Update spacy pipeline to 3.6.0
Browse files- README.md +28 -28
- config.cfg +6 -4
- hu_core_news_lg-any-py3-none-any.whl +2 -2
- meta.json +187 -193
- morphologizer/cfg +1 -0
- morphologizer/model +1 -1
- ner/model +1 -1
- parser/model +1 -1
- senter/model +1 -1
- tagger/cfg +1 -0
- tagger/model +1 -1
- tok2vec/model +1 -1
- trainable_lemmatizer/model +1 -1
- vocab/strings.json +2 -2
- vocab/vectors.cfg +2 -1
README.md
CHANGED
@@ -14,74 +14,74 @@ 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 |
Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner
|
75 |
|
76 |
| Feature | Description |
|
77 |
| --- | --- |
|
78 |
| **Name** | `hu_core_news_lg` |
|
79 |
-
| **Version** | `3.
|
80 |
-
| **spaCy** | `>=3.
|
81 |
| **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `trainable_lemmatizer`, `parser`, `ner` |
|
82 |
| **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `trainable_lemmatizer`, `parser`, `ner` |
|
83 |
| **Vectors** | -1 keys, 200000 unique vectors (300 dimensions) |
|
84 |
-
| **Sources** | [UD Hungarian Szeged](https://universaldependencies.org/treebanks/hu_szeged/index.html) (Richárd Farkas, Katalin Simkó, Zsolt Szántó, Viktor Varga, Veronika Vincze (MTA-SZTE Research Group on Artificial Intelligence))<br />[NYTK-NerKor Corpus](https://github.com/nytud/NYTK-NerKor) (Eszter Simon, Noémi Vadász (Department of Language Technology and Applied Linguistics))<br />[
|
85 |
| **License** | `cc-by-sa-4.0` |
|
86 |
| **Author** | [SzegedAI, MILAB](https://github.com/huspacy/huspacy) |
|
87 |
|
@@ -108,18 +108,18 @@ Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morpholog
|
|
108 |
| `TOKEN_P` | 99.86 |
|
109 |
| `TOKEN_R` | 99.93 |
|
110 |
| `TOKEN_F` | 99.89 |
|
111 |
-
| `SENTS_P` |
|
112 |
-
| `SENTS_R` | 97.
|
113 |
-
| `SENTS_F` | 97.
|
114 |
-
| `TAG_ACC` | 96.
|
115 |
-
| `POS_ACC` | 96.
|
116 |
-
| `MORPH_ACC` |
|
117 |
-
| `MORPH_MICRO_P` | 96.
|
118 |
-
| `MORPH_MICRO_R` | 95.
|
119 |
-
| `MORPH_MICRO_F` | 96.
|
120 |
-
| `LEMMA_ACC` | 97.
|
121 |
-
| `DEP_UAS` |
|
122 |
-
| `DEP_LAS` |
|
123 |
-
| `ENTS_P` | 86.
|
124 |
-
| `ENTS_R` |
|
125 |
-
| `ENTS_F` |
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.8636042403
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.8593530239
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.8614733874
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.964256663
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9640652663
|
38 |
- task:
|
39 |
name: MORPH
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Morph (UFeats) Accuracy
|
43 |
type: accuracy
|
44 |
+
value: 0.9316681022
|
45 |
- task:
|
46 |
name: LEMMA
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Lemma Accuracy
|
50 |
type: accuracy
|
51 |
+
value: 0.9736867285
|
52 |
- task:
|
53 |
name: UNLABELED_DEPENDENCIES
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Unlabeled Attachment Score (UAS)
|
57 |
type: f_score
|
58 |
+
value: 0.8163795538
|
59 |
- task:
|
60 |
name: LABELED_DEPENDENCIES
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Labeled Attachment Score (LAS)
|
64 |
type: f_score
|
65 |
+
value: 0.7454391415
|
66 |
- task:
|
67 |
name: SENTS
|
68 |
type: token-classification
|
69 |
metrics:
|
70 |
- name: Sentences F-Score
|
71 |
type: f_score
|
72 |
+
value: 0.9776286353
|
73 |
---
|
74 |
Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner
|
75 |
|
76 |
