adrianeboyd commited on
Commit
0e768a3
1 Parent(s): e2bbeeb

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -14,27 +14,27 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.7286295794
18
  - name: NER Recall
19
  type: recall
20
  value: 0.6754716981
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.7010443864
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
- value: 0.9713305562
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9729199051
38
  - task:
39
  name: MORPH
40
  type: token-classification
@@ -48,28 +48,28 @@ model-index:
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
- value: 0.9670526831
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.9206249156
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.9067758481
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9901574803
73
  ---
74
  ### Details: https://spacy.io/models/ja#ja_core_news_md
75
 
@@ -78,8 +78,8 @@ Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `ja_core_news_md` |
81
- | **Version** | `3.6.0` |
82
- | **spaCy** | `>=3.6.0,<3.7.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 480443 keys, 20000 unique vectors (300 dimensions) |
@@ -106,21 +106,21 @@ Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
106
  | Type | Score |
107
  | --- | --- |
108
  | `TOKEN_ACC` | 99.37 |
109
- | `TOKEN_P` | 97.65 |
110
- | `TOKEN_R` | 97.90 |
111
- | `TOKEN_F` | 97.77 |
112
- | `POS_ACC` | 97.29 |
113
  | `MORPH_ACC` | 0.00 |
114
  | `MORPH_MICRO_P` | 34.01 |
115
  | `MORPH_MICRO_R` | 98.04 |
116
  | `MORPH_MICRO_F` | 50.51 |
117
- | `SENTS_P` | 98.82 |
118
- | `SENTS_R` | 99.21 |
119
- | `SENTS_F` | 99.02 |
120
- | `DEP_UAS` | 92.06 |
121
- | `DEP_LAS` | 90.68 |
122
  | `TAG_ACC` | 97.13 |
123
- | `LEMMA_ACC` | 96.71 |
124
- | `ENTS_P` | 72.86 |
125
  | `ENTS_R` | 67.55 |
126
- | `ENTS_F` | 70.10 |
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.7266576455
18
  - name: NER Recall
19
  type: recall
20
  value: 0.6754716981
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.7001303781
24
  - task:
25
  name: TAG
26
  type: token-classification
27
  metrics:
28
  - name: TAG (XPOS) Accuracy
29
  type: accuracy
30
+ value: 0.9713282143
31
  - task:
32
  name: POS
33
  type: token-classification
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9712018326
38
  - task:
39
  name: MORPH
40
  type: token-classification
 
48
  metrics:
49
  - name: Lemma Accuracy
50
  type: accuracy
51
+ value: 0.9670499959
52
  - task:
53
  name: UNLABELED_DEPENDENCIES
54
  type: token-classification
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.9221346544
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.9092381767
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9696376102
73
  ---
74
  ### Details: https://spacy.io/models/ja#ja_core_news_md
75
 
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `ja_core_news_md` |
81
+ | **Version** | `3.7.0` |
82
+ | **spaCy** | `>=3.7.0,<3.8.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 480443 keys, 20000 unique vectors (300 dimensions) |
 
