EC2 Default User commited on
Commit
2b4ec3d
1 Parent(s): a325d13

Update spaCy pipeline

Browse files
.gitattributes CHANGED
@@ -19,3 +19,5 @@
19
  *strings.json filter=lfs diff=lfs merge=lfs -text
20
  vectors filter=lfs diff=lfs merge=lfs -text
21
  model filter=lfs diff=lfs merge=lfs -text
 
 
19
  *strings.json filter=lfs diff=lfs merge=lfs -text
20
  vectors filter=lfs diff=lfs merge=lfs -text
21
  model filter=lfs diff=lfs merge=lfs -text
22
+ *key2row filter=lfs diff=lfs merge=lfs -text
23
+ *tokenizer filter=lfs diff=lfs merge=lfs -text
README.md CHANGED
@@ -8,40 +8,55 @@ license: lgpl-lr
8
  model-index:
9
  - name: fr_dep_news_trf
10
  results:
 
 
 
 
 
 
 
11
  - task:
12
  name: POS
13
  type: token-classification
14
  metrics:
15
- - name: POS Accuracy
16
  type: accuracy
17
- value: 0.9573063834
18
  - task:
19
- name: SENTER
20
  type: token-classification
21
  metrics:
22
- - name: SENTER Precision
23
- type: precision
24
- value: 0.8835616438
25
- - name: SENTER Recall
26
- type: recall
27
- value: 0.9393203883
28
- - name: SENTER F Score
29
- type: f_score
30
- value: 0.9105882353
31
  - task:
32
- name: UNLABELED_DEPENDENCIES
33
  type: token-classification
34
  metrics:
35
- - name: Unlabeled Dependencies Accuracy
36
  type: accuracy
37
- value: 0.9492309471
 
 
 
 
 
 
 
38
  - task:
39
  name: LABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
- - name: Labeled Dependencies Accuracy
43
- type: accuracy
44
- value: 0.9492309471
 
 
 
 
 
 
 
45
  ---
46
  ### Details: https://spacy.io/models/fr#fr_dep_news_trf
47
 
@@ -50,8 +65,8 @@ French transformer pipeline (camembert-base). Components: transformer, morpholog
50
  | Feature | Description |
51
  | --- | --- |
52
  | **Name** | `fr_dep_news_trf` |
53
- | **Version** | `3.2.0` |
54
- | **spaCy** | `>=3.2.0,<3.3.0` |
55
  | **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer` |
56
  | **Components** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer` |
57
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -80,15 +95,15 @@ French transformer pipeline (camembert-base). Components: transformer, morpholog
80
  | `TOKEN_P` | 98.44 |
81
  | `TOKEN_R` | 98.96 |
82
  | `TOKEN_F` | 98.70 |
83
- | `POS_ACC` | 98.64 |
84
- | `MORPH_ACC` | 97.92 |
85
- | `MORPH_MICRO_P` | 99.34 |
86
- | `MORPH_MICRO_R` | 99.08 |
87
- | `MORPH_MICRO_F` | 99.21 |
88
- | `SENTS_P` | 88.36 |
89
- | `SENTS_R` | 93.93 |
90
- | `SENTS_F` | 91.06 |
91
- | `DEP_UAS` | 94.92 |
92
- | `DEP_LAS` | 92.96 |
93
- | `TAG_ACC` | 95.73 |
94
- | `LEMMA_ACC` | 91.18 |
8
  model-index:
9
  - name: fr_dep_news_trf
10
  results:
11
+ - task:
12
+ name: TAG
13
+ type: token-classification
14
+ metrics:
15
+ - name: TAG (XPOS) Accuracy
16
+ type: accuracy
17
+ value: 0.9580239274
18
  - task:
19
  name: POS
20
  type: token-classification
21
  metrics:
22
+ - name: POS (UPOS) Accuracy
23
  type: accuracy
24
+ value: 0.9871080858
25
  - task:
26
+ name: MORPH
27
  type: token-classification
28
  metrics:
29
+ - name: Morph (UFeats) Accuracy
30
+ type: accuracy
31
+ value: 0.9790173738
 
 
 
 
 
 
32
  - task:
33
+ name: LEMMA
34
  type: token-classification
35
  metrics:
36
+ - name: Lemma Accuracy
37
  type: accuracy
38
+ value: 0.9122482532
39
+ - task:
40
+ name: UNLABELED_DEPENDENCIES
41
+ type: token-classification
42
+ metrics:
43
+ - name: Unlabeled Attachment Score (UAS)
44
+ type: f_score
45
+ value: 0.947216113
46
  - task:
47
  name: LABELED_DEPENDENCIES
48
  type: token-classification
49
  metrics:
50
+ - name: Labeled Attachment Score (LAS)
51
+ type: f_score
52
+ value: 0.9271002083
53
+ - task:
54
+ name: SENTS
55
+ type: token-classification
56
+ metrics:
57
+ - name: Sentences F-Score
58
+ type: f_score
59
+ value: 0.9377990431
60
  ---
61
  ### Details: https://spacy.io/models/fr#fr_dep_news_trf
62
 
