEN_R` | 99.75 |
111
  | `TOKEN_F` | 99.76 |
112
+ | `POS_ACC` | 97.67 |
113
+ | `MORPH_ACC` | 97.36 |
114
  | `MORPH_MICRO_P` | 98.72 |
115
+ | `MORPH_MICRO_R` | 97.89 |
116
+ | `MORPH_MICRO_F` | 98.30 |
117
+ | `SENTS_P` | 85.84 |
118
+ | `SENTS_R` | 85.99 |
119
+ | `SENTS_F` | 85.92 |
120
+ | `DEP_UAS` | 86.49 |
121
+ | `DEP_LAS` | 83.56 |
122
+ | `LEMMA_ACC` | 94.71 |
123
+ | `TAG_ACC` | 97.67 |
124
+ | `ENTS_P` | 82.37 |
125
  | `ENTS_R` | 82.71 |
126
+ | `ENTS_F` | 82.54 |
accuracy.json CHANGED
@@ -1,53 +1,53 @@
1
  {
2
- "token_acc": 0.9994672349,
3
  "token_p": 0.9977732598,
4
  "token_r": 0.9974835463,
5
  "token_f": 0.997628382,
6
- "pos_acc": 0.9746222394,
7
- "morph_acc": 0.971716389,
8
- "morph_micro_p": 0.9871860323,
9
- "morph_micro_r": 0.9760738983,
10
- "morph_micro_f": 0.9815985177,
11
  "morph_per_feat": {
12
  "Mood": {
13
- "p": 0.9923150817,
14
- "r": 0.9847473785,
15
- "f": 0.9885167464
16
  },
17
  "Tense": {
18
- "p": 0.9870525514,
19
- "r": 0.9759036145,
20
- "f": 0.9814464218
21
  },
22
  "VerbForm": {
23
- "p": 0.9863861386,
24
- "r": 0.9755201958,
25
- "f": 0.9809230769
26
  },
27
  "Voice": {
28
- "p": 0.9917293233,
29
- "r": 0.985799701,
30
- "f": 0.9887556222
31
  },
32
  "Definite": {
33
- "p": 0.98915227,
34
  "r": 0.9727380482,
35
- "f": 0.980876494
36
  },
37
  "Gender": {
38
- "p": 0.9797843666,
39
- "r": 0.9664340312,
40
- "f": 0.9730634097
41
  },
42
  "Number": {
43
- "p": 0.9873217116,
44
- "r": 0.9749608764,
45
- "f": 0.9811023622
46
  },
47
  "AdpType": {
48
- "p": 0.9973357016,
49
- "r": 0.9929266136,
50
- "f": 0.9951262738
51
  },
52
  "PartType": {
53
  "p": 1.0,
@@ -55,19 +55,19 @@
55
  "f": 0.9983739837
56
  },
57
  "Case": {
58
- "p": 0.9919614148,
59
- "r": 0.9747235387,
60
- "f": 0.9832669323
61
  },
62
  "Person": {
63
- "p": 0.9856630824,
64
- "r": 0.9769094139,
65
- "f": 0.9812667261
66
  },
67
  "PronType": {
68
- "p": 0.9925373134,
69
- "r": 0.984375,
70
- "f": 0.9884393064
71
  },
72
  "NumType": {
73
  "p": 0.9865771812,
@@ -75,20 +75,15 @@
75
  "f": 0.98
76
  },
77
  "Degree": {
78
- "p": 0.9697702539,
79
- "r": 0.9662650602,
80
- "f": 0.968014484
81
  },
82
  "Reflex": {
83
  "p": 1.0,
84
  "r": 1.0,
85
  "f": 1.0
86
  },
87
- "Polite": {
88
- "p": 0.0,
89
- "r": 0.0,
90
- "f": 0.0
91
- },
92
  "Number[psor]": {
93
  "p": 0.9770114943,
94
  "r": 0.988372093,
@@ -100,9 +95,9 @@
100
  "f": 0.9942857143
101
  },
102
  "Foreign": {
103
- "p": 0.7777777778,
104
- "r": 0.7,
105
- "f": 0.7368421053
106
  },
107
  "Abbr": {
108
  "p": 1.0,
@@ -113,143 +108,148 @@
113
  "p": 1.0,
114
  "r": 1.0,
115
  "f": 1.0
 
 
 
 
 
116
  }
117
  },
118
- "sents_p": 0.8160136286,
119
- "sents_r": 0.8492907801,
120
- "sents_f": 0.832319722,
121
- "dep_uas": 0.8596491228,
122
- "dep_las": 0.8301675978,
123
  "dep_las_per_type": {
124
  "advmod": {
125
- "p": 0.7773109244,
126
- "r": 0.7838983051,
127
- "f": 0.7805907173
128
  },
129
  "root": {
130
- "p": 0.8293515358,
131
- "r": 0.8617021277,
132
- "f": 0.8452173913
133
  },
134
  "nsubj": {
135
- "p": 0.8976545842,
136
- "r": 0.888185654,
137
- "f": 0.8928950159
138
  },
139
  "case": {
140
- "p": 0.9175769613,
141
- "r": 0.9112426036,
142
- "f": 0.9143988125
143
  },
144
  "obl": {
145
- "p": 0.7834394904,
146
- "r": 0.7639751553,
147
- "f": 0.7735849057
148
  },
149
  "cc": {
150
- "p": 0.8425655977,
151
- "r": 0.8401162791,
152
- "f": 0.8413391557
153
  },
154
  "conj": {
155
- "p": 0.7154696133,
156
- "r": 0.6906666667,
157
- "f": 0.7028493894
158
  },
159
  "obj": {
160
- "p": 0.8701298701,
161
- "r": 0.9106796117,
162
- "f": 0.889943074
163
  },
164
  "aux": {
165
- "p": 0.8699421965,
166
- "r": 0.8775510204,
167
- "f": 0.8737300435
168
  },
169
  "acl:relcl": {
170
- "p": 0.7630057803,
171
- "r": 0.7135135135,
172
- "f": 0.7374301676
173
  },
174
  "advmod:lmod": {
175
- "p": 0.8,
176
  "r": 0.776119403,
177
- "f": 0.7878787879
178
  },
179
  "det": {
180
- "p": 0.9169381107,
181
- "r": 0.9275123558,
182
- "f": 0.9221949222
183
  },
184
  "amod": {
185
- "p": 0.8605442177,
186
- "r": 0.8634812287,
187
- "f": 0.8620102215
188
  },
189
  "nmod:poss": {
190
- "p": 0.7765957447,
191
- "r": 0.7227722772,
192
- "f": 0.7487179487
193
  },
194
  "ccomp": {
195
- "p": 0.7586206897,
196
  "r": 0.7096774194,
197
- "f": 0.7333333333
198
  },
199
  "nummod": {
200
- "p": 0.8032786885,
201
- "r": 0.8166666667,
202
- "f": 0.8099173554
203
  },
204
  "flat": {
205
- "p": 0.8364779874,
206
- "r": 0.880794702,
207
- "f": 0.8580645161
208
  },
209
  "compound:prt": {
210
- "p": 0.6666666667,
211
- "r": 0.5365853659,
212
- "f": 0.5945945946
213
  },
214
  "advcl": {
215
- "p": 0.6746031746,
216
- "r": 0.7327586207,
217
- "f": 0.7024793388
218
  },
219
  "mark": {
220
- "p": 0.9010309278,
221
- "r": 0.8973305955,
222
- "f": 0.8991769547
223
  },
224
  "cop": {
225
- "p": 0.8742857143,
226
- "r": 0.8742857143,
227
- "f": 0.8742857143
228
  },
229
  "dep": {
230
- "p": 0.2358490566,
231
- "r": 0.4716981132,
232
- "f": 0.3144654088
233
  },
234
  "nmod": {
235
- "p": 0.7105263158,
236
- "r": 0.685546875,
237
- "f": 0.6978131213
238
  },
239
  "iobj": {
240
- "p": 0.9375,
241
- "r": 0.6818181818,
242
- "f": 0.7894736842
243
  },
244
  "xcomp": {
245
- "p": 0.6,
246
- "r": 0.406779661,
247
- "f": 0.4848484848
248
  },
249
  "list": {
250
- "p": 0.5,
251
  "r": 0.2777777778,
252
- "f": 0.3571428571
253
  },
254
  "vocative": {
255
  "p": 0.0,
@@ -257,24 +257,24 @@
257
  "f": 0.0
258
  },
259
  "fixed": {
260
- "p": 0.9444444444,
261
- "r": 0.8292682927,
262
- "f": 0.8831168831
263
- },
264
- "appos": {
265
- "p": 0.7142857143,
266
- "r": 0.6060606061,
267
- "f": 0.6557377049
268
  },
269
  "expl": {
270
- "p": 0.9393939394,
271
  "r": 0.9117647059,
272
- "f": 0.9253731343
 