| Feature | Description |
|
77 |
| --- | --- |
|
78 |
| **Name** | `hu_core_news_lg` |
|
79 |
+
| **Version** | `3.6.0` |
|
80 |
+
| **spaCy** | `>=3.6.0,<3.7.0` |
|
81 |
| **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `trainable_lemmatizer`, `parser`, `ner` |
|
82 |
| **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lookup_lemmatizer`, `trainable_lemmatizer`, `parser`, `ner` |
|
83 |
| **Vectors** | -1 keys, 200000 unique vectors (300 dimensions) |
|
84 |
+
| **Sources** | [UD Hungarian Szeged](https://universaldependencies.org/treebanks/hu_szeged/index.html) (Richárd Farkas, Katalin Simkó, Zsolt Szántó, Viktor Varga, Veronika Vincze (MTA-SZTE Research Group on Artificial Intelligence))<br />[NYTK-NerKor Corpus](https://github.com/nytud/NYTK-NerKor) (Eszter Simon, Noémi Vadász (Department of Language Technology and Applied Linguistics))<br />[Szeged NER Corpus](https://rgai.inf.u-szeged.hu/node/130) (György Szarvas, Richárd Farkas, László Felföldi, András Kocsor, János Csirik (MTA-SZTE Research Group on Artificial Intelligence))<br />[Hungarian lg Floret vectors](https://huggingface.co/huspacy/hu_vectors_web_lg) (Szeged AI) |
|
85 |
| **License** | `cc-by-sa-4.0` |
|
86 |
| **Author** | [SzegedAI, MILAB](https://github.com/huspacy/huspacy) |
|
87 |
|
|
|
108 |
| `TOKEN_P` | 99.86 |
|
109 |
| `TOKEN_R` | 99.93 |
|
110 |
| `TOKEN_F` | 99.89 |
|
111 |
+
| `SENTS_P` | 98.20 |
|
112 |
+
| `SENTS_R` | 97.33 |
|
113 |
+
| `SENTS_F` | 97.76 |
|
114 |
+
| `TAG_ACC` | 96.43 |
|
115 |
+
| `POS_ACC` | 96.41 |
|
116 |
+
| `MORPH_ACC` | 93.17 |
|
117 |
+
| `MORPH_MICRO_P` | 96.48 |
|
118 |
+
| `MORPH_MICRO_R` | 95.78 |
|
119 |
+
| `MORPH_MICRO_F` | 96.13 |
|
120 |
+
| `LEMMA_ACC` | 97.37 |
|
121 |
+
| `DEP_UAS` | 81.64 |
|
122 |
+
| `DEP_LAS` | 74.54 |
|
123 |
+
| `ENTS_P` | 86.36 |
|
124 |
+
| `ENTS_R` | 85.94 |
|
125 |
+
| `ENTS_F` | 86.15 |
|
config.cfg
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
[paths]
|
2 |
-
parser_model = "models/hu_core_news_lg-parser-3.
|
3 |
-
ner_model = "models/hu_core_news_lg-ner-3.
|
4 |
-
lemmatizer_lookups = "models/hu_core_news_lg-lookup-lemmatizer-3.
|
5 |
-
tagger_model = "models/hu_core_news_lg-tagger-3.
|
6 |
train = null
|
7 |
dev = null
|
8 |
vectors = null
|
@@ -32,6 +32,7 @@ source = ${paths.lemmatizer_lookups}
|
|
32 |
[components.morphologizer]
|
33 |
factory = "morphologizer"
|
34 |
extend = false
|
|
|
35 |
overwrite = true
|
36 |
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
37 |
|
@@ -118,6 +119,7 @@ upstream = "*"
|
|
118 |
|
119 |
[components.tagger]
|
120 |
factory = "tagger"
|
|
|
121 |
neg_prefix = "!"
|
122 |
overwrite = false
|
123 |
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
|
|
1 |
[paths]
|
2 |
+
parser_model = "models/hu_core_news_lg-parser-3.6.0/model-best"
|
3 |
+
ner_model = "models/hu_core_news_lg-ner-3.6.0/model-best"
|
4 |
+
lemmatizer_lookups = "models/hu_core_news_lg-lookup-lemmatizer-3.6.0"
|
5 |
+
tagger_model = "models/hu_core_news_lg-tagger-3.6.0/model-best"
|
6 |
train = null
|
7 |
dev = null
|
8 |
vectors = null
|
|
|
32 |
[components.morphologizer]
|
33 |
factory = "morphologizer"
|
34 |
extend = false
|
35 |
+
label_smoothing = 0.0
|
36 |
overwrite = true
|
37 |
scorer = {"@scorers":"spacy.morphologizer_scorer.v1"}
|
38 |
|
|
|
119 |
|
120 |
[components.tagger]
|
121 |
factory = "tagger"
|
122 |
+
label_smoothing = 0.0
|
123 |
neg_prefix = "!"