106
  | Type | Score |
107
  | --- | --- |
108
  | `TOKEN_ACC` | 99.37 |
109
+ | `TOKEN_P` | 97.64 |
110
+ | `TOKEN_R` | 97.88 |
111
+ | `TOKEN_F` | 97.76 |
112
+ | `POS_ACC` | 97.12 |
113
  | `MORPH_ACC` | 0.00 |
114
  | `MORPH_MICRO_P` | 34.01 |
115
  | `MORPH_MICRO_R` | 98.04 |
116
  | `MORPH_MICRO_F` | 50.51 |
117
+ | `SENTS_P` | 96.30 |
118
+ | `SENTS_R` | 97.63 |
119
+ | `SENTS_F` | 96.96 |
120
+ | `DEP_UAS` | 92.21 |
121
+ | `DEP_LAS` | 90.92 |
122
  | `TAG_ACC` | 97.13 |
123
+ | `LEMMA_ACC` | 96.70 |
124
+ | `ENTS_P` | 72.67 |
125
  | `ENTS_R` | 67.55 |
126
+ | `ENTS_F` | 70.01 |
accuracy.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "token_acc": 0.9937494927,
3
- "token_p": 0.9764591282,
4
- "token_r": 0.9790021974,
5
- "token_f": 0.9777290092,
6
- "pos_acc": 0.9729199051,
7
  "morph_acc": 0.0,
8
  "morph_micro_p": 0.3401360544,
9
  "morph_micro_r": 0.9803921569,
@@ -25,188 +25,188 @@
25
  "f": 0.0
26
  }
27
  },
28
- "sents_p": 0.9882121807,
29
- "sents_r": 0.9921104536,
30
- "sents_f": 0.9901574803,
31
- "dep_uas": 0.9206249156,
32
- "dep_las": 0.9067758481,
33
  "dep_las_per_type": {
34
  "cc": {
35
- "p": 0.7872340426,
36
- "r": 0.7708333333,
37
- "f": 0.7789473684
38
  },
39
  "compound": {
40
- "p": 0.9375729288,
41
- "r": 0.9058624577,
42
- "f": 0.9214449541
43
  },
44
  "obl": {
45
- "p": 0.8119551681,
46
- "r": 0.8139825218,
47
- "f": 0.812967581
48
  },
49
  "case": {
50
- "p": 0.990015361,
51
  "r": 0.9794832827,
52
- "f": 0.9847211612
53
  },
54
  "dislocated": {
55
- "p": 0.5384615385,
56
  "r": 0.5384615385,
57
- "f": 0.5384615385
58
  },
59
  "nsubj": {
60
- "p": 0.8181818182,
61
- "r": 0.8119001919,
62
- "f": 0.8150289017
63
  },
64
  "nmod": {
65
- "p": 0.8760842627,
66
  "r": 0.8269005848,
67
- "f": 0.8507821901
68
  },
69
  "root": {
70
- "p": 0.9641434263,
71
- "r": 0.9546351085,
72
- "f": 0.9593657086
73
  },
74
  "aux": {
75
- "p": 0.977818854,
76
- "r": 0.982358403,
77
- "f": 0.9800833719
78
  },
79
  "advcl": {
80
- "p": 0.6826484018,
81
- "r": 0.6719101124,
82
- "f": 0.6772366931
83
  },
84
  "mark": {
85
- "p": 0.9738430584,
86
- "r": 0.968,
87
- "f": 0.9709127382
88
  },
89
  "fixed": {
90
- "p": 0.9553571429,
91
- "r": 0.9727272727,
92
- "f": 0.963963964
93
  },
94
  "acl": {
95
- "p": 0.8264642082,
96
  "r": 0.8373626374,
97
- "f": 0.8318777293
98
  },
99
  "obj": {
100
- "p": 0.9513677812,
101
- "r": 0.9456193353,
102
- "f": 0.9484848485
103
  },
104
  "nummod": {
105
- "p": 0.9868421053,
106
- "r": 0.8875739645,
107
- "f": 0.9345794393
108
  },
109
  "advmod": {
110
- "p": 0.7251908397,
111
- "r": 0.6785714286,
112
- "f": 0.7011070111
113
  },
114
  "amod": {
115
- "p": 0.9032258065,
116
  "r": 0.7567567568,
117
- "f": 0.8235294118
118
  },
119
  "cop": {
120
- "p": 0.9640718563,
121
- "r": 0.9360465116,
122
- "f": 0.9498525074
123
  },
124
  "ccomp": {
125
- "p": 0.9444444444,
126
- "r": 0.7727272727,
127
- "f": 0.85
128
  },
129
  "det": {
130
- "p": 0.9807692308,
131
- "r": 0.9622641509,
132
- "f": 0.9714285714
133
  },
134
  "csubj": {
135
- "p": 0.75,
136
- "r": 0.75,
137
- "f": 0.75
138
  },
139
  "dep": {
140
- "p": 0.2,
141
- "r": 0.1428571429,
142
- "f": 0.1666666667
143
  }
144
  },
145
- "tag_acc": 0.9713305562,
146
- "lemma_acc": 0.9670526831,
147
- "ents_p": 0.7286295794,
148
  "ents_r": 0.6754716981,
149
- "ents_f": 0.7010443864,
150
  "ents_per_type": {
151
  "DATE": {
152
- "p": 0.9375,
153
- "r": 0.9633027523,
154
- "f": 0.9502262443
155
- },
156
- "PERSON": {
157
- "p": 0.6959459459,
158
- "r": 0.7410071942,
159
- "f": 0.7177700348
160
  },
161
  "ORG": {
162
- "p": 0.6454545455,
163
- "r": 0.5182481752,
164
- "f": 0.5748987854
 