 
 
 
 
273
  },
274
  "obl:tmod": {
275
- "p": 0.8333333333,
276
- "r": 0.5555555556,
277
- "f": 0.6666666667
278
  },
279
  "discourse": {
280
  "p": 0.0,
@@ -287,32 +287,32 @@
287
  "f": 0.0
288
  }
289
  },
290
- "lemma_acc": 0.9459564165,
291
- "tag_acc": 0.9746222394,
292
- "ents_p": 0.8118609407,
293
  "ents_r": 0.8270833333,
294
- "ents_f": 0.8194014448,
295
  "ents_per_type": {
296
  "PER": {
297
- "p": 0.9018404908,
298
- "r": 0.8855421687,
299
- "f": 0.8936170213
300
  },
301
  "ORG": {
302
- "p": 0.7721518987,
303
- "r": 0.6777777778,
304
- "f": 0.7218934911
305
  },
306
  "MISC": {
307
- "p": 0.6717557252,
308
- "r": 0.7787610619,
309
- "f": 0.7213114754
310
  },
311
  "LOC": {
312
- "p": 0.8706896552,
313
- "r": 0.9099099099,
314
- "f": 0.8898678414
315
  }
316
  },
317
- "speed": 4656.9787909711
318
  }
 
1
  {
2
+ "token_acc": 0.9989350373,
3
  "token_p": 0.9977732598,
4
  "token_r": 0.9974835463,
5
  "token_f": 0.997628382,
6
+ "pos_acc": 0.9767058937,
7
+ "morph_acc": 0.97360647,
8
+ "morph_micro_p": 0.9872225616,
9
+ "morph_micro_r": 0.9789006108,
10
+ "morph_micro_f": 0.9830439741,
11
  "morph_per_feat": {
12
  "Mood": {
13
+ "p": 0.9904761905,
14
+ "r": 0.9914204004,
15
+ "f": 0.9909480705
16
  },
17
  "Tense": {
18
+ "p": 0.984882842,
19
+ "r": 0.9811746988,
20
+ "f": 0.9830252735
21
  },
22
  "VerbForm": {
23
+ "p": 0.9833948339,
24
+ "r": 0.9785801714,
25
+ "f": 0.9809815951
26
  },
27
  "Voice": {
28
+ "p": 0.9902985075,
29
+ "r": 0.9917787743,
30
+ "f": 0.9910380881
31
  },
32
  "Definite": {
33
+ "p": 0.9903459372,
34
  "r": 0.9727380482,
35
+ "f": 0.9814630257
36
  },
37
  "Gender": {
38
+ "p": 0.9788235294,
39
+ "r": 0.9677633765,
40
+ "f": 0.9732620321
41
  },
42
  "Number": {
43
+ "p": 0.9883935637,
44
+ "r": 0.9773082942,
45
+ "f": 0.9828196721
46
  },
47
  "AdpType": {
48
+ "p": 0.9982238011,
49
+ "r": 0.9938107869,
50
+ "f": 0.9960124058
51
  },
52
  "PartType": {
53
  "p": 1.0,
 
55
  "f": 0.9983739837
56
  },
57
  "Case": {
58
+ "p": 0.9951923077,
59
+ "r": 0.981042654,
60
+ "f": 0.9880668258
61
  },
62
  "Person": {
63
+ "p": 0.9892665474,
64
+ "r": 0.9822380107,
65
+ "f": 0.9857397504
66
  },
67
  "PronType": {
68
+ "p": 0.9901315789,
69
+ "r": 0.9901315789,
70
+ "f": 0.9901315789
71
  },
72
  "NumType": {
73
  "p": 0.9865771812,
 
75
  "f": 0.98
76
  },
77
  "Degree": {
78
+ "p": 0.9745454545,
79
+ "r": 0.9686746988,
80
+ "f": 0.9716012085
81
  },
82
  "Reflex": {
83
  "p": 1.0,
84
  "r": 1.0,
85
  "f": 1.0
86
  },
 
 
 
 
 
87
  "Number[psor]": {
88
  "p": 0.9770114943,
89
  "r": 0.988372093,
 
95
  "f": 0.9942857143
96
  },
97
  "Foreign": {
98
+ "p": 0.8571428571,
99
+ "r": 0.6,
100
+ "f": 0.7058823529
101
  },
102
  "Abbr": {
103
  "p": 1.0,
 