|
124 |
overwrite = false
|
125 |
scorer = {"@scorers":"spacy.tagger_scorer.v1"}
|
hu_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 sha256:8f18cfe459ea0cbdccee0dcb624defd4cc23459940d4ef1803e6a24fb0f76d6d
|
3 |
+
size 401395351
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"hu",
|
3 |
"name":"core_news_lg",
|
4 |
-
"version":"3.
|
5 |
"description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
|
6 |
"author":"SzegedAI, MILAB",
|
7 |
"email":"gyorgy@orosz.link",
|
8 |
"url":"https://github.com/huspacy/huspacy",
|
9 |
"license":"cc-by-sa-4.0",
|
10 |
-
"spacy_version":">=3.
|
11 |
-
"spacy_git_version":"
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":200000,
|
@@ -1268,85 +1268,90 @@
|
|
1268 |
"token_p":0.998565417,
|
1269 |
"token_r":0.9993300153,
|
1270 |
"token_f":0.9989475698,
|
1271 |
-
"sents_p":0.
|
1272 |
-
"sents_r":0.
|
1273 |
-
"sents_f":0.
|
1274 |
-
"tag_acc":0.
|
1275 |
-
"pos_acc":0.
|
1276 |
-
"morph_acc":0.
|
1277 |
-
"morph_micro_p":0.
|
1278 |
-
"morph_micro_r":0.
|
1279 |
-
"morph_micro_f":0.
|
1280 |
"morph_per_feat":{
|
1281 |
"Definite":{
|
1282 |
-
"p":0.
|
1283 |
-
"r":0.
|
1284 |
-
"f":0.
|
1285 |
},
|
1286 |
"PronType":{
|
1287 |
-
"p":0.
|
1288 |
-
"r":0.
|
1289 |
-
"f":0.
|
1290 |
},
|
1291 |
"Case":{
|
1292 |
-
"p":0.
|
1293 |
-
"r":0.
|
1294 |
-
"f":0.
|
1295 |
},
|
1296 |
"Degree":{
|
1297 |
-
"p":0.
|
1298 |
-
"r":0.
|
1299 |
-
"f":0.
|
1300 |
},
|
1301 |
"Number":{
|
1302 |
-
"p":0.
|
1303 |
-
"r":0.
|
1304 |
-
"f":0.
|
1305 |
},
|
1306 |
"Mood":{
|
1307 |
-
"p":0.
|
1308 |
-
"r":0.
|
1309 |
-
"f":0.
|
1310 |
},
|
1311 |
"Person":{
|
1312 |
-
"p":0.
|
1313 |
-
"r":0.
|
1314 |
-
"f":0.
|
1315 |
},
|
1316 |
"Tense":{
|
1317 |
-
"p":0.
|
1318 |
-
"r":0.
|
1319 |
-
"f":0.
|
1320 |
},
|
1321 |
"VerbForm":{
|
1322 |
-
"p":0.
|
1323 |
-
"r":0.
|
1324 |
-
"f":0.
|
1325 |
},
|
1326 |
"Voice":{
|
1327 |
-
"p":0.
|
1328 |
-
"r":0.
|
1329 |
-
"f":0.
|
1330 |
},
|
1331 |
"Number[psor]":{
|
1332 |
-
"p":0.
|
1333 |
-
"r":0.
|
1334 |
-
"f":0.
|
1335 |
},
|
1336 |
"Person[psor]":{
|
1337 |
-
"p":0.
|
1338 |
-
"r":0.
|
1339 |
-
"f":0.
|
1340 |
},
|
1341 |
"NumType":{
|
1342 |
-
"p":0.
|
1343 |
-
"r":0.
|
1344 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
1345 |
},
|
1346 |
"Reflex":{
|
1347 |
"p":1.0,
|
1348 |
-
"r":0.
|
1349 |
-
"f":0.