 
 
 
 
 
 
 
 
 
165
  },
166
  "GPE": {
167
- "p": 0.6956521739,
168
- "r": 0.6808510638,
169
- "f": 0.688172043
 
 
 
 
 
 
 
 
 
 
170
  },
171
  "QUANTITY": {
172
  "p": 0.8529411765,
173
  "r": 0.8787878788,
174
  "f": 0.8656716418
175
  },
176
- "TIME": {
177
- "p": 0.5714285714,
178
- "r": 1.0,
179
- "f": 0.7272727273
180
- },
181
  "NORP": {
182
- "p": 0.6896551724,
183
  "r": 0.625,
184
- "f": 0.6557377049
185
  },
186
  "ORDINAL": {
187
- "p": 0.6666666667,
188
- "r": 0.6363636364,
189
- "f": 0.6511627907
190
- },
191
- "TITLE_AFFIX": {
192
- "p": 0.8260869565,
193
- "r": 0.6333333333,
194
- "f": 0.7169811321
195
- },
196
- "PRODUCT": {
197
- "p": 0.4642857143,
198
- "r": 0.3095238095,
199
- "f": 0.3714285714
200
  },
201
  "WORK_OF_ART": {
202
- "p": 0.6470588235,
203
  "r": 0.6470588235,
204
- "f": 0.6470588235
205
  },
206
  "CARDINAL": {
207
- "p": 1.0,
208
- "r": 0.5,
209
- "f": 0.6666666667
210
  },
211
  "PERCENT": {
212
  "p": 1.0,
@@ -214,18 +214,18 @@
214
  "f": 0.4444444444
215
  },
216
  "EVENT": {
217
- "p": 0.7777777778,
218
- "r": 0.5384615385,
219
- "f": 0.6363636364
220
  },
221
  "LOC": {
222
- "p": 0.5,
223
  "r": 0.7,
224
- "f": 0.5833333333
225
  },
226
  "FAC": {
227
- "p": 0.5483870968,
228
- "r": 0.4594594595,
229
  "f": 0.5
230
  },
231
  "MOVEMENT": {
@@ -244,10 +244,10 @@
244
  "f": 1.0
245
  },
246
  "LANGUAGE": {
247
- "p": 1.0,
248
  "r": 1.0,
249
- "f": 1.0
250
  }
251
  },
252
- "speed": 8525.2225414726
253
  }
 
1
  {
2
+ "token_acc": 0.9936678032,
3
+ "token_p": 0.9763760351,
4
+ "token_r": 0.9788394238,
5
+ "token_f": 0.9776061776,
6
+ "pos_acc": 0.9712018326,
7
  "morph_acc": 0.0,
8
  "morph_micro_p": 0.3401360544,
9
  "morph_micro_r": 0.9803921569,
 
