adrianeboyd commited on
Commit
9409659
1 Parent(s): ac7f8a8

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: 0.6797583082
18
  - name: NER Recall
19
  type: recall
20
- value: 0.5660377358
21
  - name: NER F Score
22
  type: f_score
23
- value: 0.6177076184
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: 0.9626963351
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: 0.9202575532
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
- value: 0.9066774658
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
- value: 0.9940828402
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** | `3.6.0` |
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** | 0 keys, 0 unique vectors (0 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` | 96.27 |
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` | 99.41 |
118
- | `SENTS_R` | 99.41 |
119
- | `SENTS_F` | 99.41 |
120
- | `DEP_UAS` | 92.03 |
121
- | `DEP_LAS` | 90.67 |
122
  | `TAG_ACC` | 97.13 |
123
- | `LEMMA_ACC` | 96.71 |
124
- | `ENTS_P` | 67.98 |
125
- | `ENTS_R` | 56.60 |
126
- | `ENTS_F` | 61.77 |
14
  metrics:
15
  - name: NER Precision
16
  type: precision
17
+ value: 0.7109375
18
  - name: NER Recall
19
  type: recall
20
+ value: 0.572327044
21
  - name: NER F Score
22
  type: f_score
23
+ value: 0.6341463415
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: 0.9612599714
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: 0.9195153808
59
  - task:
60
  name: LABELED_DEPENDENCIES
61
  type: token-classification
62
  metrics:
63
  - name: Labeled Attachment Score (LAS)
64
  type: f_score
65
+ value: 0.9047554776
66
  - task:
67
  name: SENTS
68
  type: token-classification
69
  metrics:
70
  - name: Sentences F-Score
71
  type: f_score
72
+ value: 0.9832841691
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** | `3.7.0` |
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** | 0 keys, 0 unique vectors (0 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` | 96.13 |
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` | 98.04 |
118
+ | `SENTS_R` | 98.62 |
119
+ | `SENTS_F` | 98.33 |
120
+ | `DEP_UAS` | 91.95 |
121
+ | `DEP_LAS` | 90.48 |
122
  | `TAG_ACC` | 97.13 |
123
+ | `LEMMA_ACC` | 96.70 |
124
+ | `ENTS_P` | 71.09 |
125
+ | `ENTS_R` | 57.23 |
126
+ | `ENTS_F` | 63.41 |
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": 0.9626963351,
7
  "morph_acc": 0.0,
8
  "morph_micro_p": 0.3401360544,
9
  "morph_micro_r": 0.9803921569,
@@ -25,143 +25,153 @@
25
  "f": 0.0
26
  }
27
  },
28
- "sents_p": 0.9940828402,
29
- "sents_r": 0.9940828402,
30
- "sents_f": 0.9940828402,
31
- "dep_uas": 0.9202575532,
32
- "dep_las": 0.9066774658,
33
  "dep_las_per_type": {
34
  "cc": {
35
- "p": 0.8085106383,
36
- "r": 0.7916666667,
37
- "f": 0.8
38
  },
39
  "compound": {
40
- "p": 0.9337979094,
41
- "r": 0.9064261556,
42
- "f": 0.9199084668
43
  },
44
  "obl": {
45
- "p": 0.815889029,
46
- "r": 0.8077403246,
47
- "f": 0.8117942284
48
  },
49
  "case": {
50
- "p": 0.9907798694,
51
- "r": 0.9798632219,
52
- "f": 0.9852913085
53
  },
54
  "dislocated": {
55
- "p": 0.6363636364,
56
- "r": 0.5384615385,
57
- "f": 0.5833333333
58
  },
59
  "nsubj": {
60
- "p": 0.8143133462,
61
- "r": 0.8080614203,
62
- "f": 0.8111753372
63
  },
64
  "nmod": {
65
- "p": 0.875308642,
66
  "r": 0.8292397661,
67
- "f": 0.8516516517
68
  },
69
  "root": {
70
- "p": 0.966,
71
- "r": 0.9526627219,
72
- "f": 0.959285005
73
  },
74
  "aux": {
75
- "p": 0.9787234043,
76
  "r": 0.982358403,
77
- "f": 0.9805375348
78
  },
79
  "advcl": {
80
- "p": 0.7053364269,
81
- "r": 0.6831460674,
82
- "f": 0.6940639269
83
  },
84
  "mark": {
85
- "p": 0.966,
86
- "r": 0.966,
87
- "f": 0.966
88
  },
89
  "fixed": {
90
- "p": 0.9558303887,
91
- "r": 0.9836363636,
92
- "f": 0.9695340502
93
  },
94
  "acl": {
95
- "p": 0.8179824561,
96
  "r": 0.8197802198,
97
- "f": 0.8188803513
98
  },
99
  "obj": {
100
- "p": 0.9512195122,
101
- "r": 0.9425981873,
102
- "f": 0.9468892261
103
  },
104
  "nummod": {
105
- "p": 0.9934210526,
106
- "r": 0.8934911243,
107
- "f": 0.9408099688
108
  },
109
  "advmod": {
110
- "p": 0.6934306569,
111
- "r": 0.6785714286,
112
- "f": 0.6859205776
113
  },
114
  "amod": {
115
- "p": 0.9310344828,
116
  "r": 0.7297297297,
117
- "f": 0.8181818182
118
  },
119
  "cop": {
120
- "p": 0.981595092,
121
- "r": 0.9302325581,
122
- "f": 0.9552238806
123
  },
124
  "ccomp": {
125
- "p": 0.95,
126
  "r": 0.8636363636,
127
- "f": 0.9047619048
128
- },
129
- "csubj": {
130
- "p": 0.4444444444,
131
- "r": 0.6666666667,
132
- "f": 0.5333333333
133
  },
134
  "det": {
135
- "p": 0.9807692308,
136
- "r": 0.9622641509,
137
- "f": 0.9714285714
 