|
1350 |
},
|
1351 |
"Aspect":{
|
1352 |
"p":0.0,
|
@@ -1357,121 +1362,116 @@
|
|
1357 |
"p":0.0,
|
1358 |
"r":0.0,
|
1359 |
"f":0.0
|
1360 |
-
},
|
1361 |
-
"Poss":{
|
1362 |
-
"p":1.0,
|
1363 |
-
"r":1.0,
|
1364 |
-
"f":1.0
|
1365 |
}
|
1366 |
},
|
1367 |
-
"lemma_acc":0.
|
1368 |
-
"dep_uas":0.
|
1369 |
-
"dep_las":0.
|
1370 |
"dep_las_per_type":{
|
1371 |
"det":{
|
1372 |
-
"p":0.
|
1373 |
-
"r":0.
|
1374 |
-
"f":0.
|
1375 |
},
|
1376 |
"amod:att":{
|
1377 |
-
"p":0.
|
1378 |
-
"r":0.
|
1379 |
-
"f":0.
|
1380 |
},
|
1381 |
"nsubj":{
|
1382 |
-
"p":0.
|
1383 |
-
"r":0.
|
1384 |
-
"f":0.
|
1385 |
},
|
1386 |
"advmod:mode":{
|
1387 |
-
"p":0.
|
1388 |
-
"r":0.
|
1389 |
-
"f":0.
|
1390 |
},
|
1391 |
"nmod:att":{
|
1392 |
-
"p":0.
|
1393 |
-
"r":0.
|
1394 |
-
"f":0.
|
1395 |
},
|
1396 |
"obl":{
|
1397 |
-
"p":0.
|
1398 |
-
"r":0.
|
1399 |
-
"f":0.
|
1400 |
},
|
1401 |
"obj":{
|
1402 |
-
"p":0.
|
1403 |
-
"r":0.
|
1404 |
-
"f":0.
|
1405 |
},
|
1406 |
"root":{
|
1407 |
-
"p":0.
|
1408 |
-
"r":0.
|
1409 |
-
"f":0.
|
1410 |
},
|
1411 |
"cc":{
|
1412 |
-
"p":0.
|
1413 |
-
"r":0.
|
1414 |
-
"f":0.
|
1415 |
},
|
1416 |
"conj":{
|
1417 |
-
"p":0.
|
1418 |
-
"r":0.
|
1419 |
-
"f":0.
|
1420 |
},
|
1421 |
"advmod":{
|
1422 |
-
"p":0.
|
1423 |
-
"r":0.
|
1424 |
-
"f":0.
|
1425 |
},
|
1426 |
"flat:name":{
|
1427 |
-
"p":0.
|
1428 |
-
"r":0.
|
1429 |
-
"f":0.
|
1430 |
},
|
1431 |
"appos":{
|
1432 |
-
"p":0.
|
1433 |
-
"r":0.
|
1434 |
-
"f":0.
|
1435 |
},
|
1436 |
"advcl":{
|
1437 |
-
"p":0.
|
1438 |
-
"r":0.
|
1439 |
-
"f":0.
|
1440 |
},
|
1441 |
"advmod:tlocy":{
|
1442 |
-
"p":0.
|
1443 |
-
"r":0.
|
1444 |
-
"f":0.
|
1445 |
},
|
1446 |
"ccomp:obj":{
|
1447 |
-
"p":0.
|
1448 |
-
"r":0.
|
1449 |
-
"f":0.
|
1450 |
},
|
1451 |
"mark":{
|
1452 |
-
"p":0.
|
1453 |
-
"r":0.
|
1454 |
-
"f":0.
|
1455 |
},
|
1456 |
"compound:preverb":{
|
1457 |
-
"p":0.
|
1458 |
-
"r":0.
|
1459 |
-
"f":0.
|
1460 |
},
|
1461 |
"advmod:locy":{
|
1462 |
-
"p":0.
|
1463 |
-
"r":0.
|
1464 |
-
"f":0.
|
1465 |
},
|
1466 |
"cop":{
|
1467 |
-
"p":0.
|
1468 |
-
"r":0.
|
1469 |
-
"f":0.
|
1470 |
},
|
1471 |
"nmod:obl":{
|
1472 |
-
"p":0.
|
1473 |
-
"r":0.
|
1474 |
-
"f":0.
|
1475 |
},
|
1476 |
"advmod:to":{
|
1477 |
"p":0.0,
|
@@ -1479,54 +1479,54 @@
|
|
1479 |
"f":0.0
|
1480 |
},
|
1481 |
"obj:lvc":{
|
1482 |
-
"p":0.