25
  "f": 0.0
26
  }
27
  },
28
+ "sents_p": 0.9630350195,
29
+ "sents_r": 0.9763313609,
30
+ "sents_f": 0.9696376102,
31
+ "dep_uas": 0.9221346544,
32
+ "dep_las": 0.9092381767,
33
  "dep_las_per_type": {
34
  "cc": {
35
+ "p": 0.8913043478,
36
+ "r": 0.8541666667,
37
+ "f": 0.8723404255
38
  },
39
  "compound": {
40
+ "p": 0.938372093,
41
+ "r": 0.9098083427,
42
+ "f": 0.9238694906
43
  },
44
  "obl": {
45
+ "p": 0.822418136,
46
+ "r": 0.8152309613,
47
+ "f": 0.8188087774
48
  },
49
  "case": {
50
+ "p": 0.9896353167,
51
  "r": 0.9794832827,
52
+ "f": 0.9845331297
53
  },
54
  "dislocated": {
55
+ "p": 0.5833333333,
56
  "r": 0.5384615385,
57
+ "f": 0.56
58
  },
59
  "nsubj": {
60
+ "p": 0.8243243243,
61
+ "r": 0.8195777351,
62
+ "f": 0.8219441771
63
  },
64
  "nmod": {
65
+ "p": 0.8804483188,
66
  "r": 0.8269005848,
67
+ "f": 0.8528347407
68
  },
69
  "root": {
70
+ "p": 0.9625246548,
71
+ "r": 0.9625246548,
72
+ "f": 0.9625246548
73
  },
74
  "aux": {
75
+ "p": 0.9796484736,
76
+ "r": 0.9832869081,
77
+ "f": 0.9814643188
78
  },
79
  "advcl": {
80
+ "p": 0.7050691244,
81
+ "r": 0.6876404494,
82
+ "f": 0.6962457338
83
  },
84
  "mark": {
85
+ "p": 0.9738955823,
86
+ "r": 0.97,
87
+ "f": 0.9719438878
88
  },
89
  "fixed": {
90
+ "p": 0.9589285714,
91
+ "r": 0.9763636364,
92
+ "f": 0.9675675676
93
  },
94
  "acl": {
95
+ "p": 0.8373626374,
96
  "r": 0.8373626374,
97
+ "f": 0.8373626374
98
  },
99
  "obj": {
100
+ "p": 0.9452887538,
101
+ "r": 0.9395770393,
102
+ "f": 0.9424242424
103
  },
104
  "nummod": {
105
+ "p": 0.987012987,
106
+ "r": 0.899408284,
107
+ "f": 0.9411764706
108
  },
109
  "advmod": {
110
+ "p": 0.6917293233,
111
+ "r": 0.6571428571,
112
+ "f": 0.673992674
113
  },
114
  "amod": {
115
+ "p": 0.875,
116
  "r": 0.7567567568,
117
+ "f": 0.8115942029
118
  },
119
  "cop": {
120
+ "p": 0.9695121951,
121
+ "r": 0.9244186047,
122
+ "f": 0.9464285714
123
  },
124
  "ccomp": {
125
+ "p": 0.9473684211,
126
+ "r": 0.8181818182,
127
+ "f": 0.8780487805
128
  },
129
  "det": {
130
+ "p": 0.9803921569,
131
+ "r": 0.9433962264,
132
+ "f": 0.9615384615
133
  },
134
  "csubj": {
135
+ "p": 0.6153846154,
136
+ "r": 0.6666666667,
137
+ "f": 0.64
138
  },
139
  "dep": {
140
+ "p": 0.4,
141
+ "r": 0.2857142857,
142
+ "f": 0.3333333333
143
  }
144
  },
145
+ "tag_acc": 0.9713282143,
146
+ "lemma_acc": 0.9670499959,
147
+ "ents_p": 0.7266576455,
148
  "ents_r": 0.6754716981,
149
+ "ents_f": 0.7001303781,
150
  "ents_per_type": {
151
  "DATE": {
152
+ "p": 0.954954955,
153
+ "r": 0.9724770642,
154
+ "f": 0.9636363636
 
 
 
 
 
155
  },
156
  "ORG": {
157
+ "p": 0.6315789474,
158
+ "r": 0.5255474453,
159
+ "f": 0.5737051793
160
+ },
161
+ "TITLE_AFFIX": {
162
+ "p": 0.7391304348,
163
+ "r": 0.5666666667,
164
+ "f": 0.641509434
165
+ },
166
+ "PERSON": {
167
+ "p": 0.7163120567,
168
+ "r": 0.726618705,
169
+ "f": 0.7214285714
170
  },
171
  "GPE": {
172
+ "p": 0.6534653465,
173
+ "r": 0.7021276596,
174
+ "f": 0.6769230769
175
+ },
176
+ "PRODUCT": {
177
+ "p": 0.5555555556,
178
+ "r": 0.3571428571,
179
+ "f": 0.4347826087
180
+ },
181
+ "TIME": {
182
+ "p": 0.6666666667,
183
+ "r": 1.0,
184
+ "f": 0.8
185
  },
186
  "QUANTITY": {
187
  "p": 0.8529411765,
188
  "r": 0.8787878788,
189
  "f": 0.8656716418
190
  },
 
 
 
 
 
191
  "NORP": {
192
+ "p": 0.7142857143,
193
  "r": 0.625,
194
+ "f": 0.6666666667
195
  },
196
  "ORDINAL": {
197
+ "p": 0.5909090909,
198
+ "r": 0.5909090909,
199
+ "f": 0.5909090909
 
 
 
 
 
 
 
 
 
 
200
  },
201
  "WORK_OF_ART": {
202
+ "p": 0.6111111111,
203
  "r": 0.6470588235,
204
+ "f": 0.6285714286
205
  },
206
  "CARDINAL": {
207
+ "p": 0.0,
208
+ "r": 0.0,
209
+ "f": 0.0
210
  },
211
  "PERCENT": {
212
  "p": 1.0,
 
