Commit
·
fafa09c
1
Parent(s):
7538d68
Update spaCy pipeline
Browse files- README.md +24 -24
- accuracy.json +132 -127
- config.cfg +1 -0
- ja_core_news_lg-any-py3-none-any.whl +2 -2
- meta.json +135 -130
- morphologizer/model +1 -1
- ner/model +1 -1
- parser/model +1 -1
- senter/model +1 -1
- tok2vec/model +1 -1
- vocab/strings.json +2 -2
README.md
CHANGED
@@ -14,27 +14,27 @@ model-index:
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
-
value: 0.
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
-
value: 0.
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
-
value: 0.
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
-
value: 0.
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
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.
|
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.
|
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.
|
66 |
- task:
|
67 |
name: SENTS
|
68 |
type: token-classification
|
69 |
metrics:
|
70 |
- name: Sentences F-Score
|
71 |
type: f_score
|
72 |
-
value: 0.
|
73 |
---
|
74 |
### Details: https://spacy.io/models/ja#ja_core_news_lg
|
75 |
|
@@ -78,8 +78,8 @@ Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
|
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `ja_core_news_lg` |
|
81 |
-
| **Version** | `3.
|
82 |
-
| **spaCy** | `>=3.
|
83 |
| **Default Pipeline** | `tok2vec`, `morphologizer`, `parser`, `attribute_ruler`, `ner` |
|
84 |
| **Components** | `tok2vec`, `morphologizer`, `parser`, `senter`, `attribute_ruler`, `ner` |
|
85 |
| **Vectors** | 480443 keys, 480443 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.
|
110 |
-
| `TOKEN_R` | 97.
|
111 |
-
| `TOKEN_F` | 97.
|
112 |
-
| `POS_ACC` | 97.
|
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` |
|
118 |
-
| `SENTS_R` |
|
119 |
-
| `SENTS_F` |
|
120 |
-
| `DEP_UAS` | 92.
|
121 |
-
| `DEP_LAS` | 90.
|
122 |
| `TAG_ACC` | 97.13 |
|
123 |
-
| `LEMMA_ACC` | 96.
|
124 |
-
| `ENTS_P` |
|
125 |
-
| `ENTS_R` |
|
126 |
-
| `ENTS_F` |
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.7388362652
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.6867924528
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.7118644068
|
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: 0.9742268041
|
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: 0.9212481426
|
59 |
- task:
|
60 |
name: LABELED_DEPENDENCIES
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Labeled Attachment Score (LAS)
|
64 |
type: f_score
|
65 |
+
value: 0.9089518668
|
66 |
- task:
|
67 |
name: SENTS
|
68 |
type: token-classification
|
69 |
metrics:
|
70 |
- name: Sentences F-Score
|
71 |
type: f_score
|
72 |
+
value: 0.9658536585
|
73 |
---
|
74 |
### Details: https://spacy.io/models/ja#ja_core_news_lg
|
75 |
|
|
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `ja_core_news_lg` |
|
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, 480443 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` | 97.42 |
|
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` | 95.56 |
|
118 |
+
| `SENTS_R` | 97.63 |
|
119 |
+
| `SENTS_F` | 96.59 |
|
120 |
+
| `DEP_UAS` | 92.12 |
|
121 |
+
| `DEP_LAS` | 90.90 |
|
122 |
| `TAG_ACC` | 97.13 |
|
123 |
+
| `LEMMA_ACC` | 96.70 |
|
124 |
+
| `ENTS_P` | 73.88 |
|
125 |
+
| `ENTS_R` | 68.68 |
|
126 |
+
| `ENTS_F` | 71.19 |
|
accuracy.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"token_acc": 0.
|
3 |
-
"token_p": 0.
|
4 |
-
"token_r": 0.
|
5 |
-
"token_f": 0.
|
6 |
-
"pos_acc": 0.
|
7 |
"morph_acc": 0.0,
|
8 |
"morph_micro_p": 0.3401360544,
|
9 |
"morph_micro_r": 0.9803921569,
|
@@ -25,101 +25,101 @@
|
|
25 |
"f": 0.0
|
26 |
}
|
27 |
},
|
28 |
-
"sents_p": 0.
|
29 |
-
"sents_r": 0.
|
30 |
-
"sents_f": 0.
|
31 |
-
"dep_uas": 0.
|
32 |
-
"dep_las": 0.
|
33 |
"dep_las_per_type": {
|
34 |
"cc": {
|
35 |
-
"p": 0.
|
36 |
-
"r": 0.
|
37 |
-
"f": 0.
|
38 |
},
|
39 |
"compound": {
|
40 |
-
"p": 0.
|
41 |
-
"r": 0.
|
42 |
-
"f": 0.
|
43 |
},
|
44 |
"obl": {
|
45 |
-
"p": 0.
|
46 |
-
"r": 0.
|
47 |
-
"f": 0.