65
  | Feature | Description |
66
  | --- | --- |
67
  | **Name** | `fr_dep_news_trf` |
68
+ | **Version** | `3.3.0` |
69
+ | **spaCy** | `>=3.3.0.dev0,<3.4.0` |
70
  | **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer` |
71
  | **Components** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer` |
72
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
95
  | `TOKEN_P` | 98.44 |
96
  | `TOKEN_R` | 98.96 |
97
  | `TOKEN_F` | 98.70 |
98
+ | `POS_ACC` | 98.71 |
99
+ | `MORPH_ACC` | 97.90 |
100
+ | `MORPH_MICRO_P` | 99.40 |
101
+ | `MORPH_MICRO_R` | 99.06 |
102
+ | `MORPH_MICRO_F` | 99.23 |
103
+ | `SENTS_P` | 92.45 |
104
+ | `SENTS_R` | 95.15 |
105
+ | `SENTS_F` | 93.78 |
106
+ | `DEP_UAS` | 94.72 |
107
+ | `DEP_LAS` | 92.71 |
108
+ | `TAG_ACC` | 95.80 |
109
+ | `LEMMA_ACC` | 91.22 |
accuracy.json CHANGED
@@ -3,56 +3,56 @@
3
  "token_p": 0.9844389844,
4
  "token_r": 0.9896058454,
5
  "token_f": 0.9870156531,
6
- "pos_acc": 0.9863875425,
7
- "morph_acc": 0.9791731106,
8
- "morph_micro_p": 0.9934029687,
9
- "morph_micro_r": 0.9908005361,
10
- "morph_micro_f": 0.9921000458,
11
  "morph_per_feat": {
12
  "Definite": {
13
- "p": 0.9985358712,
14
  "r": 0.995620438,
15
- "f": 0.9970760234
16
  },
17
  "Number": {
18
- "p": 0.9959409594,
19
- "r": 0.9937407953,
20
- "f": 0.9948396609
21
  },
22
  "PronType": {
23
- "p": 0.9974293059,
24
- "r": 0.9929622521,
25
- "f": 0.9951907663
26
  },
27
  "Gender": {
28
- "p": 0.988963039,
29
- "r": 0.9846664963,
30
- "f": 0.9868100909
31
  },
32
  "Mood": {
33
- "p": 0.9946619217,
34
- "r": 0.9928952043,
35
- "f": 0.9937777778
36
  },
37
  "Person": {
38
- "p": 0.9974683544,
39
- "r": 0.9911949686,
40
- "f": 0.9943217666
41
  },
42
  "Tense": {
43
- "p": 0.9868421053,
44
  "r": 0.9959141982,
45
- "f": 0.9913573971
46
  },
47
  "VerbForm": {
48
- "p": 0.9901153213,
49
  "r": 0.9950331126,
50
- "f": 0.9925681255
51
  },
52
  "NumType": {
53
- "p": 0.9927797834,
54
- "r": 0.9385665529,
55
- "f": 0.9649122807
56
  },
57
  "Reflex": {
58
  "p": 1.0,
@@ -60,9 +60,9 @@
60
  "f": 1.0
61
  },
62
  "Voice": {
63
- "p": 0.9568965517,
64
  "r": 0.9910714286,
65
- "f": 0.9736842105
66
  },
67
  "Poss": {
68
  "p": 1.0,
@@ -75,116 +75,116 @@
75
  "f": 1.0
76
  }
77
  },
78
- "sents_p": 0.8835616438,
79
- "sents_r": 0.9393203883,
80
- "sents_f": 0.9105882353,
81
- "dep_uas": 0.9492309471,
82
- "dep_las": 0.9295953757,
83
  "dep_las_per_type": {
84
  "det": {
85
- "p": 0.9871382637,
86
- "r": 0.9911218725,
87
- "f": 0.9891260572
88
  },
89
  "nsubj": {
90
- "p": 0.945368171,
91
- "r": 0.9590361446,
92
- "f": 0.95215311
93
  },
94
  "aux:tense": {
95
- "p": 0.9761904762,
96
  "r": 0.984,
97
- "f": 0.9800796813
98
  },
99
  "root": {
100
- "p": 0.9179954442,
101
  "r": 0.9781553398,
102
- "f": 0.9471210341
103
  },
104
  "obj": {
105
