adrianeboyd
commited on
Commit
•
7069fb2
1
Parent(s):
1b34cfa
Update spaCy pipeline
Browse files- README.md +19 -19
- accuracy.json +121 -116
- attribute_ruler/patterns +0 -0
- config.cfg +3 -2
- ja_core_news_lg-any-py3-none-any.whl +2 -2
- meta.json +124 -119
- morphologizer/model +1 -1
- ner/model +1 -1
- parser/model +1 -1
- senter/model +1 -1
- tok2vec/model +2 -2
- vocab/strings.json +2 -2
README.md
CHANGED
@@ -14,13 +14,13 @@ 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
|
@@ -34,7 +34,7 @@ model-index:
|
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
-
value: 0.
|
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.
|
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) |
|
@@ -105,22 +105,22 @@ Japanese pipeline optimized for CPU. Components: tok2vec, morphologizer, parser,
|
|
105 |
|
106 |
| Type | Score |
|
107 |
| --- | --- |
|
108 |
-
| `TOKEN_ACC` | 99.
|
109 |
| `TOKEN_P` | 97.65 |
|
110 |
| `TOKEN_R` | 97.90 |
|
111 |
| `TOKEN_F` | 97.77 |
|
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` |
|
122 |
| `TAG_ACC` | 97.12 |
|
123 |
| `LEMMA_ACC` | 96.71 |
|
124 |
-
| `ENTS_P` |
|
125 |
-
| `ENTS_R` |
|
126 |
-
| `ENTS_F` |
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.754691689
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.7081761006
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.7306943543
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
|
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9749672775
|
38 |
- task:
|
39 |
name: MORPH
|
40 |
type: token-classification
|
|
|
55 |
metrics:
|
56 |
- name: Unlabeled Attachment Score (UAS)
|
57 |
type: f_score
|
58 |
+
value: 0.9233540485
|
59 |
- task:
|
60 |
name: LABELED_DEPENDENCIES
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Labeled Attachment Score (LAS)
|
64 |
type: f_score
|
65 |
+
value: 0.9101052821
|
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** | `3.5.0` |
|
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** | 480443 keys, 480443 unique vectors (300 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` | 97.50 |
|
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` | 92.34 |
|
121 |
+
| `DEP_LAS` | 91.01 |
|
122 |
| `TAG_ACC` | 97.12 |
|
123 |
| `LEMMA_ACC` | 96.71 |
|
124 |
+
| `ENTS_P` | 75.47 |
|
125 |
+
| `ENTS_R` | 70.82 |
|
126 |
+
| `ENTS_F` | 73.07 |
|
accuracy.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"token_acc": 0.
|
3 |
"token_p": 0.9764591282,
|
4 |
"token_r": 0.9790021974,
|
5 |
"token_f": 0.9777290092,
|
6 |
-
"pos_acc": 0.
|
7 |
"morph_acc": 0.0,
|
8 |
"morph_micro_p": 0.3401360544,
|
9 |
"morph_micro_r": 0.9803921569,
|
@@ -25,106 +25,106 @@
|
|
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": 0.8164794007,
|
47 |
-
"f": 0.
|
48 |
},
|
49 |
"case": {
|
50 |
-
"p": 0.
|
51 |
-
"r": 0.
|
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": 0.9842154132,
|
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.
|
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": 1.0,
|
126 |
-
"r": 0.
|
127 |
-
"f": 0.
|
128 |
},
|
129 |
"det": {
|
130 |
"p": 1.0,
|
@@ -137,96 +137,96 @@
|
|
137 |
"f": 0.64
|
138 |
},
|
139 |
"dep": {
|
140 |
-
"p": 0.
|
141 |
-
"r": 0.
|
142 |
-
"f": 0.
|
143 |
}
|
144 |
},
|
145 |
"tag_acc": 0.9712488769,
|
146 |
"lemma_acc": 0.9670526831,
|
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 |
-
"PRODUCT": {
|
172 |
-
"p": 0.4642857143,
|
173 |
-
"r": 0.3095238095,
|
174 |
-
"f": 0.3714285714
|
175 |
},
|
176 |
"TIME": {
|
177 |
-
"p": 0.
