adrianeboyd
commited on
Commit
·
b6ba757
1
Parent(s):
402d614
Update spaCy pipeline
Browse files- README.md +28 -28
- accuracy.json +159 -159
- ca_core_news_trf-any-py3-none-any.whl +2 -2
- config.cfg +51 -24
- meta.json +164 -164
- morphologizer/model +2 -2
- ner/model +2 -2
- parser/model +2 -2
- transformer/cfg +1 -1
- transformer/model +2 -2
- vocab/strings.json +2 -2
README.md
CHANGED
@@ -14,72 +14,72 @@ 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
|
41 |
metrics:
|
42 |
- name: Morph (UFeats) Accuracy
|
43 |
type: accuracy
|
44 |
-
value: 0.
|
45 |
- task:
|
46 |
name: LEMMA
|
47 |
type: token-classification
|
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/ca#ca_core_news_trf
|
75 |
|
76 |
-
Catalan transformer pipeline (projecte-aina/roberta-base-ca-v2). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer.
|
77 |
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `ca_core_news_trf` |
|
81 |
-
| **Version** | `3.
|
82 |
-
| **spaCy** | `>=3.
|
83 |
| **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
84 |
| **Components** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
85 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
@@ -109,18 +109,18 @@ Catalan transformer pipeline (projecte-aina/roberta-base-ca-v2). Components: tra
|
|
109 |
| `TOKEN_P` | 99.78 |
|
110 |
| `TOKEN_R` | 99.79 |
|
111 |
| `TOKEN_F` | 99.79 |
|
112 |
-
| `POS_ACC` |
|
113 |
-
| `MORPH_ACC` |
|
114 |
-
| `MORPH_MICRO_P` | 99.
|
115 |
-
| `MORPH_MICRO_R` |
|
116 |
-
| `MORPH_MICRO_F` |
|
117 |
-
| `SENTS_P` | 99.
|
118 |
-
| `SENTS_R` | 99.
|
119 |
-
| `SENTS_F` | 99.
|
120 |
-
| `DEP_UAS` |
|
121 |
-
| `DEP_LAS` | 93.
|
122 |
-
| `TAG_ACC` |
|
123 |
-
| `LEMMA_ACC` | 98.
|
124 |
-
| `ENTS_P` | 92.
|
125 |
-
| `ENTS_R` | 91.
|
126 |
-
| `ENTS_F` | 91.
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.9225996081
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.9139437075
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.9182512595
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.9918845029
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9918845029
|
38 |
- task:
|
39 |
name: MORPH
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Morph (UFeats) Accuracy
|
43 |
type: accuracy
|
44 |
+
value: 0.9900646831
|
45 |
- task:
|
46 |
name: LEMMA
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Lemma Accuracy
|
50 |
type: accuracy
|
51 |
+
value: 0.9819043924
|
52 |
- task:
|
53 |
name: UNLABELED_DEPENDENCIES
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Unlabeled Attachment Score (UAS)
|
57 |
type: f_score
|
58 |
+
value: 0.9522584579
|
59 |
- task:
|
60 |
name: LABELED_DEPENDENCIES
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Labeled Attachment Score (LAS)
|
64 |
type: f_score
|
65 |
+
value: 0.9367199558
|
66 |
- task:
|
67 |
name: SENTS
|
68 |
type: token-classification
|
69 |
metrics:
|
70 |
- name: Sentences F-Score
|
71 |
type: f_score
|
72 |
+
value: 0.9938506589
|
73 |
---
|
74 |
### Details: https://spacy.io/models/ca#ca_core_news_trf
|
75 |
|
76 |
+
Catalan transformer pipeline (Transformer(name='projecte-aina/roberta-base-ca-v2', piece_encoder='byte-bpe', stride=112, type='roberta', width=768, window=144, vocab_size=50262)). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer.
|
77 |
|
78 |
| Feature | Description |
|
79 |
| --- | --- |
|
80 |
| **Name** | `ca_core_news_trf` |
|
81 |
+
| **Version** | `3.7.2` |
|
82 |
+
| **spaCy** | `>=3.7.0,<3.8.0` |
|
83 |
| **Default Pipeline** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
84 |
| **Components** | `transformer`, `morphologizer`, `parser`, `attribute_ruler`, `lemmatizer`, `ner` |
|
85 |
| **Vectors** | 0 keys, 0 unique vectors (0 dimensions) |
|
|
|
109 |
| `TOKEN_P` | 99.78 |
|
110 |
| `TOKEN_R` | 99.79 |
|
111 |
| `TOKEN_F` | 99.79 |
|
112 |
+
| `POS_ACC` | 99.19 |
|
113 |
+
| `MORPH_ACC` | 99.01 |
|
114 |
+
| `MORPH_MICRO_P` | 99.74 |
|
115 |
+
| `MORPH_MICRO_R` | 99.49 |
|
116 |
+
| `MORPH_MICRO_F` | 99.62 |
|
117 |
+
| `SENTS_P` | 99.47 |
|
118 |
+
| `SENTS_R` | 99.30 |
|
119 |
+
| `SENTS_F` | 99.39 |
|
120 |
+
| `DEP_UAS` | 95.23 |
|
121 |
+
| `DEP_LAS` | 93.67 |
|
122 |
+
| `TAG_ACC` | 99.19 |
|
123 |
+
| `LEMMA_ACC` | 98.19 |
|
124 |
+
| `ENTS_P` | 92.26 |
|
125 |
+
| `ENTS_R` | 91.39 |
|
126 |
+
| `ENTS_F` | 91.83 |
|
accuracy.json
CHANGED
@@ -3,11 +3,11 @@
|
|
3 |
"token_p": 0.9978112128,
|
4 |
"token_r": 0.9979488063,
|
5 |
"token_f": 0.9978800048,
|
6 |
-
"pos_acc": 0.
|
7 |
-
"morph_acc": 0.
|
8 |
-
"morph_micro_p": 0.
|
9 |
-
"morph_micro_r": 0.
|
10 |
-
"morph_micro_f": 0.
|
11 |
"morph_per_feat": {
|
12 |
"Mood": {
|
13 |
"p": 0.9982771351,
|
@@ -15,69 +15,69 @@
|
|
15 |
"f": 0.9981543005
|
16 |
},
|
17 |
"Number": {
|
18 |
-
"p": 0.
|
19 |
-
"r": 0.
|
20 |
-
"f": 0.
|
21 |
},
|
22 |
"Person": {
|
23 |
-
"p": 0.
|
24 |
"r": 0.9973474801,
|
25 |
-
"f": 0.
|
26 |
},
|
27 |
"Tense": {
|
28 |
-
"p": 0.
|
29 |
-
"r": 0.
|
30 |
-
"f": 0.
|
31 |
},
|
32 |
"VerbForm": {
|
33 |
-
"p": 0.
|
34 |
-
"r": 0.
|
35 |
-
"f": 0.
|
36 |
},
|
37 |
"Gender": {
|
38 |
-
"p": 0.
|
39 |
-
"r": 0.
|
40 |
-
"f": 0.
|
41 |
},
|
42 |
"NumType": {
|
43 |
-
"p": 0.
|
44 |
-
"r": 0.
|
45 |
-
"f": 0.
|
46 |
},
|
47 |
"Definite": {
|
48 |
-
"p": 0.
|
49 |
-
"r": 0.