- "p": 0.9451219512,
106
- "r": 0.9198813056,
107
- "f": 0.9323308271
108
  },
109
  "cc": {
110
- "p": 0.9495412844,
111
- "r": 0.9539170507,
112
- "f": 0.9517241379
113
  },
114
  "case": {
115
- "p": 0.9850238257,
116
- "r": 0.9856948229,
117
- "f": 0.9853592101
118
  },
119
  "obl:mod": {
120
- "p": 0.8553459119,
121
- "r": 0.8119402985,
122
- "f": 0.8330781011
123
  },
124
  "nmod": {
125
- "p": 0.9012961117,
126
- "r": 0.9030969031,
127
- "f": 0.9021956088
128
  },
129
  "conj": {
130
- "p": 0.832,
131
  "r": 0.8188976378,
132
- "f": 0.8253968254
133
  },
134
  "nummod": {
135
- "p": 0.9069767442,
136
- "r": 0.9230769231,
137
- "f": 0.9149560117
138
  },
139
  "amod": {
140
- "p": 0.9664804469,
141
- "r": 0.9453551913,
142
- "f": 0.955801105
143
  },
144
  "acl": {
145
- "p": 0.85,
146
- "r": 0.8843930636,
147
- "f": 0.8668555241
148
  },
149
  "mark": {
150
- "p": 0.9733333333,
151
- "r": 0.9647577093,
152
- "f": 0.9690265487
153
  },
154
  "xcomp": {
155
- "p": 0.9350649351,
156
- "r": 0.9536423841,
157
- "f": 0.9442622951
158
  },
159
  "flat:name": {
160
- "p": 0.953271028,
161
  "r": 0.9714285714,
162
- "f": 0.9622641509
163
  },
164
  "cop": {
165
- "p": 0.9659090909,
166
- "r": 0.9444444444,
167
- "f": 0.9550561798
168
  },
169
  "advmod": {
170
- "p": 0.9361022364,
171
- "r": 0.9184952978,
172
- "f": 0.9272151899
173
  },
174
  "obl:arg": {
175
- "p": 0.8878923767,
176
- "r": 0.9,
177
- "f": 0.8939051919
178
  },
179
  "appos": {
180
- "p": 0.7078651685,
181
- "r": 0.7590361446,
182
- "f": 0.7325581395
183
  },
184
  "nsubj:pass": {
185
- "p": 0.9761904762,
186
  "r": 0.9647058824,
187
- "f": 0.9704142012
188
  },
189
  "aux:pass": {
190
  "p": 0.9910714286,
@@ -192,14 +192,14 @@
192
  "f": 0.9910714286
193
  },
194
  "acl:relcl": {
195
- "p": 0.8795180723,
196
- "r": 0.8488372093,
197
- "f": 0.8639053254
198
  },
199
  "advcl": {
200
- "p": 0.7594936709,
201
- "r": 0.7692307692,
202
- "f": 0.7643312102
203
  },
204
  "fixed": {
205
  "p": 0.9529411765,
@@ -207,44 +207,44 @@
207
  "f": 0.8756756757
208
  },
209
  "dep": {
210
- "p": 0.2388059701,
211
- "r": 0.5517241379,
212
- "f": 0.3333333333
213
  },
214
  "expl:subj": {
215
- "p": 0.8666666667,
216
  "r": 0.8125,
217
- "f": 0.8387096774
218
  },
219
  "expl:comp": {
220
- "p": 0.75,
221
- "r": 1.0,
222
- "f": 0.8571428571
223
  },
224
  "expl:pass": {
225
  "p": 0.75,
226
  "r": 0.4285714286,
227
  "f": 0.5454545455
228
  },
229
- "obl:agent": {
230
- "p": 0.975,
231
- "r": 0.9285714286,
232
- "f": 0.9512195122
233
- },
234
  "ccomp": {
235
- "p": 0.96,
236
- "r": 0.9411764706,
237
- "f": 0.9504950495
238
  },
239
  "parataxis": {
240
- "p": 0.7307692308,
241
- "r": 0.6785714286,
242
- "f": 0.7037037037
243
  },
244
  "iobj": {
245
- "p": 0.7222222222,
246
  "r": 0.52,
247
- "f": 0.6046511628
 