 
 
 
 
138
  },
139
  "dep": {
140
- "p": 0.3333333333,
141
  "r": 0.1428571429,
142
- "f": 0.2
143
  }
144
  },
145
- "tag_acc": 0.9713305562,
146
- "lemma_acc": 0.9670526831,
147
- "ents_p": 0.6797583082,
148
- "ents_r": 0.5660377358,
149
- "ents_f": 0.6177076184,
150
  "ents_per_type": {
151
  "DATE": {
152
- "p": 0.9122807018,
153
  "r": 0.9541284404,
154
- "f": 0.932735426
155
  },
156
  "PERSON": {
157
- "p": 0.5575221239,
158
- "r": 0.4532374101,
159
- "f": 0.5
 
 
 
 
 
160
  },
161
  "GPE": {
162
- "p": 0.6585365854,
163
- "r": 0.5744680851,
164
- "f": 0.6136363636
 
 
 
 
 
165
  },
166
  "TIME": {
167
  "p": 0.6666666667,
@@ -169,63 +179,53 @@
169
  "f": 0.8
170
  },
171
  "QUANTITY": {
172
- "p": 0.8656716418,
173
- "r": 0.8787878788,
174
- "f": 0.8721804511
175
  },
176
  "NORP": {
177
- "p": 0.6551724138,
178
- "r": 0.59375,
179
- "f": 0.6229508197
180
- },
181
- "ORDINAL": {
182
- "p": 0.4615384615,
183
- "r": 0.5454545455,
184
- "f": 0.5
185
- },
186
- "ORG": {
187
- "p": 0.5673076923,
188
- "r": 0.4306569343,
189
- "f": 0.489626556
190
  },
191
  "TITLE_AFFIX": {
192
  "p": 0.7368421053,
193
  "r": 0.4666666667,
194
  "f": 0.5714285714
195
  },
 
 
 
 
 