|
178 |
"r": 1.0,
|
179 |
-
"f": 0.
|
180 |
},
|
181 |
"QUANTITY": {
|
182 |
-
"p": 0.
|
183 |
-
"r": 0.
|
184 |
-
"f": 0.
|
185 |
},
|
186 |
"NORP": {
|
187 |
-
"p": 0.
|
188 |
-
"r": 0.
|
189 |
-
"f": 0.
|
190 |
-
},
|
191 |
-
"ORDINAL": {
|
192 |
-
"p": 0.652173913,
|
193 |
-
"r": 0.6818181818,
|
194 |
-
"f": 0.6666666667
|
195 |
},
|
196 |
"TITLE_AFFIX": {
|
197 |
-
"p": 0.
|
198 |
-
"r": 0.
|
199 |
-
"f": 0.
|
|
|
|
|
|
|
|
|
|
|
200 |
},
|
201 |
"WORK_OF_ART": {
|
202 |
-
"p": 0.
|
203 |
-
"r": 0.
|
204 |
-
"f": 0.
|
205 |
},
|
206 |
"CARDINAL": {
|
207 |
-
"p":
|
208 |
"r": 0.5,
|
209 |
-
"f": 0.
|
210 |
},
|
211 |
-
"
|
212 |
-
"p":
|
213 |
-
"r": 0.
|
214 |
-
"f": 0.
|
215 |
},
|
216 |
"EVENT": {
|
217 |
"p": 0.6956521739,
|
218 |
"r": 0.6153846154,
|
219 |
"f": 0.6530612245
|
220 |
},
|
|
|
|
|
|
|
|
|
|
|
221 |
"LOC": {
|
222 |
-
"p": 0.
|
223 |
"r": 0.9,
|
224 |
-
"f": 0.
|
225 |
},
|
226 |
-
"
|
227 |
-
"p": 0.
|
228 |
-
"r": 0.
|
229 |
-
"f": 0.
|
230 |
},
|
231 |
"MOVEMENT": {
|
232 |
"p": 0.0,
|
@@ -247,7 +247,12 @@
|
|
247 |
"p": 1.0,
|
248 |
"r": 1.0,
|
249 |
"f": 1.0
|
|
|
|
|
|
|
|
|
|
|
250 |
}
|
251 |
},
|
252 |
-
"speed":
|
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": 0.9749672775,
|
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": 0.9233540485,
|
32 |
+
"dep_las": 0.9101052821,
|
33 |
"dep_las_per_type": {
|
34 |
"cc": {
|
35 |
+
"p": 0.7826086957,
|
36 |
+
"r": 0.75,
|
37 |
+
"f": 0.7659574468
|
38 |
},
|
39 |
"compound": {
|
40 |
+
"p": 0.9399066511,
|
41 |
+
"r": 0.9081172492,
|
42 |
+
"f": 0.9237385321
|
43 |
},
|
44 |
"obl": {
|
45 |
+
"p": 0.8310038119,
|
46 |
"r": 0.8164794007,
|
47 |
+
"f": 0.8236775819
|
48 |
},
|
49 |
"case": {
|
50 |
+
"p": 0.9907940161,
|
51 |
+
"r": 0.9813829787,
|
52 |
+
"f": 0.9860660431
|
53 |
},
|
54 |
"dislocated": {
|
55 |
+
"p": 0.5454545455,
|
56 |
+
"r": 0.4615384615,
|
57 |
+
"f": 0.5
|
58 |
},
|
59 |
"nsubj": {
|
60 |
+
"p": 0.8359073359,
|
61 |
+
"r": 0.8310940499,
|
62 |
+
"f": 0.833493744
|
63 |
},
|
64 |
"nmod": {
|
65 |
+
"p": 0.8835192069,
|
66 |
+
"r": 0.8339181287,
|
67 |
+
"f": 0.8580024067
|
68 |
},
|
69 |
"root": {
|
70 |
+
"p": 0.9569471624,
|
71 |
+
"r": 0.9644970414,
|
72 |
+
"f": 0.9607072692
|
73 |
},
|
74 |
"aux": {
|
75 |
+
"p": 0.9796672828,
|
76 |
"r": 0.9842154132,
|
77 |
+
"f": 0.9819360815