108
  "p": 1.0,
109
  "r": 1.0,
110
  "f": 1.0
111
+ },
112
+ "Polite": {
113
+ "p": 0.0,
114
+ "r": 0.0,
115
+ "f": 0.0
116
  }
117
  },
118
+ "sents_p": 0.8584070796,
119
+ "sents_r": 0.859929078,
120
+ "sents_f": 0.8591674048,
121
+ "dep_uas": 0.8648950424,
122
+ "dep_las": 0.8355942612,
123
  "dep_las_per_type": {
124
  "advmod": {
125
+ "p": 0.7762430939,
126
+ "r": 0.7937853107,
127
+ "f": 0.7849162011
128
  },
129
  "root": {
130
+ "p": 0.8490230906,
131
+ "r": 0.8475177305,
132
+ "f": 0.8482697427
133
  },
134
  "nsubj": {
135
+ "p": 0.9080338266,
136
+ "r": 0.9061181435,
137
+ "f": 0.9070749736
138
  },
139
  "case": {
140
+ "p": 0.92,
141
+ "r": 0.9072978304,
142
+ "f": 0.9136047666
143
  },
144
  "obl": {
145
+ "p": 0.784591195,
146
+ "r": 0.7748447205,
147
+ "f": 0.7796875
148
  },
149
  "cc": {
150
+ "p": 0.8579710145,
151
+ "r": 0.8604651163,
152
+ "f": 0.8592162554
153
  },
154
  "conj": {
155
+ "p": 0.7146596859,
156
+ "r": 0.728,
157
+ "f": 0.7212681638
158
  },
159
  "obj": {
160
+ "p": 0.8661710037,
161
+ "r": 0.9048543689,
162
+ "f": 0.8850902184
163
  },
164
  "aux": {
165
+ "p": 0.8927536232,
166
+ "r": 0.8979591837,
167
+ "f": 0.8953488372
168
  },
169
  "acl:relcl": {
170
+ "p": 0.7314285714,
171
+ "r": 0.6918918919,
172
+ "f": 0.7111111111
173
  },
174
  "advmod:lmod": {
175
+ "p": 0.7878787879,
176
  "r": 0.776119403,
177
+ "f": 0.7819548872
178
  },
179
  "det": {
180
+ "p": 0.9248366013,
181
+ "r": 0.9324546952,
182
+ "f": 0.9286300246
183
  },
184
  "amod": {
185
+ "p": 0.8700854701,
186
+ "r": 0.8686006826,
187
+ "f": 0.8693424424
188
  },
189
  "nmod:poss": {
190
+ "p": 0.7326732673,
191
+ "r": 0.7326732673,
192
+ "f": 0.7326732673
193
  },
194
  "ccomp": {
195
+ "p": 0.6875,
196
  "r": 0.7096774194,
197
+ "f": 0.6984126984
198
  },
199
  "nummod": {
200
+ "p": 0.8211382114,
201
+ "r": 0.8416666667,
202
+ "f": 0.8312757202
203
  },
204
  "flat": {
205
+ "p": 0.8846153846,
206
+ "r": 0.9139072848,
207
+ "f": 0.8990228013
208
  },
209
  "compound:prt": {
210
+ "p": 0.6333333333,
211
+ "r": 0.4634146341,
212
+ "f": 0.5352112676
213
  },
214
  "advcl": {
215
+ "p": 0.7433628319,
216
+ "r": 0.724137931,
217
+ "f": 0.7336244541
218
  },
219
  "mark": {
220
+ "p": 0.9074074074,
221
+ "r": 0.9055441478,
222
+ "f": 0.9064748201
223
  },
224
  "cop": {
225
+ "p": 0.8806818182,
226
+ "r": 0.8857142857,
227
+ "f": 0.8831908832
228
  },
229
  "dep": {
230
+ "p": 0.219047619,
231
+ "r": 0.4339622642,
232
+ "f": 0.2911392405
233
  },
234
  "nmod": {
235
+ "p": 0.7094188377,
236
+ "r": 0.69140625,
237
+ "f": 0.7002967359
238
  },
239
  "iobj": {
240
+ "p": 0.9230769231,
241
+ "r": 0.5454545455,
242
+ "f": 0.6857142857
243
  },
244
  "xcomp": {
245
+ "p": 0.6388888889,
246
+ "r": 0.3898305085,
247
+ "f": 0.4842105263
248
  },
249
  "list": {
250
+ "p": 0.3571428571,
251
  "r": 0.2777777778,
252
+ "f": 0.3125
253
  },
254
  "vocative": {
255
  "p": 0.0,
 
257
  "f": 0.0
258
  },
259
  "fixed": {
260
+ "p": 0.9428571429,
261
+ "r": 0.8048780488,
262
+ "f": 0.8684210526
 
 
 
 
 
263
  },
264
  "expl": {
265
+ "p": 0.9117647059,
266
  "r": 0.9117647059,
267
+ "f": 0.9117647059
268
+ },
269
+ "appos": {
270
+ "p": 0.7096774194,
271
+ "r": 0.6666666667,
272
+ "f": 0.6875
273
  },
274
  "obl:tmod": {
275
+ "p": 0.9,
276
+ "r": 0.5,
277
+ "f": 0.6428571429
278
  },
279
  "discourse": {
280
  "p": 0.0,
 
287
  "f": 0.0
288
  }
289
  },
290
+ "lemma_acc": 0.9471186441,
291
+ "tag_acc": 0.9767058937,
292
+ "ents_p": 0.8236514523,
293
  "ents_r": 0.8270833333,
294
+ "ents_f": 0.8253638254,
295
  "ents_per_type": {
296
  "PER": {
297
+ "p": 0.8988095238,
298
+ "r": 0.9096385542,
299
+ "f": 0.9041916168
300
  },
301
  "ORG": {
302
+ "p": 0.7590361446,
303
+ "r": 0.7,
304
+ "f": 0.7283236994
305
  },
306
  "MISC": {
307
+ "p": 0.7043478261,
308
+ "r": 0.7168141593,
309
+ "f": 0.7105263158
310
  },
311
  "LOC": {
312
+ "p": 0.8793103448,
313
+ "r": 0.9189189189,
314
+ "f": 0.8986784141
315
  }
316
  },
317
+ "speed": 4246.2689210915
318
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -155,11 +155,12 @@ dropout = 0.1
155
  accumulate_gradient = 3
156
  patience = 5000
157
  max_epochs = 0
158
- max_steps = 16000
159
  eval_frequency = 1000
160
  frozen_components = []
161
  before_to_disk = null
162
  annotating_components = []
 
163
 
164
  [training.batcher]
165
  @batchers = "spacy.batch_by_padded.v1"
 