|
50 |
-
"f": 0.
|
51 |
},
|
52 |
"PronType": {
|
53 |
-
"p": 0.
|
54 |
-
"r": 0.
|
55 |
-
"f": 0.
|
56 |
},
|
57 |
"PunctType": {
|
58 |
-
"p": 0.
|
59 |
-
"r": 0.
|
60 |
-
"f": 0.
|
61 |
},
|
62 |
"NumForm": {
|
63 |
-
"p": 0.
|
64 |
-
"r": 0.
|
65 |
-
"f": 0.
|
66 |
},
|
67 |
"Polarity": {
|
68 |
"p": 1.0,
|
69 |
-
"r": 0.
|
70 |
-
"f": 0.
|
71 |
},
|
72 |
"Case": {
|
73 |
-
"p": 0.
|
74 |
-
"r": 0.
|
75 |
-
"f": 0.
|
76 |
},
|
77 |
"PrepCase": {
|
78 |
-
"p": 0.
|
79 |
"r": 0.9986187845,
|
80 |
-
"f": 0.
|
81 |
},
|
82 |
"Reflex": {
|
83 |
"p": 0.9986052999,
|
@@ -86,165 +86,165 @@
|
|
86 |
},
|
87 |
"Degree": {
|
88 |
"p": 1.0,
|
89 |
-
"r": 0.
|
90 |
-
"f": 0.
|
91 |
},
|
92 |
"Poss": {
|
93 |
"p": 1.0,
|
94 |
-
"r": 0.
|
95 |
-
"f": 0.
|
96 |
},
|
97 |
"AdvType": {
|
98 |
-
"p": 0.
|
99 |
-
"r": 0.
|
100 |
-
"f": 0.
|
101 |
},
|
102 |
"PunctSide": {
|
103 |
-
"p": 0.
|
104 |
-
"r": 0.
|
105 |
-
"f": 0.
|
106 |
},
|
107 |
"Number[psor]": {
|
108 |
-
"p":
|
109 |
"r": 1.0,
|
110 |
-
"f":
|
111 |
},
|
112 |
"Polite": {
|
113 |
"p": 1.0,
|
114 |
-
"r": 0
|
115 |
-
"f": 0
|
116 |
}
|
117 |
},
|
118 |
-
"sents_p": 0.
|
119 |
-
"sents_r": 0.
|
120 |
-
"sents_f": 0.
|
121 |
-
"dep_uas": 0.
|
122 |
-
"dep_las": 0.
|
123 |
"dep_las_per_type": {
|
124 |
"nsubj": {
|
125 |
-
"p": 0.
|
126 |
-
"r": 0.
|
127 |
-
"f": 0.
|
128 |
},
|
129 |
"flat": {
|
130 |
-
"p": 0.
|
131 |
-
"r": 0.
|
132 |
-
"f": 0.
|
133 |
},
|
134 |
"case": {
|
135 |
-
"p": 0.
|
136 |
-
"r": 0.
|
137 |
-
"f": 0.
|
138 |
},
|
139 |
"aux": {
|
140 |
-
"p": 0.
|
141 |
-
"r": 0.
|
142 |
-
"f": 0.
|
143 |
},
|
144 |
"root": {
|
145 |
-
"p": 0.
|
146 |
-
"r": 0.
|
147 |
-
"f": 0.
|
148 |
},
|
149 |
"nummod": {
|
150 |
-
"p": 0.
|
151 |
-
"r": 0.
|
152 |
-
"f": 0.
|
153 |
},
|
154 |
"obj": {
|
155 |
-
"p": 0.
|
156 |
-
"r": 0.
|
157 |
-
"f": 0.
|
158 |
},
|
159 |
"det": {
|
160 |
-
"p": 0.
|
161 |
-
"r": 0.
|
162 |
-
"f": 0.
|
163 |
},
|
164 |
"nmod": {
|
165 |
-
"p": 0.
|
166 |
-
"r": 0.
|
167 |
-
"f": 0.
|
168 |
},
|
169 |
"amod": {
|
170 |
-
"p": 0.
|
171 |
-
"r": 0.
|
172 |
-
"f": 0.
|
173 |
},
|
174 |
"obl": {
|
175 |
-
"p": 0.
|
176 |
-
"r": 0.
|
177 |
-
"f": 0.
|
178 |
},
|
179 |
"cc": {
|
180 |
-
"p": 0.
|
181 |
-
"r": 0.
|
182 |
-
"f": 0.
|
183 |
},
|
184 |
"fixed": {
|
185 |
-
"p": 0.
|
186 |
-
"r": 0.
|
187 |
-
"f": 0.
|
188 |
},
|
189 |
"conj": {
|
190 |
-
"p": 0.
|
191 |
-
"r": 0.
|
192 |
-
"f": 0.
|
193 |
},
|
194 |
"advmod": {
|
195 |
-
"p": 0.
|
196 |
-
"r": 0.
|
197 |
-
"f": 0.
|
198 |
},
|
199 |
"advcl": {
|
200 |
-
"p": 0.
|
201 |
-
"r": 0.
|
202 |
-
"f": 0.
|
203 |
},
|
204 |
"compound": {
|
205 |
-
"p": 0.
|
206 |
-
"r": 0.
|
207 |
-
"f": 0.
|
208 |
},
|
209 |
"mark": {
|
210 |
-
"p": 0.
|
211 |
-
"r": 0.
|
212 |
-
"f": 0.
|
213 |
},
|
214 |
"cop": {
|
215 |
-
"p": 0.
|
216 |
-
"r": 0.
|
217 |
-
"f": 0.
|
218 |
},
|
219 |
"ccomp": {
|
220 |
-
"p": 0.
|
221 |
-
"r": 0.
|
222 |
-
"f": 0.
|
223 |
},
|
224 |
"acl": {
|
225 |
-
"p": 0.
|
226 |
-
"r": 0.
|
227 |
-
"f": 0.
|
228 |
},
|
229 |
"expl:pass": {
|
230 |
-
"p": 0.
|
231 |
-
"r": 0.
|
232 |
-
"f": 0.
|
233 |
},
|
234 |
"appos": {
|
235 |
-
"p": 0.
|
236 |
-
"r": 0.
|
237 |
-
"f": 0.
|
238 |
},
|
239 |
"xcomp": {
|
240 |
-
"p": 0.
|
241 |
-
"r": 0.
|
242 |
-
"f": 0.
|
243 |
},
|
244 |
"iobj": {
|
245 |
-
"p": 0.
|
246 |
-
"r": 0.
|
247 |
-
"f": 0.
|
248 |
},
|
249 |
"dep": {
|
250 |
"p": 0.0,
|
@@ -252,14 +252,14 @@
|
|
252 |
"f": 0.0
|
253 |
},
|
254 |
"csubj": {
|
255 |
-
"p": 0.
|
256 |
-
"r": 0.
|
257 |
-
"f": 0.
|
258 |
},
|
259 |
"parataxis": {
|
260 |
-
"p": 0.
|
261 |
-
"r": 0.
|
262 |
-
"f": 0.
|
263 |
},
|
264 |
"nsubj:pass": {
|
265 |
"p": 0.0,
|
@@ -272,32 +272,32 @@
|
|
272 |
"f": 0.0
|
273 |
}
|
274 |
},
|
275 |
-
"tag_acc": 0.
|
276 |
-
"lemma_acc": 0.
