Jacobo commited on
Commit
d3a8831
1 Parent(s): 53cd854

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -13,55 +13,55 @@ model-index:
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
- value: 0.9605186053
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
- value: 0.9557573982
24
  - task:
25
  name: MORPH
26
  type: token-classification
27
  metrics:
28
  - name: Morph (UFeats) Accuracy
29
  type: accuracy
30
- value: 0.8745238793
31
  - task:
32
  name: LEMMA
33
  type: token-classification
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
- value: 0.966891298
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
- value: 0.7632581307
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
- value: 0.706782889
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
- value: 0.5236742424
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
62
  | **Name** | `grc_proiel_sm` |
63
  | **Version** | `3.5.3` |
64
- | **spaCy** | `>=3.5.3,<3.6.0` |
65
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
66
  | **Components** | `tok2vec`, `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` | 95.89 |
91
- | `MORPH_ACC` | 88.10 |
92
- | `TAG_ACC` | 96.24 |
93
- | `DEP_UAS` | 76.22 |
94
- | `DEP_LAS` | 70.53 |
95
- | `SENTS_P` | 51.87 |
96
- | `SENTS_R` | 54.37 |
97
- | `SENTS_F` | 53.09 |
98
- | `LEMMA_ACC` | 96.69 |
99
- | `TOK2VEC_LOSS` | 4107659.15 |
100
- | `MORPHOLOGIZER_LOSS` | 127942.48 |
101
- | `TAGGER_LOSS` | 38984.64 |
102
- | `PARSER_LOSS` | 1907099.83 |
 
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
+ value: 0.9607383534
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
+ value: 0.9580281277
24
  - task:
25
  name: MORPH
26
  type: token-classification
27
  metrics:
28
  - name: Morph (UFeats) Accuracy
29
  type: accuracy
30
+ value: 0.8734251392
31
  - task:
32
  name: LEMMA
33
  type: token-classification
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
+ value: 0.9656460592
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
+ value: 0.759668913
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
+ value: 0.70443891
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
+ value: 0.5297098111
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
62
  | **Name** | `grc_proiel_sm` |
63
  | **Version** | `3.5.3` |
64
+ | **spaCy** | `>=3.6.0,<3.7.0` |
65
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
66
  | **Components** | `tok2vec`, `morphologizer`, `tagger`, `parser`, `lemmatizer`, `attribute_ruler` |
67
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
 
