adrianeboyd commited on
Commit
a82b0b4
1 Parent(s): 871a9a9

Update spaCy pipeline

Browse files
README.md CHANGED
@@ -14,13 +14,13 @@ model-index:
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
- value: 0.6792168675
18
  - name: NER Recall
19
  type: recall
20
- value: 0.5672955975
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.6182316655
24
  - task:
25
  name: TAG
26
  type: token-classification
@@ -34,7 +34,7 @@ model-index:
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
- value: 0.9615085696
38
  - task:
39
  name: MORPH
40
  type: token-classification
@@ -55,21 +55,21 @@ model-index:
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
- value: 0.9200288184
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.9060559705
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9745596869
73
  ---
74
  ### Details: https://spacy.io/models/ja#ja_core_news_sm
75
 
@@ -78,8 +78,8 @@ Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `ja_core_news_sm` |
81
- | **Version** | `3.4.0` |
82
- | **spaCy** | `>=3.4.0,<3.5.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
@@ -105,22 +105,22 @@ Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
105
 
106
  | Type | Score |
107
  | --- | --- |
108
- | `TOKEN_ACC` | 99.69 |
109
  | `TOKEN_P` | 97.65 |
110
  | `TOKEN_R` | 97.90 |
111
  | `TOKEN_F` | 97.77 |
112
- | `POS_ACC` | 96.15 |
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` | 96.70 |
118
- | `SENTS_R` | 98.22 |
119
- | `SENTS_F` | 97.46 |
120
- | `DEP_UAS` | 92.00 |
121
- | `DEP_LAS` | 90.61 |
122
  | `TAG_ACC` | 97.12 |
123
  | `LEMMA_ACC` | 96.71 |
124
- | `ENTS_P` | 67.92 |
125
- | `ENTS_R` | 56.73 |
126
- | `ENTS_F` | 61.82 |
 
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.680620155
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.5522012579
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.6097222222
24
  - task:
25
  name: TAG
26
  type: token-classification
 
34
  metrics:
35
  - name: POS (UPOS) Accuracy
36
  type: accuracy
37
+ value: 0.9608508898
38
  - task:
39
  name: MORPH
40
  type: token-classification
 
55
  metrics:
56
  - name: Unlabeled Attachment Score (UAS)
57
  type: f_score
58
+ value: 0.9191282421
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.903437725
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9891838741
73
  ---
74
  ### Details: https://spacy.io/models/ja#ja_core_news_sm
75
 
 
78
  | Feature | Description |
79
  | --- | --- |
80
  | **Name** | `ja_core_news_sm` |
81
+ | **Version** | `3.5.0` |
82
+ | **spaCy** | `>=3.5.0,<3.6.0` |
83
  | **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `ner` |
84
  | **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `ner` |
85
  | **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
 