|
277 |
-
"ents_p": 0.
|
278 |
-
"ents_r": 0.
|
279 |
-
"ents_f": 0.
|
280 |
"ents_per_type": {
|
281 |
"ORG": {
|
282 |
-
"p": 0.
|
283 |
-
"r": 0.
|
284 |
-
"f": 0.
|
285 |
},
|
286 |
"LOC": {
|
287 |
-
"p": 0.
|
288 |
-
"r": 0.
|
289 |
-
"f": 0.
|
290 |
},
|
291 |
"MISC": {
|
292 |
-
"p": 0.
|
293 |
-
"r": 0.
|
294 |
-
"f": 0.
|
295 |
},
|
296 |
"PER": {
|
297 |
-
"p": 0.
|
298 |
-
"r": 0.
|
299 |
-
"f": 0.
|
300 |
}
|
301 |
},
|
302 |
-
"speed":
|
303 |
}
|
|
|
3 |
"token_p": 0.9978112128,
|
4 |
"token_r": 0.9979488063,
|
5 |
"token_f": 0.9978800048,
|
6 |
+
"pos_acc": 0.9918845029,
|
7 |
+
"morph_acc": 0.9900646831,
|
8 |
+
"morph_micro_p": 0.997430458,
|
9 |
+
"morph_micro_r": 0.9948740873,
|
10 |
+
"morph_micro_f": 0.9961506326,
|
11 |
"morph_per_feat": {
|
12 |
"Mood": {
|
13 |
"p": 0.9982771351,
|
|
|
15 |
"f": 0.9981543005
|
16 |
},
|
17 |
"Number": {
|
18 |
+
"p": 0.998884531,
|
19 |
+
"r": 0.9963033413,
|
20 |
+
"f": 0.9975922665
|
21 |
},
|
22 |
"Person": {
|
23 |
+
"p": 0.9987604038,
|
24 |
"r": 0.9973474801,
|
25 |
+
"f": 0.9980534419
|
26 |
},
|
27 |
"Tense": {
|
28 |
+
"p": 0.9937251621,
|
29 |
+
"r": 0.9962256238,
|
30 |
+
"f": 0.994973822
|
31 |
},
|
32 |
"VerbForm": {
|
33 |
+
"p": 0.9977330311,
|
34 |
+
"r": 0.9966697749,
|
35 |
+
"f": 0.9972011196
|
36 |
},
|
37 |
"Gender": {
|
38 |
+
"p": 0.9973378509,
|
39 |
+
"r": 0.9922469421,
|
40 |
+
"f": 0.9947858833
|
41 |
},
|
42 |
"NumType": {
|
43 |
+
"p": 0.9706439394,
|
44 |
+
"r": 0.9660697455,
|
45 |
+
"f": 0.9683514407
|
46 |
},
|
47 |
"Definite": {
|
48 |
+
"p": 0.9971922565,
|
49 |
+
"r": 0.9941072481,
|
50 |
+
"f": 0.9956473626
|
51 |
},
|
52 |
"PronType": {
|
53 |
+
"p": 0.9965301286,
|
54 |
+
"r": 0.9945101351,
|
55 |
+
"f": 0.9955191072
|
56 |
},
|
57 |
"PunctType": {
|
58 |
+
"p": 0.9998172181,
|
59 |
+
"r": 0.9974471189,
|
60 |
+
"f": 0.9986307622
|
61 |
},
|
62 |
"NumForm": {
|
63 |
+
"p": 0.9819193324,
|
64 |
+
"r": 0.9915730337,
|
65 |
+
"f": 0.9867225716
|
66 |
},
|
67 |
"Polarity": {
|
68 |
"p": 1.0,
|
69 |
+
"r": 0.9902912621,
|
70 |
+
"f": 0.9951219512
|
71 |
},
|
72 |
"Case": {
|
73 |
+
"p": 0.9991652755,
|
74 |
+
"r": 0.9966694421,
|
75 |
+
"f": 0.9979157982
|
76 |
},
|
77 |
"PrepCase": {
|
78 |
+
"p": 0.9986187845,
|
79 |
"r": 0.9986187845,
|
80 |
+
"f": 0.9986187845
|
81 |
},
|
82 |
"Reflex": {
|
83 |
"p": 0.9986052999,
|
|
|
86 |
},
|
87 |
"Degree": {
|
88 |
"p": 1.0,
|
89 |
+
"r": 0.9929328622,
|
90 |
+
"f": 0.9964539007
|
91 |
},
|
92 |
"Poss": {
|
93 |
"p": 1.0,
|
94 |
+
"r": 0.9914529915,
|
95 |
+
"f": 0.9957081545
|
96 |
},
|
97 |
"AdvType": {
|
98 |
+
"p": 0.9921875,
|
99 |
+
"r": 0.9270072993,
|
100 |
+
"f": 0.958490566
|
101 |
},
|
102 |
"PunctSide": {
|
103 |
+
"p": 0.9975845411,
|
104 |
+
"r": 0.9975845411,
|
105 |
+
"f": 0.9975845411
|
106 |
},
|
107 |
"Number[psor]": {
|
108 |
+
"p": 0.9411764706,
|
109 |
"r": 1.0,
|
110 |
+
"f": 0.9696969697
|
111 |
},
|
112 |
"Polite": {
|
113 |
"p": 1.0,
|
114 |
+
"r": 1.0,
|
115 |
+
"f": 1.0
|
116 |
}
|
117 |
},
|
118 |
+
"sents_p": 0.9947245018,
|
119 |
+
"sents_r": 0.9929783499,
|
120 |
+
"sents_f": 0.9938506589,
|
121 |
+
"dep_uas": 0.9522584579,
|
122 |
+
"dep_las": 0.9367199558,
|
123 |
"dep_las_per_type": {
|
124 |
"nsubj": {
|
125 |
+
"p": 0.9610479145,
|
126 |
+
"r": 0.9603858078,
|
127 |
+
"f": 0.9607167471
|
128 |
},
|
129 |
"flat": {
|
130 |
+
"p": 0.9334415584,
|
131 |
+
"r": 0.9426229508,
|
132 |
+
"f": 0.9380097879
|
133 |
},
|
134 |
"case": {
|
135 |
+
"p": 0.9792044493,
|
136 |
+
"r": 0.9737886257,
|
137 |
+
"f": 0.9764890282
|
138 |
},
|
139 |
"aux": {
|
140 |
+
"p": 0.9695512821,
|
141 |
+
"r": 0.9690336359,
|
142 |
+
"f": 0.9692923899
|
143 |
},
|
144 |
"root": {
|
145 |
+
"p": 0.9730363423,
|
146 |
+
"r": 0.9713282621,
|
147 |
+
"f": 0.972181552
|
148 |
},
|
149 |
"nummod": {
|
150 |
+
"p": 0.9326241135,
|
151 |
+
"r": 0.926056338,
|
152 |
+
"f": 0.9293286219
|
153 |
},
|
154 |
"obj": {
|
155 |
+
"p": 0.931773399,
|
156 |
+
"r": 0.9375464684,
|
157 |
+
"f": 0.9346510191
|
158 |
},
|
159 |
"det": {
|
160 |
+
"p": 0.9877590465,
|
161 |
+
"r": 0.9876529955,
|
162 |
+
"f": 0.9877060181
|
163 |
},
|
164 |
"nmod": {
|
165 |
+
"p": 0.8882657463,
|
166 |
+
"r": 0.8819875776,
|
167 |
+
"f": 0.8851155293
|
168 |
},
|
169 |
"amod": {
|
170 |
+
"p": 0.9682539683,
|
171 |
+
"r": 0.9667924528,
|
172 |
+
"f": 0.9675226586
|
173 |
},
|
174 |
"obl": {
|
175 |
+
"p": 0.8433286843,
|
176 |
+
"r": 0.8260473588,
|
177 |
+
"f": 0.8345985737
|