|
1483 |
-
"r":0.
|
1484 |
-
"f":0.
|
1485 |
},
|
1486 |
"ccomp:obl":{
|
1487 |
-
"p":0.
|
1488 |
-
"r":0.
|
1489 |
-
"f":0.
|
1490 |
},
|
1491 |
-
"
|
1492 |
-
"p":0.
|
1493 |
-
"r":0.
|
1494 |
-
"f":0.
|
1495 |
},
|
1496 |
"csubj":{
|
1497 |
-
"p":0.
|
1498 |
-
"r":0.
|
1499 |
-
"f":0.
|
1500 |
},
|
1501 |
"parataxis":{
|
1502 |
-
"p":0.
|
1503 |
-
"r":0.
|
1504 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1505 |
},
|
1506 |
"dep":{
|
1507 |
"p":0.0,
|
1508 |
"r":0.0,
|
1509 |
"f":0.0
|
1510 |
},
|
1511 |
-
"case":{
|
1512 |
-
"p":0.9090909091,
|
1513 |
-
"r":0.9183673469,
|
1514 |
-
"f":0.9137055838
|
1515 |
-
},
|
1516 |
-
"xcomp":{
|
1517 |
-
"p":0.7948717949,
|
1518 |
-
"r":0.8378378378,
|
1519 |
-
"f":0.8157894737
|
1520 |
-
},
|
1521 |
-
"nummod":{
|
1522 |
-
"p":0.5421686747,
|
1523 |
-
"r":0.4838709677,
|
1524 |
-
"f":0.5113636364
|
1525 |
-
},
|
1526 |
"acl":{
|
1527 |
-
"p":0.
|
1528 |
-
"r":0.
|
1529 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
1530 |
},
|
1531 |
"advmod:tto":{
|
1532 |
"p":0.6666666667,
|
@@ -1534,14 +1534,14 @@
|
|
1534 |
"f":0.3076923077
|
1535 |
},
|
1536 |
"nmod":{
|
1537 |
-
"p":0.
|
1538 |
"r":0.0909090909,
|
1539 |
-
"f":0.
|
1540 |
},
|
1541 |
"aux":{
|
1542 |
-
"p":0
|
1543 |
-
"r":0.
|
1544 |
-
"f":0.
|
1545 |
},
|
1546 |
"advmod:tfrom":{
|
1547 |
"p":0.0,
|
@@ -1554,9 +1554,9 @@
|
|
1554 |
"f":0.0
|
1555 |
},
|
1556 |
"compound":{
|
1557 |
-
"p":0.
|
1558 |
-
"r":0.
|
1559 |
-
"f":0.
|
1560 |
},
|
1561 |
"obl:lvc":{
|
1562 |
"p":0.0,
|
@@ -1584,9 +1584,9 @@
|
|
1584 |
"f":0.0
|
1585 |
},
|
1586 |
"advmod:que":{
|
1587 |
-
"p":
|
1588 |
-
"r":0.
|
1589 |
-
"f":0.
|
1590 |
},
|
1591 |
"ccomp:pred":{
|
1592 |
"p":0.0,
|
@@ -1594,32 +1594,32 @@
|
|
1594 |
"f":0.0
|
1595 |
}
|
1596 |
},
|
1597 |
-
"ents_p":0.
|
1598 |
-
"ents_r":0.
|
1599 |
-
"ents_f":0.
|
1600 |
"ents_per_type":{
|
1601 |
"ORG":{
|
1602 |
-
"p":0.
|
1603 |
-
"r":0.
|
1604 |
-
"f":0.
|
1605 |
},
|
1606 |
"PER":{
|
1607 |
-
"p":0.
|
1608 |
-
"r":0.
|
1609 |
-
"f":0.
|
1610 |
},
|
1611 |
"LOC":{
|
1612 |
-
"p":0.
|
1613 |
"r":0.8506944444,
|
1614 |
-
"f":0.
|
1615 |
},
|
1616 |
"MISC":{
|
1617 |
-
"p":0.
|
1618 |
-
"r":0.
|
1619 |
-
"f":0.