196
  "WORK_OF_ART": {
197
- "p": 0.7142857143,
198
- "r": 0.5882352941,
199
- "f": 0.6451612903
200
  },
201
- "PERCENT": {
202
- "p": 0.6666666667,
203
- "r": 0.2857142857,
204
- "f": 0.4
205
  },
206
  "FAC": {
207
- "p": 0.5454545455,
208
- "r": 0.3243243243,
209
- "f": 0.406779661
210
  },
211
  "EVENT": {
212
- "p": 0.6666666667,
213
  "r": 0.3846153846,
214
- "f": 0.487804878
215
- },
216
- "CARDINAL": {
217
- "p": 0.0,
218
- "r": 0.0,
219
- "f": 0.0
220
  },
221
- "PRODUCT": {
222
- "p": 0.44,
223
- "r": 0.2619047619,
224
- "f": 0.328358209
225
  },
226
  "LOC": {
227
- "p": 0.75,
228
- "r": 0.6,
229
  "f": 0.6666666667
230
  },
231
  "MOVEMENT": {
@@ -234,9 +234,9 @@
234
  "f": 0.0
235
  },
236
  "LAW": {
237
- "p": 0.0,
238
- "r": 0.0,
239
- "f": 0.0
240
  },
241
  "MONEY": {
242
  "p": 1.0,
@@ -244,10 +244,10 @@
244
  "f": 1.0
245
  },
246
  "LANGUAGE": {
247
- "p": 1.0,
248
- "r": 0.8333333333,
249
- "f": 0.9090909091
250
  }
251
  },
252
- "speed": 10554.2597388988
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": 0.9612599714,
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": 0.9803921569,
29
+ "sents_r": 0.9861932939,
30
+ "sents_f": 0.9832841691,
31
+ "dep_uas": 0.9195153808,
32
+ "dep_las": 0.9047554776,
33
  "dep_las_per_type": {
34
  "cc": {
35
+ "p": 0.7826086957,
36
+ "r": 0.75,
37
+ "f": 0.7659574468
38
  },
39
  "compound": {
40
+ "p": 0.930875576,
41
+ "r": 0.9109357384,
42
+ "f": 0.9207977208
43
  },
44
  "obl": {
45
+ "p": 0.7995049505,
46
+ "r": 0.8064918851,
47
+ "f": 0.8029832194
48
  },
49
  "case": {
50
+ "p": 0.9881180529,
51
+ "r": 0.9794832827,
52
+ "f": 0.983781721
53
  },
54
  "dislocated": {
55
+ "p": 0.6,
56
+ "r": 0.4615384615,
57
+ "f": 0.5217391304
58
  },
59
  "nsubj": {
60
+ "p": 0.7972972973,
61
+ "r": 0.792706334,
62
+ "f": 0.7949951877
63
  },
64
  "nmod": {
65
+ "p": 0.8895859473,
66
  "r": 0.8292397661,
67
+ "f": 0.8583535109
68
  },
69
  "root": {
70
+ "p": 0.9741550696,
71
+ "r": 0.966469428,
72
+ "f": 0.9702970297
73
  },
74
  "aux": {
75
+ "p": 0.977818854,
76
  "r": 0.982358403,
77
+ "f": 0.9800833719
78
  },
79
  "advcl": {
80
+ "p": 0.6787330317,
81
+ "r": 0.6741573034,
82
+ "f": 0.6764374295
83
  },
84
  "mark": {
85
+ "p": 0.9674796748,
86
+ "r": 0.952,
87
+ "f": 0.9596774194
88
  },
89
  "fixed": {
90
+ "p": 0.9569120287,
91
+ "r": 0.9690909091,
92
+ "f": 0.962962963
93
  },
94
  "acl": {
95
+ "p": 0.8515981735,
96
  "r": 0.8197802198,
97
+ "f": 0.8353863382
98
  },
99
  "obj": {
100
+ "p": 0.9509202454,
101
+ "r": 0.9365558912,
102
+ "f": 0.9436834094
103
  },
104
  "nummod": {
105
+ "p": 0.974025974,
106
+ "r": 0.8875739645,
107
+ "f": 0.9287925697
108
  },
109
  "advmod": {
110
+ "p": 0.7,
111
+ "r": 0.65,
112
+ "f": 0.6740740741
113
  },
114
  "amod": {
115
+ "p": 0.8709677419,
116
  "r": 0.7297297297,
117
+ "f": 0.7941176471
118
  },
119
  "cop": {
120
+ "p": 0.9761904762,
121
+ "r": 0.9534883721,
122
+ "f": 0.9647058824
123
  },
124
  "ccomp": {
125
+ "p": 0.9047619048,
126
  "r": 0.8636363636,
127
+ "f": 0.8837209302
 