 
 
 
 
248
  },
249
  "nsubj:caus": {
250
  "p": 0.0,
@@ -267,9 +267,9 @@
267
  "f": 0.0
268
  },
269
  "vocative": {
270
- "p": 1.0,
271
  "r": 0.625,
272
- "f": 0.7692307692
273
  },
274
  "dislocated": {
275
  "p": 0.0,
@@ -277,9 +277,9 @@
277
  "f": 0.0
278
  },
279
  "flat:foreign": {
280
- "p": 1.0,
281
  "r": 0.4285714286,
282
- "f": 0.6
283
  },
284
  "orphan": {
285
  "p": 0.0,
@@ -297,7 +297,7 @@
297
  "f": 0.0
298
  }
299
  },
300
- "tag_acc": 0.9573063834,
301
- "lemma_acc": 0.911837238,
302
- "speed": 1637.6043941996
303
  }
3
  "token_p": 0.9844389844,
4
  "token_r": 0.9896058454,
5
  "token_f": 0.9870156531,
6
+ "pos_acc": 0.9871080858,
7
+ "morph_acc": 0.9790173738,
8
+ "morph_micro_p": 0.9940090476,
9
+ "morph_micro_r": 0.9906177653,
10
+ "morph_micro_f": 0.992310509,
11
  "morph_per_feat": {
12
  "Definite": {
13
+ "p": 0.9978054133,
14
  "r": 0.995620438,
15
+ "f": 0.9967117282
16
  },
17
  "Number": {
18
+ "p": 0.9952020668,
19
+ "r": 0.992820324,
20
+ "f": 0.9940097687
21
  },
22
  "PronType": {
23
+ "p": 0.9980694981,
24
+ "r": 0.9923224568,
25
+ "f": 0.9951876805
26
  },
27
  "Gender": {
28
+ "p": 0.9892141757,
29
+ "r": 0.9844109379,
30
+ "f": 0.9868067119
31
  },
32
  "Mood": {
33
+ "p": 0.9982206406,
34
+ "r": 0.9964476021,
35
+ "f": 0.9973333333
36
  },
37
  "Person": {
38
+ "p": 0.997471555,
39
+ "r": 0.9924528302,
40
+ "f": 0.9949558638
41
  },
42
  "Tense": {
43
+ "p": 0.991861648,
44
  "r": 0.9959141982,
45
+ "f": 0.993883792
46
  },
47
  "VerbForm": {
48
+ "p": 0.994210091,
49
  "r": 0.9950331126,
50
+ "f": 0.9946214315
51
  },
52
  "NumType": {
53
+ "p": 0.9928057554,
54
+ "r": 0.9419795222,
55
+ "f": 0.9667250438
56
  },
57
  "Reflex": {
58
  "p": 1.0,
60
  "f": 1.0
61
  },
62
  "Voice": {
63
+ "p": 0.9652173913,
64
  "r": 0.9910714286,
65
+ "f": 0.9779735683
66
  },
67
  "Poss": {
68
  "p": 1.0,
75
  "f": 1.0
76
  }
77
  },
78
+ "sents_p": 0.9245283019,
79
+ "sents_r": 0.9514563107,
80
+ "sents_f": 0.9377990431,
81
+ "dep_uas": 0.947216113,
82
+ "dep_las": 0.9271002083,
83
  "dep_las_per_type": {
84
  "det": {
85
+ "p": 0.9902991108,
86
+ "r": 0.988700565,
87
+ "f": 0.9894991922
88
  },
89
  "nsubj": {
90
+ "p": 0.9452380952,
91
+ "r": 0.956626506,
92
+ "f": 0.9508982036
93
  },
94
  "aux:tense": {
95
+ "p": 0.9609375,
96
  "r": 0.984,
97
+ "f": 0.9723320158
98
  },
99
  "root": {
100
+ "p": 0.9460093897,
101
  "r": 0.9781553398,
102
+ "f": 0.9618138425
103
  },
104
  "obj": {
105
+ "p": 0.936746988,
106
+ "r": 0.9228486647,
107
+ "f": 0.9297458894
108
  },
109
  "cc": {
110
+ "p": 0.9541284404,
111
+ "r": 0.9585253456,
112
+ "f": 0.9563218391
113
  },
114
  "case": {
115
+ "p": 0.9843110505,
116
+ "r": 0.9829700272,
117
+ "f": 0.9836400818
118
  },
119
  "obl:mod": {
120
+ "p": 0.8145896657,
121
+ "r": 0.8,
122
+ "f": 0.8072289157
123
  },
124
  "nmod": {
125
+ "p": 0.8952095808,
126
+ "r": 0.8961038961,
127
+ "f": 0.8956565152
128
  },
129
  "conj": {
130
+ "p": 0.828685259,
131
  "r": 0.8188976378,
132
+ "f": 0.8237623762
133
  },
134
  "nummod": {
135
+ "p": 0.8735632184,
136
+ "r": 0.899408284,
137
+ "f": 0.8862973761
138
  },
139
  "amod": {
140
+ "p": 0.957952468,
141
+ "r": 0.9544626594,
142
+ "f": 0.9562043796
143
  },
144
  "acl": {
145
+ "p": 0.8571428571,
146
+ "r": 0.8670520231,
147
+ "f": 0.8620689655
148
  },
149
  "mark": {
150
+ "p": 0.9692982456,
151
+ "r": 0.9735682819,
152
+ "f": 0.9714285714
153
  },
154
  "xcomp": {
155
+ "p": 0.9225806452,
156
+ "r": 0.9470198675,
157
+ "f": 0.9346405229
158
  },
159
  "flat:name": {
160
+ "p": 0.9714285714,
161
  "r": 0.9714285714,
162
+ "f": 0.9714285714
163
  },
164
  "cop": {
165
+ "p": 0.9333333333,
166
+ "r": 0.9333333333,
167
+ "f": 0.9333333333
168
  },
169
  "advmod": {
170
+ "p": 0.9381107492,
171
+ "r": 0.9028213166,
172
+ "f": 0.9201277955
173
  },
174
  "obl:arg": {
175
+ "p": 0.8828828829,
176
+ "r": 0.8909090909,
177
+ "f": 0.8868778281
178
  },
179
  "appos": {
180
+ "p": 0.6931818182,
181
+ "r": 0.734939759,
182
+ "f": 0.7134502924
183
  },
184
  "nsubj:pass": {
185
+ "p": 1.0,
186
  "r": 0.9647058824,
187
+ "f": 0.9820359281
188
  },
189
  "aux:pass": {
190
  "p": 0.9910714286,
192
  "f": 0.9910714286
193
  },
194
  "acl:relcl": {
195
+ "p": 0.8604651163,
196
+ "r": 0.8604651163,
197
+ "f": 0.8604651163
198
  },
199
  "advcl": {
200
+ "p": 0.756097561,
201
+ "r": 0.7948717949,
202
+ "f": 0.775
203
  },
204
  "fixed": {
205
  "p": 0.9529411765,
207
  "f": 0.8756756757
208
  },
209
  "dep": {
210
+ "p": 0.2931034483,
211
+ "r": 0.5862068966,
212
+ "f": 0.3908045977
213
  },
214
  "expl:subj": {
215
+ "p": 0.8965517241,
216
  "r": 0.8125,
217
+ "f": 0.8524590164
218
  },
219
  "expl:comp": {
220
+ "p": 0.7179487179,
221
+ "r": 0.9333333333,
222
+ "f": 0.8115942029
223
  },
224
  "expl:pass": {
225
  "p": 0.75,
226
  "r": 0.4285714286,
227
  "f": 0.5454545455
228
  },
 
 
 
 
 