87
 
88
  | Type | Score |
89
  | --- | --- |
90
+ | `POS_ACC` | 95.80 |
91
+ | `MORPH_ACC` | 87.34 |
92
+ | `TAG_ACC` | 96.07 |
93
+ | `DEP_UAS` | 75.97 |
94
+ | `DEP_LAS` | 70.44 |
95
+ | `SENTS_P` | 49.91 |
96
+ | `SENTS_R` | 56.43 |
97
+ | `SENTS_F` | 52.97 |
98
+ | `LEMMA_ACC` | 96.56 |
99
+ | `TOK2VEC_LOSS` | 3641174.13 |
100
+ | `MORPHOLOGIZER_LOSS` | 196842.81 |
101
+ | `TAGGER_LOSS` | 59134.79 |
102
+ | `PARSER_LOSS` | 2326839.78 |
accuracy.json CHANGED
@@ -3,194 +3,194 @@
3
  "token_p":1.0,
4
  "token_r":1.0,
5
  "token_f":1.0,
6
- "pos_acc":0.9522307346,
7
- "morph_acc":0.8679585399,
8
- "morph_micro_p":0.9386159703,
9
- "morph_micro_r":0.9353097905,
10
- "morph_micro_f":0.9369599638,
11
  "morph_per_feat":{
12
  "Case":{
13
- "p":0.9519483939,
14
- "r":0.9510719453,
15
- "f":0.9515099678
16
  },
17
  "Gender":{
18
- "p":0.8993377483,
19
- "r":0.9004110861,
20
- "f":0.8998740971
21
  },
22
  "Number":{
23
- "p":0.9764389457,
24
- "r":0.9738197425,
25
- "f":0.9751275853
26
  },
27
  "Aspect":{
28
- "p":0.8838028169,
29
- "r":0.8794674142,
30
- "f":0.8816297857
31
  },
32
  "Mood":{
33
- "p":0.9252501471,
34
- "r":0.9155503786,
35
- "f":0.9203747073
36
  },
37
  "Person":{
38
- "p":0.9468003084,
39
- "r":0.9338403042,
40
- "f":0.9402756508
41
  },
42
  "Tense":{
43
- "p":0.8789996322,
44
- "r":0.8722627737,
45
- "f":0.8756182451
46
  },
47
  "VerbForm":{
48
- "p":0.9532916513,
49
- "r":0.9456402773,
50
- "f":0.9494505495
51
  },
52
  "Voice":{
53
- "p":0.9106289077,
54
- "r":0.903649635,
55
- "f":0.9071258472
56
  },
57
  "PronType":{
58
- "p":0.9730549006,
59
- "r":0.9662207358,
60
- "f":0.9696257761
61
  },
62
  "Degree":{
63
- "p":0.8448500652,
64
- "r":0.8481675393,
65
- "f":0.8465055519
66
  },
67
  "Definite":{
68
- "p":0.9812568908,
69
- "r":0.991643454,
70
- "f":0.9864228318
71
  },
72
  "Reflex":{
73
- "p":0.9777777778,
74
- "r":0.9565217391,
75
- "f":0.967032967
76
  },
77
  "Polarity":{
78
- "p":0.995412844,
79
- "r":0.9819004525,
80
- "f":0.9886104784
81
  },
82
  "Poss":{
83
- "p":0.875,
84
- "r":0.5384615385,
85
- "f":0.6666666667
86
  }
87
  },
88
- "tag_acc":0.95598618,
89
- "sents_p":0.5046040516,
90
- "sents_r":0.523400191,
91
- "sents_f":0.513830286,
92
- "dep_uas":0.7510139703,
93
- "dep_las":0.6927294577,
94
  "dep_las_per_type":{
95
  "iobj":{
96
- "p":0.6517647059,
97
- "r":0.6338672769,
98
- "f":0.6426914153
99
  },
100
  "root":{
101
- "p":0.7246777164,
102
- "r":0.7516714422,
103
- "f":0.7379278012
104
  },
105
  "nsubj":{
106
- "p":0.6446927374,
107
- "r":0.6468609865,
108
- "f":0.645775042
109
  },
110
  "advmod":{
111
- "p":0.633744856,
112
- "r":0.6416666667,
113
- "f":0.6376811594
114
  },
115
  "advcl":{
116
- "p":0.5542168675,
117
- "r":0.6102819237,
118
- "f":0.5808997632
119
  },
120
  "ccomp":{
121
- "p":0.4700854701,
122
- "r":0.3395061728,
123
- "f":0.394265233
124
  },
125
  "discourse":{
126
- "p":0.7565698479,
127
- "r":0.7524071527,
128
- "f":0.7544827586
129
  },
130
  "obj":{
131
- "p":0.7187851519,
132
- "r":0.7045203969,
133
- "f":0.7115812918
134
  },
135
  "det":{
136
- "p":0.9036197122,
137
- "r":0.9091706889,
138
- "f":0.9063867017
139
  },
140
  "nmod":{
141
- "p":0.6400742115,
142
- "r":0.666023166,
143
- "f":0.6527909177
144
  },
145
  "cop":{
146
- "p":0.6457399103,
147
- "r":0.679245283,
148
- "f":0.6620689655
149
  },
150
  "appos":{
151
- "p":0.4,
152
- "r":0.256097561,
153
- "f":0.312267658
154
  },
155
  "case":{
156
- "p":0.9377123443,
157
- "r":0.9419795222,
158
- "f":0.9398410897
159
  },
160
  "acl":{
161
- "p":0.4307692308,
162
- "r":0.3414634146,
163
- "f":0.380952381
164
  },
165
  "mark":{
166
- "p":0.7863636364,
167
- "r":0.8009259259,
168
- "f":0.7935779817
169
  },
170
  "obl":{
171
- "p":0.6577608142,
172
- "r":0.6494974874,
173
- "f":0.6536030341
174
  },
175
  "nsubj:pass":{
176
- "p":0.5222222222,
177
- "r":0.4947368421,
178
- "f":0.5081081081
179
  },
180
  "xcomp":{
181
- "p":0.5155555556,
182
- "r":0.4833333333,
183
- "f":0.4989247312
184
  },
185
  "cc":{
186
- "p":0.5595595596,
187
- "r":0.5534653465,
188
- "f":0.556495769
189
  },
190
  "conj":{
191
- "p":0.4795783926,
192
- "r":0.4727272727,
193
- "f":0.4761281884
194
  },
195
  "dislocated":{
196
  "p":0.0,
@@ -198,34 +198,34 @@
198
  "f":0.0
199
  },
200
  "amod":{
201
- "p":0.5900900901,
202
- "r":0.6064814815,
203
- "f":0.598173516
204
  },
205
  "parataxis":{
206
  "p":0.0,
207
  "r":0.0,
208
  "f":0.0
209
  },
 
 
 
 
 
210
  "dep":{
211
  "p":0.0,
212
  "r":0.0,
213
  "f":0.0
214
  },
215
  "nummod":{
216
- "p":0.8428571429,
217
- "r":0.8428571429,
218
- "f":0.8428571429
219
  },
220
  "fixed":{
221
- "p":0.5,
222
- "r":0.75,
223
- "f":0.6
224
- },
225
- "orphan":{
226
- "p":0.0714285714,
227
- "r":0.0571428571,
228
- "f":0.0634920635
229
  },
230
  "csubj:pass":{
231
  "p":0.0,
@@ -233,14 +233,19 @@
233
  "f":0.0
234
  },
235
  "obl:agent":{
236
- "p":0.7,
237
- "r":0.3181818182,
238
- "f":0.4375
239
  },
240
- "vocative":{
241
- "p":0.74,
242
- "r":0.606557377,
243
- "f":0.6666666667
 