|
78 |
},
|
79 |
"advcl": {
|
80 |
+
"p": 0.6888888889,
|
81 |
+
"r": 0.6966292135,
|
82 |
+
"f": 0.6927374302
|
83 |
},
|
84 |
"mark": {
|
85 |
+
"p": 0.9777777778,
|
86 |
+
"r": 0.968,
|
87 |
+
"f": 0.9728643216
|
88 |
},
|
89 |
"fixed": {
|
90 |
+
"p": 0.9621621622,
|
91 |
+
"r": 0.9709090909,
|
92 |
+
"f": 0.9665158371
|
93 |
},
|
94 |
"acl": {
|
95 |
+
"p": 0.8422222222,
|
96 |
+
"r": 0.832967033,
|
97 |
+
"f": 0.8375690608
|
98 |
},
|
99 |
"obj": {
|
100 |
+
"p": 0.9476923077,
|
101 |
+
"r": 0.9305135952,
|
102 |
+
"f": 0.9390243902
|
103 |
},
|
104 |
"nummod": {
|
105 |
+
"p": 0.9805194805,
|
106 |
+
"r": 0.8934911243,
|
107 |
+
"f": 0.9349845201
|
108 |
},
|
109 |
"advmod": {
|
110 |
+
"p": 0.6739130435,
|
111 |
+
"r": 0.6642857143,
|
112 |
+
"f": 0.6690647482
|
113 |
},
|
114 |
"amod": {
|
115 |
+
"p": 0.8709677419,
|
116 |
+
"r": 0.7297297297,
|
117 |
+
"f": 0.7941176471
|
118 |
},
|
119 |
"cop": {
|
120 |
+
"p": 0.9640718563,
|
121 |
+
"r": 0.9360465116,
|
122 |
+
"f": 0.9498525074
|
123 |
},
|
124 |
"ccomp": {
|
125 |
"p": 1.0,
|
126 |
+
"r": 0.9545454545,
|
127 |
+
"f": 0.976744186
|
128 |
},
|
129 |
"det": {
|
130 |
"p": 1.0,
|
|
|
137 |
"f": 0.64
|
138 |
},
|
139 |
"dep": {
|
140 |
+
"p": 0.25,
|
141 |
+
"r": 0.1428571429,
|
142 |
+
"f": 0.1818181818
|
143 |
}
|
144 |
},
|
145 |
"tag_acc": 0.9712488769,
|
146 |
"lemma_acc": 0.9670526831,
|
147 |
+
"ents_p": 0.754691689,
|
148 |
+
"ents_r": 0.7081761006,
|
149 |
+
"ents_f": 0.7306943543,
|
150 |
"ents_per_type": {
|
151 |
"DATE": {
|
152 |
+
"p": 0.9363636364,
|
153 |
+
"r": 0.9449541284,
|
154 |
+
"f": 0.9406392694
|
155 |
},
|
156 |
"ORG": {
|
157 |
+
"p": 0.6456692913,
|
158 |
+
"r": 0.598540146,
|
159 |
+
"f": 0.6212121212
|
160 |
},
|
161 |
"PERSON": {
|
162 |
+
"p": 0.7666666667,
|
163 |
+
"r": 0.8273381295,
|
164 |
+
"f": 0.7958477509
|
165 |
},
|
166 |
"GPE": {
|
167 |
+
"p": 0.7386363636,
|
168 |
+
"r": 0.6914893617,
|
169 |
+
"f": 0.7142857143
|
|
|
|
|
|
|
|
|
|
|
170 |
},
|
171 |
"TIME": {
|
172 |
+
"p": 0.5,
|
173 |
"r": 1.0,
|
174 |
+
"f": 0.6666666667
|
175 |
},
|
176 |
"QUANTITY": {
|
177 |
+
"p": 0.8923076923,
|
178 |
+
"r": 0.8787878788,
|
179 |
+
"f": 0.8854961832
|
180 |
},
|
181 |
"NORP": {
|
182 |
+
"p": 0.7037037037,
|
183 |
+
"r": 0.59375,
|
184 |
+
"f": 0.6440677966
|
|
|
|
|
|
|
|
|
|
|
185 |