 
 
 
 
128
  },
129
  "det": {
130
+ "p": 0.9803921569,
131
+ "r": 0.9433962264,
132
+ "f": 0.9615384615
133
+ },
134
+ "csubj": {
135
+ "p": 0.6428571429,
136
+ "r": 0.75,
137
+ "f": 0.6923076923
138
  },
139
  "dep": {
140
+ "p": 0.25,
141
  "r": 0.1428571429,
142
+ "f": 0.1818181818
143
  }
144
  },
145
+ "tag_acc": 0.9713282143,
146
+ "lemma_acc": 0.9670499959,
147
+ "ents_p": 0.7109375,
148
+ "ents_r": 0.572327044,
149
+ "ents_f": 0.6341463415,
150
  "ents_per_type": {
151
  "DATE": {
152
+ "p": 0.962962963,
153
  "r": 0.9541284404,
154
+ "f": 0.9585253456
155
  },
156
  "PERSON": {
157
+ "p": 0.64,
158
+ "r": 0.4604316547,
159
+ "f": 0.5355648536
160
+ },
161
+ "ORG": {
162
+ "p": 0.5555555556,
163
+ "r": 0.4379562044,
164
+ "f": 0.4897959184
165
  },
166
  "GPE": {
167
+ "p": 0.6708860759,
168
+ "r": 0.5638297872,
169
+ "f": 0.612716763
170
+ },
171
+ "PRODUCT": {
172
+ "p": 0.347826087,
173
+ "r": 0.1904761905,
174
+ "f": 0.2461538462
175
  },
176
  "TIME": {
177
  "p": 0.6666666667,
179
  "f": 0.8
180
  },
181
  "QUANTITY": {
182
+ "p": 0.8732394366,
183
+ "r": 0.9393939394,
184
+ "f": 0.9051094891
185
  },
186
  "NORP": {
187
+ "p": 0.75,
188
+ "r": 0.5625,
189
+ "f": 0.6428571429
 
 
 
 
 
 
 
 
 
 
190
  },
191
  "TITLE_AFFIX": {
192
  "p": 0.7368421053,
193
  "r": 0.4666666667,
194
  "f": 0.5714285714
195
  },
196
+ "ORDINAL": {
197
+ "p": 0.5384615385,
198
+ "r": 0.6363636364,
199
+ "f": 0.5833333333
200
+ },
201
  "WORK_OF_ART": {
202
+ "p": 0.75,
203
+ "r": 0.5294117647,
204
+ "f": 0.6206896552
205
  },
206
+ "CARDINAL": {
207
+ "p": 1.0,
208
+ "r": 0.5,
209
+ "f": 0.6666666667
210
  },
211
  "FAC": {
212
+ "p": 0.6111111111,
213
+ "r": 0.2972972973,
214
+ "f": 0.4
215
  },
216
  "EVENT": {
217
+ "p": 0.7142857143,
218
  "r": 0.3846153846,
219
+ "f": 0.5
 
 
 
 
 