105
 
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` | 96.09 |
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` | 98.63 |
118
+ | `SENTS_R` | 99.21 |
119
+ | `SENTS_F` | 98.92 |
120
+ | `DEP_UAS` | 91.91 |
121
+ | `DEP_LAS` | 90.34 |
122
  | `TAG_ACC` | 97.12 |
123
  | `LEMMA_ACC` | 96.71 |
124
+ | `ENTS_P` | 68.06 |
125
+ | `ENTS_R` | 55.22 |
126
+ | `ENTS_F` | 60.97 |
accuracy.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "token_acc": 0.9968649485,
3
  "token_p": 0.9764591282,
4
  "token_r": 0.9790021974,
5
  "token_f": 0.9777290092,
6
- "pos_acc": 0.9615085696,
7
  "morph_acc": 0.0,
8
  "morph_micro_p": 0.3401360544,
9
  "morph_micro_r": 0.9803921569,
@@ -25,128 +25,128 @@
25
  "f": 0.0
26
  }
27
  },
28
- "sents_p": 0.9669902913,
29
- "sents_r": 0.9822485207,
30
- "sents_f": 0.9745596869,
31
- "dep_uas": 0.9200288184,
32
- "dep_las": 0.9060559705,
33
  "dep_las_per_type": {
34
  "cc": {
35
- "p": 0.7959183673,
36
- "r": 0.8125,
37
- "f": 0.8041237113
38
  },
39
  "compound": {
40
- "p": 0.9388824214,
41
- "r": 0.9092446449,
42
- "f": 0.9238258877
43
  },
44
  "obl": {
45
- "p": 0.8032581454,
46
- "r": 0.8002496879,
47
- "f": 0.8017510944
48
  },
49
  "case": {
50
- "p": 0.9888718342,
51
- "r": 0.9791033435,
52
- "f": 0.9839633448
53
  },
54
  "dislocated": {
55
- "p": 0.625,
56
- "r": 0.3846153846,
57
- "f": 0.4761904762
58
  },
59
  "nsubj": {
60
- "p": 0.8188824663,
61
- "r": 0.8157389635,
62
- "f": 0.8173076923
63
  },
64
  "nmod": {
65
- "p": 0.8813349815,
66
- "r": 0.8339181287,
67
- "f": 0.8569711538
68
  },
69
  "root": {
70
- "p": 0.9625984252,
71
- "r": 0.9644970414,
72
- "f": 0.963546798
73
  },
74
  "aux": {
75
- "p": 0.9760147601,
76
- "r": 0.982358403,
77
- "f": 0.9791763073
78
  },
79
  "advcl": {
80
- "p": 0.6756756757,
81
- "r": 0.6741573034,
82
- "f": 0.6749156355
83
  },
84
  "mark": {
85
- "p": 0.9754601227,
86
- "r": 0.954,
87
- "f": 0.9646107179
88
  },
89
  "fixed": {
90
- "p": 0.9572192513,
91
- "r": 0.9763636364,
92
- "f": 0.9666966697
93
  },
94
  "acl": {
95
- "p": 0.8296943231,
96
- "r": 0.8351648352,
97
- "f": 0.8324205915
98
  },
99
  "obj": {
100
- "p": 0.9480122324,
101
- "r": 0.9365558912,
102
- "f": 0.9422492401
103
  },
104
  "nummod": {
105
- "p": 0.9869281046,
106
- "r": 0.8934911243,
107
- "f": 0.9378881988
108
  },
109
  "advmod": {
110
- "p": 0.6923076923,
111
- "r": 0.6428571429,
112
- "f": 0.6666666667
113
  },
114
  "amod": {
115
- "p": 0.8965517241,
116
  "r": 0.7027027027,
117
- "f": 0.7878787879
118
  },
119
  "cop": {
120
- "p": 0.9640718563,
121
- "r": 0.9360465116,
122
- "f": 0.9498525074
123
  },
124
  "ccomp": {
125
  "p": 0.9473684211,
126
  "r": 0.8181818182,
127
  "f": 0.8780487805
128
  },
 
 
 
 
 
129
  "det": {
130
- "p": 0.9807692308,
131
- "r": 0.9622641509,
132
- "f": 0.9714285714
133
  },
134
  "csubj": {
135
- "p": 0.8,
136
- "r": 0.6666666667,
137
- "f": 0.7272727273
138
- },
139
- "dep": {
140
- "p": 0.0,
141
- "r": 0.0,
142
- "f": 0.0
143
  }
144
  },
145
  "tag_acc": 0.9712488769,
146
  "lemma_acc": 0.9670526831,
147
- "ents_p": 0.6792168675,
148
- "ents_r": 0.5672955975,
149
- "ents_f": 0.6182316655,
150
  "ents_per_type": {
151
  "DATE": {
152
  "p": 0.9449541284,
@@ -154,79 +154,79 @@
154
  "f": 0.9449541284
155
  },
156
  "PERSON": {
157
- "p": 0.5384615385,
158
- "r": 0.4532374101,
159
- "f": 0.4921875
 
 
 
 
 
160
  },
161
  "GPE": {
162
- "p": 0.6578947368,
163
- "r": 0.5319148936,
164
- "f": 0.5882352941
165
  },
166
  "PRODUCT": {
167
- "p": 0.48,
168
- "r": 0.2857142857,
169
- "f": 0.3582089552
170
  },
171
  "TIME": {
172
- "p": 0.6666666667,
173
  "r": 1.0,
174
- "f": 0.8
175
  },
176
  "QUANTITY": {
177
- "p": 0.8676470588,
178
- "r": 0.8939393939,
179
- "f": 0.8805970149
180
  },
181
  "NORP": {
182
- "p": 0.7916666667,
183
  "r": 0.59375,
184
- "f": 0.6785714286
185
- },
186
- "TITLE_AFFIX": {
187
- "p": 0.7368421053,
188
- "r": 0.4666666667,
189
- "f": 0.5714285714
190
- },
191
- "ORG": {
192
- "p": 0.5,
193
- "r": 0.4160583942,
194
- "f": 0.4541832669
195
  },
196
  "ORDINAL": {
197
- "p": 0.5,
198
  "r": 0.5909090909,
199
- "f": 0.5416666667
 