},
|
186 |
"TITLE_AFFIX": {
|
187 |
+
"p": 0.8,
|
188 |
+
"r": 0.6666666667,
|
189 |
+
"f": 0.7272727273
|
190 |
+
},
|
191 |
+
"ORDINAL": {
|
192 |
+
"p": 0.5652173913,
|
193 |
+
"r": 0.5909090909,
|
194 |
+
"f": 0.5777777778
|
195 |
},
|
196 |
"WORK_OF_ART": {
|
197 |
+
"p": 0.75,
|
198 |
+
"r": 0.7058823529,
|
199 |
+
"f": 0.7272727273
|
200 |
},
|
201 |
"CARDINAL": {
|
202 |
+
"p": 0.5,
|
203 |
"r": 0.5,
|
204 |
+
"f": 0.5
|
205 |
},
|
206 |
+
"FAC": {
|
207 |
+
"p": 0.6666666667,
|
208 |
+
"r": 0.4324324324,
|
209 |
+
"f": 0.5245901639
|
210 |
},
|
211 |
"EVENT": {
|
212 |
"p": 0.6956521739,
|
213 |
"r": 0.6153846154,
|
214 |
"f": 0.6530612245
|
215 |
},
|
216 |
+
"PERCENT": {
|
217 |
+
"p": 1.0,
|
218 |
+
"r": 0.2857142857,
|
219 |
+
"f": 0.4444444444
|
220 |
+
},
|
221 |
"LOC": {
|
222 |
+
"p": 0.75,
|
223 |
"r": 0.9,
|
224 |
+
"f": 0.8181818182
|
225 |
},
|
226 |
+
"PRODUCT": {
|
227 |
+
"p": 0.5384615385,
|
228 |
+
"r": 0.3333333333,
|
229 |
+
"f": 0.4117647059
|
230 |
},
|
231 |
"MOVEMENT": {
|
232 |
"p": 0.0,
|
|
|
247 |
"p": 1.0,
|
248 |
"r": 1.0,
|
249 |
"f": 1.0
|
250 |
+
},
|
251 |
+
"PET_NAME": {
|
252 |
+
"p": 0.0,
|
253 |
+
"r": 0.0,
|
254 |
+
"f": 0.0
|
255 |
}
|
256 |
},
|
257 |
+
"speed": 9928.6122863321
|
258 |
}
|
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 = true
|
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 = true
|
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_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 sha256:457d095ddd2243b4546fa5188a9ebd1ac622ba1178ecf0d8517b7334241b4c2c
|
3 |
+
size 555256203
|
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":"contact@explosion.ai",
|
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":0.9764591282,
|
118 |
"token_r":0.9790021974,
|
119 |
"token_f":0.9777290092,
|
120 |
-
"pos_acc":0.
|
121 |
"morph_acc":0.0,
|
122 |
"morph_micro_p":0.3401360544,
|
123 |
"morph_micro_r":0.9803921569,
|
@@ -139,106 +139,106 @@
|
|
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":0.8164794007,
|
161 |
-
"f":0.
|
162 |
},
|
163 |
"case":{
|
164 |
-
"p":0.
|
165 |
-
"r":0.
|
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":0.9842154132,
|
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.
|
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":1.0,
|
240 |
-
"r":0.
|
241 |
-
"f":0.