|
1620 |
}
|
1621 |
},
|
1622 |
-
"speed":
|
1623 |
},
|
1624 |
"sources":[
|
1625 |
{
|
@@ -1634,12 +1634,6 @@
|
|
1634 |
"license":"CC BY-SA 4.0",
|
1635 |
"author":"Eszter Simon, No\u00e9mi Vad\u00e1sz (Department of Language Technology and Applied Linguistics)"
|
1636 |
},
|
1637 |
-
{
|
1638 |
-
"name":"hunNERwiki",
|
1639 |
-
"url":"http://hlt.sztaki.hu/resources/hunnerwiki.html",
|
1640 |
-
"license":"CC-BY-SA-3.0",
|
1641 |
-
"author":"Eszter Simon, D\u00e1vid M\u00e1rk Nemeskey (HLT Group, Budapest University of Technology and Economics)"
|
1642 |
-
},
|
1643 |
{
|
1644 |
"name":"Szeged NER Corpus",
|
1645 |
"url":"https://rgai.inf.u-szeged.hu/node/130",
|
@@ -1647,10 +1641,10 @@
|
|
1647 |
"author":"Gy\u00f6rgy Szarvas, Rich\u00e1rd Farkas, L\u00e1szl\u00f3 Felf\u00f6ldi, Andr\u00e1s Kocsor, J\u00e1nos Csirik (MTA-SZTE Research Group on Artificial Intelligence)"
|
1648 |
},
|
1649 |
{
|
1650 |
-
"name":"
|
1651 |
-
"url":"https://
|
1652 |
"license":"CC-BY-SA-4.0",
|
1653 |
-
"author":"
|
1654 |
}
|
1655 |
],
|
1656 |
"requirements":[
|
|
|
1 |
{
|
2 |
"lang":"hu",
|
3 |
"name":"core_news_lg",
|
4 |
+
"version":"3.6.0",
|
5 |
"description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
|
6 |
"author":"SzegedAI, MILAB",
|
7 |
"email":"gyorgy@orosz.link",
|
8 |
"url":"https://github.com/huspacy/huspacy",
|
9 |
"license":"cc-by-sa-4.0",
|
10 |
+
"spacy_version":">=3.6.0,<3.7.0",
|
11 |
+
"spacy_git_version":"6fc153a26",
|
12 |
"vectors":{
|
13 |
"width":300,
|
14 |
"vectors":200000,
|
|
|
1268 |
"token_p":0.998565417,
|
1269 |
"token_r":0.9993300153,
|
1270 |
"token_f":0.9989475698,
|
1271 |
+
"sents_p":0.9820224719,
|
1272 |
+
"sents_r":0.9732739421,
|
1273 |
+
"sents_f":0.9776286353,
|
1274 |
+
"tag_acc":0.964256663,
|
1275 |
+
"pos_acc":0.9640652663,
|
1276 |
+
"morph_acc":0.9316681022,
|
1277 |
+
"morph_micro_p":0.9648484848,
|
1278 |
+
"morph_micro_r":0.9577997422,
|
1279 |
+
"morph_micro_f":0.9613111926,
|
1280 |
"morph_per_feat":{
|
1281 |
"Definite":{
|
1282 |
+
"p":0.9579908676,
|
1283 |
+
"r":0.9790013999,
|
1284 |
+
"f":0.9683821832
|
1285 |
},
|
1286 |
"PronType":{
|
1287 |
+
"p":0.9712707182,
|
1288 |
+
"r":0.9701986755,
|
1289 |
+
"f":0.9707344009
|
1290 |
},
|
1291 |
"Case":{
|
1292 |
+
"p":0.9725835501,
|
1293 |
+
"r":0.9602845287,
|
1294 |
+
"f":0.9663949095
|
1295 |
},
|
1296 |
"Degree":{
|
1297 |
+
"p":0.9126637555,
|
1298 |
+
"r":0.8693843594,
|
1299 |
+
"f":0.8904985087
|
1300 |
},
|
1301 |
"Number":{
|
1302 |
+
"p":0.9851351351,
|
1303 |
+
"r":0.9773755656,
|
1304 |
+