 
 
 
 
 
 
 
 
 
200
  },
201
  "WORK_OF_ART": {
202
  "p": 0.6666666667,
203
  "r": 0.5882352941,
204
  "f": 0.625
205
  },
206
- "CARDINAL": {
207
- "p": 1.0,
208
- "r": 0.5,
209
- "f": 0.6666666667
210
- },
211
- "EVENT": {
212
- "p": 0.8,
213
- "r": 0.4615384615,
214
- "f": 0.5853658537
215
- },
216
  "PERCENT": {
217
  "p": 0.6666666667,
218
  "r": 0.2857142857,
219
  "f": 0.4
220
  },
221
- "FAC": {
222
- "p": 0.6666666667,
223
- "r": 0.3243243243,
224
- "f": 0.4363636364
 
 
 
 
 
225
  },
226
  "LOC": {
227
- "p": 0.5833333333,
228
- "r": 0.7,
229
- "f": 0.6363636364
230
  },
231
  "MOVEMENT": {
232
  "p": 0.0,
@@ -244,10 +244,10 @@
244
  "f": 1.0
245
  },
246
  "LANGUAGE": {
247
- "p": 0.8571428571,
248
- "r": 1.0,
249
- "f": 0.9230769231
250
  }
251
  },
252
- "speed": 11044.5862640641
253
  }
 
1
  {
2
+ "token_acc": 0.9937494927,
3
  "token_p": 0.9764591282,
4
  "token_r": 0.9790021974,
5
  "token_f": 0.9777290092,
6
+ "pos_acc": 0.9608508898,
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": 0.9862745098,
29
+ "sents_r": 0.9921104536,
30
+ "sents_f": 0.9891838741,
31
+ "dep_uas": 0.9191282421,
32
+ "dep_las": 0.903437725,
33
  "dep_las_per_type": {
34
  "cc": {
35
+ "p": 0.7826086957,
36
+ "r": 0.75,
37
+ "f": 0.7659574468
38
  },
39
  "compound": {
40
+ "p": 0.9355400697,
41
+ "r": 0.9081172492,
42
+ "f": 0.921624714
43
  },
44
  "obl": {
45
+ "p": 0.8102372035,
46
+ "r": 0.8102372035,
47
+ "f": 0.8102372035
48
  },
49
  "case": {
50
+ "p": 0.9876970396,
51
+ "r": 0.9760638298,
52
+ "f": 0.9818459775
53
  },
54
  "dislocated": {
55
+ "p": 0.5384615385,
56
+ "r": 0.5384615385,
57
+ "f": 0.5384615385
58
  },
59
  "nsubj": {
60
+ "p": 0.8077669903,
61
+ "r": 0.7984644914,
62
+ "f": 0.8030888031
63
  },
64
  "nmod": {
65
+ "p": 0.88375,
66
+ "r": 0.8269005848,
67
+ "f": 0.8543806647
68
  },
69
  "root": {
70
+ "p": 0.9602385686,
71
+ "r": 0.9526627219,
72
+ "f": 0.9564356436
73
  },
74
  "aux": {
75
+ "p": 0.9768732655,
76
+ "r": 0.9805013928,
77
+ "f": 0.9786839666
78
  },
79
  "advcl": {
80
+ "p": 0.6859688196,
81
+ "r": 0.6921348315,
82
+ "f": 0.6890380313
83
  },
84
  "mark": {
85
+ "p": 0.9598393574,
86
+ "r": 0.956,
87
+ "f": 0.9579158317
88
  },
89
  "fixed": {
90
+ "p": 0.9534883721,
91
+ "r": 0.9690909091,
92
+ "f": 0.96122633
93
  },
94
  "acl": {
95
+ "p": 0.8355855856,
96
+ "r": 0.8153846154,
97
+ "f": 0.8253615128
98
  },
99
  "obj": {
100
+ "p": 0.9420731707,
101
+ "r": 0.9335347432,
102
+ "f": 0.937784522
103
  },
104
  "nummod": {
105
+ "p": 0.9743589744,
106
+ "r": 0.899408284,
107
+ "f": 0.9353846154
108
  },
109
  "advmod": {
110
+ "p": 0.6641791045,
111
+ "r": 0.6357142857,
112
+ "f": 0.6496350365
113
  },
114
  "amod": {
115
+ "p": 0.9285714286,
116
  "r": 0.7027027027,
117
+ "f": 0.8
118
  },
119
  "cop": {
120
+ "p": 0.9523809524,
121
+ "r": 0.9302325581,
122
+ "f": 0.9411764706
123
  },
124
  "ccomp": {
125
  "p": 0.9473684211,
126
  "r": 0.8181818182,
127
  "f": 0.8780487805
128
  },
129
+ "dep": {
130
+ "p": 0.1111111111,
131
+ "r": 0.1428571429,
132
+ "f": 0.125
133
+ },
134
  "det": {
135
+ "p": 0.9803921569,
136
+ "r": 0.9433962264,
137
+ "f": 0.9615384615
138
  },
139
  "csubj": {
140
+ "p": 0.7692307692,
141
+ "r": 0.8333333333,
142
+ "f": 0.8
 