229
  "ccomp": {
230
+ "p": 0.98,
231
+ "r": 0.9607843137,
232
+ "f": 0.9702970297
233
  },
234
  "parataxis": {
235
+ "p": 0.7272727273,
236
+ "r": 0.5714285714,
237
+ "f": 0.64
238
  },
239
  "iobj": {
240
+ "p": 0.6842105263,
241
  "r": 0.52,
242
+ "f": 0.5909090909
243
+ },
244
+ "obl:agent": {
245
+ "p": 0.95,
246
+ "r": 0.9047619048,
247
+ "f": 0.9268292683
248
  },
249
  "nsubj:caus": {
250
  "p": 0.0,
267
  "f": 0.0
268
  },
269
  "vocative": {
270
+ "p": 0.8333333333,
271
  "r": 0.625,
272
+ "f": 0.7142857143
273
  },
274
  "dislocated": {
275
  "p": 0.0,
277
  "f": 0.0
278
  },
279
  "flat:foreign": {
280
+ "p": 0.75,
281
  "r": 0.4285714286,
282
+ "f": 0.5454545455
283
  },
284
  "orphan": {
285
  "p": 0.0,
297
  "f": 0.0
298
  }
299
  },
300
+ "tag_acc": 0.9580239274,
301
+ "lemma_acc": 0.9122482532,
302
+ "speed": 484.5019750434
303
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
config.cfg CHANGED
@@ -39,8 +39,9 @@ overwrite = true
39
  scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
40
 
41
  [components.morphologizer.model]
42
- @architectures = "spacy.Tagger.v1"
43
  nO = null
 
44
 
45
  [components.morphologizer.model.tok2vec]
46
  @architectures = "spacy-transformers.TransformerListener.v1"
@@ -120,7 +121,7 @@ dropout = 0.1
120
  accumulate_gradient = 3
121
  patience = 5000
122
  max_epochs = 0
123
- max_steps = 20000
124
  eval_frequency = 1000
125
  frozen_components = []
126
  before_to_disk = null
39
  scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
40
 
41
  [components.morphologizer.model]
42
+ @architectures = "spacy.Tagger.v2"
43
  nO = null
44
+ normalize = false
45
 