|
48 |
},
|
49 |
"case": {
|
50 |
-
"p": 0.
|
51 |
"r": 0.9802431611,
|
52 |
-
"f": 0.
|
53 |
},
|
54 |
"dislocated": {
|
55 |
-
"p": 0.
|
56 |
-
"r": 0.
|
57 |
-
"f": 0.
|
58 |
},
|
59 |
"nsubj": {
|
60 |
-
"p": 0.
|
61 |
-
"r": 0.
|
62 |
-
"f": 0.
|
63 |
},
|
64 |
"nmod": {
|
65 |
-
"p": 0.
|
66 |
-
"r": 0.
|
67 |
-
"f": 0.
|
68 |
},
|
69 |
"root": {
|
70 |
-
"p": 0.
|
71 |
-
"r": 0.
|
72 |
-
"f": 0.
|
73 |
},
|
74 |
"aux": {
|
75 |
-
"p": 0.
|
76 |
-
"r": 0.
|
77 |
-
"f": 0.
|
78 |
},
|
79 |
"advcl": {
|
80 |
-
"p": 0.
|
81 |
-
"r": 0.
|
82 |
-
"f": 0.
|
83 |
},
|
84 |
"mark": {
|
85 |
-
"p": 0.
|
86 |
-
"r": 0.
|
87 |
-
"f": 0.
|
88 |
},
|
89 |
"fixed": {
|
90 |
-
"p": 0.
|
91 |
-
"r": 0.
|
92 |
-
"f": 0.
|
93 |
},
|
94 |
"acl": {
|
95 |
-
"p": 0.
|
96 |
-
"r": 0.
|
97 |
-
"f": 0.
|
98 |
},
|
99 |
"obj": {
|
100 |
-
"p": 0.
|
101 |
-
"r": 0.
|
102 |
-
"f": 0.
|
103 |
},
|
104 |
"nummod": {
|
105 |
-
"p": 0.
|
106 |
"r": 0.8934911243,
|
107 |
-
"f": 0.
|
108 |
},
|
109 |
"advmod": {
|
110 |
-
"p": 0.
|
111 |
-
"r": 0.
|
112 |
-
"f": 0.
|
113 |
},
|
114 |
"amod": {
|
115 |
-
"p": 0.
|
116 |
-
"r": 0.
|
117 |
-
"f": 0.
|
118 |
},
|
119 |
"cop": {
|
120 |
-
"p": 0.
|
121 |
-
"r": 0.
|
122 |
-
"f": 0.
|
123 |
},
|
124 |
"ccomp": {
|
125 |
"p": 0.95,
|
@@ -127,46 +127,51 @@
|
|
127 |
"f": 0.9047619048
|
128 |
},
|
129 |
"det": {
|
130 |
-
"p": 0
|
131 |
-
"r": 0.
|
132 |
-
"f": 0.
|
133 |
},
|
134 |
"csubj": {
|
135 |
-
"p": 0.
|
136 |
-
"r": 0.
|
137 |
-
"f": 0.
|
138 |
},
|
139 |
"dep": {
|
140 |
-
"p": 0.
|
141 |
"r": 0.1428571429,
|
142 |
-
"f": 0.
|
143 |
}
|
144 |
},
|
145 |
-
"tag_acc": 0.
|
146 |
-
"lemma_acc": 0.
|
147 |
-
"ents_p": 0.
|
148 |
-
"ents_r": 0.
|
149 |
-
"ents_f": 0.
|
150 |
"ents_per_type": {
|
151 |
"DATE": {
|
152 |
-
"p": 0.
|
153 |
-
"r": 0.
|
154 |
-
"f": 0.
|
155 |
},
|
156 |
"ORG": {
|
157 |
-
"p": 0.
|
158 |
-
"r": 0.
|
159 |
-
"f": 0.
|
160 |
},
|
161 |
"PERSON": {
|
162 |
-
"p": 0.
|
163 |
-
"r": 0.
|
164 |
-
"f": 0.
|
165 |
},
|
166 |
"GPE": {
|
167 |
-
"p": 0.
|
168 |
-
"r": 0.
|
169 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
170 |
},
|
171 |
"TIME": {
|
172 |
"p": 0.5714285714,
|
@@ -174,69 +179,69 @@
|
|
174 |
"f": 0.7272727273
|
175 |
},
|
176 |
"QUANTITY": {
|
177 |
-
"p": 0.
|
178 |
-
"r": 0.
|
179 |
-
"f": 0.
|
180 |
},
|
181 |
"NORP": {
|
182 |
-
"p": 0.
|
183 |
-
"r": 0.
|
184 |
-
"f": 0.
|
185 |
},
|
186 |
"TITLE_AFFIX": {
|
187 |
-
"p": 0.
|
188 |
-
"r": 0.
|
189 |
-
"f": 0.