 
 
 
 
244
  },
245
  "aux":{
246
  "p":0.0,
@@ -251,13 +256,8 @@
251
  "p":0.0,
252
  "r":0.0,
253
  "f":0.0
254
- },
255
- "flat:name":{
256
- "p":0.8571428571,
257
- "r":0.8571428571,
258
- "f":0.8571428571
259
  }
260
  },
261
- "lemma_acc":0.9646237044,
262
- "speed":3911.0083510692
263
  }
 
3
  "token_p":1.0,
4
  "token_r":1.0,
5
  "token_f":1.0,
6
+ "pos_acc":0.9532071504,
7
+ "morph_acc":0.8695358269,
8
+ "morph_micro_p":0.9394069812,
9
+ "morph_micro_r":0.936416185,
10
+ "morph_micro_f":0.9379091988,
11
  "morph_per_feat":{
12
  "Case":{
13
+ "p":0.9515980534,
14
+ "r":0.9515980534,
15
+ "f":0.9515980534
16
  },
17
  "Gender":{
18
+ "p":0.8999206769,
19
+ "r":0.902665429,
20
+ "f":0.9012909633
21
  },
22
  "Number":{
23
+ "p":0.9756018917,
24
+ "r":0.9739270386,
25
+ "f":0.9747637457
26
  },
27
  "Aspect":{
28
+ "p":0.8845070423,
29
+ "r":0.880168185,
30
+ "f":0.8823322796
31
  },
32
  "Mood":{
33
+ "p":0.9276895944,
34
+ "r":0.9190448457,
35
+ "f":0.9233469865
36
  },
37
  "Person":{
38
+ "p":0.9530227185,
39
+ "r":0.9410646388,
40
+ "f":0.9470059307
41
  },
42
  "Tense":{
43
+ "p":0.8856402665,
44
+ "r":0.8733576642,
45
+ "f":0.8794560823
46
  },
47
  "VerbForm":{
48
+ "p":0.9603997039,
49
+ "r":0.9467347683,
50
+ "f":0.9535182804
51
  },
52
  "Voice":{
53
+ "p":0.9115470022,
54
+ "r":0.8989051095,
55
+ "f":0.9051819184
56
  },
57
  "PronType":{
58
+ "p":0.9747644684,
59
+ "r":0.9688963211,
60
+ "f":0.9718215364
61
  },
62
  "Degree":{
63
+ "p":0.8155216285,
64
+ "r":0.8390052356,
65
+ "f":0.8270967742
66
  },
67
  "Definite":{
68
+ "p":0.9796926454,
69
+ "r":0.9944289694,
70
+ "f":0.9870058059
71
  },
72
  "Reflex":{
73
+ "p":1.0,
74
+ "r":1.0,
75
+ "f":1.0
76
  },
77
  "Polarity":{
78
+ "p":0.9953917051,
79
+ "r":0.9773755656,
80
+ "f":0.9863013699
81
  },
82
  "Poss":{
83
+ "p":0.8888888889,
84
+ "r":0.6153846154,
85
+ "f":0.7272727273
86
  }
87
  },
88
+ "tag_acc":0.9569625958,
89
+ "sents_p":0.4862542955,
90
+ "sents_r":0.5405921681,
91
+ "sents_f":0.5119855269,
92
+ "dep_uas":0.7486855941,
93
+ "dep_las":0.6950578339,
94
  "dep_las_per_type":{
95
  "iobj":{
96
+ "p":0.6644591611,
97
+ "r":0.6887871854,
98
+ "f":0.6764044944
99
  },
100
  "root":{
101
+ "p":0.691580756,
102
+ "r":0.7688634193,
103
+ "f":0.7281772953
104
  },
105
  "nsubj":{
106
+ "p":0.6414686825,
107
+ "r":0.6659192825,
108
+ "f":0.6534653465
109
  },
110
  "advmod":{
111
+ "p":0.637254902,
112
+ "r":0.6319444444,
113
+ "f":0.6345885635
114
  },
115
  "advcl":{
116
+ "p":0.5568,
117
+ "r":0.5771144279,
118
+ "f":0.5667752443
119
  },
120
  "ccomp":{
121
+ "p":0.4015151515,
122
+ "r":0.3271604938,
123
+ "f":0.3605442177
124
  },
125
  "discourse":{
126
+ "p":0.7424242424,
127
+ "r":0.7414030261,
128
+ "f":0.7419132829
129
  },
130
  "obj":{
131
+ "p":0.7176079734,
132
+ "r":0.7144432194,
133
+ "f":0.7160220994
134
  },
135
  "det":{
136
+ "p":0.8997384481,
137
+ "r":0.9056603774,
138
+ "f":0.9026897004
139
  },
140
  "nmod":{
141
+ "p":0.6962025316,
142
+ "r":0.6370656371,
143
+ "f":0.6653225806
144
  },
145
  "cop":{
146
+ "p":0.6713615023,
147
+ "r":0.6745283019,
148
+ "f":0.6729411765
149
  },
150
  "appos":{
151
+ "p":0.3786407767,
152
+ "r":0.237804878,
153
+ "f":0.2921348315
154
  },
155
  "case":{
156
+ "p":0.933030647,
157
+ "r":0.9351535836,
158
+ "f":0.9340909091
159
  },
160
  "acl":{
161
+ "p":0.4461538462,
162
+ "r":0.3536585366,
163
+ "f":0.3945578231
164
  },
165
  "mark":{
166
+ "p":0.8450704225,
167
+ "r":0.8333333333,
168
+ "f":0.8391608392
169
  },
170
  "obl":{
171
+ "p":0.6448484848,
172
+ "r":0.6683417085,
173
+ "f":0.6563849476
174
  },
175
  "nsubj:pass":{
176
+ "p":0.6417910448,
177
+ "r":0.4526315789,
178
+ "f":0.5308641975
179
  },
180
  "xcomp":{
181
+ "p":0.5045454545,
182
+ "r":0.4625,
183
+ "f":0.4826086957
184
  },
185
  "cc":{
186
+ "p":0.5577492596,
187
+ "r":0.5594059406,
188
+ "f":0.5585763717
189
  },
190
  "conj":{
191
+ "p":0.4921671018,
192
+ "r":0.4896103896,
193
+ "f":0.4908854167
194
  },
195
  "dislocated":{
196
  "p":0.0,
 