155
  accumulate_gradient = 3
156
  patience = 5000
157
  max_epochs = 0
158
+ max_steps = 20000
159
  eval_frequency = 1000
160
  frozen_components = []
161
  before_to_disk = null
162
  annotating_components = []
163
+ before_update = null
164
 
165
  [training.batcher]
166
  @batchers = "spacy.batch_by_padded.v1"
da_core_news_trf-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd6c07a3173c0df1bd4fe360bf39067d6bc4f694a45d7db9f4eef0e7bcbdf8ac
3
- size 413509117
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7aa2530ba32c611b2552c6c0f549d0347557c9da4dff57ea0d61d9c42559b0
3
+ size 413504819
lemmatizer/cfg CHANGED
@@ -110,18 +110,18 @@
110
  229,
111
  231,
112
  232,
113
- 233,
114
  235,
115
- 236,
116
  238,
117
- 239,
118
- 243,
119
- 249,
120
- 253,
121
- 255,
122
- 257,
123
- 259,
124
- 261,
125
  263,
126
  264,
127
  265,
@@ -133,134 +133,133 @@
133
  277,
134
  279,
135
  281,
136
- 283,
137
  285,
138
- 287,
139
- 289,
140
- 293,
 
141
  294,
142
- 296,
 
143
  298,
144
- 300,
145
- 302,
146
- 304,
147
  306,
148
- 308,
149
  310,
150
  312,
151
- 314,
152
  316,
153
  318,
154
  319,
155
- 320,
156
  322,
157
  324,
 
158
  327,
159
- 330,
160
  331,
161
  333,
162
- 336,
163
  337,
164
  339,
165
  340,
166
  342,
167
  343,
168
- 344,
169
- 346,
170
  347,
171
  349,
172
  350,
173
  354,
174
  356,
175
- 357,
176
- 358,
177
- 362,
178
  364,
179
- 366,
180
  368,
181
- 370,
182
- 374,
 
 
 
183
  377,
184
- 378,
185
- 381,
186
- 382,
187
- 384,
188
- 385,
189
  386,
190
- 389,
191
  390,
192
- 393,
 
 
193
  396,
194
  397,
195
- 400,
196
- 404,
 
 
197
  406,
198
  407,
199
- 408,
200
  409,
201
- 410,
202
- 412,
203
  413,
204
- 415,
205
  416,
 
206
  419,
 
207
  421,
208
  422,
209
- 423,
210
  424,
211
  426,
212
- 427,
213
  430,
214
- 431,
215
- 433,
216
  434,
217
- 436,
218
  437,
219
  439,
220
  441,
221
  443,
222
  445,
223
- 446,
224
- 448,
225
  449,
226
  451,
227
- 452,
228
  454,
229
  456,
230
  457,
231
- 461,
 
232
  462,
233
  464,
234
  465,
235
- 467,
236
  470,
237
- 472,
 
 
238
  475,
239
- 478,
240
- 479,
241
  481,
242
- 483,
243
  484,
244
- 487,
245
  488,
 
246
  491,
247
  493,
248
- 496,
 
249
  498,
250
- 499,
251
- 500,
252
  501,
253
- 502,
254
- 504,
255
- 505,
256
  506,
257
  508,
258
  509,
 
259
  511,
260
- 512,
261
  514,
262
- 516,
263
- 518,
264
  519,
265
  521,
266
  522,
@@ -269,7 +268,7 @@
269
  525,
270
  527,
271
  528,
272
- 529,
273
  531,
274
  532,
275
  533,
@@ -282,21 +281,23 @@
282
  543,
283
  546,
284
  547,
 
285
  549,
286
  551,
287
- 555,
288
- 557,
289
  558,
290
- 559,
291
  560,
292
  561,
 
293
  563,
294
  564,
295
- 566,
296
- 568,
297
  569,
298
- 571,
299
- 573,
 
300
  575,
301
  576,
302
  577,
@@ -304,153 +305,152 @@
304
  580,
305
  584,
306
  586,
307
- 587,
308
- 590,
309
- 593,
310
- 595,
311
- 597,
312
- 601,
313
  602,
314
- 604,
 
315
  606,
316
- 607,
317
- 608,
318
- 609,
319
- 613,
320
- 615,
321
- 617,
322
  621,
 
323
  623,
324
  624,
325
  625,
326
  626,
327
- 627,
328
  628,
329
- 629,
330
  631,
331
- 632,
332
  633,
333
- 635,
334
  636,
335
- 638,
336
- 639,
337
  640,
338
- 643,
339
- 645,
340
- 649,
 
341
  650,
342
- 651,
343
  653,
 
344
  656,
345
  658,
346
  659,
347
- 661,
 
348
  663,
349
  664,
350
- 665,
351
- 667,
352
  669,
353
- 670,
354
- 672,
355
  674,
356
- 675,
357
- 677,
358
  679,
359
- 680,
360
  681,
361
  683,
 
362
  685,
363
  687,
364
  688,
365
- 689,
366
  691,
367
- 692,
368
  693,
369
  694,
370
- 697,
371
  698,
372
  699,
373
  700,
374
- 702,
375
- 704,
 
376
  706,
377
- 707,
378
  708,
379
  709,
380
- 713,
381
- 716,
 
382
  718,
383
- 719,
384
- 723,
385
  725,
386
- 728,
387
- 729,
388
- 731,
389
  732,
390
- 733,
391
  735,
392
- 737,
393
  738,
394
- 739,
395
  740,
396
  741,
397
  742,
 
 
398
  745,
399
  746,
 
400
  748,
 
401
  752,
 
402
  755,
403
- 756,
404
- 758,
405
- 760,
406
- 761,
407
  762,
408
  764,
409
  765,
 
410
  767,
411
  769,
412
  770,
413
- 771,
414
  772,
415
- 773,
416
  774,
 
 
 
417
  778,
418
- 780,
419
- 781,
420
  782,
421
- 783,
 
422
  786,
423
  789,
424
- 790,
425
- 791,
426
  793,
427
  795,
428
- 796,
429
  797,
 
430
  799,
431
- 800,
432
  801,
433
  802,
434
  803,
435
  804,
436
- 806,
437
  807,
438
  808,
439
  809,
440
  810,
441
- 812,
442
- 814,
443
- 816,
444
  817,
445
- 819,
446
- 821,
 
447
  823,
448
- 824,
449
- 826,
450
- 828,
451
- 830,
452
- 832,
453
- 834,
454
- 835
455
  ]
456
  }
 