46
  [components.morphologizer.model.tok2vec]
47
  @architectures = "spacy-transformers.TransformerListener.v1"
121
  accumulate_gradient = 3
122
  patience = 5000
123
  max_epochs = 0
124
+ max_steps = 16000
125
  eval_frequency = 1000
126
  frozen_components = []
127
  before_to_disk = null
fr_dep_news_trf-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:620ddfdd1ca028837fbc8686f8f22738dbc7d34754c7a293a9cef07a166ef8bf
3
- size 400717231
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c011eb4592353ee7f6dc3aee8ea54dd26954176a93c29eca9d11b14b92c0a69e
3
+ size 400758890
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"fr",
3
  "name":"dep_news_trf",
4
- "version":"3.2.0",
5
  "description":"French transformer pipeline (camembert-base). Components: transformer, morphologizer, parser, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"LGPL-LR",
10
- "spacy_version":">=3.2.0,<3.3.0",
11
- "spacy_git_version":"bb26550e2",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -284,56 +284,56 @@
284
  "token_p":0.9844389844,
285
  "token_r":0.9896058454,
286
  "token_f":0.9870156531,
287
- "pos_acc":0.9863875425,
288
- "morph_acc":0.9791731106,
289
- "morph_micro_p":0.9934029687,
290
- "morph_micro_r":0.9908005361,
291
- "morph_micro_f":0.9921000458,
292
  "morph_per_feat":{
293
  "Definite":{
294
- "p":0.9985358712,
295
  "r":0.995620438,
296
- "f":0.9970760234
297
  },
298
  "Number":{
299
- "p":0.9959409594,
300
- "r":0.9937407953,
301
- "f":0.9948396609
302
  },
303
  "PronType":{
304
- "p":0.9974293059,
305
- "r":0.9929622521,
306
- "f":0.9951907663
307
  },
308
  "Gender":{
309
- "p":0.988963039,
310
- "r":0.9846664963,
311
- "f":0.9868100909
312
  },
313
  "Mood":{
314
- "p":0.9946619217,
315
- "r":0.9928952043,
316
- "f":0.9937777778
317
  },
318
  "Person":{
319
- "p":0.9974683544,
320
- "r":0.9911949686,
321
- "f":0.9943217666
322
  },
323
  "Tense":{
324
- "p":0.9868421053,
325
  "r":0.9959141982,
326
- "f":0.9913573971
327
  },
328
  "VerbForm":{
329
- "p":0.9901153213,
330
  "r":0.9950331126,
331
- "f":0.9925681255
332
  },
333
  "NumType":{
334
- "p":0.9927797834,
335
- "r":0.9385665529,
336
- "f":0.9649122807
337
  },
338
  "Reflex":{
339
  "p":1.0,
@@ -341,9 +341,9 @@
341
  "f":1.0
342
  },
343
  "Voice":{
344
- "p":0.9568965517,
345
  "r":0.9910714286,
346
- "f":0.9736842105
347
  },
348
  "Poss":{
349
  "p":1.0,
@@ -356,116 +356,116 @@
356
  "f":1.0
357
  }
358
  },
359
- "sents_p":0.8835616438,
360
- "sents_r":0.9393203883,
361
- "sents_f":0.9105882353,
362
- "dep_uas":0.9492309471,
363
- "dep_las":0.9295953757,
364
  "dep_las_per_type":{
365
  "det":{
366
- "p":0.9871382637,
367
- "r":0.9911218725,
368
- "f":0.9891260572
369
  },
370
  "nsubj":{
371
- "p":0.945368171,
372
- "r":0.9590361446,
373
- "f":0.95215311
374
  },
375
  "aux:tense":{
376
- "p":0.9761904762,
377
  "r":0.984,
378
- "f":0.9800796813
379
  },
380
  "root":{
381
- "p":0.9179954442,
382
  "r":0.9781553398,
383
- "f":0.9471210341
384
  },
385
  "obj":{
386
- "p":0.9451219512,
387
- "r":0.9198813056,
388
- "f":0.9323308271
389
  },
390
  "cc":{
391
- "p":0.9495412844,
392
- "r":0.9539170507,
393
- "f":0.9517241379
394
  },
395
  "case":{
396
- "p":0.9850238257,
397
- "r":0.9856948229,
398
- "f":0.9853592101
399
  },
400
  "obl:mod":{
401
- "p":0.8553459119,
402
- "r":0.8119402985,
403
- "f":0.8330781011
404
  },
405
  "nmod":{
406
- "p":0.9012961117,
407
- "r":0.9030969031,
408
- "f":0.9021956088
409
  },
410
  "conj":{
411
- "p":0.832,
412
  "r":0.8188976378,
413
- "f":0.8253968254
414
  },
415
  "nummod":{
416
- "p":0.9069767442,
417
- "r":0.9230769231,
418
- "f":0.9149560117
419
  },
420
  "amod":{
421
- "p":0.9664804469,
422
- "r":0.9453551913,
423
- "f":0.955801105
424
  },
425
  "acl":{
426
- "p":0.85,
427
- "r":0.8843930636,
428
- "f":0.8668555241
429
  },
430
  "mark":{
431
- "p":0.9733333333,
432
- "r":0.9647577093,
433
- "f":0.9690265487
434
  },
435
  "xcomp":{
436
- "p":0.9350649351,
437
- "r":0.9536423841,
438
- "f":0.9442622951
439
  },
440
  "flat:name":{
441
- "p":0.953271028,
442
  "r":0.9714285714,
443
- "f":0.9622641509
444
  },
445
  "cop":{
446
- "p":0.9659090909,
447
- "r":0.9444444444,
448
- "f":0.9550561798
449
  },
450
  "advmod":{
451
- "p":0.9361022364,
452
- "r":0.9184952978,
453
- "f":0.9272151899
454
  },
455
  "obl:arg":{
456
- "p":0.8878923767,
457
- "r":0.9,
458
- "f":0.8939051919
459
  },
460
  "appos":{
461
- "p":0.7078651685,
462
- "r":0.7590361446,
463
- "f":0.7325581395
464
  },
465
  "nsubj:pass":{
466
- "p":0.9761904762,
467
  "r":0.9647058824,
468
- "f":0.9704142012
469
  },
470
  "aux:pass":{
471
  "p":0.9910714286,
@@ -473,14 +473,14 @@
473
  "f":0.9910714286
474
  },
475
  "acl:relcl":{
476
- "p":0.8795180723,
477
- "r":0.8488372093,
478
- "f":0.8639053254
479
  },
480
  "advcl":{
481
- "p":0.7594936709,
482
- "r":0.7692307692,
483
- "f":0.7643312102
484
  },
485
  "fixed":{
486
  "p":0.9529411765,
@@ -488,44 +488,44 @@
488
  "f":0.8756756757
489
  },
490
  "dep":{
491
- "p":0.2388059701,
492
- "r":0.5517241379,
493
- "f":0.3333333333
494
  },
495
  "expl:subj":{
496
- "p":0.8666666667,
497
  "r":0.8125,
498
- "f":0.8387096774
499
  },
500
  "expl:comp":{
501
- "p":0.75,
502
- "r":1.0,
503
- "f":0.8571428571
504
  },
505
  "expl:pass":{
506
  "p":0.75,
507
  "r":0.4285714286,
508
  "f":0.5454545455
509
  },
510
- "obl:agent":{
511
- "p":0.975,
512
- "r":0.9285714286,
513
- "f":0.9512195122
514
- },
515
  "ccomp":{
516
- "p":0.96,
517
- "r":0.9411764706,
518
- "f":0.9504950495
519
  },
520
  "parataxis":{
521
- "p":0.7307692308,
522
- "r":0.6785714286,
523
- "f":0.7037037037
524
  },
525
  "iobj":{
526
- "p":0.7222222222,
527
  "r":0.52,
528
- "f":0.6046511628
 
 
 
 
 