178 |
},
|
179 |
"cc": {
|
180 |
+
"p": 0.9579145729,
|
181 |
+
"r": 0.9609325772,
|
182 |
+
"f": 0.9594212016
|
183 |
},
|
184 |
"fixed": {
|
185 |
+
"p": 0.932938856,
|
186 |
+
"r": 0.9403578529,
|
187 |
+
"f": 0.9366336634
|
188 |
},
|
189 |
"conj": {
|
190 |
+
"p": 0.8519153802,
|
191 |
+
"r": 0.8533791523,
|
192 |
+
"f": 0.8526466381
|
193 |
},
|
194 |
"advmod": {
|
195 |
+
"p": 0.8939393939,
|
196 |
+
"r": 0.8928987194,
|
197 |
+
"f": 0.8934187536
|
198 |
},
|
199 |
"advcl": {
|
200 |
+
"p": 0.7478684531,
|
201 |
+
"r": 0.7675,
|
202 |
+
"f": 0.7575570635
|
203 |
},
|
204 |
"compound": {
|
205 |
+
"p": 0.897810219,
|
206 |
+
"r": 0.8880866426,
|
207 |
+
"f": 0.8929219601
|
208 |
},
|
209 |
"mark": {
|
210 |
+
"p": 0.9427235535,
|
211 |
+
"r": 0.9438267993,
|
212 |
+
"f": 0.9432748538
|
213 |
},
|
214 |
"cop": {
|
215 |
+
"p": 0.9002123142,
|
216 |
+
"r": 0.9177489177,
|
217 |
+
"f": 0.9088960343
|
218 |
},
|
219 |
"ccomp": {
|
220 |
+
"p": 0.8777292576,
|
221 |
+
"r": 0.8993288591,
|
222 |
+
"f": 0.8883977901
|
223 |
},
|
224 |
"acl": {
|
225 |
+
"p": 0.8672397326,
|
226 |
+
"r": 0.8747591522,
|
227 |
+
"f": 0.8709832134
|
228 |
},
|
229 |
"expl:pass": {
|
230 |
+
"p": 0.8611111111,
|
231 |
+
"r": 0.6739130435,
|
232 |
+
"f": 0.756097561
|
233 |
},
|
234 |
"appos": {
|
235 |
+
"p": 0.8524590164,
|
236 |
+
"r": 0.8600508906,
|
237 |
+
"f": 0.8562381254
|
238 |
},
|
239 |
"xcomp": {
|
240 |
+
"p": 0.9128329298,
|
241 |
+
"r": 0.8849765258,
|
242 |
+
"f": 0.8986889154
|
243 |
},
|
244 |
"iobj": {
|
245 |
+
"p": 0.8670520231,
|
246 |
+
"r": 0.8021390374,
|
247 |
+
"f": 0.8333333333
|
248 |
},
|
249 |
"dep": {
|
250 |
"p": 0.0,
|
|
|
252 |
"f": 0.0
|
253 |
},
|
254 |
"csubj": {
|
255 |
+
"p": 0.8125,
|
256 |
+
"r": 0.858490566,
|
257 |
+
"f": 0.8348623853
|
258 |
},
|
259 |
"parataxis": {
|
260 |
+
"p": 0.8461538462,
|
261 |
+
"r": 0.6470588235,
|
262 |
+
"f": 0.7333333333
|
263 |
},
|
264 |
"nsubj:pass": {
|
265 |
"p": 0.0,
|
|
|
272 |
"f": 0.0
|
273 |
}
|
274 |
},
|
275 |
+
"tag_acc": 0.9918845029,
|
276 |
+
"lemma_acc": 0.9819043924,
|
277 |
+
"ents_p": 0.9225996081,
|
278 |
+
"ents_r": 0.9139437075,
|
279 |
+
"ents_f": 0.9182512595,
|
280 |
"ents_per_type": {
|
281 |
"ORG": {
|
282 |
+
"p": 0.9112107623,
|
283 |
+
"r": 0.9161406673,
|
284 |
+
"f": 0.9136690647
|
285 |
},
|
286 |
"LOC": {
|
287 |
+
"p": 0.9353778751,
|
288 |
+
"r": 0.9163090129,
|
289 |
+
"f": 0.9257452575
|
290 |
},
|
291 |
"MISC": {
|
292 |
+
"p": 0.8539944904,
|
293 |
+
"r": 0.8093994778,
|
294 |
+
"f": 0.8310991957
|
295 |
},
|
296 |
"PER": {
|
297 |
+
"p": 0.9612518629,
|
298 |
+
"r": 0.9670164918,
|
299 |
+
"f": 0.9641255605
|
300 |
}
|
301 |
},
|
302 |
+
"speed": 1944.0672670287
|
303 |
}
|
ca_core_news_trf-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 sha256:4bbc29626e73283096a70097b307e9c898878c6b005648f0bfa89b736345c672
|
3 |
+
size 457100783
|
config.cfg
CHANGED
@@ -17,6 +17,7 @@ after_creation = null
|
|
17 |
after_pipeline_creation = null
|
18 |
batch_size = 64
|
19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
|
|
20 |
|
21 |
[components]
|
22 |
|
@@ -45,10 +46,11 @@ nO = null
|
|
45 |
normalize = false
|
46 |
|
47 |
[components.morphologizer.model.tok2vec]
|
48 |
-
@architectures = "spacy-transformers.
|
49 |
-
|
50 |
upstream = "transformer"
|
51 |
pooling = {"@layers":"reduce_mean.v1"}
|
|
|
52 |
|
53 |
[components.ner]
|
54 |
factory = "ner"
|
@@ -67,10 +69,11 @@ use_upper = false
|
|
67 |
nO = null
|
68 |
|
69 |
[components.ner.model.tok2vec]
|
70 |
-
@architectures = "spacy-transformers.
|
71 |
-
|
72 |
upstream = "transformer"
|
73 |
pooling = {"@layers":"reduce_mean.v1"}
|
|
|
74 |
|
75 |
[components.parser]
|
76 |
factory = "parser"
|
@@ -90,32 +93,44 @@ use_upper = false
|
|
90 |
nO = null
|
91 |
|
92 |
[components.parser.model.tok2vec]
|
93 |
-
@architectures = "spacy-transformers.
|
94 |
-
|
95 |
upstream = "transformer"
|
96 |
pooling = {"@layers":"reduce_mean.v1"}
|
|
|
97 |
|
98 |
[components.transformer]
|
99 |
-
factory = "
|
100 |
-
|
101 |
-
|
102 |
|
103 |
[components.transformer.model]
|
104 |
-
|
105 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
106 |
mixed_precision = false
|
107 |
-
|
108 |
-
[components.transformer.model.get_spans]
|
109 |
-
@span_getters = "spacy-transformers.strided_spans.v1"
|
110 |
-
window = 128
|
111 |
-
stride = 96
|
112 |
|
113 |
[components.transformer.model.grad_scaler_config]
|
114 |
|
115 |
-
[components.transformer.model.