220
  },
221
+ "PERCENT": {
222
+ "p": 1.0,
223
+ "r": 0.2857142857,
224
+ "f": 0.4444444444
225
  },
226
  "LOC": {
227
+ "p": 0.6363636364,
228
+ "r": 0.7,
229
  "f": 0.6666666667
230
  },
231
  "MOVEMENT": {
234
  "f": 0.0
235
  },
236
  "LAW": {
237
+ "p": 1.0,
238
+ "r": 0.3333333333,
239
+ "f": 0.5
240
  },
241
  "MONEY": {
242
  "p": 1.0,
244
  "f": 1.0
245
  },
246
  "LANGUAGE": {
247
+ "p": 0.6666666667,
248
+ "r": 1.0,
249
+ "f": 0.8
250
  }
251
  },
252
+ "speed": 8098.5108221259
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_sm-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:52bcd3df687c9ae1b55806b4d9e49b517d419d0633951a2d8806c8fa2eef498a
3
- size 12098567
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1191e5bbffcc90670146616c274a64850e54d12070bc5846e78a094f2f6fcfca
3
+ size 12090035
meta.json CHANGED
@@ -1,14 +1,14 @@
1
  {
2
  "lang":"ja",
3
  "name":"core_news_sm",
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":0,
14
  "vectors":0,
@@ -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":0.9626963351,
121
  "morph_acc":0.0,
122
  "morph_micro_p":0.3401360544,
123
  "morph_micro_r":0.9803921569,
@@ -139,143 +139,153 @@
139
  "f":0.0
140
  }
141
  },
142
- "sents_p":0.9940828402,
143
- "sents_r":0.9940828402,
144
- "sents_f":0.9940828402,
145
- "dep_uas":0.9202575532,
146
- "dep_las":0.9066774658,
147
  "dep_las_per_type":{
148
  "cc":{
149
- "p":0.8085106383,
150
- "r":0.7916666667,
151
- "f":0.8
152
  },
153
  "compound":{
154
- "p":0.9337979094,
155
- "r":0.9064261556,
156
- "f":0.9199084668
157
  },
158
  "obl":{
159
- "p":0.815889029,
160
- "r":0.8077403246,
161
- "f":0.8117942284
162
  },
163
  "case":{
164
- "p":0.9907798694,
165
- "r":0.9798632219,
166
- "f":0.9852913085
167
  },
168
  "dislocated":{
169
- "p":0.6363636364,
170
- "r":0.5384615385,
171
- "f":0.5833333333
172
  },
173
  "nsubj":{
174
- "p":0.8143133462,
175
- "r":0.8080614203,
176
- "f":0.8111753372
177
  },
178
  "nmod":{
179
- "p":0.875308642,
180
  "r":0.8292397661,
181
- "f":0.8516516517
182
  },
183
  "root":{
184
- "p":0.966,
185
- "r":0.9526627219,
186
- "f":0.959285005
187
  },
188
  "aux":{
189
- "p":0.9787234043,
190
  "r":0.982358403,
191
- "f":0.9805375348
192
  },
193
  "advcl":{
194
- "p":0.7053364269,
195
- "r":0.6831460674,
196
- "f":0.6940639269
197
  },
198
  "mark":{
199
- "p":0.966,
200
- "r":0.966,
201
- "f":0.966
202
  },
203
  "fixed":{
204
- "p":0.9558303887,
205
- "r":0.9836363636,
206
- "f":0.9695340502
207
  },
208
  "acl":{
209
- "p":0.8179824561,
210
  "r":0.8197802198,
211
- "f":0.8188803513
212
  },
213
  "obj":{
214
- "p":0.9512195122,
215
- "r":0.9425981873,
216
- "f":0.9468892261
217
  },
218
  "nummod":{
219
- "p":0.9934210526,
220
- "r":0.8934911243,
221
- "f":0.9408099688
222
  },
223
  "advmod":{
224
- "p":0.6934306569,
225
- "r":0.6785714286,
226
- "f":0.6859205776
227
  },
228
  "amod":{
229
- "p":0.9310344828,
230
  "r":0.7297297297,
231
- "f":0.8181818182
232
  },
233
  "cop":{
234
- "p":0.981595092,
235
- "r":0.9302325581,
236
- "f":0.9552238806
237
  },
238
  "ccomp":{
239
- "p":0.95,
240
  "r":0.8636363636,
241
- "f":0.9047619048
242
- },
243
- "csubj":{
244
- "p":0.4444444444,
245
- "r":0.6666666667,
246
- "f":0.5333333333
247
  },
248
  "det":{
249
- "p":0.9807692308,
250
- "r":0.9622641509,
251
- "f":0.9714285714
 