110
  229,
111
  231,
112
  232,
113
+ 234,
114
  235,
115
+ 237,
116
  238,
117
+ 242,
118
+ 248,
119
+ 252,
120
+ 254,
121
+ 256,
122
+ 258,
123
+ 260,
124
+ 262,
125
  263,
126
  264,
127
  265,
 
133
  277,
134
  279,
135
  281,
 
136
  285,
137
+ 286,
138
+ 288,
139
+ 290,
140
+ 292,
141
  294,
142
+ 295,
143
+ 297,
144
  298,
145
+ 299,
146
+ 301,
147
+ 303,
148
  306,
149
+ 309,
150
  310,
151
  312,
152
+ 315,
153
  316,
154
  318,
155
  319,
156
+ 321,
157
  322,
158
  324,
159
+ 326,
160
  327,
161
+ 329,
162
  331,
163
  333,
164
+ 335,
165
  337,
166
  339,
167
  340,
168
  342,
169
  343,
 
 
170
  347,
171
  349,
172
  350,
173
  354,
174
  356,
175
+ 360,
176
+ 363,
 
177
  364,
178
+ 365,
179
  368,
180
+ 369,
181
+ 371,
182
+ 372,
183
+ 373,
184
+ 376,
185
  377,
186
+ 380,
187
+ 383,
 
 
 
188
  386,
 
189
  390,
190
+ 392,
191
+ 394,
192
+ 395,
193
  396,
194
  397,
195
+ 399,
196
+ 401,
197
+ 403,
198
+ 405,
199
  406,
200
  407,
 
201
  409,
202
+ 411,
 
203
  413,
 
204
  416,
205
+ 418,
206
  419,
207
+ 420,
208
  421,
209
  422,
 
210
  424,
211
  426,
212
+ 429,
213
  430,
214
+ 432,
 
215
  434,
216
+ 435,
217
  437,
218
  439,
219
  441,
220
  443,
221
  445,
222
+ 447,
 
223
  449,
224
  451,
225
+ 453,
226
  454,
227
  456,
228
  457,
229
+ 459,
230
+ 460,
231
  462,
232
  464,
233
  465,
234
+ 469,
235
  470,
236
+ 471,
237
+ 473,
238
+ 474,
239
  475,
240
+ 477,
241
+ 480,
242
  481,
 
243
  484,
244
+ 485,
245
  488,
246
+ 489,
247
  491,
248
  493,
249
+ 494,
250
+ 497,
251
  498,
 
 
252
  501,
253
+ 503,
 
 
254
  506,
255
  508,
256
  509,
257
+ 510,
258
  511,
259
+ 513,
260
  514,
261
+ 515,
262
+ 517,
263
  519,
264
  521,
265
  522,
 
268
  525,
269
  527,
270
  528,
271
+ 530,
272
  531,
273
  532,
274
  533,
 
281
  543,
282
  546,
283
  547,
284
+ 548,
285
  549,
286
  551,
287
+ 552,
288
+ 554,
289
  558,
 
290
  560,
291
  561,
292
+ 562,
293
  563,
294
  564,
295
+ 565,
296
+ 567,
297
  569,
298
+ 570,
299
+ 572,
300
+ 574,
301
  575,
302
  576,
303
  577,
 
305
  580,
306
  584,
307
  586,
308
+ 589,
309
+ 591,
310
+ 594,
311
+ 596,
312
+ 598,
 
313
  602,
314
+ 603,
315
+ 605,
316
  606,
317
+ 610,
318
+ 612,
319
+ 614,
320
+ 618,
321
+ 620,
 
322
  621,
323
+ 622,
324
  623,
325
  624,
326
  625,
327
  626,
 
328
  628,
329
+ 630,
330
  631,
 
331
  633,
332
+ 634,
333
  636,
334
+ 637,
 
335
  640,
336
+ 642,
337
+ 646,
338
+ 647,
339
+ 648,
340
  650,
 
341
  653,
342
+ 655,
343
  656,
344
  658,
345
  659,
346
+ 660,
347
+ 662,
348
  663,
349
  664,
350
+ 666,
351
+ 668,
352
  669,
353
+ 671,
354
+ 673,
355
  674,
356
+ 676,
357
+ 678,
358
  679,
 
359
  681,
360
  683,
361
+ 684,
362
  685,
363
  687,
364
  688,
365
+ 690,
366
  691,
 
367
  693,
368
  694,
369
+ 695,
370
  698,
371
  699,
372
  700,
373
+ 701,
374
+ 703,
375
+ 705,
376
  706,
 
377
  708,
378
  709,
379
+ 710,
380
+ 711,
381
+ 715,
382
  718,
383
+ 720,
384
+ 721,
385
  725,
386
+ 727,
387
+ 730,
 
388
  732,
389
+ 734,
390
  735,
391
+ 736,
392
  738,
 
393
  740,
394
  741,
395
  742,
396
+ 743,
397
+ 744,
398
  745,
399
  746,
400
+ 747,
401
  748,
402
+ 751,
403
  752,
404
+ 754,
405
  755,
406
+ 759,
 
 
 
407
  762,
408
  764,
409
  765,
410
+ 766,
411
  767,
412
  769,
413
  770,
 
414
  772,
 
415
  774,
416
+ 775,
417
+ 776,
418
+ 777,
419
  778,
 
 
420
  782,
421
+ 784,
422
+ 785,
423
  786,
424
  789,
425
+ 792,
 
426
  793,
427
  795,
 
428
  797,
429
+ 798,
430
  799,
 
431
  801,
432
  802,
433
  803,
434
  804,
435
+ 805,
436
  807,
437
  808,
438
  809,
439
  810,
440
+ 811,
441
+ 813,
442
+ 815,
443
  817,
444
+ 818,
445
+ 820,
446
+ 822,
447
  823,
448
+ 825,
449
+ 827,
450
+ 829,
451
+ 831,
452
+ 833,
453
+ 835,
454
+ 837
455
  ]
456
  }
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72880591a0a6b98e895eacb328491d7923cf6c86bd6b3c56a63582e53daa0796
3
  size 1391005
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6276af3c9a930d48e7caaf06aff36e32abc0cdadba2dc7ea9d3b78110037dd52
3
  size 1391005
lemmatizer/trees CHANGED
Binary files a/lemmatizer/trees and b/lemmatizer/trees differ
 
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"da",
3
  "name":"core_news_trf",
4
- "version":"3.4.0",
5
  "description":"Danish transformer pipeline (Maltehb/danish-bert-botxo). Components: transformer, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner, attribute_ruler.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"CC BY-SA 4.0",
10
- "spacy_version":">=3.4.0,<3.5.0",
11
- "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -242,55 +242,55 @@
242
 