|
190 |
},
|
191 |
"ORDINAL": {
|
192 |
-
"p": 0.
|
193 |
-
"r": 0.
|
194 |
-
"f": 0.
|
195 |
},
|
196 |
"WORK_OF_ART": {
|
197 |
-
"p": 0.
|
198 |
"r": 0.6470588235,
|
199 |
-
"f": 0.
|
200 |
},
|
201 |
-
"
|
202 |
-
"p":
|
203 |
-
"r": 0.
|
204 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
205 |
},
|
206 |
"PERCENT": {
|
207 |
-
"p": 0
|
208 |
"r": 0.2857142857,
|
209 |
-
"f": 0.
|
210 |
},
|
211 |
-
"
|
212 |
-
"p": 0.
|
213 |
-
"r": 0.
|
214 |
-
"f": 0.
|
215 |
},
|
216 |
"LOC": {
|
217 |
-
"p": 0.
|
218 |
"r": 0.8,
|
219 |
-
"f": 0.
|
220 |
-
},
|
221 |
-
"FAC": {
|
222 |
-
"p": 0.5862068966,
|
223 |
-
"r": 0.4594594595,
|
224 |
-
"f": 0.5151515152
|
225 |
},
|
226 |
-
"
|
227 |
"p": 0.0,
|
228 |
"r": 0.0,
|
229 |
"f": 0.0
|
230 |
},
|
231 |
-
"
|
232 |
-
"p": 0.
|
233 |
-
"r": 0.
|
234 |
-
"f": 0.
|
235 |
},
|
236 |
"LAW": {
|
237 |
-
"p":
|
238 |
-
"r": 0.
|
239 |
-
"f": 0.
|
240 |
},
|
241 |
"MONEY": {
|
242 |
"p": 1.0,
|
@@ -249,5 +254,5 @@
|
|
249 |
"f": 1.0
|
250 |
}
|
251 |
},
|
252 |
-
"speed":
|
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": 0.9742268041,
|
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": 0.9555984556,
|
29 |
+
"sents_r": 0.9763313609,
|
30 |
+
"sents_f": 0.9658536585,
|
31 |
+
"dep_uas": 0.9212481426,
|
32 |
+
"dep_las": 0.9089518668,
|
33 |
"dep_las_per_type": {
|
34 |
"cc": {
|
35 |
+
"p": 0.7777777778,
|
36 |
+
"r": 0.7291666667,
|
37 |
+
"f": 0.752688172
|
38 |
},
|
39 |
"compound": {
|
40 |
+
"p": 0.942206655,
|
41 |
+
"r": 0.9098083427,
|
42 |
+
"f": 0.9257241182
|
43 |
},
|
44 |
"obl": {
|
45 |
+
"p": 0.840357599,
|
46 |
+
"r": 0.8214731586,
|
47 |
+
"f": 0.8308080808
|
48 |
},
|
49 |
"case": {
|
50 |
+
"p": 0.9892638037,
|
51 |
"r": 0.9802431611,
|
52 |
+
"f": 0.9847328244
|
53 |
},
|
54 |
"dislocated": {
|
55 |
+
"p": 0.5384615385,
|
56 |
+
"r": 0.5384615385,
|
57 |
+
"f": 0.5384615385
|
58 |
},
|
59 |
"nsubj": {
|
60 |
+
"p": 0.8027079304,
|
61 |
+
"r": 0.7965451056,
|
62 |
+
"f": 0.7996146435
|
63 |
},
|
64 |
"nmod": {
|
65 |
+
"p": 0.8683886839,
|
66 |
+
"r": 0.8257309942,
|
67 |
+
"f": 0.8465227818
|
68 |
},
|
69 |
"root": {
|
70 |
+
"p": 0.9607843137,
|
71 |
+
"r": 0.966469428,
|
72 |
+
"f": 0.9636184857
|
73 |
},
|
74 |
"aux": {
|
75 |
+
"p": 0.9814986124,
|
76 |
+
"r": 0.9851439183,
|
77 |
+
"f": 0.9833178869
|
78 |
},
|
79 |
"advcl": {
|
80 |
+
"p": 0.698630137,
|
81 |
+
"r": 0.6876404494,
|
82 |
+
"f": 0.6930917327
|
83 |
},
|
84 |
"mark": {
|
85 |
+
"p": 0.9776876268,
|
86 |
+
"r": 0.964,
|
87 |
+
"f": 0.970795569
|
88 |
},
|
89 |
"fixed": {
|
90 |
+
"p": 0.9501779359,
|
91 |
+
"r": 0.9709090909,
|
92 |
+
"f": 0.9604316547
|
93 |
},
|
94 |
"acl": {
|
95 |
+
"p": 0.825708061,
|
96 |
+
"r": 0.832967033,
|
97 |
+
"f": 0.829321663
|
98 |
},
|
99 |
"obj": {
|
100 |
+
"p": 0.9571865443,
|