 
 
 
 
143
  }
144
  },
145
  "tag_acc": 0.9712488769,
146
  "lemma_acc": 0.9670526831,
147
+ "ents_p": 0.680620155,
148
+ "ents_r": 0.5522012579,
149
+ "ents_f": 0.6097222222,
150
  "ents_per_type": {
151
  "DATE": {
152
  "p": 0.9449541284,
 
154
  "f": 0.9449541284
155
  },
156
  "PERSON": {
157
+ "p": 0.592920354,
158
+ "r": 0.4820143885,
159
+ "f": 0.5317460317
160
+ },
161
+ "ORG": {
162
+ "p": 0.5204081633,
163
+ "r": 0.3722627737,
164
+ "f": 0.4340425532
165
  },
166
  "GPE": {
167
+ "p": 0.6842105263,
168
+ "r": 0.5531914894,
169
+ "f": 0.6117647059
170
  },
171
  "PRODUCT": {
172
+ "p": 0.4090909091,
173
+ "r": 0.2142857143,
174
+ "f": 0.28125
175
  },
176
  "TIME": {
177
+ "p": 0.5714285714,
178
  "r": 1.0,
179
+ "f": 0.7272727273
180
  },
181
  "QUANTITY": {
182
+ "p": 0.8333333333,
183
+ "r": 0.9090909091,
184
+ "f": 0.8695652174
185
  },
186
  "NORP": {
187
+ "p": 0.7037037037,
188
  "r": 0.59375,
189
+ "f": 0.6440677966
 
 
 
 
 
 
 
 
 
 
190
  },
191
  "ORDINAL": {
192
+ "p": 0.5652173913,
193
  "r": 0.5909090909,
194
+ "f": 0.5777777778
195
+ },
196
+ "TITLE_AFFIX": {
197
+ "p": 0.75,
198
+ "r": 0.4,
199
+ "f": 0.5217391304
200
+ },
201
+ "FAC": {
202
+ "p": 0.375,
203
+ "r": 0.2432432432,
204
+ "f": 0.2950819672
205
  },
206
  "WORK_OF_ART": {
207
  "p": 0.6666666667,
208
  "r": 0.5882352941,
209
  "f": 0.625
210
  },
 
 
 
 
 
 
 
 
 
 
211
  "PERCENT": {
212
  "p": 0.6666666667,
213
  "r": 0.2857142857,
214
  "f": 0.4
215
  },
216
+ "EVENT": {
217
+ "p": 0.5882352941,
218
+ "r": 0.3846153846,
219
+ "f": 0.4651162791
220
+ },
221
+ "CARDINAL": {
222
+ "p": 0.0,
223
+ "r": 0.0,
224
+ "f": 0.0
225
  },
226
  "LOC": {
227
+ "p": 0.6666666667,
228
+ "r": 0.6,
229
+ "f": 0.6315789474
230
  },
231
  "MOVEMENT": {
232
  "p": 0.0,
 