|
242 |
},
|
243 |
"det":{
|
244 |
"p":1.0,
|
@@ -251,96 +251,96 @@
|
|
251 |
"f":0.64
|
252 |
},
|
253 |
"dep":{
|
254 |
-
"p":0.
|
255 |
-
"r":0.
|
256 |
-
"f":0.
|
257 |
}
|
258 |
},
|
259 |
"tag_acc":0.9712488769,
|
260 |
"lemma_acc":0.9670526831,
|
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 |
-
"PRODUCT":{
|
286 |
-
"p":0.4642857143,
|
287 |
-
"r":0.3095238095,
|
288 |
-
"f":0.3714285714
|
289 |
},
|
290 |
"TIME":{
|
291 |
-
"p":0.
|
292 |
"r":1.0,
|
293 |
-
"f":0.
|
294 |
},
|
295 |
"QUANTITY":{
|
296 |
-
"p":0.
|
297 |
-
"r":0.
|
298 |
-
"f":0.
|
299 |
},
|
300 |
"NORP":{
|
301 |
-
"p":0.
|
302 |
-
"r":0.
|
303 |
-
"f":0.
|
304 |
-
},
|
305 |
-
"ORDINAL":{
|
306 |
-
"p":0.652173913,
|
307 |
-
"r":0.6818181818,
|
308 |
-
"f":0.6666666667
|
309 |
},
|
310 |
"TITLE_AFFIX":{
|
311 |
-
"p":0.
|
312 |
-
"r":0.
|
313 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
314 |
},
|
315 |
"WORK_OF_ART":{
|
316 |
-
"p":0.
|
317 |
-
"r":0.
|
318 |
-
"f":0.
|
319 |
},
|
320 |
"CARDINAL":{
|
321 |
-
"p":
|
322 |
"r":0.5,
|
323 |
-
"f":0.
|
324 |
},
|
325 |
-
"
|
326 |
-
"p":
|
327 |
-
"r":0.
|
328 |
-
"f":0.
|
329 |
},
|
330 |
"EVENT":{
|
331 |
"p":0.6956521739,
|
332 |
"r":0.6153846154,
|
333 |
"f":0.6530612245
|
334 |
},
|
|
|
|
|
|
|
|
|
|
|
335 |
"LOC":{
|
336 |
-
"p":0.
|
337 |
"r":0.9,
|
338 |
-
"f":0.
|
339 |
},
|
340 |
-
"
|
341 |
-
"p":0.
|
342 |
-
"r":0.
|
343 |
-
"f":0.
|
344 |
},
|
345 |
"MOVEMENT":{
|
346 |
"p":0.0,
|
@@ -361,9 +361,14 @@
|
|
361 |
"p":1.0,
|
362 |
"r":1.0,
|
363 |
"f":1.0
|
|
|
|
|
|
|
|
|
|
|
364 |
}
|
365 |
},
|
366 |
-
"speed":
|
367 |
},
|
368 |
"sources":[
|
369 |
{
|
|
|
1 |
{
|
2 |
"lang":"ja",
|
3 |
"name":"core_news_lg",
|
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":300,
|
14 |
"vectors":480443,
|
|
|
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":0.9749672775,
|
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":0.9233540485,
|
146 |
+
"dep_las":0.9101052821,
|
147 |
"dep_las_per_type":{
|
148 |
"cc":{
|
149 |
+
"p":0.7826086957,
|
150 |
+
"r":0.75,
|
151 |
+
"f":0.7659574468
|
152 |
},
|
153 |
"compound":{
|
154 |
+
"p":0.9399066511,
|
155 |
+
"r":0.9081172492,
|
156 |
+
"f":0.9237385321
|
157 |
},
|
158 |
"obl":{
|
159 |
+
"p":0.8310038119,
|
160 |
"r":0.8164794007,
|
161 |
+
"f":0.8236775819
|
162 |
},
|
163 |
"case":{
|
164 |
+
"p":0.9907940161,
|
165 |
+
"r":0.9813829787,
|
166 |
+
"f":0.9860660431