529
  },
530
  "nsubj:caus":{
531
  "p":0.0,
@@ -548,9 +548,9 @@
548
  "f":0.0
549
  },
550
  "vocative":{
551
- "p":1.0,
552
  "r":0.625,
553
- "f":0.7692307692
554
  },
555
  "dislocated":{
556
  "p":0.0,
@@ -558,9 +558,9 @@
558
  "f":0.0
559
  },
560
  "flat:foreign":{
561
- "p":1.0,
562
  "r":0.4285714286,
563
- "f":0.6
564
  },
565
  "orphan":{
566
  "p":0.0,
@@ -578,9 +578,9 @@
578
  "f":0.0
579
  }
580
  },
581
- "tag_acc":0.9573063834,
582
- "lemma_acc":0.911837238,
583
- "speed":1637.6043941996
584
  },
585
  "sources":[
586
  {
1
  {
2
  "lang":"fr",
3
  "name":"dep_news_trf",
4
+ "version":"3.3.0",
5
  "description":"French transformer pipeline (camembert-base). Components: transformer, morphologizer, parser, attribute_ruler, lemmatizer.",
6
  "author":"Explosion",
7
  "email":"contact@explosion.ai",
8
  "url":"https://explosion.ai",
9
  "license":"LGPL-LR",
10
+ "spacy_version":">=3.3.0.dev0,<3.4.0",
11
+ "spacy_git_version":"849bef2de",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
284
  "token_p":0.9844389844,
285
  "token_r":0.9896058454,
286
  "token_f":0.9870156531,
287
+ "pos_acc":0.9871080858,
288
+ "morph_acc":0.9790173738,
289
+ "morph_micro_p":0.9940090476,
290
+ "morph_micro_r":0.9906177653,
291
+ "morph_micro_f":0.992310509,
292
  "morph_per_feat":{
293
  "Definite":{
294
+ "p":0.9978054133,
295
  "r":0.995620438,
296
+ "f":0.9967117282
297
  },
298
  "Number":{
299
+ "p":0.9952020668,
300
+ "r":0.992820324,
301
+ "f":0.9940097687
302
  },
303
  "PronType":{
304
+ "p":0.9980694981,
305
+ "r":0.9923224568,
306
+ "f":0.9951876805
307
  },
308
  "Gender":{
309
+ "p":0.9892141757,
310
+ "r":0.9844109379,
311
+ "f":0.9868067119
312
  },
313
  "Mood":{
314
+ "p":0.9982206406,
315
+ "r":0.9964476021,
316
+ "f":0.9973333333
317
  },
318
  "Person":{
319
+ "p":0.997471555,
320
+ "r":0.9924528302,
321
+ "f":0.9949558638
322
  },
323
  "Tense":{
324
+ "p":0.991861648,
325
  "r":0.9959141982,
326
+ "f":0.993883792
327
  },
328
  "VerbForm":{
329
+ "p":0.994210091,
330
  "r":0.9950331126,
331
+ "f":0.9946214315
332
  },
333
  "NumType":{
334
+ "p":0.9928057554,
335
+ "r":0.9419795222,
336
+ "f":0.9667250438
337
  },
338
  "Reflex":{
339
  "p":1.0,
341
  "f":1.0
342
  },
343
  "Voice":{
344
+ "p":0.9652173913,
345
  "r":0.9910714286,
346
+ "f":0.9779735683
347
  },
348
  "Poss":{
349
  "p":1.0,
356
  "f":1.0
357
  }
358
  },
359
+ "sents_p":0.9245283019,
360
+ "sents_r":0.9514563107,
361
+ "sents_f":0.9377990431,
362
+ "dep_uas":0.947216113,
363
+ "dep_las":0.9271002083,
364
  "dep_las_per_type":{
365
  "det":{
366
+ "p":0.9902991108,
367
+ "r":0.988700565,
368
+ "f":0.9894991922
369
  },
370
  "nsubj":{
371
+ "p":0.9452380952,
372
+ "r":0.956626506,
373
+ "f":0.9508982036
374
  },
375
  "aux:tense":{
376
+ "p":0.9609375,
377
  "r":0.984,
378
+ "f":0.9723320158
379
  },
380
  "root":{
381
+ "p":0.9460093897,
382
  "r":0.9781553398,
383
+ "f":0.9618138425
384
  },
385
  "obj":{
386
+ "p":0.936746988,
387
+ "r":0.9228486647,
388
+ "f":0.9297458894
389
  },
390
  "cc":{
391
+ "p":0.9541284404,
392
+ "r":0.9585253456,
393
+ "f":0.9563218391
394
  },
395
  "case":{
396
+ "p":0.9843110505,
397
+ "r":0.9829700272,
398
+ "f":0.9836400818
399
  },
400
  "obl:mod":{
401
+ "p":0.8145896657,
402
+ "r":0.8,
403
+ "f":0.8072289157
404
  },
405
  "nmod":{
406
+ "p":0.8952095808,
407
+ "r":0.8961038961,
408
+ "f":0.8956565152
409
  },
410
  "conj":{
411
+ "p":0.828685259,
412
  "r":0.8188976378,
413
+ "f":0.8237623762
414
  },
415
  "nummod":{
416
+ "p":0.8735632184,
417
+ "r":0.899408284,
418
+ "f":0.8862973761
419
  },
420
  "amod":{
421
+ "p":0.957952468,
422
+ "r":0.9544626594,
423
+ "f":0.9562043796
424
  },
425
  "acl":{
426
+ "p":0.8571428571,
427
+ "r":0.8670520231,
428
+ "f":0.8620689655
429
  },
430
  "mark":{
431
+ "p":0.9692982456,
432
+ "r":0.9735682819,
433
+ "f":0.9714285714
434
  },
435
  "xcomp":{
436
+ "p":0.9225806452,
437
+ "r":0.9470198675,
438
+ "f":0.9346405229
439
  },
440
  "flat:name":{
441
+ "p":0.9714285714,
442
  "r":0.9714285714,
443
+ "f":0.9714285714
444
  },
445
  "cop":{
446
+ "p":0.9333333333,
447
+ "r":0.9333333333,
448
+ "f":0.9333333333
449
  },
450
  "advmod":{
451
+ "p":0.9381107492,
452
+ "r":0.9028213166,
453
+ "f":0.9201277955
454
  },
455
  "obl:arg":{
456
+ "p":0.8828828829,
457
+ "r":0.8909090909,
458
+ "f":0.8868778281
459
  },
460
  "appos":{
461
+ "p":0.6931818182,
462
+ "r":0.734939759,
463
+ "f":0.7134502924
464
  },
465
  "nsubj:pass":{
466
+ "p":1.0,
467
  "r":0.9647058824,
468
+ "f":0.9820359281
469
  },
470
  "aux:pass":{
471
  "p":0.9910714286,
473
  "f":0.9910714286
474
  },
475
  "acl:relcl":{
476
+ "p":0.8604651163,
477
+ "r":0.8604651163,
478
+ "f":0.8604651163
479
  },
480
  "advcl":{
481
+ "p":0.756097561,
482
+ "r":0.7948717949,
483
+ "f":0.775
484
  },
485
  "fixed":{
486
  "p":0.9529411765,
488
  "f":0.8756756757
489
  },
490
  "dep":{
491
+ "p":0.2931034483,
492
+ "r":0.5862068966,
493
+ "f":0.3908045977
494
  },
495
  "expl:subj":{
496
+ "p":0.8965517241,
497
  "r":0.8125,
498
+ "f":0.8524590164
499
  },
500
  "expl:comp":{
501
+ "p":0.7179487179,
502
+ "r":0.9333333333,
503
+ "f":0.8115942029
504
  },
505
  "expl:pass":{
506
  "p":0.75,
507
  "r":0.4285714286,
508
  "f":0.5454545455
509
  },
 