 
 
 
 
252
  },
253
  "dep":{
254
- "p":0.3333333333,
255
  "r":0.1428571429,
256
- "f":0.2
257
  }
258
  },
259
- "tag_acc":0.9713305562,
260
- "lemma_acc":0.9670526831,
261
- "ents_p":0.6797583082,
262
- "ents_r":0.5660377358,
263
- "ents_f":0.6177076184,
264
  "ents_per_type":{
265
  "DATE":{
266
- "p":0.9122807018,
267
  "r":0.9541284404,
268
- "f":0.932735426
269
  },
270
  "PERSON":{
271
- "p":0.5575221239,
272
- "r":0.4532374101,
273
- "f":0.5
 
 
 
 
 
274
  },
275
  "GPE":{
276
- "p":0.6585365854,
277
- "r":0.5744680851,
278
- "f":0.6136363636
 
 
 
 
 
279
  },
280
  "TIME":{
281
  "p":0.6666666667,
@@ -283,63 +293,53 @@
283
  "f":0.8
284
  },
285
  "QUANTITY":{
286
- "p":0.8656716418,
287
- "r":0.8787878788,
288
- "f":0.8721804511
289
  },
290
  "NORP":{
291
- "p":0.6551724138,
292
- "r":0.59375,
293
- "f":0.6229508197
294
- },
295
- "ORDINAL":{
296
- "p":0.4615384615,
297
- "r":0.5454545455,
298
- "f":0.5
299
- },
300
- "ORG":{
301
- "p":0.5673076923,
302
- "r":0.4306569343,
303
- "f":0.489626556
304
  },
305
  "TITLE_AFFIX":{
306
  "p":0.7368421053,
307
  "r":0.4666666667,
308
  "f":0.5714285714
309
  },
 
 
 
 
 