244
  "f": 1.0
245
  },
246
  "LANGUAGE": {
247
+ "p": 1.0,
248
+ "r": 0.8333333333,
249
+ "f": 0.9090909091
250
  }
251
  },
252
+ "speed": 10095.0961085464
253
  }
attribute_ruler/patterns CHANGED
Binary files a/attribute_ruler/patterns and b/attribute_ruler/patterns differ
 
config.cfg CHANGED
@@ -135,8 +135,8 @@ factory = "tok2vec"
135
  [components.tok2vec.model.embed]
136
  @architectures = "spacy.MultiHashEmbed.v2"
137
  width = ${components.tok2vec.model.encode:width}
138
- attrs = ["NORM","PREFIX","SUFFIX","SHAPE"]
139
- rows = [5000,1000,2500,2500]
140
  include_static_vectors = false
141
 
142
  [components.tok2vec.model.encode]
@@ -178,6 +178,7 @@ eval_frequency = 1000
178
  frozen_components = []
179
  before_to_disk = null
180
  annotating_components = []
 
181
 
182
  [training.batcher]
183
  @batchers = "spacy.batch_by_words.v1"
 
135
  [components.tok2vec.model.embed]
136
  @architectures = "spacy.MultiHashEmbed.v2"
137
  width = ${components.tok2vec.model.encode:width}
138
+ attrs = ["NORM","PREFIX","SUFFIX","SHAPE","IS_SPACE"]
139
+ rows = [5000,1000,2500,2500,50]
140
  include_static_vectors = false
141
 
142
  [components.tok2vec.model.encode]
 
178
  frozen_components = []
179
  before_to_disk = null
180
  annotating_components = []
181
+ before_update = null
182
 
183
  [training.batcher]
184
  @batchers = "spacy.batch_by_words.v1"
ja_core_news_sm-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cbc125fb8e0c4fa41923294eedec9f16792e96c8911e9c086f55443f84bc822e
3
- size 11973416
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11d8eda21e78c1395fa30c4eb098c5d1188338d0c37368bef3bef0ceb7b61346
3
+ size 12095275
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"ja",
3
  "name":"core_news_sm",
4
- "version":"3.4.0",
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":">=3.4.0,<3.5.0",
11
- "spacy_git_version":"dd038b536",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
@@ -113,11 +113,11 @@
113
  "senter"
114
  ],
115
  "performance":{
116
- "token_acc":0.9968649485,
117
  "token_p":0.9764591282,
118
  "token_r":0.9790021974,
119
  "token_f":0.9777290092,
120
- "pos_acc":0.9615085696,
121
  "morph_acc":0.0,
122
  "morph_micro_p":0.3401360544,
123
  "morph_micro_r":0.9803921569,
@@ -139,128 +139,128 @@
139
  "f":0.0
140
  }
141
  },
142
- "sents_p":0.9669902913,
143
- "sents_r":0.9822485207,
144
- "sents_f":0.9745596869,
145
- "dep_uas":0.9200288184,
146
- "dep_las":0.9060559705,
147
  "dep_las_per_type":{
148
  "cc":{
149
- "p":0.7959183673,
150
- "r":0.8125,
151
- "f":0.8041237113
152
  },
153
  "compound":{
154
- "p":0.9388824214,
155
- "r":0.9092446449,
156
- "f":0.9238258877
157
  },
158
  "obl":{
159
- "p":0.8032581454,
160
- "r":0.8002496879,
161
- "f":0.8017510944
162
  },
163
  "case":{
164
- "p":0.9888718342,
165
- "r":0.9791033435,
166
- "f":0.9839633448
167
  },
168
  "dislocated":{
169
- "p":0.625,
170
- "r":0.3846153846,
171
- "f":0.4761904762
172
  },
173
  "nsubj":{
174
- "p":0.8188824663,
175
- "r":0.8157389635,
176
- "f":0.8173076923
177
  },
178
  "nmod":{
179
- "p":0.8813349815,
180
- "r":0.8339181287,
181
- "f":0.8569711538
182
  },
183
  "root":{
184
- "p":0.9625984252,
185
- "r":0.9644970414,
186
- "f":0.963546798
187
  },
188
  "aux":{
189
- "p":0.9760147601,
190
- "r":0.982358403,
191
- "f":0.9791763073
192
  },
193
  "advcl":{
194
- "p":0.6756756757,
195
- "r":0.6741573034,
196
- "f":0.6749156355
197
  },
198
  "mark":{
199
- "p":0.9754601227,
200
- "r":0.954,
201
- "f":0.9646107179
202
  },
203
  "fixed":{
204
- "p":0.9572192513,
205
- "r":0.9763636364,
206
- "f":0.9666966697
207
  },
208
  "acl":{
209
- "p":0.8296943231,
210
- "r":0.8351648352,
211
- "f":0.8324205915
212
  },
213
  "obj":{
214
- "p":0.9480122324,
215
- "r":0.9365558912,
216
- "f":0.9422492401
217
  },
218
  "nummod":{
219
- "p":0.9869281046,
220
- "r":0.8934911243,
221
- "f":0.9378881988
222
  },
223
  "advmod":{
224
- "p":0.6923076923,
225
- "r":0.6428571429,
226
- "f":0.6666666667
227
  },
228
  "amod":{
229
- "p":0.8965517241,
230
  "r":0.7027027027,
231
- "f":0.7878787879
232
  },
233
  "cop":{
234
- "p":0.9640718563,
235
- "r":0.9360465116,
236
- "f":0.9498525074
237
  },
238
  "ccomp":{
239
  "p":0.9473684211,
240
  "r":0.8181818182,
241
  "f":0.8780487805
242
  },
 