214
  "f": 0.4444444444
215
  },
216
  "EVENT": {
217
+ "p": 0.6666666667,
218
+ "r": 0.6153846154,
219
+ "f": 0.64
220
  },
221
  "LOC": {
222
+ "p": 0.5384615385,
223
  "r": 0.7,
224
+ "f": 0.6086956522
225
  },
226
  "FAC": {
227
+ "p": 0.652173913,
228
+ "r": 0.4054054054,
229
  "f": 0.5
230
  },
231
  "MOVEMENT": {
 
244
  "f": 1.0
245
  },
246
  "LANGUAGE": {
247
+ "p": 0.8571428571,
248
  "r": 1.0,
249
+ "f": 0.9230769231
250
  }
251
  },
252
+ "speed": 7926.2334345884
253
  }
config.cfg CHANGED
@@ -16,6 +16,7 @@ before_creation = null
16
  after_creation = null
17
  after_pipeline_creation = null
18
  batch_size = 256
 
19
 
20
  [nlp.tokenizer]
21
  @tokenizers = "spacy.ja.JapaneseTokenizer"
 
16
  after_creation = null
17
  after_pipeline_creation = null
18
  batch_size = 256
19
+ vectors = {"@vectors":"spacy.Vectors.v1"}
20
 
21
  [nlp.tokenizer]
22
  @tokenizers = "spacy.ja.JapaneseTokenizer"
ja_core_news_md-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee6dac35b142ccf6fbe1414593be4414b7ebc571be729e3d14c793860be32867
3
- size 42109137
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9620316189c3638feec33d3abd0375d532650860d4e6cd2b2a6232594e14d440
3
+ size 42112454
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"ja",
3
  "name":"core_news_md",
4
- "version":"3.6.0",
5
  "description":"Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, 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":">=3.6.0,<3.7.0",
11
- "spacy_git_version":"cb4fdc83e",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
@@ -113,11 +113,11 @@
113
  "senter"
114
  ],
115
  "performance":{
116
- "token_acc":0.9937494927,
117
- "token_p":0.9764591282,
118
- "token_r":0.9790021974,
119
- "token_f":0.9777290092,
120
- "pos_acc":0.9729199051,
121
  "morph_acc":0.0,
122
  "morph_micro_p":0.3401360544,
123
  "morph_micro_r":0.9803921569,
@@ -139,188 +139,188 @@
139
  "f":0.0
140
  }
141
  },
142
- "sents_p":0.9882121807,
143
- "sents_r":0.9921104536,
144
- "sents_f":0.9901574803,
145
- "dep_uas":0.9206249156,
146
- "dep_las":0.9067758481,
147
  "dep_las_per_type":{
148
  "cc":{
149
- "p":0.7872340426,
150
- "r":0.7708333333,
151
- "f":0.7789473684
152
  },
153
  "compound":{
154
- "p":0.9375729288,
155
- "r":0.9058624577,
156
- "f":0.9214449541
157
  },
158
  "obl":{
159
- "p":0.8119551681,
160
- "r":0.8139825218,
161
- "f":0.812967581
162
  },
163
  "case":{
164
- "p":0.990015361,
165
  "r":0.9794832827,
166
- "f":0.9847211612
167
  },
168
  "dislocated":{
169
- "p":0.5384615385,
170
  "r":0.5384615385,
171
- "f":0.5384615385
172
  },
173
  "nsubj":{
174
- "p":0.8181818182,
175
- "r":0.8119001919,
176
- "f":0.8150289017
177
  },
178
  "nmod":{
179
- "p":0.8760842627,
180
  "r":0.8269005848,
181
- "f":0.8507821901
182
  },
183
  "root":{
184
- "p":0.9641434263,
185
- "r":0.9546351085,
186
- "f":0.9593657086
187
  },
188
  "aux":{
189
- "p":0.977818854,
190
- "r":0.982358403,
191
- "f":0.9800833719
192
  },
193
  "advcl":{
194
- "p":0.6826484018,
195
- "r":0.6719101124,
196
- "f":0.6772366931
197
  },
198
  "mark":{
199
- "p":0.9738430584,
200
- "r":0.968,
201
- "f":0.9709127382
202
  },
203
  "fixed":{
204
- "p":0.9553571429,
205
- "r":0.9727272727,
206
- "f":0.963963964
207
  },
208
  "acl":{
209
- "p":0.8264642082,
210
  "r":0.8373626374,
211
- "f":0.8318777293
212
  },
213
  "obj":{
214
- "p":0.9513677812,
215
- "r":0.9456193353,
216
- "f":0.9484848485
217
  },
218
  "nummod":{
219
- "p":0.9868421053,
220
- "r":0.8875739645,
221
- "f":0.9345794393
222
  },
223
  "advmod":{
224
- "p":0.7251908397,
225
- "r":0.6785714286,
226
- "f":0.7011070111
227
  },
228
  "amod":{
229
- "p":0.9032258065,
230
  "r":0.7567567568,
231
- "f":0.8235294118
232
  },
233
  "cop":{
234
- "p":0.9640718563,
235
- "r":0.9360465116,
236
- "f":0.9498525074
237
  },
238
  "ccomp":{
239
- "p":0.9444444444,
240
- "r":0.7727272727,
241
- "f":0.85
242
  },
243
  "det":{
244
- "p":0.9807692308,
245
- "r":0.9622641509,
246
- "f":0.9714285714
247
  },
248
  "csubj":{
249
- "p":0.75,
250
- "r":0.75,
251
- "f":0.75
252
  },
253
  "dep":{
254
- "p":0.2,
255
- "r":0.1428571429,
256
- "f":0.1666666667
257
  }
258
  },
259
- "tag_acc":0.9713305562,
260
- "lemma_acc":0.9670526831,
261
- "ents_p":0.7286295794,
262
  "ents_r":0.6754716981,
263
- "ents_f":0.7010443864,
264
  "ents_per_type":{
265
  "DATE":{
266
- "p":0.9375,
267
- "r":0.9633027523,
268
- "f":0.9502262443
269
- },
270
- "PERSON":{
271
- "p":0.6959459459,
272
- "r":0.7410071942,
273
- "f":0.7177700348
274
  },
275
  "ORG":{
276
- "p":0.6454545455,
277
- "r":0.5182481752,
278
- "f":0.5748987854
 