310
  "WORK_OF_ART":{
311
- "p":0.7142857143,
312
- "r":0.5882352941,
313
- "f":0.6451612903
314
  },
315
- "PERCENT":{
316
- "p":0.6666666667,
317
- "r":0.2857142857,
318
- "f":0.4
319
  },
320
  "FAC":{
321
- "p":0.5454545455,
322
- "r":0.3243243243,
323
- "f":0.406779661
324
  },
325
  "EVENT":{
326
- "p":0.6666666667,
327
  "r":0.3846153846,
328
- "f":0.487804878
329
- },
330
- "CARDINAL":{
331
- "p":0.0,
332
- "r":0.0,
333
- "f":0.0
334
  },
335
- "PRODUCT":{
336
- "p":0.44,
337
- "r":0.2619047619,
338
- "f":0.328358209
339
  },
340
  "LOC":{
341
- "p":0.75,
342
- "r":0.6,
343
  "f":0.6666666667
344
  },
345
  "MOVEMENT":{
@@ -348,9 +348,9 @@
348
  "f":0.0
349
  },
350
  "LAW":{
351
- "p":0.0,
352
- "r":0.0,
353
- "f":0.0
354
  },
355
  "MONEY":{
356
  "p":1.0,
@@ -358,12 +358,12 @@
358
  "f":1.0
359
  },
360
  "LANGUAGE":{
361
- "p":1.0,
362
- "r":0.8333333333,
363
- "f":0.9090909091
364
  }
365
  },
366
- "speed":10554.2597388988
367
  },
368
  "sources":[
369
  {
1
  {
2
  "lang":"ja",
3
  "name":"core_news_sm",
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":0,
14
  "vectors":0,
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":0.9612599714,
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":0.9803921569,
143
+ "sents_r":0.9861932939,
144
+ "sents_f":0.9832841691,
145
+ "dep_uas":0.9195153808,
146
+ "dep_las":0.9047554776,
147
  "dep_las_per_type":{
148
  "cc":{
149
+ "p":0.7826086957,
150
+ "r":0.75,
151
+ "f":0.7659574468
152
  },
153
  "compound":{
154
+ "p":0.930875576,
155
+ "r":0.9109357384,
156
+ "f":0.9207977208
157
  },
158
  "obl":{
159
+ "p":0.7995049505,
160
+ "r":0.8064918851,
161
+ "f":0.8029832194
162
  },
163
  "case":{
164
+ "p":0.9881180529,
165
+ "r":0.9794832827,
166
+ "f":0.983781721
167
  },
168
  "dislocated":{
169
+ "p":0.6,
170
+ "r":0.4615384615,
171
+ "f":0.5217391304
172
  },
173
  "nsubj":{
174
+ "p":0.7972972973,
175
+ "r":0.792706334,
176
+ "f":0.7949951877
177
  },
178
  "nmod":{
179
+ "p":0.8895859473,
180
  "r":0.8292397661,
181
+ "f":0.8583535109
182
  },
183
  "root":{
184
+ "p":0.9741550696,
185
+ "r":0.966469428,
186
+ "f":0.9702970297
187
  },
188
  "aux":{
189
+ "p":0.977818854,
190
  "r":0.982358403,
191
+ "f":0.9800833719
192
  },
193
  "advcl":{
194
+ "p":0.6787330317,
195
+ "r":0.6741573034,
196
+ "f":0.6764374295
197
  },
198
  "mark":{
199
+ "p":0.9674796748,
200
+ "r":0.952,
201
+ "f":0.9596774194
202
  },
203
  "fixed":{
204
+ "p":0.9569120287,
205
+ "r":0.9690909091,
206
+ "f":0.962962963
207
  },
208
  "acl":{
209
+ "p":0.8515981735,
210
  "r":0.8197802198,
211
+ "f":0.8353863382
212
  },
213
  "obj":{
214
+ "p":0.9509202454,
215
+ "r":0.9365558912,
216
+ "f":0.9436834094
217
  },
218
  "nummod":{
219
+ "p":0.974025974,
220
+ "r":0.8875739645,
221
+ "f":0.9287925697
222
  },
223
  "advmod":{
224
+ "p":0.7,
225
+ "r":0.65,
226
+ "f":0.6740740741
227
  },
228
  "amod":{
229
+ "p":0.8709677419,
230
  "r":0.7297297297,
231
+ "f":0.7941176471
232
  },
233
  "cop":{
234
+ "p":0.9761904762,
235
+ "r":0.9534883721,
236
+ "f":0.9647058824
237
  },
238
  "ccomp":{
239
+ "p":0.9047619048,
240
  "r":0.8636363636,
241
+ "f":0.8837209302
 
 
 
 
 
242
  },
243
  "det":{
244
+ "p":0.9803921569,
245
+ "r":0.9433962264,
246
+ "f":0.9615384615
247
+ },
248
+ "csubj":{
249
+ "p":0.6428571429,
250
+ "r":0.75,
251
+ "f":0.6923076923
252
  },
253
  "dep":{
254
+ "p":0.25,
255
  "r":0.1428571429,
256
+ "f":0.1818181818
257
  }
258
  },
259
+ "tag_acc":0.9713282143,
260
+ "lemma_acc":0.9670499959,
261
+ "ents_p":0.7109375,
262
+ "ents_r":0.572327044,
263
+ "ents_f":0.6341463415,
264
  "ents_per_type":{
265
  "DATE":{
266
+ "p":0.962962963,
267
  "r":0.9541284404,
268
+ "f":0.9585253456
269
  },
270
  "PERSON":{
271
+ "p":0.64,
272
+ "r":0.4604316547,
273
+ "f":0.5355648536
274
+ },
275
+ "ORG":{
276
+ "p":0.5555555556,
277
+ "r":0.4379562044,
278
+ "f":0.4897959184
279
  },
280
  "GPE":{
281
+ "p":0.6708860759,
282
+ "r":0.5638297872,
283
+ "f":0.612716763
284
+ },
285
+ "PRODUCT":{
286
+ "p":0.347826087,
287
+ "r":0.1904761905,
288
+ "f":0.2461538462
289
  },
290
  "TIME":{
291
  "p":0.6666666667,
293
  "f":0.8
294
  },
295
  "QUANTITY":{
296
+ "p":0.8732394366,
297
+ "r":0.9393939394,
298
+ "f":0.9051094891
299
  },
300
  "NORP":{
301
+ "p":0.75,
302
+ "r":0.5625,
303
+ "f":0.6428571429
 