"f":0.9812400101
|
1305 |
},
|
1306 |
"Mood":{
|
1307 |
+
"p":0.9326818675,
|
1308 |
+
"r":0.9523281596,
|
1309 |
+
"f":0.942402633
|
1310 |
},
|
1311 |
"Person":{
|
1312 |
+
"p":0.9488026424,
|
1313 |
+
"r":0.9449013158,
|
1314 |
+
"f":0.9468479604
|
1315 |
},
|
1316 |
"Tense":{
|
1317 |
+
"p":0.9543973941,
|
1318 |
+
"r":0.9712707182,
|
1319 |
+
"f":0.9627601314
|
1320 |
},
|
1321 |
"VerbForm":{
|
1322 |
+
"p":0.950166113,
|
1323 |
+
"r":0.9174017642,
|
1324 |
+
"f":0.933496532
|
1325 |
},
|
1326 |
"Voice":{
|
1327 |
+
"p":0.9508525577,
|
1328 |
+
"r":0.9693251534,
|
1329 |
+
"f":0.96
|
1330 |
},
|
1331 |
"Number[psor]":{
|
1332 |
+
"p":0.9708029197,
|
1333 |
+
"r":0.9472934473,
|
1334 |
+
"f":0.9589041096
|
1335 |
},
|
1336 |
"Person[psor]":{
|
1337 |
+
"p":0.9722627737,
|
1338 |
+
"r":0.9500713267,
|
1339 |
+
"f":0.961038961
|
1340 |
},
|
1341 |
"NumType":{
|
1342 |
+
"p":0.9305210918,
|
1343 |
+
"r":0.9146341463,
|
1344 |
+
"f":0.9225092251
|
1345 |
+
},
|
1346 |
+
"Poss":{
|
1347 |
+
"p":0.75,
|
1348 |
+
"r":1.0,
|
1349 |
+
"f":0.8571428571
|
1350 |
},
|
1351 |
"Reflex":{
|
1352 |
"p":1.0,
|
1353 |
+
"r":0.875,
|
1354 |
+
"f":0.9333333333
|
1355 |
},
|
1356 |
"Aspect":{
|
1357 |
"p":0.0,
|
|
|
1362 |
"p":0.0,
|
1363 |
"r":0.0,
|
1364 |
"f":0.0
|
|
|
|
|
|
|
|
|
|
|
1365 |
}
|
1366 |
},
|
1367 |
+
"lemma_acc":0.9736867285,
|
1368 |
+
"dep_uas":0.8163795538,
|
1369 |
+
"dep_las":0.7454391415,
|
1370 |
"dep_las_per_type":{
|
1371 |
"det":{
|
1372 |
+
"p":0.8554125662,
|
1373 |
+
"r":0.8996815287,
|
1374 |
+
"f":0.8769887466
|
1375 |
},
|
1376 |
"amod:att":{
|
1377 |
+
"p":0.8253968254,
|
1378 |
+
"r":0.8503679477,
|
1379 |
+
"f":0.8376963351
|
1380 |
},
|
1381 |
"nsubj":{
|
1382 |
+
"p":0.7557755776,
|
1383 |
+
"r":0.715625,
|
1384 |
+
"f":0.735152488
|
1385 |
},
|
1386 |
"advmod:mode":{
|
1387 |
+
"p":0.6124031008,
|
1388 |
+
"r":0.5808823529,
|
1389 |
+
"f":0.5962264151
|
1390 |
},
|
1391 |
"nmod:att":{
|
1392 |
+
"p":0.8036697248,
|
1393 |
+
"r":0.7423728814,
|
1394 |
+
"f":0.7718061674
|
1395 |
},
|
1396 |
"obl":{
|
1397 |
+
"p":0.7622005324,
|
1398 |
+
"r":0.7731773177,
|
1399 |
+
"f":0.7676496872
|
1400 |
},
|
1401 |
"obj":{
|
1402 |
+
"p":0.842920354,
|
1403 |
+
"r":0.8561797753,
|
1404 |
+
"f":0.8494983278
|
1405 |
},
|
1406 |
"root":{
|
1407 |
+
"p":0.806741573,
|
1408 |
+
"r":0.7995545657,
|
1409 |
+
"f":0.8031319911
|
1410 |
},
|
1411 |
"cc":{
|
1412 |
+
"p":0.6993318486,
|
1413 |
+
"r":0.6610526316,
|
1414 |
+
"f":0.6796536797
|
1415 |
},
|
1416 |
"conj":{
|
1417 |
+
"p":0.5103448276,
|
1418 |
+