 
 
 
 
 
 
 
 
 
279
  },
280
  "GPE":{
281
- "p":0.6956521739,
282
- "r":0.6808510638,
283
- "f":0.688172043
 
 
 
 
 
 
 
 
 
 
284
  },
285
  "QUANTITY":{
286
  "p":0.8529411765,
287
  "r":0.8787878788,
288
  "f":0.8656716418
289
  },
290
- "TIME":{
291
- "p":0.5714285714,
292
- "r":1.0,
293
- "f":0.7272727273
294
- },
295
  "NORP":{
296
- "p":0.6896551724,
297
  "r":0.625,
298
- "f":0.6557377049
299
  },
300
  "ORDINAL":{
301
- "p":0.6666666667,
302
- "r":0.6363636364,
303
- "f":0.6511627907
304
- },
305
- "TITLE_AFFIX":{
306
- "p":0.8260869565,
307
- "r":0.6333333333,
308
- "f":0.7169811321
309
- },
310
- "PRODUCT":{
311
- "p":0.4642857143,
312
- "r":0.3095238095,
313
- "f":0.3714285714
314
  },
315
  "WORK_OF_ART":{
316
- "p":0.6470588235,
317
  "r":0.6470588235,
318
- "f":0.6470588235
319
  },
320
  "CARDINAL":{
321
- "p":1.0,
322
- "r":0.5,
323
- "f":0.6666666667
324
  },
325
  "PERCENT":{
326
  "p":1.0,
@@ -328,18 +328,18 @@
328
  "f":0.4444444444
329
  },
330
  "EVENT":{
331
- "p":0.7777777778,
332
- "r":0.5384615385,
333
- "f":0.6363636364
334
  },
335
  "LOC":{
336
- "p":0.5,
337
  "r":0.7,
338
- "f":0.5833333333
339
  },
340
  "FAC":{
341
- "p":0.5483870968,
342
- "r":0.4594594595,
343
  "f":0.5
344
  },
345
  "MOVEMENT":{
@@ -358,12 +358,12 @@
358
  "f":1.0
359
  },
360
  "LANGUAGE":{
361
- "p":1.0,
362
  "r":1.0,
363
- "f":1.0
364
  }
365
  },
366
- "speed":8525.2225414726
367
  },
368
  "sources":[
369
  {
 