101 |
+
"r": 0.9456193353,
|
102 |
+
"f": 0.9513677812
|
103 |
},
|
104 |
"nummod": {
|
105 |
+
"p": 0.9934210526,
|
106 |
"r": 0.8934911243,
|
107 |
+
"f": 0.9408099688
|
108 |
},
|
109 |
"advmod": {
|
110 |
+
"p": 0.7050359712,
|
111 |
+
"r": 0.7,
|
112 |
+
"f": 0.7025089606
|
113 |
},
|
114 |
"amod": {
|
115 |
+
"p": 0.935483871,
|
116 |
+
"r": 0.7837837838,
|
117 |
+
"f": 0.8529411765
|
118 |
},
|
119 |
"cop": {
|
120 |
+
"p": 0.9761904762,
|
121 |
+
"r": 0.9534883721,
|
122 |
+
"f": 0.9647058824
|
123 |
},
|
124 |
"ccomp": {
|
125 |
"p": 0.95,
|
|
|
127 |
"f": 0.9047619048
|
128 |
},
|
129 |
"det": {
|
130 |
+
"p": 1.0,
|
131 |
+
"r": 0.9433962264,
|
132 |
+
"f": 0.9708737864
|
133 |
},
|
134 |
"csubj": {
|
135 |
+
"p": 0.7333333333,
|
136 |
+
"r": 0.9166666667,
|
137 |
+
"f": 0.8148148148
|
138 |
},
|
139 |
"dep": {
|
140 |
+
"p": 0.3333333333,
|
141 |
"r": 0.1428571429,
|
142 |
+
"f": 0.2
|
143 |
}
|
144 |
},
|
145 |
+
"tag_acc": 0.9713282143,
|
146 |
+
"lemma_acc": 0.9670499959,
|
147 |
+
"ents_p": 0.7388362652,
|
148 |
+
"ents_r": 0.6867924528,
|
149 |
+
"ents_f": 0.7118644068,
|
150 |
"ents_per_type": {
|
151 |
"DATE": {
|
152 |
+
"p": 0.9626168224,
|
153 |
+
"r": 0.9449541284,
|
154 |
+
"f": 0.9537037037
|
155 |
},
|
156 |
"ORG": {
|
157 |
+
"p": 0.6090225564,
|
158 |
+
"r": 0.5912408759,
|
159 |
+
"f": 0.6
|
160 |
},
|
161 |
"PERSON": {
|
162 |
+
"p": 0.7883211679,
|
163 |
+
"r": 0.7769784173,
|
164 |
+
"f": 0.7826086957
|
165 |
},
|
166 |
"GPE": {
|
167 |
+
"p": 0.6666666667,
|
168 |
+
"r": 0.6595744681,
|
169 |
+
"f": 0.6631016043
|
170 |
+
},
|
171 |
+
"PRODUCT": {
|
172 |
+
"p": 0.5769230769,
|
173 |
+
"r": 0.3571428571,
|
174 |
+
"f": 0.4411764706
|
175 |
},
|
176 |
"TIME": {
|
177 |
"p": 0.5714285714,
|
|
|
179 |
"f": 0.7272727273
|
180 |
},
|
181 |
"QUANTITY": {
|
182 |
+
"p": 0.8823529412,
|
183 |
+
"r": 0.9090909091,
|
184 |
+
"f": 0.8955223881
|
185 |
},
|
186 |
"NORP": {
|
187 |
+
"p": 0.6206896552,
|
188 |
+
"r": 0.5625,
|
189 |
+
"f": 0.5901639344
|
190 |
},
|
191 |
"TITLE_AFFIX": {
|
192 |
+
"p": 0.7727272727,
|
193 |
+
"r": 0.5666666667,
|
194 |
+
"f": 0.6538461538
|
195 |
},
|
196 |
"ORDINAL": {
|
197 |
+
"p": 0.56,
|
198 |
+
"r": 0.6363636364,
|
199 |
+
"f": 0.5957446809
|
200 |
},
|
201 |
"WORK_OF_ART": {
|
202 |
+
"p": 0.8461538462,
|
203 |
"r": 0.6470588235,
|
204 |
+
"f": 0.7333333333
|
205 |
},
|
206 |
+
"FAC": {
|
207 |
+
"p": 0.64,
|
208 |
+
"r": 0.4324324324,
|
209 |
+
"f": 0.5161290323
|
210 |
+
},
|
211 |
+
"EVENT": {
|
212 |
+
"p": 0.6315789474,
|
213 |
+
"r": 0.4615384615,
|
214 |
+
"f": 0.5333333333
|
215 |
},
|
216 |
"PERCENT": {
|
217 |
+
"p": 1.0,
|
218 |
"r": 0.2857142857,
|
219 |
+
"f": 0.4444444444
|
220 |
},
|
221 |
+
"CARDINAL": {
|
222 |
+
"p": 0.0,
|
223 |
+
"r": 0.0,
|
224 |
+
"f": 0.0
|
225 |
},
|
226 |