198
  "f":0.0
199
  },
200
  "amod":{
201
+ "p":0.5919282511,
202
+ "r":0.6111111111,
203
+ "f":0.6013667426
204
  },
205
  "parataxis":{
206
  "p":0.0,
207
  "r":0.0,
208
  "f":0.0
209
  },
210
+ "vocative":{
211
+ "p":0.6851851852,
212
+ "r":0.606557377,
213
+ "f":0.6434782609
214
+ },
215
  "dep":{
216
  "p":0.0,
217
  "r":0.0,
218
  "f":0.0
219
  },
220
  "nummod":{
221
+ "p":0.8636363636,
222
+ "r":0.8142857143,
223
+ "f":0.8382352941
224
  },
225
  "fixed":{
226
+ "p":0.7272727273,
227
+ "r":1.0,
228
+ "f":0.8421052632
 
 
 
 
 
229
  },
230
  "csubj:pass":{
231
  "p":0.0,
 
233
  "f":0.0
234
  },
235
  "obl:agent":{
236
+ "p":0.4,
237
+ "r":0.2727272727,
238
+ "f":0.3243243243
239
  },
240
+ "orphan":{
241
+ "p":0.0833333333,
242
+ "r":0.0285714286,
243
+ "f":0.0425531915
244
+ },
245
+ "flat:name":{
246
+ "p":0.6,
247
+ "r":0.8571428571,
248
+ "f":0.7058823529
249
  },
250
  "aux":{
251
  "p":0.0,
 
256
  "p":0.0,
257
  "r":0.0,
258
  "f":0.0
 
 
 
 
 
259
  }
260
  },
261
+ "lemma_acc":0.9643232687,
262
+ "speed":6477.8090414567
263
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -51,6 +51,7 @@ subword_features = true
51
  [components.morphologizer]
52
  factory = "morphologizer"
53
  extend = false
 
54
  overwrite = true
55
  scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
56
 
@@ -88,6 +89,7 @@ upstream = "tok2vec"
88
 
89
  [components.tagger]
90
  factory = "tagger"
 
91
  neg_prefix = "!"
92
  overwrite = false
93
  scorer = {"@scorers":"spacy.tagger_scorer.v1"}
 
51
  [components.morphologizer]
52
  factory = "morphologizer"
53
  extend = false
54
+ label_smoothing = 0.0
55
  overwrite = true
56
  scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
57
 