|
116 |
-
|
117 |
-
|
118 |
-
|
|
|
119 |
|
120 |
[corpora]
|
121 |
|
@@ -152,11 +167,11 @@ annotating_components = []
|
|
152 |
before_update = null
|
153 |
|
154 |
[training.batcher]
|
155 |
-
@batchers = "spacy.
|
156 |
-
discard_oversize =
|
157 |
-
get_length = null
|
158 |
size = 2000
|
159 |
-
|
|
|
160 |
|
161 |
[training.logger]
|
162 |
@loggers = "spacy.ConsoleLogger.v1"
|
@@ -227,6 +242,18 @@ require = false
|
|
227 |
path = "corpus/labels/parser.json"
|
228 |
require = false
|
229 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
230 |
[initialize.lookups]
|
231 |
@misc = "spacy.LookupsDataLoader.v1"
|
232 |
lang = ${nlp.lang}
|
|
|
17 |
after_pipeline_creation = null
|
18 |
batch_size = 64
|
19 |
tokenizer = {"@tokenizers":"spacy.Tokenizer.v1"}
|
20 |
+
vectors = {"@vectors":"spacy.Vectors.v1"}
|
21 |
|
22 |
[components]
|
23 |
|
|
|
46 |
normalize = false
|
47 |
|
48 |
[components.morphologizer.model.tok2vec]
|
49 |
+
@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
|
50 |
+
width = ${components.transformer.model.hidden_width}
|
51 |
upstream = "transformer"
|
52 |
pooling = {"@layers":"reduce_mean.v1"}
|
53 |
+
grad_factor = 1.0
|
54 |
|
55 |
[components.ner]
|
56 |
factory = "ner"
|
|
|
69 |
nO = null
|
70 |
|
71 |
[components.ner.model.tok2vec]
|
72 |
+
@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
|
73 |
+
width = ${components.transformer.model.hidden_width}
|
74 |
upstream = "transformer"
|
75 |
pooling = {"@layers":"reduce_mean.v1"}
|
76 |
+
grad_factor = 1.0
|
77 |
|
78 |
[components.parser]
|
79 |
factory = "parser"
|
|
|
93 |
nO = null
|
94 |
|
95 |
[components.parser.model.tok2vec]
|
96 |
+
@architectures = "spacy-curated-transformers.LastTransformerLayerListener.v1"
|
97 |
+
width = ${components.transformer.model.hidden_width}
|
98 |
upstream = "transformer"
|
99 |
pooling = {"@layers":"reduce_mean.v1"}
|
100 |
+
grad_factor = 1.0
|
101 |
|
102 |
[components.transformer]
|
103 |
+
factory = "curated_transformer"
|
104 |
+
all_layer_outputs = false
|
105 |
+
frozen = false
|
106 |
|
107 |
[components.transformer.model]
|
108 |
+
@architectures = "spacy-curated-transformers.RobertaTransformer.v1"
|
109 |
+
vocab_size = 50262
|
110 |
+
hidden_width = 768
|
111 |
+
piece_encoder = {"@architectures":"spacy-curated-transformers.ByteBpeEncoder.v1"}
|
112 |
+
attention_probs_dropout_prob = 0.1
|
113 |
+
hidden_act = "gelu"
|
114 |
+
hidden_dropout_prob = 0.1
|
115 |
+
intermediate_width = 3072
|
116 |
+
layer_norm_eps = 0.00001
|
117 |
+
max_position_embeddings = 514
|
118 |
+
model_max_length = 512
|
119 |
+
num_attention_heads = 12
|
120 |
+
num_hidden_layers = 12
|
121 |
+
padding_idx = 1
|
122 |
+
type_vocab_size = 1
|
123 |
+
torchscript = false
|
124 |
mixed_precision = false
|
125 |
+
wrapped_listener = null
|
|
|
|
|
|
|
|
|
126 |
|
127 |
[components.transformer.model.grad_scaler_config]
|
128 |
|
129 |
+
[components.transformer.model.with_spans]
|
130 |
+
@architectures = "spacy-curated-transformers.WithStridedSpans.v1"
|
131 |
+
stride = 112
|
132 |
+
window = 144
|
133 |
+
batch_size = 384
|
134 |
|
135 |
[corpora]
|
136 |
|
|
|
167 |
before_update = null
|
168 |
|
169 |
[training.batcher]
|
170 |
+
@batchers = "spacy.batch_by_words.v1"
|
171 |
+
discard_oversize = false
|
|
|
172 |
size = 2000
|
173 |
+
tolerance = 0.2
|
174 |
+
get_length = null
|
175 |
|
176 |
[training.logger]
|
177 |
@loggers = "spacy.ConsoleLogger.v1"
|
|
|
242 |
path = "corpus/labels/parser.json"
|
243 |
require = false
|
244 |
|
245 |
+
[initialize.components.transformer]
|
246 |
+
|
247 |
+
[initialize.components.transformer.encoder_loader]
|
248 |
+
@model_loaders = "spacy-curated-transformers.HFTransformerEncoderLoader.v1"
|
249 |
+
name = "projecte-aina/roberta-base-ca-v2"
|
250 |
+
revision = "main"
|
251 |
+
|
252 |
+
[initialize.components.transformer.piecer_loader]
|
253 |
+
@model_loaders = "spacy-curated-transformers.HFPieceEncoderLoader.v1"
|
254 |
+
name = "projecte-aina/roberta-base-ca-v2"
|
255 |
+
revision = "main"
|
256 |
+
|
257 |
[initialize.lookups]
|
258 |
@misc = "spacy.LookupsDataLoader.v1"
|
259 |
lang = ${nlp.lang}
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"ca",
|
3 |
"name":"core_news_trf",
|
4 |
-
"version":"3.
|
5 |
-
"description":"Catalan transformer pipeline (projecte-aina/roberta-base-ca-v2). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer.",
|
6 |
"author":"Explosion",
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"GNU GPL 3.0",
|
10 |
-
"spacy_version":">=3.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
@@ -372,11 +372,11 @@
|
|
372 |
"token_p":0.9978112128,
|
373 |
"token_r":0.9979488063,
|
374 |
"token_f":0.9978800048,
|
375 |
-
"pos_acc":0.
|
376 |
-
"morph_acc":0.
|
377 |
-
"morph_micro_p":0.
|
378 |
-
"morph_micro_r":0.
|
379 |
-
"morph_micro_f":0.
|
380 |
"morph_per_feat":{
|
381 |
"Mood":{
|
382 |
"p":0.9982771351,
|
@@ -384,69 +384,69 @@
|
|
384 |
"f":0.9981543005
|
385 |
},
|
386 |
"Number":{
|
387 |
-
"p":0.
|
388 |
-
"r":0.
|
389 |
-
"f":0.
|
390 |
},
|
391 |
"Person":{
|
392 |
-
"p":0.
|
393 |
"r":0.9973474801,
|
394 |
-
"f":0.
|
395 |
},
|
396 |
"Tense":{
|
397 |
-
"p":0.
|
398 |
-
"r":0.
|
399 |
-
"f":0.
|
400 |
},
|
401 |
"VerbForm":{
|
402 |
-
"p":0.