1
  {
2
  "lang":"ja",
3
  "name":"core_news_md",
4
+ "version":"3.7.0",
5
  "description":"Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, 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":">=3.7.0,<3.8.0",
11
+ "spacy_git_version":"6b4f77441",
12
  "vectors":{
13
  "width":300,
14
  "vectors":20000,
 
113
  "senter"
114
  ],
115
  "performance":{
116
+ "token_acc":0.9936678032,
117
+ "token_p":0.9763760351,
118
+ "token_r":0.9788394238,
119
+ "token_f":0.9776061776,
120
+ "pos_acc":0.9712018326,
121
  "morph_acc":0.0,
122
  "morph_micro_p":0.3401360544,
123
  "morph_micro_r":0.9803921569,
 
139
  "f":0.0
140
  }
141
  },
142
+ "sents_p":0.9630350195,
143
+ "sents_r":0.9763313609,
144
+ "sents_f":0.9696376102,
145
+ "dep_uas":0.9221346544,
146
+ "dep_las":0.9092381767,
147
  "dep_las_per_type":{
148
  "cc":{
149
+ "p":0.8913043478,
150
+ "r":0.8541666667,
151
+ "f":0.8723404255
152
  },
153
  "compound":{
154
+ "p":0.938372093,
155
+ "r":0.9098083427,
156
+ "f":0.9238694906
157
  },
158
  "obl":{
159
+ "p":0.822418136,
160
+ "r":0.8152309613,
161
+ "f":0.8188087774
162
  },
163
  "case":{
164
+ "p":0.9896353167,
165
  "r":0.9794832827,
166
+ "f":0.9845331297
167
  },
168
  "dislocated":{
169
+ "p":0.5833333333,
170
  "r":0.5384615385,
171
+ "f":0.56
172
  },
173
  "nsubj":{
174
+ "p":0.8243243243,
175
+ "r":0.8195777351,
176
+ "f":0.8219441771
177
  },
178
  "nmod":{
179
+ "p":0.8804483188,
180
  "r":0.8269005848,
181
+ "f":0.8528347407
182
  },
183
  "root":{
184
+ "p":0.9625246548,
185
+ "r":0.9625246548,
186
+ "f":0.9625246548
187
  },
188
  "aux":{
189
+ "p":0.9796484736,
190
+ "r":0.9832869081,
191
+ "f":0.9814643188
192
  },
193
  "advcl":{
194
+ "p":0.7050691244,
195
+ "r":0.6876404494,
196
+ "f":0.6962457338
197
  },
198
  "mark":{
199
+ "p":0.9738955823,
200
+ "r":0.97,
201
+ "f":0.9719438878
202
  },
203
  "fixed":{
204
+ "p":0.9589285714,
205
+ "r":0.9763636364,
206
+ "f":0.9675675676
207
  },
208
  "acl":{
209
+ "p":0.8373626374,
210
  "r":0.8373626374,
211
+ "f":0.8373626374
212
  },
213
  "obj":{
214
+ "p":0.9452887538,
215
+ "r":0.9395770393,
216
+ "f":0.9424242424
217
  },
218
  "nummod":{
219
+ "p":0.987012987,
220
+ "r":0.899408284,
221
+ "f":0.9411764706
222
  },
223
  "advmod":{
224
+ "p":0.6917293233,
225
+ "r":0.6571428571,
226
+ "f":0.673992674
227
  },
228
  "amod":{
229
+ "p":0.875,
230
  "r":0.7567567568,
231
+ "f":0.8115942029
232
  },
233
  "cop":{
234
+ "p":0.9695121951,
235
+ "r":0.9244186047,
236
+ "f":0.9464285714
237
  },
238
  "ccomp":{
239
+ "p":0.9473684211,
240
+ "r":0.8181818182,
241
+ "f":0.8780487805
242
  },
243
  "det":{
244
+ "p":0.9803921569,
245
+ "r":0.9433962264,
246
+ "f":0.9615384615
247
  },
248
  "csubj":{
249
+ "p":0.6153846154,
250
+ "r":0.6666666667,
251
+ "f":0.64
252
  },
253
  "dep":{
254
+ "p":0.4,
255
+ "r":0.2857142857,
256
+ "f":0.3333333333
257
  }
258
  },
259
+ "tag_acc":0.9713282143,
260
+ "lemma_acc":0.9670499959,
261
+ "ents_p":0.7266576455,
262
  "ents_r":0.6754716981,
263
+ "ents_f":0.7001303781,
264
  "ents_per_type":{
265
  "DATE":{
266
+ "p":0.954954955,
267
+ "r":0.9724770642,
268
+ "f":0.9636363636
 