"LOC": {
|
227 |
+
"p": 0.6666666667,
|
228 |
"r": 0.8,
|
229 |
+
"f": 0.7272727273
|
|
|
|
|
|
|
|
|
|
|
230 |
},
|
231 |
+
"PET_NAME": {
|
232 |
"p": 0.0,
|
233 |
"r": 0.0,
|
234 |
"f": 0.0
|
235 |
},
|
236 |
+
"MOVEMENT": {
|
237 |
+
"p": 0.2,
|
238 |
+
"r": 0.2,
|
239 |
+
"f": 0.2
|
240 |
},
|
241 |
"LAW": {
|
242 |
+
"p": 1.0,
|
243 |
+
"r": 0.3333333333,
|
244 |
+
"f": 0.5
|
245 |
},
|
246 |
"MONEY": {
|
247 |
"p": 1.0,
|
|
|
254 |
"f": 1.0
|
255 |
}
|
256 |
},
|
257 |
+
"speed": 8472.2177519611
|
258 |
}
|
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_lg-any-py3-none-any.whl
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f08eecb4d40523045c9478ce59a67564fd71edd215f32c076fa91dc1f05cc7fd
|
3 |
+
size 555247573
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"ja",
|
3 |
"name":"core_news_lg",
|
4 |
-
"version":"3.
|
5 |
"description":"Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser, senter, ner, attribute_ruler.",
|
6 |
"author":"Explosion",
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"CC BY-SA 4.0",
|
10 |
-
"spacy_version":">=3.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":480443,
|
@@ -113,11 +113,11 @@
|
|
113 |
"senter"
|
114 |
],
|
115 |
"performance":{
|
116 |
-
"token_acc":0.
|
117 |
-
"token_p":0.
|
118 |
-
"token_r":0.
|
119 |
-
"token_f":0.
|
120 |
-
"pos_acc":0.
|
121 |
"morph_acc":0.0,
|
122 |
"morph_micro_p":0.3401360544,
|
123 |
"morph_micro_r":0.9803921569,
|
@@ -139,101 +139,101 @@
|
|
139 |
"f":0.0
|
140 |
}
|
141 |
},
|
142 |
-
"sents_p":0.
|
143 |
-
"sents_r":0.
|
144 |
-
"sents_f":0.
|
145 |
-
"dep_uas":0.
|
146 |
-
"dep_las":0.
|
147 |
"dep_las_per_type":{
|
148 |
"cc":{
|
149 |
-
"p":0.
|
150 |
-
"r":0.
|
151 |
-
"f":0.
|
152 |
},
|
153 |
"compound":{
|
154 |
-
"p":0.
|
155 |
-
"r":0.
|
156 |
-
"f":0.
|
157 |
},
|
158 |
"obl":{
|
159 |
-
"p":0.
|
160 |
-
"r":0.
|
161 |
-
"f":0.
|
162 |
},
|
163 |
"case":{
|
164 |
-
"p":0.
|
165 |
"r":0.9802431611,
|
166 |
-
"f":0.
|
167 |
},
|
168 |
"dislocated":{
|
169 |
-
"p":0.
|
170 |
-
"r":0.
|
171 |
-
"f":0.
|
172 |
},
|
173 |
"nsubj":{
|
174 |
-
"p":0.
|
175 |
-
"r":0.
|
176 |
-
"f":0.
|
177 |
},
|
178 |
"nmod":{
|
179 |
-
"p":0.
|
180 |
-
"r":0.
|
181 |
-
"f":0.
|
182 |
},
|
183 |
"root":{
|
184 |
-
"p":0.
|
185 |
-
"r":0.
|
186 |
-
"f":0.
|
187 |
},
|
188 |
"aux":{
|
189 |
-
"p":0.
|
190 |
-
"r":0.
|
191 |
-
"f":0.
|
192 |
},
|
193 |
"advcl":{
|
194 |
-
"p":0.
|
195 |
-
"r":0.
|
196 |
-
"f":0.
|
197 |
},
|
198 |
"mark":{
|
199 |
-
"p":0.
|
200 |
-
"r":0.
|
201 |
-
"f":0.
|
202 |
},
|
203 |
"fixed":{
|
204 |
-
"p":0.
|
205 |
-
"r":0.
|
206 |
-
"f":0.
|
207 |
},
|
208 |
"acl":{
|
209 |
-
"p":0.
|
210 |
-
"r":0.
|
211 |
-
"f":0.
|
212 |
},
|
213 |
"obj":{
|
214 |
-
"p":0.
|
215 |
-
"r":0.
|
216 |
-
"f":0.
|
217 |
},
|
218 |
"nummod":{
|
219 |
-
"p":0.