 
89
 
90
  [components.tagger]
91
  factory = "tagger"
92
+ label_smoothing = 0.0
93
  neg_prefix = "!"
94
  overwrite = false
95
  scorer = {"@scorers":"spacy.tagger_scorer.v1"}
grc_proiel_sm-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ca9dc9f460a7ee7eb9c5946a3c15c14d3a3690df38ef2a69693a851620490e6
3
- size 60071653
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f6b8975255172119791a1832ef7656fb921dae150a8122d8bbb9b09d6725467
3
+ size 60074034
lemmatizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7943319b989596449853f63213d3598cab16ee8576e94756e1406f352f95469c
3
  size 24263260
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47c2c081c979e7cb5953f63ec0f8c30fb603c65e6cb7315730d37776e684fa40
3
  size 24263260
meta.json CHANGED
@@ -7,8 +7,8 @@
7
  "email":"",
8
  "url":"",
9
  "license":"",
10
- "spacy_version":">=3.5.3,<3.6.0",
11
- "spacy_git_version":"512241e12",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -1132,33 +1132,33 @@
1132
 
1133
  ],
1134
  "performance":{
1135
- "pos_acc":0.9557573982,
1136
- "morph_acc":0.8745238793,
1137
  "morph_per_feat":{
1138
  "Case":{
1139
- "p":0.9518209408,
1140
- "r":0.9498990409,
1141
- "f":0.9508590197
1142
  },
1143
  "Gender":{
1144
- "p":0.905669972,
1145
- "r":0.9090213092,
1146
- "f":0.907342546
1147
  },
1148
  "Number":{
1149
- "p":0.9802863665,
1150
- "r":0.9769413711,
1151
- "f":0.9786110104
1152
  },
1153
  "Person":{
1154
- "p":0.9588169225,
1155
- "r":0.9453672942,
1156
- "f":0.9520446097
1157
  },
1158
  "PronType":{
1159
- "p":0.9773918742,
1160
- "r":0.9685064935,
1161
- "f":0.9729288976
1162
  },
1163
  "Polarity":{
1164
  "p":1.0,
@@ -1166,39 +1166,39 @@
1166
  "f":0.9921671018
1167
  },
1168
  "Aspect":{
1169
- "p":0.9186460808,
1170
- "r":0.8779795687,
1171
- "f":0.8978525827
1172
  },
1173
  "Mood":{
1174
- "p":0.9375722543,
1175
- "r":0.9284487693,
1176
- "f":0.9329882082
1177
  },
1178
  "Tense":{
1179
- "p":0.891966759,
1180
- "r":0.8849192717,
1181
- "f":0.8884290395
1182
  },
1183
  "VerbForm":{
1184
- "p":0.9650277008,
1185
- "r":0.9567456231,
1186
- "f":0.9608688157
1187
  },
1188
  "Voice":{
1189
- "p":0.9193213296,
1190
- "r":0.9120577121,
1191
- "f":0.9156751164
1192
  },
1193
  "Degree":{
1194
- "p":0.8700564972,
1195
- "r":0.8279569892,
1196
- "f":0.8484848485
1197
  },
1198
  "Definite":{
1199
- "p":0.9829333333,
1200
- "r":0.9956780119,
1201
- "f":0.9892646269
1202
  },
1203
  "Reflex":{
1204
  "p":1.0,
@@ -1207,188 +1207,188 @@
1207
  },
1208
  "Poss":{
1209
  "p":1.0,
1210
- "r":0.6842105263,
1211
- "f":0.8125
1212
  }
1213
  },
1214
- "tag_acc":0.9605186053,
1215
- "dep_uas":0.7632581307,
1216
- "dep_las":0.706782889,
1217
  "dep_las_per_type":{
1218
  "nsubj":{
1219
- "p":0.664910432,
1220
- "r":0.6836403034,
1221
- "f":0.6741452991
1222
  },
1223
  "discourse":{
1224
- "p":0.7728531856,
1225
- "r":0.7664835165,
1226
- "f":0.7696551724
1227
  },
1228
  "mark":{
1229
- "p":0.756302521,
1230
- "r":0.7258064516,
1231
- "f":0.7407407407
1232
  },
1233
  "advmod":{
1234
- "p":0.6637931034,
1235
- "r":0.6864784547,
1236
- "f":0.6749452155
1237
  },
1238
  "advcl":{
1239
- "p":0.5973509934,
1240
- "r":0.6161202186,
1241
- "f":0.6065904506
1242
  },
1243
  "xcomp":{
1244
- "p":0.5022222222,
1245
- "r":0.452,
1246
- "f":0.4757894737
1247
  },
1248
  "cop":{
1249
- "p":0.7417840376,
1250
- "r":0.738317757,
1251
- "f":0.7400468384
1252
  },
1253
  "root":{
1254
- "p":0.725526075,
1255
- "r":0.7782139352,
1256
- "f":0.7509469697
1257
  },
1258
  "det":{
1259
- "p":0.9003864319,
1260
- "r":0.909366869,
1261
- "f":0.9048543689
1262
  },
1263
  "nmod":{
1264
- "p":0.64,
1265
- "r":0.6478873239,
1266
- "f":0.6439195101
1267
  },
1268
  "obj":{
1269
- "p":0.7393117831,
1270
- "r":0.7362409138,
1271
- "f":0.737773153
1272
  },
1273
  "case":{
1274
- "p":0.9390642002,
1275
- "r":0.9462719298,
1276
- "f":0.9426542873
1277
  },
1278
  "obl":{
1279
- "p":0.6793611794,
1280
- "r":0.6752136752,
1281
- "f":0.6772810778
1282
  },
1283
  "cc":{
1284
- "p":0.5799793602,
1285
  "r":0.5781893004,
1286
- "f":0.5790829469
1287
  },
1288
  "conj":{
1289
- "p":0.5361702128,
1290
- "r":0.4960629921,
1291
- "f":0.5153374233
1292
  },
1293
  "obl:agent":{
1294
- "p":0.8888888889,
1295
- "r":0.4324324324,
1296
- "f":0.5818181818
1297
  },
1298
  "ccomp":{
1299
- "p":0.432748538,
1300
- "r":0.368159204,
1301
- "f":0.3978494624
1302
  },
1303
  "nsubj:pass":{
1304
- "p":0.5274725275,
1305
- "r":0.4485981308,
1306
- "f":0.4848484848
1307
  },
1308
  "amod":{
1309
- "p":0.6176470588,
1310
- "r":0.5915492958,
1311
- "f":0.6043165468
1312
  },
1313
  "acl":{
1314
- "p":0.4066666667,
1315
  "r":0.3696969697,
1316
- "f":0.3873015873
1317
  },
1318
  "iobj":{
1319
- "p":0.6753554502,
1320
- "r":0.6581986143,
1321
- "f":0.6666666667
1322
- },
1323
- "parataxis":{
1324
- "p":0.125,
1325
- "r":0.05,
1326
- "f":0.0714285714
1327
- },
1328
- "dep":{
1329
- "p":0.0,
1330
- "r":0.0,
1331
- "f":0.0
1332
  },
1333
  "orphan":{
1334
- "p":0.1578947368,
1335
  "r":0.0697674419,
1336
- "f":0.0967741935
1337
  },
1338
  "nummod":{
1339
- "p":0.78125,
1340
- "r":0.7352941176,
1341
- "f":0.7575757576
1342
  },
1343
  "vocative":{
1344
- "p":0.6923076923,
1345
- "r":0.652173913,
1346
- "f":0.671641791
1347
  },
1348
  "appos":{
1349
- "p":0.3596491228,
1350
  "r":0.2907801418,
1351
- "f":0.3215686275
1352
  },
1353
- "flat:name":{
1354
- "p":0.8,
1355
- "r":0.5454545455,
1356
- "f":0.6486486486
 