 
 
 
 
243
  "det":{
244
- "p":0.9807692308,
245
- "r":0.9622641509,
246
- "f":0.9714285714
247
  },
248
  "csubj":{
249
- "p":0.8,
250
- "r":0.6666666667,
251
- "f":0.7272727273
252
- },
253
- "dep":{
254
- "p":0.0,
255
- "r":0.0,
256
- "f":0.0
257
  }
258
  },
259
  "tag_acc":0.9712488769,
260
  "lemma_acc":0.9670526831,
261
- "ents_p":0.6792168675,
262
- "ents_r":0.5672955975,
263
- "ents_f":0.6182316655,
264
  "ents_per_type":{
265
  "DATE":{
266
  "p":0.9449541284,
@@ -268,79 +268,79 @@
268
  "f":0.9449541284
269
  },
270
  "PERSON":{
271
- "p":0.5384615385,
272
- "r":0.4532374101,
273
- "f":0.4921875
 
 
 
 
 
274
  },
275
  "GPE":{
276
- "p":0.6578947368,
277
- "r":0.5319148936,
278
- "f":0.5882352941
279
  },
280
  "PRODUCT":{
281
- "p":0.48,
282
- "r":0.2857142857,
283
- "f":0.3582089552
284
  },
285
  "TIME":{
286
- "p":0.6666666667,
287
  "r":1.0,
288
- "f":0.8
289
  },
290
  "QUANTITY":{
291
- "p":0.8676470588,
292
- "r":0.8939393939,
293
- "f":0.8805970149
294
  },
295
  "NORP":{
296
- "p":0.7916666667,
297
  "r":0.59375,
298
- "f":0.6785714286
299
- },
300
- "TITLE_AFFIX":{
301
- "p":0.7368421053,
302
- "r":0.4666666667,
303
- "f":0.5714285714
304
- },
305
- "ORG":{
306
- "p":0.5,
307
- "r":0.4160583942,
308
- "f":0.4541832669
309
  },
310
  "ORDINAL":{
311
- "p":0.5,
312
  "r":0.5909090909,
313
- "f":0.5416666667
 
 
 
 
 
 
 
 
 
 
314
  },
315
  "WORK_OF_ART":{
316
  "p":0.6666666667,
317
  "r":0.5882352941,
318
  "f":0.625
319
  },
320
- "CARDINAL":{
321
- "p":1.0,
322
- "r":0.5,
323
- "f":0.6666666667
324
- },
325
- "EVENT":{
326
- "p":0.8,
327
- "r":0.4615384615,
328
- "f":0.5853658537
329
- },
330
  "PERCENT":{
331
  "p":0.6666666667,
332
  "r":0.2857142857,
333
  "f":0.4
334
  },
335
- "FAC":{
336
- "p":0.6666666667,
337
- "r":0.3243243243,
338
- "f":0.4363636364
 
 
 
 
 
339
  },
340
  "LOC":{
341
- "p":0.5833333333,
342
- "r":0.7,
343
- "f":0.6363636364
344
  },
345
  "MOVEMENT":{
346
  "p":0.0,
@@ -358,12 +358,12 @@
358
  "f":1.0
359
  },
360
  "LANGUAGE":{
361
- "p":0.8571428571,
362
- "r":1.0,
363
- "f":0.9230769231
364
  }
365
  },
366
- "speed":11044.5862640641
367
  },
368
  "sources":[
369
  {
 