|
220 |
"r":0.8934911243,
|
221 |
-
"f":0.
|
222 |
},
|
223 |
"advmod":{
|
224 |
-
"p":0.
|
225 |
-
"r":0.
|
226 |
-
"f":0.
|
227 |
},
|
228 |
"amod":{
|
229 |
-
"p":0.
|
230 |
-
"r":0.
|
231 |
-
"f":0.
|
232 |
},
|
233 |
"cop":{
|
234 |
-
"p":0.
|
235 |
-
"r":0.
|
236 |
-
"f":0.
|
237 |
},
|
238 |
"ccomp":{
|
239 |
"p":0.95,
|
@@ -241,46 +241,51 @@
|
|
241 |
"f":0.9047619048
|
242 |
},
|
243 |
"det":{
|
244 |
-
"p":0
|
245 |
-
"r":0.
|
246 |
-
"f":0.
|
247 |
},
|
248 |
"csubj":{
|
249 |
-
"p":0.
|
250 |
-
"r":0.
|
251 |
-
"f":0.
|
252 |
},
|
253 |
"dep":{
|
254 |
-
"p":0.
|
255 |
"r":0.1428571429,
|
256 |
-
"f":0.
|
257 |
}
|
258 |
},
|
259 |
-
"tag_acc":0.
|
260 |
-
"lemma_acc":0.
|
261 |
-
"ents_p":0.
|
262 |
-
"ents_r":0.
|
263 |
-
"ents_f":0.
|
264 |
"ents_per_type":{
|
265 |
"DATE":{
|
266 |
-
"p":0.
|
267 |
-
"r":0.
|
268 |
-
"f":0.
|
269 |
},
|
270 |
"ORG":{
|
271 |
-
"p":0.
|
272 |
-
"r":0.
|
273 |
-
"f":0.
|
274 |
},
|
275 |
"PERSON":{
|
276 |
-
"p":0.
|
277 |
-
"r":0.
|
278 |
-
"f":0.
|
279 |
},
|
280 |
"GPE":{
|
281 |
-
"p":0.
|
282 |
-
"r":0.
|
283 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
284 |
},
|
285 |
"TIME":{
|
286 |
"p":0.5714285714,
|
@@ -288,69 +293,69 @@
|
|
288 |
"f":0.7272727273
|
289 |
},
|
290 |
"QUANTITY":{
|
291 |
-
"p":0.
|
292 |
-
"r":0.
|
293 |
-
"f":0.
|
294 |
},
|
295 |
"NORP":{
|
296 |
-
"p":0.
|
297 |
-
"r":0.
|
298 |
-
"f":0.
|
299 |
},
|
300 |
"TITLE_AFFIX":{
|
301 |
-
"p":0.
|
302 |
-
"r":0.
|
303 |
-
"f":0.
|
304 |
},
|
305 |
"ORDINAL":{
|
306 |
-
"p":0.
|
307 |
-
"r":0.
|
308 |
-
"f":0.
|
309 |
},
|
310 |
"WORK_OF_ART":{
|
311 |
-
"p":0.
|
312 |
"r":0.6470588235,
|
313 |
-
"f":0.
|
314 |
},
|
315 |
-
"
|
316 |
-
"p":
|
317 |
-
"r":0.
|
318 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
319 |
},
|
320 |
"PERCENT":{
|
321 |
-
"p":0
|
322 |
"r":0.2857142857,
|
323 |
-
"f":0.
|
324 |
},
|
325 |
-
"
|
326 |
-
"p":0.
|
327 |
-
"r":0.
|
328 |
-
"f":0.
|
329 |
},
|
330 |
"LOC":{
|
331 |
-
"p":0.
|
332 |
"r":0.8,
|
333 |
-
"f":0.
|
334 |
-
},
|
335 |
-
"FAC":{
|
336 |
-
"p":0.5862068966,
|
337 |
-
"r":0.4594594595,
|
338 |
-
"f":0.5151515152
|
339 |
},
|
340 |
-
"
|
341 |
"p":0.0,
|
342 |
"r":0.0,
|
343 |
"f":0.0
|
344 |
},
|
345 |
-
"
|
346 |
-
"p":0.
|
347 |
-
"r":0.
|
348 |
-
"f":0.
|
349 |
},
|
350 |
"LAW":{
|
351 |
-
"p":
|
352 |
-
"r":0.
|
353 |
-
"f":0.