 
 
 
 
1357
  },
1358
  "dislocated":{
1359
- "p":0.4545454545,
1360
- "r":0.1923076923,
1361
- "f":0.2702702703
1362
  },
1363
  "csubj:pass":{
1364
  "p":0.0,
1365
  "r":0.0,
1366
  "f":0.0
1367
  },
 
 
 
 
 
 
 
 
 
 
1368
  "aux:pass":{
1369
  "p":0.0,
1370
  "r":0.0,
1371
  "f":0.0
1372
  },
1373
- "fixed":{
1374
- "p":0.5454545455,
1375
- "r":0.6,
1376
- "f":0.5714285714
1377
- },
1378
  "aux":{
1379
  "p":0.0,
1380
  "r":0.0,
1381
  "f":0.0
1382
  }
1383
  },
1384
- "sents_p":0.505946935,
1385
- "sents_r":0.5426889107,
1386
- "sents_f":0.5236742424,
1387
- "lemma_acc":0.966891298,
1388
- "tok2vec_loss":41113.3756506196,
1389
- "morphologizer_loss":1305.2082611322,
1390
- "tagger_loss":386.3325280659,
1391
- "parser_loss":19471.5545363693
1392
  },
1393
  "requirements":[
1394
 
 
7
  "email":"",
8
  "url":"",
9
  "license":"",
10
+ "spacy_version":">=3.6.0,<3.7.0",
11
+ "spacy_git_version":"6fc153a26",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
 
1132
 
1133
  ],
1134
  "performance":{
1135
+ "pos_acc":0.9580281277,
1136
+ "morph_acc":0.8734251392,
1137
  "morph_per_feat":{
1138
  "Case":{
1139
+ "p":0.9517311094,
1140
+ "r":0.9505300353,
1141
+ "f":0.9511301932
1142
  },
1143
  "Gender":{
1144
+ "p":0.9020801624,
1145
+ "r":0.907490111,
1146
+ "f":0.9047770498
1147
  },
1148
  "Number":{
1149
+ "p":0.9808190772,
1150
+ "r":0.9781821942,
1151
+ "f":0.979498861
1152
  },
1153
  "Person":{
1154
+ "p":0.9597465524,
1155
+ "r":0.9505352529,
1156
+ "f":0.9551186944
1157
  },
1158
  "PronType":{
1159
+ "p":0.9787720444,
1160
+ "r":0.9730519481,
1161
+ "f":0.9759036145
1162
  },
1163
  "Polarity":{
1164
  "p":1.0,
 