 
 
 
 
510
  "ccomp":{
511
+ "p":0.98,
512
+ "r":0.9607843137,
513
+ "f":0.9702970297
514
  },
515
  "parataxis":{
516
+ "p":0.7272727273,
517
+ "r":0.5714285714,
518
+ "f":0.64
519
  },
520
  "iobj":{
521
+ "p":0.6842105263,
522
  "r":0.52,
523
+ "f":0.5909090909
524
+ },
525
+ "obl:agent":{
526
+ "p":0.95,
527
+ "r":0.9047619048,
528
+ "f":0.9268292683
529
  },
530
  "nsubj:caus":{
531
  "p":0.0,
548
  "f":0.0
549
  },
550
  "vocative":{
551
+ "p":0.8333333333,
552
  "r":0.625,
553
+ "f":0.7142857143
554
  },
555
  "dislocated":{
556
  "p":0.0,
558
  "f":0.0
559
  },
560
  "flat:foreign":{
561
+ "p":0.75,
562
  "r":0.4285714286,
563
+ "f":0.5454545455
564
  },
565
  "orphan":{
566
  "p":0.0,
578
  "f":0.0
579
  }
580
  },
581
+ "tag_acc":0.9580239274,
582
+ "lemma_acc":0.9122482532,
583
+ "speed":484.5019750434
584
  },
585
  "sources":[
586
  {
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cb843eb188d7793276850fc4d5ba7510c5d7a50c8641b69c56eb02741ad6a646
3
- size 603492
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9bd5b13b1c6ced4e4c0d999f138c76f455c1c4a030412a9553cfdc989808d64d
3
+ size 603544
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:003262584fb85ef96f8d557d20af4d406ccfd8391f4c48792272b4da44825673
3
  size 397805
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed7ee86919c9b9883fe7b06216c35fb1a69548b9b6fc681d4a7cc22b8bc42c7f
3
  size 397805
parser/moves CHANGED
@@ -1 +1 @@
1
- ��moves��{"0":{"":25253},"1":{"":21681},"2":{"case":7257,"det":6061,"nsubj":1982,"punct":1645,"advmod":1210,"cc":1205,"mark":1051,"aux:tense":673,"amod":662,"nummod":595,"aux:pass":544,"obl:mod":483,"nsubj:pass":425,"cop":365,"expl:comp":204,"obj":170,"expl:subj":164,"iobj":139,"advcl":123,"nmod":92,"expl:pass":40,"vocative":35,"dep":0},"3":{"nmod":5132,"punct":3954,"amod":2083,"conj":1517,"obj":1410,"obl:mod":1184,"obl:arg":1079,"acl":782,"xcomp":739,"flat:name":657,"advmod":562,"fixed":409,"appos":408,"acl:relcl":365,"advcl":306,"ccomp":238,"obl:agent":206,"dep":138,"nummod":117,"parataxis":92,"nsubj":75,"flat:foreign":63},"4":{"ROOT":2219}}�cfg��neg_key�
1
+ ��moves��{"0":{"":25345},"1":{"":21571},"2":{"case":7318,"det":6066,"nsubj":1969,"punct":1660,"cc":1214,"advmod":1209,"mark":1055,"aux:tense":673,"amod":664,"nummod":609,"aux:pass":546,"obl:mod":480,"nsubj:pass":420,"cop":366,"expl:comp":204,"obj":170,"expl:subj":165,"iobj":139,"advcl":123,"nmod":92,"expl:pass":40,"vocative":35,"dep":0},"3":{"nmod":4995,"punct":4040,"amod":2051,"conj":1514,"obj":1405,"obl:mod":1188,"obl:arg":1070,"acl":785,"xcomp":739,"flat:name":622,"advmod":564,"fixed":413,"appos":412,"acl:relcl":368,"advcl":306,"ccomp":238,"obl:agent":203,"dep":142,"nummod":124,"parataxis":95,"nsubj":76,"flat:foreign":59},"4":{"ROOT":2231}}�cfg��neg_key�
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 sha256:12846daf03978627be431b4b4f08f9b5554803fad9cc07794ad72a49a864b73a
3
- size 444773224
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117f35b51802043fab1b6ec14774e6b37f11c71fc0124480af53e56d6952fb5f
3
+ size 445799744
vocab/key2row CHANGED
@@ -1 +1,3 @@
1
-
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:76be8b528d0075f7aae98d6fa57a6d3c83ae480a8469e668d7b0af968995ac71
3
+ size 1