|
354 |
},
|
355 |
"MONEY":{
|
356 |
"p":1.0,
|
@@ -363,7 +368,7 @@
|
|
363 |
"f":1.0
|
364 |
}
|
365 |
},
|
366 |
-
"speed":
|
367 |
},
|
368 |
"sources":[
|
369 |
{
|
|
|
1 |
{
|
2 |
"lang":"ja",
|
3 |
"name":"core_news_lg",
|
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":"[email protected]",
|
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":480443,
|
|
|
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":0.9742268041,
|
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":0.9555984556,
|
143 |
+
"sents_r":0.9763313609,
|
144 |
+
"sents_f":0.9658536585,
|
145 |
+
"dep_uas":0.9212481426,
|
146 |
+
"dep_las":0.9089518668,
|
147 |
"dep_las_per_type":{
|
148 |
"cc":{
|
149 |
+
"p":0.7777777778,
|
150 |
+
"r":0.7291666667,
|
151 |
+
"f":0.752688172
|
152 |
},
|
153 |
"compound":{
|
154 |
+
"p":0.942206655,
|
155 |
+
"r":0.9098083427,
|
156 |
+
"f":0.9257241182
|
157 |
},
|
158 |
"obl":{
|
159 |
+
"p":0.840357599,
|
160 |
+
"r":0.8214731586,
|
161 |
+
"f":0.8308080808
|
162 |
},
|
163 |
"case":{
|
164 |
+
"p":0.9892638037,
|
165 |
"r":0.9802431611,
|
166 |
+
"f":0.9847328244
|
167 |
},
|
168 |
"dislocated":{
|
169 |
+
"p":0.5384615385,
|
170 |
+
"r":0.5384615385,
|
171 |
+
"f":0.5384615385
|
172 |
},
|
173 |
"nsubj":{
|
174 |
+
"p":0.8027079304,
|
175 |
+
"r":0.7965451056,
|
176 |
+
"f":0.7996146435
|
177 |
},
|
178 |
"nmod":{
|
179 |
+
"p":0.8683886839,
|
180 |
+
"r":0.8257309942,
|
181 |
+
"f":0.8465227818
|
182 |
},
|
183 |
"root":{
|
184 |
+
"p":0.9607843137,
|
185 |
+
"r":0.966469428,
|
186 |
+
"f":0.9636184857
|
187 |
},
|
188 |
"aux":{
|
189 |
+
"p":0.9814986124,
|
190 |
+
"r":0.9851439183,
|
191 |
+
"f":0.9833178869
|
192 |
},
|
193 |
"advcl":{
|
194 |
+
"p":0.698630137,
|
195 |
+
"r":0.6876404494,
|
196 |
+
"f":0.6930917327
|
197 |
},
|
198 |
"mark":{
|
199 |
+
"p":0.9776876268,
|
200 |
+
"r":0.964,
|
201 |
+
"f":0.970795569
|
202 |
},
|
203 |
"fixed":{
|
204 |
+
"p":0.9501779359,
|
205 |
+
"r":0.9709090909,
|
206 |
+
"f":0.9604316547
|
207 |
},
|
208 |
"acl":{
|
209 |
+
"p":0.825708061,
|
210 |
+
"r":0.832967033,
|
211 |
+
"f":0.829321663
|
212 |
},
|
213 |
"obj":{
|
214 |
+
"p":0.9571865443,
|
215 |
+
"r":0.9456193353,
|
216 |
+
"f":0.9513677812
|
217 |
},
|
218 |
"nummod":{
|
219 |
+
"p":0.9934210526,
|
220 |
"r":0.8934911243,
|
221 |
+
"f":0.9408099688
|
222 |
},
|
223 |
"advmod":{
|
224 |
+
"p":0.7050359712,
|
225 |
+
"r":0.7,
|
226 |
+
"f":0.7025089606
|
227 |
},
|
228 |
"amod":{
|
229 |
+
"p":0.935483871,
|
230 |
+
"r":0.7837837838,
|
231 |
+
"f":0.8529411765
|
232 |
},
|
233 |
"cop":{
|
234 |
+
"p":0.9761904762,
|
235 |
+
"r":0.9534883721,
|
236 |
+
"f":0.9647058824
|
237 |
},
|
238 |
"ccomp":{
|
239 |
"p":0.95,
|
|
|
241 |
"f":0.9047619048
|
242 |
},
|
243 |
"det":{
|
244 |
+
"p":1.0,
|
245 |
+
"r":0.9433962264,
|
246 |
+
"f":0.9708737864
|
247 |
},
|
248 |
"csubj":{
|
249 |
+
"p":0.7333333333,
|
250 |
+
"r":0.9166666667,
|
251 |
+
"f":0.8148148148
|
252 |
},
|
253 |
"dep":{
|
254 |
+
"p":0.3333333333,
|
255 |
"r":0.1428571429,
|
256 |
+
"f":0.2
|
257 |
}
|
258 |
},
|
259 |
+
"tag_acc":0.9713282143,
|
260 |
+
"lemma_acc":0.9670499959,
|
261 |
+
"ents_p":0.7388362652,
|
262 |
+
"ents_r":0.6867924528,
|
263 |
+
"ents_f":0.7118644068,
|
264 |
"ents_per_type":{
|
265 |
"DATE":{
|
266 |
+
"p":0.9626168224,