1166
  "f":0.9921671018
1167
  },
1168
  "Aspect":{
1169
+ "p":0.9048453006,
1170
+ "r":0.8796821793,
1171
+ "f":0.8920863309
1172
  },
1173
  "Mood":{
1174
+ "p":0.9387637204,
1175
+ "r":0.9301659989,
1176
+ "f":0.9344450834
1177
  },
1178
  "Tense":{
1179
+ "p":0.8936243936,
1180
+ "r":0.8859498454,
1181
+ "f":0.889770571
1182
  },
1183
  "VerbForm":{
1184
+ "p":0.9688149688,
1185
+ "r":0.9598352214,
1186
+ "f":0.9643041904
1187
  },
1188
  "Voice":{
1189
+ "p":0.9230769231,
1190
+ "r":0.9151494332,
1191
+ "f":0.9190960842
1192
  },
1193
  "Degree":{
1194
+ "p":0.8666666667,
1195
+ "r":0.8212365591,
1196
+ "f":0.8433402346
1197
  },
1198
  "Definite":{
1199
+ "p":0.9814225053,
1200
+ "r":0.998919503,
1201
+ "f":0.9900937082
1202
  },
1203
  "Reflex":{
1204
  "p":1.0,
 
1207
  },
1208
  "Poss":{
1209
  "p":1.0,
1210
+ "r":0.7368421053,
1211
+ "f":0.8484848485
1212
  }
1213
  },
1214
+ "tag_acc":0.9607383534,
1215
+ "dep_uas":0.759668913,
1216
+ "dep_las":0.70443891,
1217
  "dep_las_per_type":{
1218
  "nsubj":{
1219
+ "p":0.6441717791,
1220
+ "r":0.6825568797,
1221
+ "f":0.6628090479
1222
  },
1223
  "discourse":{
1224
+ "p":0.7658402204,
1225
+ "r":0.7637362637,
1226
+ "f":0.764786795
1227
  },
1228
  "mark":{
1229
+ "p":0.7983193277,
1230
+ "r":0.7661290323,
1231
+ "f":0.7818930041
1232
  },
1233
  "advmod":{
1234
+ "p":0.6778425656,
1235
+ "r":0.690936107,
1236
+ "f":0.6843267108
1237
  },
1238
  "advcl":{
1239
+ "p":0.6126373626,
1240
+ "r":0.6092896175,
1241
+ "f":0.6109589041
1242
  },
1243
  "xcomp":{
1244
+ "p":0.5196078431,
1245
+ "r":0.424,
1246
+ "f":0.4669603524
1247
  },
1248
  "cop":{
1249
+ "p":0.7298578199,
1250
+ "r":0.7196261682,
1251
+ "f":0.7247058824
1252
  },
1253
  "root":{
1254
+ "p":0.7048611111,
1255
+ "r":0.7968596663,
1256
+ "f":0.7480423768
1257
  },
1258
  "det":{
1259
+ "p":0.8931788932,
1260
+ "r":0.9028620989,
1261
+ "f":0.8979943929
1262
  },
1263
  "nmod":{
1264
+ "p":0.6964980545,
1265
+ "r":0.6302816901,
1266
+ "f":0.6617375231
1267
  },
1268
  "obj":{
1269
+ "p":0.7238883144,
1270
+ "r":0.7268951194,
1271
+ "f":0.725388601
1272
  },
1273
  "case":{
1274
+ "p":0.9339111593,
1275
+ "r":0.9451754386,
1276
+ "f":0.9395095368
1277
  },
1278
  "obl":{
1279
+ "p":0.6456599287,
1280
+ "r":0.663003663,
1281
+ "f":0.6542168675
1282
  },
1283
  "cc":{
1284
+ "p":0.578784758,
1285
  "r":0.5781893004,
1286
+ "f":0.578486876
1287
  },
1288
  "conj":{
1289
+ "p":0.5190217391,
1290
+ "r":0.501312336,
1291
+ "f":0.5100133511
1292
  },
1293
  "obl:agent":{
1294
+ "p":0.6363636364,
1295
+ "r":0.3783783784,
1296
+ "f":0.4745762712
1297
  },
1298
  "ccomp":{
1299
+ "p":0.4285714286,
1300
+ "r":0.3880597015,
1301
+ "f":0.407310705
1302
  },
1303
  "nsubj:pass":{
1304
+ "p":0.6507936508,
1305
+ "r":0.3831775701,
1306
+ "f":0.4823529412
1307
  },
1308
  "amod":{
1309
+ "p":0.5990566038,
1310
+ "r":0.5962441315,
1311
+ "f":0.5976470588
1312
  },
1313
  "acl":{
1314
+ "p":0.4919354839,
1315
  "r":0.3696969697,
1316
+ "f":0.4221453287
1317
  },
1318
  "iobj":{
1319
+ "p":0.6416309013,
1320
+ "r":0.6905311778,
1321
+ "f":0.6651835373
 