|
167 |
},
|
168 |
"dislocated":{
|
169 |
+
"p":0.5454545455,
|
170 |
+
"r":0.4615384615,
|
171 |
+
"f":0.5
|
172 |
},
|
173 |
"nsubj":{
|
174 |
+
"p":0.8359073359,
|
175 |
+
"r":0.8310940499,
|
176 |
+
"f":0.833493744
|
177 |
},
|
178 |
"nmod":{
|
179 |
+
"p":0.8835192069,
|
180 |
+
"r":0.8339181287,
|
181 |
+
"f":0.8580024067
|
182 |
},
|
183 |
"root":{
|
184 |
+
"p":0.9569471624,
|
185 |
+
"r":0.9644970414,
|
186 |
+
"f":0.9607072692
|
187 |
},
|
188 |
"aux":{
|
189 |
+
"p":0.9796672828,
|
190 |
"r":0.9842154132,
|
191 |
+
"f":0.9819360815
|
192 |
},
|
193 |
"advcl":{
|
194 |
+
"p":0.6888888889,
|
195 |
+
"r":0.6966292135,
|
196 |
+
"f":0.6927374302
|
197 |
},
|
198 |
"mark":{
|
199 |
+
"p":0.9777777778,
|
200 |
+
"r":0.968,
|
201 |
+
"f":0.9728643216
|
202 |
},
|
203 |
"fixed":{
|
204 |
+
"p":0.9621621622,
|
205 |
+
"r":0.9709090909,
|
206 |
+
"f":0.9665158371
|
207 |
},
|
208 |
"acl":{
|
209 |
+
"p":0.8422222222,
|
210 |
+
"r":0.832967033,
|
211 |
+
"f":0.8375690608
|
212 |
},
|
213 |
"obj":{
|
214 |
+
"p":0.9476923077,
|
215 |
+
"r":0.9305135952,
|
216 |
+
"f":0.9390243902
|
217 |
},
|
218 |
"nummod":{
|
219 |
+
"p":0.9805194805,
|
220 |
+
"r":0.8934911243,
|
221 |
+
"f":0.9349845201
|
222 |
},
|
223 |
"advmod":{
|
224 |
+
"p":0.6739130435,
|
225 |
+
"r":0.6642857143,
|
226 |
+
"f":0.6690647482
|
227 |
},
|
228 |
"amod":{
|
229 |
+
"p":0.8709677419,
|
230 |
+
"r":0.7297297297,
|
231 |
+
"f":0.7941176471
|
232 |
},
|
233 |
"cop":{
|
234 |
+
"p":0.9640718563,
|
235 |
+
"r":0.9360465116,
|
236 |
+
"f":0.9498525074
|
237 |
},
|
238 |
"ccomp":{
|
239 |
"p":1.0,
|
240 |
+
"r":0.9545454545,
|
241 |
+
"f":0.976744186
|
242 |
},
|
243 |
"det":{
|
244 |
"p":1.0,
|
|
|
251 |
"f":0.64
|
252 |
},
|
253 |
"dep":{
|
254 |
+
"p":0.25,
|
255 |
+
"r":0.1428571429,
|
256 |
+
"f":0.1818181818
|
257 |
}
|
258 |
},
|
259 |
"tag_acc":0.9712488769,
|
260 |
"lemma_acc":0.9670526831,
|
261 |
+
"ents_p":0.754691689,
|
262 |
+
"ents_r":0.7081761006,
|
263 |
+
"ents_f":0.7306943543,
|
264 |
"ents_per_type":{
|
265 |
"DATE":{
|
266 |
+
"p":0.9363636364,
|
267 |
+
"r":0.9449541284,
|
268 |
+
"f":0.9406392694
|
269 |
},
|
270 |
"ORG":{
|
271 |
+
"p":0.6456692913,
|
272 |
+
"r":0.598540146,
|
273 |
+
"f":0.6212121212
|
274 |
},
|
275 |
"PERSON":{
|
276 |
+
"p":0.7666666667,
|
277 |
+
"r":0.8273381295,
|
278 |
+
"f":0.7958477509
|
279 |
},
|
280 |
"GPE":{
|
281 |
+
"p":0.7386363636,
|
282 |
+