|
267 |
+
"r":0.9449541284,
|
268 |
+
"f":0.9537037037
|
269 |
},
|
270 |
"ORG":{
|
271 |
+
"p":0.6090225564,
|
272 |
+
"r":0.5912408759,
|
273 |
+
"f":0.6
|
274 |
},
|
275 |
"PERSON":{
|
276 |
+
"p":0.7883211679,
|
277 |
+
"r":0.7769784173,
|
278 |
+
"f":0.7826086957
|
279 |
},
|
280 |
"GPE":{
|
281 |
+
"p":0.6666666667,
|
282 |
+
"r":0.6595744681,
|
283 |
+
"f":0.6631016043
|
284 |
+
},
|
285 |
+
"PRODUCT":{
|
286 |
+
"p":0.5769230769,
|
287 |
+
"r":0.3571428571,
|
288 |
+
"f":0.4411764706
|
289 |
},
|
290 |
"TIME":{
|
291 |
"p":0.5714285714,
|
|
|
293 |
"f":0.7272727273
|
294 |
},
|
295 |
"QUANTITY":{
|
296 |
+
"p":0.8823529412,
|
297 |
+
"r":0.9090909091,
|
298 |
+
"f":0.8955223881
|
299 |
},
|
300 |
"NORP":{
|
301 |
+
"p":0.6206896552,
|
302 |
+
"r":0.5625,
|
303 |
+
"f":0.5901639344
|
304 |
},
|
305 |
"TITLE_AFFIX":{
|
306 |
+
"p":0.7727272727,
|
307 |
+
"r":0.5666666667,
|
308 |
+
"f":0.6538461538
|
309 |
},
|
310 |
"ORDINAL":{
|
311 |
+
"p":0.56,
|
312 |
+
"r":0.6363636364,
|
313 |
+
"f":0.5957446809
|
314 |
},
|
315 |
"WORK_OF_ART":{
|
316 |
+
"p":0.8461538462,
|
317 |
"r":0.6470588235,
|
318 |
+
"f":0.7333333333
|
319 |
},
|
320 |
+
"FAC":{
|
321 |
+
"p":0.64,
|
322 |
+
"r":0.4324324324,
|
323 |
+
"f":0.5161290323
|
324 |
+
},
|
325 |
+
"EVENT":{
|
326 |
+
"p":0.6315789474,
|
327 |
+
"r":0.4615384615,
|
328 |
+
"f":0.5333333333
|
329 |
},
|
330 |
"PERCENT":{
|
331 |
+
"p":1.0,
|
332 |
"r":0.2857142857,
|
333 |
+
"f":0.4444444444
|
334 |
},
|
335 |
+
"CARDINAL":{
|
336 |
+
"p":0.0,
|
337 |
+
"r":0.0,
|
338 |
+
"f":0.0
|
339 |
},
|
340 |
"LOC":{
|
341 |
+
"p":0.6666666667,
|
342 |
"r":0.8,
|
343 |
+
"f":0.7272727273
|
|
|
|
|
|
|
|
|
|
|
344 |
},
|
345 |
+
"PET_NAME":{
|
346 |
"p":0.0,
|
347 |
"r":0.0,
|
348 |
"f":0.0
|
349 |
},
|
350 |
+
"MOVEMENT":{
|
351 |
+
"p":0.2,
|
352 |
+
"r":0.2,
|
353 |
+
"f":0.2
|
354 |
},
|
355 |
"LAW":{
|
356 |
+
"p":1.0,
|
357 |
+
"r":0.3333333333,
|
358 |
+
"f":0.5
|
359 |
},
|
360 |
"MONEY":{
|
361 |
"p":1.0,
|
|
|
368 |
"f":1.0
|
369 |
}
|
370 |
},
|
371 |
+
"speed":8472.2177519611
|
372 |
},
|
373 |
"sources":[
|
374 |
{
|
morphologizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8189
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57e44b34052187828a8d8fe50e2d197cd7042bd27345993630ab5b3bd4cf0fae
|
3 |
size 8189
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6385103
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f78672c987d24d24dbbfa057d614381869018805f17f1e9379bb79c9d7226099
|
3 |
size 6385103
|
parser/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 299888
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d8e840827228759b9cdc34cb061fd2731f845d2a5614d2027924d2577e325cc
|
3 |
size 299888
|
senter/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 213263
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:998163f26b6ab22c19d2245695d67f06627202d483366052c9dabe6fe91f9f67
|
3 |
size 213263
|
tok2vec/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6365607
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09689879145db884c04afed29f42b4856c292dc5087775bd9c64aef5dd652ed7
|
3 |
size 6365607
|
vocab/strings.json
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fcecfe50517fafc05d011bb0d014175312135d2a24adacc6947afdb68f9e4648
|
3 |
+
size 15614384
|