|
403 |
-
"r":0.
|
404 |
-
"f":0.
|
405 |
},
|
406 |
"Gender":{
|
407 |
-
"p":0.
|
408 |
-
"r":0.
|
409 |
-
"f":0.
|
410 |
},
|
411 |
"NumType":{
|
412 |
-
"p":0.
|
413 |
-
"r":0.
|
414 |
-
"f":0.
|
415 |
},
|
416 |
"Definite":{
|
417 |
-
"p":0.
|
418 |
-
"r":0.
|
419 |
-
"f":0.
|
420 |
},
|
421 |
"PronType":{
|
422 |
-
"p":0.
|
423 |
-
"r":0.
|
424 |
-
"f":0.
|
425 |
},
|
426 |
"PunctType":{
|
427 |
-
"p":0.
|
428 |
-
"r":0.
|
429 |
-
"f":0.
|
430 |
},
|
431 |
"NumForm":{
|
432 |
-
"p":0.
|
433 |
-
"r":0.
|
434 |
-
"f":0.
|
435 |
},
|
436 |
"Polarity":{
|
437 |
"p":1.0,
|
438 |
-
"r":0.
|
439 |
-
"f":0.
|
440 |
},
|
441 |
"Case":{
|
442 |
-
"p":0.
|
443 |
-
"r":0.
|
444 |
-
"f":0.
|
445 |
},
|
446 |
"PrepCase":{
|
447 |
-
"p":0.
|
448 |
"r":0.9986187845,
|
449 |
-
"f":0.
|
450 |
},
|
451 |
"Reflex":{
|
452 |
"p":0.9986052999,
|
@@ -455,165 +455,165 @@
|
|
455 |
},
|
456 |
"Degree":{
|
457 |
"p":1.0,
|
458 |
-
"r":0.
|
459 |
-
"f":0.
|
460 |
},
|
461 |
"Poss":{
|
462 |
"p":1.0,
|
463 |
-
"r":0.
|
464 |
-
"f":0.
|
465 |
},
|
466 |
"AdvType":{
|
467 |
-
"p":0.
|
468 |
-
"r":0.
|
469 |
-
"f":0.
|
470 |
},
|
471 |
"PunctSide":{
|
472 |
-
"p":0.
|
473 |
-
"r":0.
|
474 |
-
"f":0.
|
475 |
},
|
476 |
"Number[psor]":{
|
477 |
-
"p":
|
478 |
"r":1.0,
|
479 |
-
"f":
|
480 |
},
|
481 |
"Polite":{
|
482 |
"p":1.0,
|
483 |
-
"r":0
|
484 |
-
"f":0
|
485 |
}
|
486 |
},
|
487 |
-
"sents_p":0.
|
488 |
-
"sents_r":0.
|
489 |
-
"sents_f":0.
|
490 |
-
"dep_uas":0.
|
491 |
-
"dep_las":0.
|
492 |
"dep_las_per_type":{
|
493 |
"nsubj":{
|
494 |
-
"p":0.
|
495 |
-
"r":0.
|
496 |
-
"f":0.
|
497 |
},
|
498 |
"flat":{
|
499 |
-
"p":0.
|
500 |
-
"r":0.
|
501 |
-
"f":0.
|
502 |
},
|
503 |
"case":{
|
504 |
-
"p":0.
|
505 |
-
"r":0.
|
506 |
-
"f":0.
|
507 |
},
|
508 |
"aux":{
|
509 |
-
"p":0.
|
510 |
-
"r":0.
|
511 |
-
"f":0.
|
512 |
},
|
513 |
"root":{
|
514 |
-
"p":0.
|
515 |
-
"r":0.
|
516 |
-
"f":0.
|
517 |
},
|
518 |
"nummod":{
|
519 |
-
"p":0.
|
520 |
-
"r":0.
|
521 |
-
"f":0.
|
522 |
},
|
523 |
"obj":{
|
524 |
-
"p":0.
|
525 |
-
"r":0.
|
526 |
-
"f":0.
|
527 |
},
|
528 |
"det":{
|
529 |
-
"p":0.
|
530 |
-
"r":0.
|
531 |
-
"f":0.
|
532 |
},
|
533 |
"nmod":{
|
534 |
-
"p":0.
|
535 |
-
"r":0.
|
536 |
-
"f":0.
|
537 |
},
|
538 |
"amod":{
|
539 |
-
"p":0.
|
540 |
-
"r":0.
|
541 |
-
"f":0.
|
542 |
},
|
543 |
"obl":{
|
544 |
-
"p":0.
|
545 |
-
"r":0.
|
546 |
-
"f":0.
|
547 |
},
|
548 |
"cc":{
|
549 |
-
"p":0.
|
550 |
-
"r":0.
|
551 |
-
"f":0.
|
552 |
},
|
553 |
"fixed":{
|
554 |
-
"p":0.
|
555 |
-
"r":0.
|
556 |
-
"f":0.
|
557 |
},
|
558 |
"conj":{
|
559 |
-
"p":0.
|
560 |
-
"r":0.
|
561 |
-
"f":0.
|
562 |
},
|
563 |
"advmod":{
|
564 |
-
"p":0.
|
565 |
-
"r":0.
|
566 |
-
"f":0.
|
567 |
},
|
568 |
"advcl":{
|
569 |
-
"p":0.
|
570 |
-
"r":0.
|
571 |
-
"f":0.
|
572 |
},
|
573 |
"compound":{
|
574 |
-
"p":0.
|
575 |
-
"r":0.
|
576 |
-
"f":0.
|
577 |
},
|
578 |
"mark":{
|
579 |
-
"p":0.
|
580 |
-
"r":0.
|
581 |
-
"f":0.
|
582 |
},
|
583 |
"cop":{
|
584 |
-
"p":0.
|
585 |
-
"r":0.
|
586 |
-
"f":0.
|
587 |
},
|
588 |
"ccomp":{
|
589 |
-
"p":0.
|
590 |
-
"r":0.
|
591 |
-
"f":0.
|
592 |
},
|
593 |
"acl":{
|
594 |
-
"p":0.
|
595 |
-
"r":0.
|
596 |
-
"f":0.
|
597 |
},
|
598 |
"expl:pass":{
|
599 |
-
"p":0.
|
600 |
-
"r":0.
|
601 |
-
"f":0.
|
602 |
},
|
603 |
"appos":{
|
604 |
-
"p":0.
|
605 |
-
"r":0.
|
606 |
-
"f":0.
|
607 |
},
|
608 |
"xcomp":{
|
609 |
-
"p":0.
|
610 |
-
"r":0.
|
611 |
-
"f":0.
|
612 |
},
|
613 |
"iobj":{
|
614 |
-
"p":0.
|
615 |
-
"r":0.
|
616 |
-
"f":0.
|
617 |
},
|
618 |
"dep":{
|
619 |
"p":0.0,
|
@@ -621,14 +621,14 @@
|
|
621 |
"f":0.0
|
622 |
},
|
623 |
"csubj":{
|
624 |
-
"p":0.
|
625 |
-
"r":0.
|
626 |
-
"f":0.
|
627 |
},
|
628 |
"parataxis":{
|
629 |
-
"p":0.
|
630 |
-
"r":0.
|
631 |
-
"f":0.