243
  ],
244
  "performance":{
245
- "token_acc":0.9994672349,
246
  "token_p":0.9977732598,
247
  "token_r":0.9974835463,
248
  "token_f":0.997628382,
249
- "pos_acc":0.9746222394,
250
- "morph_acc":0.971716389,
251
- "morph_micro_p":0.9871860323,
252
- "morph_micro_r":0.9760738983,
253
- "morph_micro_f":0.9815985177,
254
  "morph_per_feat":{
255
  "Mood":{
256
- "p":0.9923150817,
257
- "r":0.9847473785,
258
- "f":0.9885167464
259
  },
260
  "Tense":{
261
- "p":0.9870525514,
262
- "r":0.9759036145,
263
- "f":0.9814464218
264
  },
265
  "VerbForm":{
266
- "p":0.9863861386,
267
- "r":0.9755201958,
268
- "f":0.9809230769
269
  },
270
  "Voice":{
271
- "p":0.9917293233,
272
- "r":0.985799701,
273
- "f":0.9887556222
274
  },
275
  "Definite":{
276
- "p":0.98915227,
277
  "r":0.9727380482,
278
- "f":0.980876494
279
  },
280
  "Gender":{
281
- "p":0.9797843666,
282
- "r":0.9664340312,
283
- "f":0.9730634097
284
  },
285
  "Number":{
286
- "p":0.9873217116,
287
- "r":0.9749608764,
288
- "f":0.9811023622
289
  },
290
  "AdpType":{
291
- "p":0.9973357016,
292
- "r":0.9929266136,
293
- "f":0.9951262738
294
  },
295
  "PartType":{
296
  "p":1.0,
@@ -298,19 +298,19 @@
298
  "f":0.9983739837
299
  },
300
  "Case":{
301
- "p":0.9919614148,
302
- "r":0.9747235387,
303
- "f":0.9832669323
304
  },
305
  "Person":{
306
- "p":0.9856630824,
307
- "r":0.9769094139,
308
- "f":0.9812667261
309
  },
310
  "PronType":{
311
- "p":0.9925373134,
312
- "r":0.984375,
313
- "f":0.9884393064
314
  },
315
  "NumType":{
316
  "p":0.9865771812,
@@ -318,20 +318,15 @@
318
  "f":0.98
319
  },
320
  "Degree":{
321
- "p":0.9697702539,
322
- "r":0.9662650602,
323
- "f":0.968014484
324
  },
325
  "Reflex":{
326
  "p":1.0,
327
  "r":1.0,
328
  "f":1.0
329
  },
330
- "Polite":{
331
- "p":0.0,
332
- "r":0.0,
333
- "f":0.0
334
- },
335
  "Number[psor]":{
336
  "p":0.9770114943,
337
  "r":0.988372093,
@@ -343,9 +338,9 @@
343
  "f":0.9942857143
344
  },
345
  "Foreign":{
346
- "p":0.7777777778,
347
- "r":0.7,
348
- "f":0.7368421053
349
  },
350
  "Abbr":{
351
  "p":1.0,
@@ -356,143 +351,148 @@
356
  "p":1.0,
357
  "r":1.0,
358
  "f":1.0
 
 
 
 
 
359
  }
360
  },
361
- "sents_p":0.8160136286,
362
- "sents_r":0.8492907801,
363
- "sents_f":0.832319722,
364
- "dep_uas":0.8596491228,
365
- "dep_las":0.8301675978,
366
  "dep_las_per_type":{
367
  "advmod":{
368
- "p":0.7773109244,
369
- "r":0.7838983051,
370
- "f":0.7805907173
371
  },
372
  "root":{
373
- "p":0.8293515358,
374
- "r":0.8617021277,
375
- "f":0.8452173913
376
  },
377
  "nsubj":{
378
- "p":0.8976545842,
379
- "r":0.888185654,
380
- "f":0.8928950159
381
  },
382
  "case":{
383
- "p":0.9175769613,
384
- "r":0.9112426036,
385
- "f":0.9143988125
386
  },
387
  "obl":{
388
- "p":0.7834394904,
389
- "r":0.7639751553,
390
- "f":0.7735849057
391
  },
392
  "cc":{
393
- "p":0.8425655977,
394
- "r":0.8401162791,
395
- "f":0.8413391557
396
  },
397
  "conj":{
398
- "p":0.7154696133,
399
- "r":0.6906666667,
400
- "f":0.7028493894
401
  },
402
  "obj":{
403
- "p":0.8701298701,
404
- "r":0.9106796117,
405
- "f":0.889943074
406
  },
407
  "aux":{
408
- "p":0.8699421965,
409
- "r":0.8775510204,
410
- "f":0.8737300435
411
  },
412
  "acl:relcl":{
413
- "p":0.7630057803,
414
- "r":0.7135135135,
415
- "f":0.7374301676
416
  },
417
  "advmod:lmod":{
418
- "p":0.8,
419
  "r":0.776119403,
420
- "f":0.7878787879
421
  },
422
  "det":{
423
- "p":0.9169381107,
424
- "r":0.9275123558,
425
- "f":0.9221949222
426
  },
427
  "amod":{
428
- "p":0.8605442177,
429
- "r":0.8634812287,
430
- "f":0.8620102215
431
  },
432
  "nmod:poss":{
433
- "p":0.7765957447,
434
- "r":0.7227722772,
435
- "f":0.7487179487
436
  },
437
  "ccomp":{
438
- "p":0.7586206897,
439
  "r":0.7096774194,
440
- "f":0.7333333333
441
  },
442
  "nummod":{
443
- "p":0.8032786885,
444
- "r":0.8166666667,
445
- "f":0.8099173554
446
  },
447
  "flat":{
448
- "p":0.8364779874,
449
- "r":0.880794702,
450
- "f":0.8580645161
451
  },
452
  "compound:prt":{
453
- "p":0.6666666667,
454
- "r":0.5365853659,
455
- "f":0.5945945946
456
  },
457
  "advcl":{
458
- "p":0.6746031746,
459
- "r":0.7327586207,
460
- "f":0.7024793388
461
  },
462
  "mark":{
463
- "p":0.9010309278,
464
- "r":0.8973305955,
465
- "f":0.8991769547
466
  },
467
  "cop":{
468
- "p":0.8742857143,
469
- "r":0.8742857143,
470
- "f":0.8742857143
471
  },
472
  "dep":{
473
- "p":0.2358490566,
474
- "r":0.4716981132,
475
- "f":0.3144654088
476
  },
477
  "nmod":{
478
- "p":0.7105263158,
479
- "r":0.685546875,
480
- "f":0.6978131213
481
  },
482
  "iobj":{
483
- "p":0.9375,
484
- "r":0.6818181818,
485
- "f":0.7894736842
486
  },
487
  "xcomp":{
488
- "p":0.6,
489
- "r":0.406779661,
490
- "f":0.4848484848
491
  },
492
  "list":{
493
- "p":0.5,
494
  "r":0.2777777778,
495
- "f":0.3571428571
496
  },
497
  "vocative":{
498
  "p":0.0,
@@ -500,24 +500,24 @@
500
  "f":0.0
501
  },
502
  "fixed":{
503
- "p":0.9444444444,
504
- "r":0.8292682927,
505
- "f":0.8831168831
506
- },
507
- "appos":{
508
- "p":0.7142857143,
509
- "r":0.6060606061,
510
- "f":0.6557377049
511
  },
512
  "expl":{
513
- "p":0.9393939394,
514
  "r":0.9117647059,
515
- "f":0.9253731343
 