1
  {
2
  "lang":"ja",
3
  "name":"core_news_sm",
4
+ "version":"3.5.0",
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":">=3.5.0,<3.6.0",
11
+ "spacy_git_version":"9e0322de1",
12
  "vectors":{
13
  "width":0,
14
  "vectors":0,
 
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":0.9608508898,
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":0.9862745098,
143
+ "sents_r":0.9921104536,
144
+ "sents_f":0.9891838741,
145
+ "dep_uas":0.9191282421,
146
+ "dep_las":0.903437725,
147
  "dep_las_per_type":{
148
  "cc":{
149
+ "p":0.7826086957,
150
+ "r":0.75,
151
+ "f":0.7659574468
152
  },
153
  "compound":{
154
+ "p":0.9355400697,
155
+ "r":0.9081172492,
156
+ "f":0.921624714
157
  },
158
  "obl":{
159
+ "p":0.8102372035,
160
+ "r":0.8102372035,
161
+ "f":0.8102372035
162
  },
163
  "case":{
164
+ "p":0.9876970396,
165
+ "r":0.9760638298,
166
+ "f":0.9818459775
167
  },
168
  "dislocated":{
169
+ "p":0.5384615385,
170
+ "r":0.5384615385,
171
+ "f":0.5384615385
172
  },
173
  "nsubj":{
174
+ "p":0.8077669903,
175
+ "r":0.7984644914,
176
+ "f":0.8030888031
177
  },
178
  "nmod":{
179
+ "p":0.88375,
180
+ "r":0.8269005848,
181
+ "f":0.8543806647
182
  },
183
  "root":{
184
+ "p":0.9602385686,
185
+ "r":0.9526627219,
186
+ "f":0.9564356436
187
  },
188
  "aux":{
189
+ "p":0.9768732655,
190
+ "r":0.9805013928,
191
+ "f":0.9786839666
192
  },
193
  "advcl":{
194
+ "p":0.6859688196,
195
+ "r":0.6921348315,
196
+ "f":0.6890380313
197
  },
198
  "mark":{
199
+ "p":0.9598393574,
200
+ "r":0.956,
201
+ "f":0.9579158317
202
  },
203
  "fixed":{
204
+ "p":0.9534883721,
205
+ "r":0.9690909091,
206
+ "f":0.96122633
207
  },
208
  "acl":{
209
+ "p":0.8355855856,
210
+ "r":0.8153846154,
211
+ "f":0.8253615128
212
  },
213
  "obj":{
214
+ "p":0.9420731707,
215
+ "r":0.9335347432,
216
+ "f":0.937784522
217
  },
218
  "nummod":{
219
+ "p":0.9743589744,
220
+ "r":0.899408284,
221
+ "f":0.9353846154
222
  },
223
  "advmod":{
224
+ "p":0.6641791045,
225
+ "r":0.6357142857,
226
+ "f":0.6496350365
227
  },
228
  "amod":{
229
+ "p":0.9285714286,
230
  "r":0.7027027027,
231
+ "f":0.8
232
  },
233
  "cop":{
234
+ "p":0.9523809524,
235
+ "r":0.9302325581,
236
+ "f":0.9411764706
237
  },
238
  "ccomp":{
239
  "p":0.9473684211,
240
  "r":0.8181818182,
241
  "f":0.8780487805
242
  },
243
+ "dep":{
244
+ "p":0.1111111111,
245
+ "r":0.1428571429,
246
+ "f":0.125
247
+ },
248
  "det":{
249
+ "p":0.9803921569,
250
+ "r":0.9433962264,
251
+ "f":0.9615384615
252
  },
253
  "csubj":{
254
+ "p":0.7692307692,
255
+ "r":0.8333333333,
256
+ "f":0.8
 
 
 
 
 
257
  }
258
  },
259
  "tag_acc":0.9712488769,
260
  "lemma_acc":0.9670526831,
261
+ "ents_p":0.680620155,
262
+ "ents_r":0.5522012579,
263
+ "ents_f":0.6097222222,
264
  "ents_per_type":{
265
  "DATE":{
266
  "p":0.9449541284,
 