|
632 |
},
|
633 |
"nsubj:pass":{
|
634 |
"p":0.0,
|
@@ -641,34 +641,34 @@
|
|
641 |
"f":0.0
|
642 |
}
|
643 |
},
|
644 |
-
"tag_acc":0.
|
645 |
-
"lemma_acc":0.
|
646 |
-
"ents_p":0.
|
647 |
-
"ents_r":0.
|
648 |
-
"ents_f":0.
|
649 |
"ents_per_type":{
|
650 |
"ORG":{
|
651 |
-
"p":0.
|
652 |
-
"r":0.
|
653 |
-
"f":0.
|
654 |
},
|
655 |
"LOC":{
|
656 |
-
"p":0.
|
657 |
-
"r":0.
|
658 |
-
"f":0.
|
659 |
},
|
660 |
"MISC":{
|
661 |
-
"p":0.
|
662 |
-
"r":0.
|
663 |
-
"f":0.
|
664 |
},
|
665 |
"PER":{
|
666 |
-
"p":0.
|
667 |
-
"r":0.
|
668 |
-
"f":0.
|
669 |
}
|
670 |
},
|
671 |
-
"speed":
|
672 |
},
|
673 |
"sources":[
|
674 |
{
|
@@ -697,6 +697,6 @@
|
|
697 |
}
|
698 |
],
|
699 |
"requirements":[
|
700 |
-
"spacy-transformers>=
|
701 |
]
|
702 |
}
|
|
|
1 |
{
|
2 |
"lang":"ca",
|
3 |
"name":"core_news_trf",
|
4 |
+
"version":"3.7.2",
|
5 |
+
"description":"Catalan transformer pipeline (Transformer(name='projecte-aina/roberta-base-ca-v2', piece_encoder='byte-bpe', stride=112, type='roberta', width=768, window=144, vocab_size=50262)). Components: transformer, morphologizer, parser, ner, attribute_ruler, lemmatizer.",
|
6 |
"author":"Explosion",
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://explosion.ai",
|
9 |
"license":"GNU GPL 3.0",
|
10 |
+
"spacy_version":">=3.7.0,<3.8.0",
|
11 |
+
"spacy_git_version":"6b4f77441",
|
12 |
"vectors":{
|
13 |
"width":0,
|
14 |
"vectors":0,
|
|
|
372 |
"token_p":0.9978112128,
|
373 |
"token_r":0.9979488063,
|
374 |
"token_f":0.9978800048,
|
375 |
+
"pos_acc":0.9918845029,
|
376 |
+
"morph_acc":0.9900646831,
|
377 |
+
"morph_micro_p":0.997430458,
|
378 |
+
"morph_micro_r":0.9948740873,
|
379 |
+
"morph_micro_f":0.9961506326,
|
380 |
"morph_per_feat":{
|
381 |
"Mood":{
|
382 |
"p":0.9982771351,
|
|
|
384 |
"f":0.9981543005
|
385 |
},
|
386 |
"Number":{
|
387 |
+
"p":0.998884531,
|
388 |
+
"r":0.9963033413,
|
389 |
+
"f":0.9975922665
|
390 |
},
|
391 |
"Person":{
|
392 |
+
"p":0.9987604038,
|
393 |
"r":0.9973474801,
|
394 |
+
"f":0.9980534419
|
395 |
},
|
396 |
"Tense":{
|
397 |
+
"p":0.9937251621,
|
398 |
+
"r":0.9962256238,
|
399 |
+
"f":0.994973822
|
400 |
},
|
401 |
"VerbForm":{
|
402 |
+
"p":0.9977330311,
|
403 |
+
"r":0.9966697749,
|
404 |
+
"f":0.9972011196
|
405 |
},
|
406 |
"Gender":{
|
407 |
+
"p":0.9973378509,
|
408 |
+
"r":0.9922469421,
|
409 |
+
"f":0.9947858833
|
410 |
},
|
411 |
"NumType":{
|
412 |
+
"p":0.9706439394,
|
413 |
+
"r":0.9660697455,
|
414 |
+
"f":0.9683514407
|
415 |
},
|
416 |
"Definite":{
|
417 |
+
"p":0.9971922565,
|
418 |
+
"r":0.9941072481,
|
419 |
+
"f":0.9956473626
|
420 |
},
|
421 |
"PronType":{
|
422 |
+
"p":0.9965301286,
|
423 |
+
"r":0.9945101351,
|
424 |
+
"f":0.9955191072
|
425 |
},
|
426 |
"PunctType":{
|
427 |
+
"p":0.9998172181,
|
428 |
+
"r":0.9974471189,
|
429 |
+
"f":0.9986307622
|
430 |
},
|
431 |
"NumForm":{
|
432 |
+
"p":0.9819193324,
|
433 |
+
"r":0.9915730337,
|
434 |
+
"f":0.9867225716
|
435 |
},
|
436 |
"Polarity":{
|
437 |
"p":1.0,
|
438 |
+
"r":0.9902912621,
|
439 |
+
"f":0.9951219512
|
440 |
},
|
441 |
"Case":{
|
442 |
+
"p":0.9991652755,
|
443 |
+
"r":0.9966694421,
|
444 |
+
"f":0.9979157982
|
445 |
},
|
446 |
"PrepCase":{
|
447 |
+
"p":0.9986187845,
|
448 |
"r":0.9986187845,
|
449 |
+
"f":0.9986187845
|
450 |
},
|
451 |
"Reflex":{
|
452 |
"p":0.9986052999,
|
|
|
455 |
},
|
456 |
"Degree":{
|
457 |
"p":1.0,
|
458 |
+
"r":0.9929328622,
|
459 |
+
"f":0.9964539007
|
460 |
},
|
461 |
"Poss":{
|
462 |
"p":1.0,
|
463 |
+
"r":0.9914529915,
|
464 |
+
"f":0.9957081545
|
465 |
},
|
466 |
"AdvType":{
|
467 |
+
"p":0.9921875,
|
468 |
+
"r":0.9270072993,
|
469 |
+
"f":0.958490566
|
470 |
},
|
471 |
"PunctSide":{
|
472 |
+
"p":0.9975845411,
|
473 |
+
"r":0.9975845411,
|
474 |
+
"f":0.9975845411
|
475 |
},
|
476 |
"Number[psor]":{
|
477 |
+
"p":0.9411764706,
|
478 |
"r":1.0,
|
479 |
+
"f":0.9696969697
|
480 |
},
|
481 |
"Polite":{
|
482 |
"p":1.0,
|
483 |
+
"r":1.0,
|
484 |
+
"f":1.0
|
485 |
}
|
486 |
},
|
487 |
+
"sents_p":0.9947245018,
|
488 |
+
"sents_r":0.9929783499,
|
489 |
+
"sents_f":0.9938506589,
|
490 |
+
"dep_uas":0.9522584579,
|
491 |
+
"dep_las":0.9367199558,
|
492 |
"dep_las_per_type":{
|
493 |
"nsubj":{
|
494 |
+
"p":0.9610479145,
|
495 |
+
"r":0.9603858078,
|
496 |
+
"f":0.9607167471
|
497 |
},
|
498 |
"flat":{
|
499 |
+
"p":0.9334415584,
|
500 |
+
"r":0.9426229508,
|
501 |
+
"f":0.9380097879
|
502 |
},
|
503 |
"case":{
|
504 |
+
"p":0.9792044493,
|
505 |
+
"r":0.9737886257,
|
506 |
+
"f":0.9764890282
|
507 |
},
|
508 |
"aux":{
|
509 |