 
 
 
 
516
  },
517
  "obl:tmod":{
518
- "p":0.8333333333,
519
- "r":0.5555555556,
520
- "f":0.6666666667
521
  },
522
  "discourse":{
523
  "p":0.0,
@@ -530,34 +530,34 @@
530
  "f":0.0
531
  }
532
  },
533
- "lemma_acc":0.9459564165,
534
- "tag_acc":0.9746222394,
535
- "ents_p":0.8118609407,
536
  "ents_r":0.8270833333,
537
- "ents_f":0.8194014448,
538
  "ents_per_type":{
539
  "PER":{
540
- "p":0.9018404908,
541
- "r":0.8855421687,
542
- "f":0.8936170213
543
  },
544
  "ORG":{
545
- "p":0.7721518987,
546
- "r":0.6777777778,
547
- "f":0.7218934911
548
  },
549
  "MISC":{
550
- "p":0.6717557252,
551
- "r":0.7787610619,
552
- "f":0.7213114754
553
  },
554
  "LOC":{
555
- "p":0.8706896552,
556
- "r":0.9099099099,
557
- "f":0.8898678414
558
  }
559
  },
560
- "speed":4656.9787909711
561
  },
562
  "sources":[
563
  {
@@ -580,6 +580,6 @@
580
  }
581
  ],
582
  "requirements":[
583
- "spacy-transformers>=1.1.2,<1.2.0"
584
  ]
585
  }
 
1
  {
2
  "lang":"da",
3
  "name":"core_news_trf",
4
+ "version":"3.5.0",
5
  "description":"Danish transformer pipeline (Maltehb/danish-bert-botxo). Components: transformer, morphologizer, parser, lemmatizer (trainable_lemmatizer), ner, attribute_ruler.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"CC BY-SA 4.0",
10
+ "spacy_version":">=3.5.0,<3.6.0",
11
+ "spacy_git_version":"9e0322de1",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
 
242
 
243
  ],
244
  "performance":{
245
+ "token_acc":0.9989350373,
246
  "token_p":0.9977732598,
247
  "token_r":0.9974835463,
248
  "token_f":0.997628382,
249
+ "pos_acc":0.9767058937,
250
+ "morph_acc":0.97360647,
251
+ "morph_micro_p":0.9872225616,
252
+ "morph_micro_r":0.9789006108,
253
+ "morph_micro_f":0.9830439741,
254
  "morph_per_feat":{
255
  "Mood":{
256
+ "p":0.9904761905,
257
+ "r":0.9914204004,
258
+ "f":0.9909480705
259
  },
260
  "Tense":{
261
+ "p":0.984882842,
262
+ "r":0.9811746988,
263
+ "f":0.9830252735
264
  },
265
  "VerbForm":{
266
+ "p":0.9833948339,
267
+ "r":0.9785801714,
268
+ "f":0.9809815951
269
  },
270
  "Voice":{
271
+ "p":0.9902985075,
272
+ "r":0.9917787743,
273
+ "f":0.9910380881
274
  },
275
  "Definite":{
276
+ "p":0.9903459372,
277
  "r":0.9727380482,
278
+ "f":0.9814630257
279
  },
280
  "Gender":{
281
+ "p":0.9788235294,
282
+ "r":0.9677633765,
283
+ "f":0.9732620321
284
  },
285
  "Number":{
286
+ "p":0.9883935637,
287
+ "r":0.9773082942,
288
+ "f":0.9828196721
289
  },
290
  "AdpType":{
291
+ "p":0.9982238011,
292
+ "r":0.9938107869,
293
+ "f":0.9960124058
294
  },
295
  "PartType":{
296
  "p":1.0,
 
298
  "f":0.9983739837
299
  },
300
  "Case":{
301
+ "p":0.9951923077,
302
+ "r":0.981042654,
303
+ "f":0.9880668258
304
  },
305
  "Person":{
306
+ "p":0.9892665474,
307
+ "r":0.9822380107,
308
+ "f":0.9857397504
309
  },
310
  "PronType":{
311
+ "p":0.9901315789,
312
+ "r":0.9901315789,
313
+ "f":0.9901315789
314
  },
315
  "NumType":{
316
  "p":0.9865771812,
 
318
  "f":0.98
319
  },
320
  "Degree":{
321
+ "p":0.9745454545,
322
+ "r":0.9686746988,
323
+ "f":0.9716012085
324
  },
325
  "Reflex":{
326
  "p":1.0,
327
  "r":1.0,
328
  "f":1.0
329
  },
 
 
 
 
 
330
  "Number[psor]":{
331
  "p":0.9770114943,
332
  "r":0.988372093,
 
338
  "f":0.9942857143
339
  },
340
  "Foreign":{
341
+ "p":0.8571428571,
342
+ "r":0.6,
343
+ "f":0.7058823529
344
  },
345
  "Abbr":{
346
  "p":1.0,
 