 
 
 
 
 
 
 
 
 
304
  },
305
  "TITLE_AFFIX":{
306
  "p":0.7368421053,
307
  "r":0.4666666667,
308
  "f":0.5714285714
309
  },
310
+ "ORDINAL":{
311
+ "p":0.5384615385,
312
+ "r":0.6363636364,
313
+ "f":0.5833333333
314
+ },
315
  "WORK_OF_ART":{
316
+ "p":0.75,
317
+ "r":0.5294117647,
318
+ "f":0.6206896552
319
  },
320
+ "CARDINAL":{
321
+ "p":1.0,
322
+ "r":0.5,
323
+ "f":0.6666666667
324
  },
325
  "FAC":{
326
+ "p":0.6111111111,
327
+ "r":0.2972972973,
328
+ "f":0.4
329
  },
330
  "EVENT":{
331
+ "p":0.7142857143,
332
  "r":0.3846153846,
333
+ "f":0.5
 
 
 
 
 
334
  },
335
+ "PERCENT":{
336
+ "p":1.0,
337
+ "r":0.2857142857,
338
+ "f":0.4444444444
339
  },
340
  "LOC":{
341
+ "p":0.6363636364,
342
+ "r":0.7,
343
  "f":0.6666666667
344
  },
345
  "MOVEMENT":{
348
  "f":0.0
349
  },
350
  "LAW":{
351
+ "p":1.0,
352
+ "r":0.3333333333,
353
+ "f":0.5
354
  },
355
  "MONEY":{
356
  "p":1.0,
358
  "f":1.0
359
  },
360
  "LANGUAGE":{
361
+ "p":0.6666666667,
362
+ "r":1.0,
363
+ "f":0.8
364
  }
365
  },
366
+ "speed":8098.5108221259
367
  },
368
  "sources":[
369
  {
morphologizer/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e3dd42bafae9803c621ce3d9e986a436d1ff355a0307552e55271f921a8a8499
3
  size 8189
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d72c6474d3c39461c1d3e71991200b22d7a42973027325219a107766e451d45
3
  size 8189
ner/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f39f29b809c3daed4256be85e5872cf8f0140428074a99f2b952138c90be7d1c
3
  size 6158761
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:604b5d433ba74dc6d522953599d994a82c028a711809910948a150579a381d93
3
  size 6158761
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d42b9d066cb43785d218323845dab36f3114ed98582e09ff38af7b8c9e887a59
3
  size 299888
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:526aefd8be7f01b2414496df350b7ddde6acc0bfb5ee39866564974d34791ee9
3
  size 299888
senter/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ee45326f8244d4750fce99aa0bd53d8ee8e959306b71dae9b52aad7f2e734a56
3
  size 190447
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f57b76e9c332a0a603de35d3c12bd2141215de429862362e215a72a8923995f4
3
  size 190447
tok2vec/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a66493ac27d3d1832f6e061a43e125e5a9b0f65002a85eb1d0e80a4e49ea5452
3
  size 6139232
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89bd45e8a722c0e09ed01bd1f102d911ea49c238c8a187e9895a7a3e665b7880
3
  size 6139232
vocab/strings.json CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:458ad010a464041121257cc23794c876c9f6d086aafca3926b9fffeb5167ccc8
3
- size 1601026
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a025a3985441f6c357751fe02ef00fc3a0bff0ecf3b6c1f3935bc7a150323a9c
3
+ size 1601239