"r":0.6914893617,
|
283 |
+
"f":0.7142857143
|
|
|
|
|
|
|
|
|
|
|
284 |
},
|
285 |
"TIME":{
|
286 |
+
"p":0.5,
|
287 |
"r":1.0,
|
288 |
+
"f":0.6666666667
|
289 |
},
|
290 |
"QUANTITY":{
|
291 |
+
"p":0.8923076923,
|
292 |
+
"r":0.8787878788,
|
293 |
+
"f":0.8854961832
|
294 |
},
|
295 |
"NORP":{
|
296 |
+
"p":0.7037037037,
|
297 |
+
"r":0.59375,
|
298 |
+
"f":0.6440677966
|
|
|
|
|
|
|
|
|
|
|
299 |
},
|
300 |
"TITLE_AFFIX":{
|
301 |
+
"p":0.8,
|
302 |
+
"r":0.6666666667,
|
303 |
+
"f":0.7272727273
|
304 |
+
},
|
305 |
+
"ORDINAL":{
|
306 |
+
"p":0.5652173913,
|
307 |
+
"r":0.5909090909,
|
308 |
+
"f":0.5777777778
|
309 |
},
|
310 |
"WORK_OF_ART":{
|
311 |
+
"p":0.75,
|
312 |
+
"r":0.7058823529,
|
313 |
+
"f":0.7272727273
|
314 |
},
|
315 |
"CARDINAL":{
|
316 |
+
"p":0.5,
|
317 |
"r":0.5,
|
318 |
+
"f":0.5
|
319 |
},
|
320 |
+
"FAC":{
|
321 |
+
"p":0.6666666667,
|
322 |
+
"r":0.4324324324,
|
323 |
+
"f":0.5245901639
|
324 |
},
|
325 |
"EVENT":{
|
326 |
"p":0.6956521739,
|
327 |
"r":0.6153846154,
|
328 |
"f":0.6530612245
|
329 |
},
|
330 |
+
"PERCENT":{
|
331 |
+
"p":1.0,
|
332 |
+
"r":0.2857142857,
|
333 |
+
"f":0.4444444444
|
334 |
+
},
|
335 |
"LOC":{
|
336 |
+
"p":0.75,
|
337 |
"r":0.9,
|
338 |
+
"f":0.8181818182
|
339 |
},
|
340 |
+
"PRODUCT":{
|
341 |
+
"p":0.5384615385,
|
342 |
+
"r":0.3333333333,
|
343 |
+
"f":0.4117647059
|
344 |
},
|
345 |
"MOVEMENT":{
|
346 |
"p":0.0,
|
|
|
361 |
"p":1.0,
|
362 |
"r":1.0,
|
363 |
"f":1.0
|
364 |
+
},
|
365 |
+
"PET_NAME":{
|
366 |
+
"p":0.0,
|
367 |
+
"r":0.0,
|
368 |
+
"f":0.0
|
369 |
}
|
370 |
},
|
371 |
+
"speed":9928.6122863321
|
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:c8d23551cf53ffa3585e26fc8e06d3e3a7265b8ad7a73f8a63b8eee2bf42f78b
|
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 sha256:58802755429b2dc7306702fa82fe1c85080c286173b95fa1afed63bde43c2403
|
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:e216c21ed16e491746e35ff4f12cef0d1ca23442bbf6554e269fef6f6785a0c4
|
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 sha256:9e72d004aa89e236df87ab02681650d2e964e53711fd8b20822c52fa91648c4c
|
3 |
size 213263
|
tok2vec/model
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 sha256:7ad60f2fd971cbf79314623752998752df0952bde7227145ff6491777747dd08
|
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 sha256:8a947c6843c5d34ba6cc46d45c3e198363bfa9f0e9385b21ec04468ebe7e810b
|
3 |
+
size 15614147
|