 
 
 
 
269
  },
270
  "ORG":{
271
+ "p":0.6315789474,
272
+ "r":0.5255474453,
273
+ "f":0.5737051793
274
+ },
275
+ "TITLE_AFFIX":{
276
+ "p":0.7391304348,
277
+ "r":0.5666666667,
278
+ "f":0.641509434
279
+ },
280
+ "PERSON":{
281
+ "p":0.7163120567,
282
+ "r":0.726618705,
283
+ "f":0.7214285714
284
  },
285
  "GPE":{
286
+ "p":0.6534653465,
287
+ "r":0.7021276596,
288
+ "f":0.6769230769
289
+ },
290
+ "PRODUCT":{
291
+ "p":0.5555555556,
292
+ "r":0.3571428571,
293
+ "f":0.4347826087
294
+ },
295
+ "TIME":{
296
+ "p":0.6666666667,
297
+ "r":1.0,
298
+ "f":0.8
299
  },
300
  "QUANTITY":{
301
  "p":0.8529411765,
302
  "r":0.8787878788,
303
  "f":0.8656716418
304
  },
 
 
 
 
 
305
  "NORP":{
306
+ "p":0.7142857143,
307
  "r":0.625,
308
+ "f":0.6666666667
309
  },
310
  "ORDINAL":{
311
+ "p":0.5909090909,
312
+ "r":0.5909090909,
313
+ "f":0.5909090909
 
 
 
 
 
 
 
 
 
 
314
  },
315
  "WORK_OF_ART":{
316
+ "p":0.6111111111,
317
  "r":0.6470588235,
318
+ "f":0.6285714286
319
  },
320
  "CARDINAL":{
321
+ "p":0.0,
322
+ "r":0.0,
323
+ "f":0.0
324
  },
325
  "PERCENT":{
326
  "p":1.0,
 
328
  "f":0.4444444444
329
  },
330
  "EVENT":{
331
+ "p":0.6666666667,
332
+ "r":0.6153846154,
333
+ "f":0.64
334
  },
335
  "LOC":{
336
+ "p":0.5384615385,
337
  "r":0.7,
338
+ "f":0.6086956522
339
  },
340
  "FAC":{
341
+ "p":0.652173913,
342
+ "r":0.4054054054,
343
  "f":0.5
344
  },
345
  "MOVEMENT":{
 
358
  "f":1.0
359
  },
360
  "LANGUAGE":{
361
+ "p":0.8571428571,
362
  "r":1.0,
363
+ "f":0.9230769231
364
  }
365
  },
366
+ "speed":7926.2334345884
367
  },
368
  "sources":[
369
  {
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b256385af2b284d8ec194b7f29f99880ef93f080f7ffce204f15159b568e19bd
3
  size 8189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c83c9c4d6f14f089b29eb4a2d8d419f6305078df8a6e1d7a431c5589ed070c4
3
  size 8189
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c1395a55781e19ebd23fe6f5db459b537c02f1d2de98b5bfb3ef1b2674e3580e
3
  size 6385103
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36c4b6677a3af1c2faec4bfbfdfe69dda723c7cf6b33ee93078befb9de4a20f8
3
  size 6385103
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:39d342f188347e7e7eb2ceadc904dfc761a43dadc1e54f6db085e1d504624a6f
3
  size 299888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a5fe5baae5e2be19440cddaacc6d7b1803e8d0e27c73ab7856f9ab3f07091f7
3
  size 299888
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3d29d577d1ce6ae912a99a356db7f78ede7363943104a76666df7686bb2e39fd
3
  size 213263
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13a25ddabb7d35c5f487e65ca2a211862260e5970031d8e784dc907a3309c1cf
3
  size 213263
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2f633072a97899b1331a62dcf041d2c638942d872444755e512eaeb1821d3d4
3
  size 6365607
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38570646b13755bac8a51cc7bd72d8126303bc37c682db087366782288f769de
3
  size 6365607
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3aa3edb6b4c2ff7cdc802411a4494ff4e2dfc181e3020e18a8b82308b3da03b7
3
- size 15613755
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ee3873dbf1e450a553ec721049d432be8949e8752b4e985e243f5251104378f
3
+ size 15614261