+
"p":0.9695512821,
|
510 |
+
"r":0.9690336359,
|
511 |
+
"f":0.9692923899
|
512 |
},
|
513 |
"root":{
|
514 |
+
"p":0.9730363423,
|
515 |
+
"r":0.9713282621,
|
516 |
+
"f":0.972181552
|
517 |
},
|
518 |
"nummod":{
|
519 |
+
"p":0.9326241135,
|
520 |
+
"r":0.926056338,
|
521 |
+
"f":0.9293286219
|
522 |
},
|
523 |
"obj":{
|
524 |
+
"p":0.931773399,
|
525 |
+
"r":0.9375464684,
|
526 |
+
"f":0.9346510191
|
527 |
},
|
528 |
"det":{
|
529 |
+
"p":0.9877590465,
|
530 |
+
"r":0.9876529955,
|
531 |
+
"f":0.9877060181
|
532 |
},
|
533 |
"nmod":{
|
534 |
+
"p":0.8882657463,
|
535 |
+
"r":0.8819875776,
|
536 |
+
"f":0.8851155293
|
537 |
},
|
538 |
"amod":{
|
539 |
+
"p":0.9682539683,
|
540 |
+
"r":0.9667924528,
|
541 |
+
"f":0.9675226586
|
542 |
},
|
543 |
"obl":{
|
544 |
+
"p":0.8433286843,
|
545 |
+
"r":0.8260473588,
|
546 |
+
"f":0.8345985737
|
547 |
},
|
548 |
"cc":{
|
549 |
+
"p":0.9579145729,
|
550 |
+
"r":0.9609325772,
|
551 |
+
"f":0.9594212016
|
552 |
},
|
553 |
"fixed":{
|
554 |
+
"p":0.932938856,
|
555 |
+
"r":0.9403578529,
|
556 |
+
"f":0.9366336634
|
557 |
},
|
558 |
"conj":{
|
559 |
+
"p":0.8519153802,
|
560 |
+
"r":0.8533791523,
|
561 |
+
"f":0.8526466381
|
562 |
},
|
563 |
"advmod":{
|
564 |
+
"p":0.8939393939,
|
565 |
+
"r":0.8928987194,
|
566 |
+
"f":0.8934187536
|
567 |
},
|
568 |
"advcl":{
|
569 |
+
"p":0.7478684531,
|
570 |
+
"r":0.7675,
|
571 |
+
"f":0.7575570635
|
572 |
},
|
573 |
"compound":{
|
574 |
+
"p":0.897810219,
|
575 |
+
"r":0.8880866426,
|
576 |
+
"f":0.8929219601
|
577 |
},
|
578 |
"mark":{
|
579 |
+
"p":0.9427235535,
|
580 |
+
"r":0.9438267993,
|
581 |
+
"f":0.9432748538
|
582 |
},
|
583 |
"cop":{
|
584 |
+
"p":0.9002123142,
|
585 |
+
"r":0.9177489177,
|
586 |
+
"f":0.9088960343
|
587 |
},
|
588 |
"ccomp":{
|
589 |
+
"p":0.8777292576,
|
590 |
+
"r":0.8993288591,
|
591 |
+
"f":0.8883977901
|
592 |
},
|
593 |
"acl":{
|
594 |
+
"p":0.8672397326,
|
595 |
+
"r":0.8747591522,
|
596 |
+
"f":0.8709832134
|
597 |
},
|
598 |
"expl:pass":{
|
599 |
+
"p":0.8611111111,
|
600 |
+
"r":0.6739130435,
|
601 |
+
"f":0.756097561
|
602 |
},
|
603 |
"appos":{
|
604 |
+
"p":0.8524590164,
|
605 |
+
"r":0.8600508906,
|
606 |
+
"f":0.8562381254
|
607 |
},
|
608 |
"xcomp":{
|
609 |
+
"p":0.9128329298,
|
610 |
+
"r":0.8849765258,
|
611 |
+
"f":0.8986889154
|
612 |
},
|
613 |
"iobj":{
|
614 |
+
"p":0.8670520231,
|
615 |
+
"r":0.8021390374,
|
616 |
+
"f":0.8333333333
|
617 |
},
|
618 |
"dep":{
|
619 |
"p":0.0,
|
|
|
621 |
"f":0.0
|
622 |
},
|
623 |
"csubj":{
|
624 |
+
"p":0.8125,
|
625 |
+
"r":0.858490566,
|
626 |
+
"f":0.8348623853
|
627 |
},
|
628 |
"parataxis":{
|
629 |
+
"p":0.8461538462,
|
630 |
+
"r":0.6470588235,
|
631 |
+
"f":0.7333333333
|
632 |
},
|
633 |
"nsubj:pass":{
|
634 |
"p":0.0,
|
|
|
641 |
"f":0.0
|
642 |
}
|
643 |
},
|
644 |
+
"tag_acc":0.9918845029,
|
645 |
+
"lemma_acc":0.9819043924,
|
646 |
+
"ents_p":0.9225996081,
|
647 |
+
"ents_r":0.9139437075,
|
648 |
+
"ents_f":0.9182512595,
|
649 |
"ents_per_type":{
|
650 |
"ORG":{
|
651 |
+
"p":0.9112107623,
|
652 |
+
"r":0.9161406673,
|
653 |
+
"f":0.9136690647
|
654 |
},
|
655 |
"LOC":{
|
656 |
+
"p":0.9353778751,
|
657 |
+
"r":0.9163090129,
|
658 |
+
"f":0.9257452575
|
659 |
},
|
660 |
"MISC":{
|
661 |
+
"p":0.8539944904,
|
662 |
+
"r":0.8093994778,
|
663 |
+
"f":0.8310991957
|
664 |
},
|
665 |
"PER":{
|
666 |
+
"p":0.9612518629,
|
667 |
+
"r":0.9670164918,
|
668 |
+
"f":0.9641255605
|
669 |
}
|
670 |
},
|
671 |
+
"speed":1944.0672670287
|
672 |
},
|
673 |
"sources":[
|
674 |
{
|
|
|
697 |
}
|
698 |
],
|
699 |
"requirements":[
|
700 |
+
"spacy-curated-transformers>=0.2.0,<0.3.0"
|
701 |
]
|
702 |
}
|
morphologizer/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 sha256:16b0e7dc5ca70f1dabbc604c2f8aa790fa883a13d636a670b110f4a4a677e484
|
3 |
+
size 871245
|
ner/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:f25e4338cd60f3d30b4801a8cd26ab2a684ae70be4620d616ddd6dd22d3b392e
|
3 |
+
size 226046
|
parser/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 sha256:636b1a25fb2efdbdb8f3716d9a3c3f0a6e1494938d51df9300e8e85b198868b8
|
3 |
+
size 460409
|
transformer/cfg
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
{
|
2 |
-
|
3 |
}
|
|
|
1 |
{
|
2 |
+
|
3 |
}
|
transformer/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:cb98b432634b701ebfa18a7a3e3b84860e58f29b07d88842f51febea4de0394f
|
3 |
+
size 497432290
|
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 sha256:33111f72872b678ee90b376a310c25a9762839a9d8a68ef47c723418c0812a76
|
3 |
+
size 733932
|