351
  "p":1.0,
352
  "r":1.0,
353
  "f":1.0
354
+ },
355
+ "Polite":{
356
+ "p":0.0,
357
+ "r":0.0,
358
+ "f":0.0
359
  }
360
  },
361
+ "sents_p":0.8584070796,
362
+ "sents_r":0.859929078,
363
+ "sents_f":0.8591674048,
364
+ "dep_uas":0.8648950424,
365
+ "dep_las":0.8355942612,
366
  "dep_las_per_type":{
367
  "advmod":{
368
+ "p":0.7762430939,
369
+ "r":0.7937853107,
370
+ "f":0.7849162011
371
  },
372
  "root":{
373
+ "p":0.8490230906,
374
+ "r":0.8475177305,
375
+ "f":0.8482697427
376
  },
377
  "nsubj":{
378
+ "p":0.9080338266,
379
+ "r":0.9061181435,
380
+ "f":0.9070749736
381
  },
382
  "case":{
383
+ "p":0.92,
384
+ "r":0.9072978304,
385
+ "f":0.9136047666
386
  },
387
  "obl":{
388
+ "p":0.784591195,
389
+ "r":0.7748447205,
390
+ "f":0.7796875
391
  },
392
  "cc":{
393
+ "p":0.8579710145,
394
+ "r":0.8604651163,
395
+ "f":0.8592162554
396
  },
397
  "conj":{
398
+ "p":0.7146596859,
399
+ "r":0.728,
400
+ "f":0.7212681638
401
  },
402
  "obj":{
403
+ "p":0.8661710037,
404
+ "r":0.9048543689,
405
+ "f":0.8850902184
406
  },
407
  "aux":{
408
+ "p":0.8927536232,
409
+ "r":0.8979591837,
410
+ "f":0.8953488372
411
  },
412
  "acl:relcl":{
413
+ "p":0.7314285714,
414
+ "r":0.6918918919,
415
+ "f":0.7111111111
416
  },
417
  "advmod:lmod":{
418
+ "p":0.7878787879,
419
  "r":0.776119403,
420
+ "f":0.7819548872
421
  },
422
  "det":{
423
+ "p":0.9248366013,
424
+ "r":0.9324546952,
425
+ "f":0.9286300246
426
  },
427
  "amod":{
428
+ "p":0.8700854701,
429
+ "r":0.8686006826,
430
+ "f":0.8693424424
431
  },
432
  "nmod:poss":{
433
+ "p":0.7326732673,
434
+ "r":0.7326732673,
435
+ "f":0.7326732673
436
  },
437
  "ccomp":{
438
+ "p":0.6875,
439
  "r":0.7096774194,
440
+ "f":0.6984126984
441
  },
442
  "nummod":{
443
+ "p":0.8211382114,
444
+ "r":0.8416666667,
445
+ "f":0.8312757202
446
  },
447
  "flat":{
448
+ "p":0.8846153846,
449
+ "r":0.9139072848,
450
+ "f":0.8990228013
451
  },
452
  "compound:prt":{
453
+ "p":0.6333333333,
454
+ "r":0.4634146341,
455
+ "f":0.5352112676
456
  },
457
  "advcl":{
458
+ "p":0.7433628319,
459
+ "r":0.724137931,
460
+ "f":0.7336244541
461
  },
462
  "mark":{
463
+ "p":0.9074074074,
464
+ "r":0.9055441478,
465
+ "f":0.9064748201
466
  },
467
  "cop":{
468
+ "p":0.8806818182,
469
+ "r":0.8857142857,
470
+ "f":0.8831908832
471
  },
472
  "dep":{
473
+ "p":0.219047619,
474
+ "r":0.4339622642,
475
+ "f":0.2911392405
476
  },
477
  "nmod":{
478
+ "p":0.7094188377,
479
+ "r":0.69140625,
480
+ "f":0.7002967359
481
  },
482
  "iobj":{
483
+ "p":0.9230769231,
484
+ "r":0.5454545455,
485
+ "f":0.6857142857
486
  },
487
  "xcomp":{
488
+ "p":0.6388888889,
489
+ "r":0.3898305085,
490
+ "f":0.4842105263
491
  },
492
  "list":{
493
+ "p":0.3571428571,
494
  "r":0.2777777778,
495
+ "f":0.3125
496
  },
497
  "vocative":{
498
  "p":0.0,
 
500
  "f":0.0
501
  },
502
  "fixed":{
503
+ "p":0.9428571429,
504
+ "r":0.8048780488,
505
+ "f":0.8684210526
 
 
 
 
 
506
  },
507
  "expl":{
508
+ "p":0.9117647059,
509
  "r":0.9117647059,
510
+ "f":0.9117647059
511
+ },
512
+ "appos":{
513
+ "p":0.7096774194,
514
+ "r":0.6666666667,
515
+ "f":0.6875
516
  },
517
  "obl:tmod":{
518
+ "p":0.9,
519
+ "r":0.5,
520
+ "f":0.6428571429
521
  },
522
  "discourse":{
523
  "p":0.0,
 
530
  "f":0.0
531
  }
532
  },
533
+ "lemma_acc":0.9471186441,
534
+ "tag_acc":0.9767058937,
535
+ "ents_p":0.8236514523,
536
  "ents_r":0.8270833333,
537
+ "ents_f":0.8253638254,
538
  "ents_per_type":{
539
  "PER":{
540
+ "p":0.8988095238,
541
+ "r":0.9096385542,
542
+ "f":0.9041916168
543
  },
544
  "ORG":{
545
+ "p":0.7590361446,
546
+ "r":0.7,
547
+ "f":0.7283236994
548
  },
549
  "MISC":{
550
+ "p":0.7043478261,
551
+ "r":0.7168141593,
552
+ "f":0.7105263158
553
  },
554
  "LOC":{
555
+ "p":0.8793103448,
556
+ "r":0.9189189189,
557
+ "f":0.8986784141
558
  }
559
  },
560
+ "speed":4246.2689210915
561
  },
562
  "sources":[
563
  {
 
580
  }
581
  ],
582
  "requirements":[
583
+ "spacy-transformers>=1.2.0.dev0,<1.3.0"
584
  ]
585
  }
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c8a3ae82c904aa28889940d9016755ac854a0a9c9afb2df2b70cdcfef1aa05b3
3
  size 483580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c38a379d45fb0918696257de7f95b9d88cd3823a8764f360fb6db04643f255c
3
  size 483580
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:197720aa3b307d6f5848667f84118234ab76bbebbb3c13e69c76a35c3011a940
3
  size 225962
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90b951cedd72c096c107dee5d9dec2e0f167f3e36609e3e9044e388d89c2e134
3
  size 225962
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:26bac3bcbe1f667cd32dbeb56fa105c836c07793fd807ce05535c65b805f6d31
3
  size 460325
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65cb1e68770082f252ade9487134863e7d3268336600cffdcb65e9648bebb83
3
  size 460325
tokenizer CHANGED
The diff for this file is too large to render. See raw diff
 
transformer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:baaad1b1983daf896766f03d629faafd62a9e8de1d70f61d0f03553695c46a8a
3
- size 443557655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cd238ce9d1077d8ff9de3bf1a24af4b7b2b7398fe8f430d23475e797752440f2
3
+ size 443557781
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:847c6829b856ad53cba8dd709f129df89311d57390c82a164d70c6ed000daa01
3
- size 469274
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cab468a09183a54b44da3197064c2bcf4cb4945f2ec1d1a78d9ce909529b6f9f
3
+ size 469421