268
  "f":0.9449541284
269
  },
270
  "PERSON":{
271
+ "p":0.592920354,
272
+ "r":0.4820143885,
273
+ "f":0.5317460317
274
+ },
275
+ "ORG":{
276
+ "p":0.5204081633,
277
+ "r":0.3722627737,
278
+ "f":0.4340425532
279
  },
280
  "GPE":{
281
+ "p":0.6842105263,
282
+ "r":0.5531914894,
283
+ "f":0.6117647059
284
  },
285
  "PRODUCT":{
286
+ "p":0.4090909091,
287
+ "r":0.2142857143,
288
+ "f":0.28125
289
  },
290
  "TIME":{
291
+ "p":0.5714285714,
292
  "r":1.0,
293
+ "f":0.7272727273
294
  },
295
  "QUANTITY":{
296
+ "p":0.8333333333,
297
+ "r":0.9090909091,
298
+ "f":0.8695652174
299
  },
300
  "NORP":{
301
+ "p":0.7037037037,
302
  "r":0.59375,
303
+ "f":0.6440677966
 
 
 
 
 
 
 
 
 
 
304
  },
305
  "ORDINAL":{
306
+ "p":0.5652173913,
307
  "r":0.5909090909,
308
+ "f":0.5777777778
309
+ },
310
+ "TITLE_AFFIX":{
311
+ "p":0.75,
312
+ "r":0.4,
313
+ "f":0.5217391304
314
+ },
315
+ "FAC":{
316
+ "p":0.375,
317
+ "r":0.2432432432,
318
+ "f":0.2950819672
319
  },
320
  "WORK_OF_ART":{
321
  "p":0.6666666667,
322
  "r":0.5882352941,
323
  "f":0.625
324
  },
 
 
 
 
 
 
 
 
 
 
325
  "PERCENT":{
326
  "p":0.6666666667,
327
  "r":0.2857142857,
328
  "f":0.4
329
  },
330
+ "EVENT":{
331
+ "p":0.5882352941,
332
+ "r":0.3846153846,
333
+ "f":0.4651162791
334
+ },
335
+ "CARDINAL":{
336
+ "p":0.0,
337
+ "r":0.0,
338
+ "f":0.0
339
  },
340
  "LOC":{
341
+ "p":0.6666666667,
342
+ "r":0.6,
343
+ "f":0.6315789474
344
  },
345
  "MOVEMENT":{
346
  "p":0.0,
 
358
  "f":1.0
359
  },
360
  "LANGUAGE":{
361
+ "p":1.0,
362
+ "r":0.8333333333,
363
+ "f":0.9090909091
364
  }
365
  },
366
+ "speed":10095.0961085464
367
  },
368
  "sources":[
369
  {
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b06b5631b6158914b83210df4c9c3f2f97f4bdb911e380a3aa80276223f52b3
3
  size 8189
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:077ce5ccf5f35157308cdd0eaf994a7b9aa7da314d9915f66d6c40637a915a07
3
  size 8189
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2451b5201fd7b812b16ad9aba82db399514afada6fb39703bef3b4a143bf9811
3
  size 6158761
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78d7e1e9fcbe04b63baa9c5f3b4246c45a8c261b9fb468b15f58f54ac13f1af8
3
  size 6158761
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:123648e466c6d2a1374fa5b6ababffcf4380f314c3a7d8e0f5c4772d697c082b
3
  size 299888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d10b2d91b6c1c91ea6749e34960e39b91c0387879a0725c66f6e356d61150652
3
  size 299888
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d9fae2019492ddc4015a4779f8bcccc539e33e75b3a5987fd4c7e1a9b3109abf
3
  size 190447
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e702c1f7108f4f94161d62ec2ee467f23b408c380c092f03f0b04899f9759255
3
  size 190447
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:03d8b91d52feaf870e0274b308d51f16888184475719544be4dfca28e68a6a40
3
- size 6009091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c221d02a9bc2dc9899215d5db015abf4de1258c93faa8dc01275692ed925513
3
+ size 6139232
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1bf573690c4ec067dd67641c1dd1d61cff10480e193d93d94ba3f305bfc2d58
3
- size 1604157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5857ba34d91114e1cb4480ccdcfabfdf22f582bbd892893967485a2938ecd019
3
+ size 1601625