 
 
 
 
 
 
 
 
 
1322
  },
1323
  "orphan":{
1324
+ "p":0.1111111111,
1325
  "r":0.0697674419,
1326
+ "f":0.0857142857
1327
  },
1328
  "nummod":{
1329
+ "p":0.7833333333,
1330
+ "r":0.6911764706,
1331
+ "f":0.734375
1332
  },
1333
  "vocative":{
1334
+ "p":0.7321428571,
1335
+ "r":0.5942028986,
1336
+ "f":0.656
1337
  },
1338
  "appos":{
1339
+ "p":0.376146789,
1340
  "r":0.2907801418,
1341
+ "f":0.328
1342
  },
1343
+ "dep":{
1344
+ "p":0.0,
1345
+ "r":0.0,
1346
+ "f":0.0
1347
+ },
1348
+ "parataxis":{
1349
+ "p":0.0,
1350
+ "r":0.0,
1351
+ "f":0.0
1352
  },
1353
  "dislocated":{
1354
+ "p":0.0,
1355
+ "r":0.0,
1356
+ "f":0.0
1357
  },
1358
  "csubj:pass":{
1359
  "p":0.0,
1360
  "r":0.0,
1361
  "f":0.0
1362
  },
1363
+ "flat:name":{
1364
+ "p":0.6666666667,
1365
+ "r":0.5454545455,
1366
+ "f":0.6
1367
+ },
1368
+ "fixed":{
1369
+ "p":0.5,
1370
+ "r":0.5,
1371
+ "f":0.5
1372
+ },
1373
  "aux:pass":{
1374
  "p":0.0,
1375
  "r":0.0,
1376
  "f":0.0
1377
  },
 
 
 
 
 
1378
  "aux":{
1379
  "p":0.0,
1380
  "r":0.0,
1381
  "f":0.0
1382
  }
1383
  },
1384
+ "sents_p":0.4991319444,
1385
+ "sents_r":0.5642787046,
1386
+ "sents_f":0.5297098111,
1387
+ "lemma_acc":0.9656460592,
1388
+ "tok2vec_loss":36411.7413094571,
1389
+ "morphologizer_loss":1968.4281498194,
1390
+ "tagger_loss":591.3479025513,
1391
+ "parser_loss":23268.3977727098
1392
  },
1393
  "requirements":[
1394
 
morphologizer/cfg CHANGED
@@ -1,5 +1,6 @@
1
  {
2
  "extend":false,
 
3
  "labels_morph":{
4
  "Case=Gen|Gender=Masc|Number=Sing|POS=PROPN":"Case=Gen|Gender=Masc|Number=Sing",
5
  "Case=Gen|Gender=Masc|Number=Sing|POS=NOUN":"Case=Gen|Gender=Masc|Number=Sing",
 
1
  {
2
  "extend":false,
3
+ "label_smoothing":0.0,
4
  "labels_morph":{
5
  "Case=Gen|Gender=Masc|Number=Sing|POS=PROPN":"Case=Gen|Gender=Masc|Number=Sing",
6
  "Case=Gen|Gender=Masc|Number=Sing|POS=NOUN":"Case=Gen|Gender=Masc|Number=Sing",
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b7ee6c20379d3c111219186138f1d3c73cfc003b04be262c3d2b24639b0eb1f
3
  size 1058262
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff0118ec59f3f5776c6ab8c7cf76352ac4f5c4575741b19907ce157bc6a612f9
3
  size 1058262
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c3eb61c9d2bc2165c69fec042210aca3c5e21f3eaa13802090e1517c0142dffb
3
  size 1782009
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73a4045d552ed558c4cb34c2c3f478a2d19040b3cb32467cdba99e2f9b06020
3
  size 1782009
tagger/cfg CHANGED
@@ -1,4 +1,5 @@
1
  {
 
2
  "labels":[
3
  "A-",
4
  "C-",
 
1
  {
2
+ "label_smoothing":0.0,
3
  "labels":[
4
  "A-",
5
  "C-",
tagger/model CHANGED
Binary files a/tagger/model and b/tagger/model differ
 
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5cb4218a151193e173376f503b898f17b2f7072d1bd1e0eef0d44b26f732cbd2
3
  size 34875837
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4212fc1a3e715434a7c5d5374343fb250ba019e832797db75aa3b17a16335ffe
3
  size 34875837
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6495dc4bdfaf7e158ce3d30a90606674a3df4dcd5b13bb716ff2ad1fca297a65
3
- size 17984960
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c3ce996c8b982a050dafae1aa7b15164181246f3940f37ae82111e5cf014914
3
+ size 17972361