"r":0.4625,
|
1419 |
+
"f":0.4852459016
|
1420 |
},
|
1421 |
"advmod":{
|
1422 |
+
"p":0.7572815534,
|
1423 |
+
"r":0.8210526316,
|
1424 |
+
"f":0.7878787879
|
1425 |
},
|
1426 |
"flat:name":{
|
1427 |
+
"p":0.7791164659,
|
1428 |
+
"r":0.9065420561,
|
1429 |
+
"f":0.838012959
|
1430 |
},
|
1431 |
"appos":{
|
1432 |
+
"p":0.4426229508,
|
1433 |
+
"r":0.2872340426,
|
1434 |
+
"f":0.3483870968
|
1435 |
},
|
1436 |
"advcl":{
|
1437 |
+
"p":0.3186813187,
|
1438 |
+
"r":0.2959183673,
|
1439 |
+
"f":0.3068783069
|
1440 |
},
|
1441 |
"advmod:tlocy":{
|
1442 |
+
"p":0.7327586207,
|
1443 |
+
"r":0.7391304348,
|
1444 |
+
"f":0.7359307359
|
1445 |
},
|
1446 |
"ccomp:obj":{
|
1447 |
+
"p":0.2105263158,
|
1448 |
+
"r":0.3636363636,
|
1449 |
+
"f":0.2666666667
|
1450 |
},
|
1451 |
"mark":{
|
1452 |
+
"p":0.7701863354,
|
1453 |
+
"r":0.7848101266,
|
1454 |
+
"f":0.7774294671
|
1455 |
},
|
1456 |
"compound:preverb":{
|
1457 |
+
"p":0.9026548673,
|
1458 |
+
"r":0.9357798165,
|
1459 |
+
"f":0.9189189189
|
1460 |
},
|
1461 |
"advmod:locy":{
|
1462 |
+
"p":0.652173913,
|
1463 |
+
"r":0.46875,
|
1464 |
+
"f":0.5454545455
|
1465 |
},
|
1466 |
"cop":{
|
1467 |
+
"p":0.6666666667,
|
1468 |
+
"r":0.6829268293,
|
1469 |
+
"f":0.6746987952
|
1470 |
},
|
1471 |
"nmod:obl":{
|
1472 |
+
"p":0.2962962963,
|
1473 |
+
"r":0.2,
|
1474 |
+
"f":0.2388059701
|
1475 |
},
|
1476 |
"advmod:to":{
|
1477 |
"p":0.0,
|
|
|
1479 |
"f":0.0
|
1480 |
},
|
1481 |
"obj:lvc":{
|
1482 |
+
"p":0.0,
|
1483 |
+
"r":0.0,
|
1484 |
+
"f":0.0
|
1485 |
},
|
1486 |
"ccomp:obl":{
|
1487 |
+
"p":0.3684210526,
|
1488 |
+
"r":0.21875,
|
1489 |
+
"f":0.2745098039
|
1490 |
},
|
1491 |
+
"case":{
|
1492 |
+
"p":0.9468085106,
|
1493 |
+
"r":0.9081632653,
|
1494 |
+
"f":0.9270833333
|
1495 |
},
|
1496 |
"csubj":{
|
1497 |
+
"p":0.4375,
|
1498 |
+
"r":0.1891891892,
|
1499 |
+
"f":0.2641509434
|
1500 |
},
|
1501 |
"parataxis":{
|
1502 |
+
"p":0.1612903226,
|
1503 |
+
"r":0.0684931507,
|
1504 |
+
"f":0.0961538462
|
1505 |
+
},
|
1506 |
+
"xcomp":{
|
1507 |
+
"p":0.8472222222,
|
1508 |
+
"r":0.8243243243,
|
1509 |
+
"f":0.8356164384
|
1510 |
+
},
|
1511 |
+
"nummod":{
|
1512 |
+
"p":0.6111111111,
|
1513 |
+
"r":0.4731182796,
|
1514 |
+
"f":0.5333333333
|
1515 |
},
|
1516 |
"dep":{
|
1517 |
"p":0.0,
|
1518 |
"r":0.0,
|
1519 |
"f":0.0
|
1520 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1521 |
"acl":{
|
1522 |
+
"p":0.3043478261,
|
1523 |
+
"r":0.2916666667,
|
1524 |
+
"f":0.2978723404
|
1525 |
+
},
|
1526 |
+
"iobj":{
|
1527 |
+
"p":0.0,
|
1528 |
+
"r":0.0,
|
1529 |
+
"f":0.0
|
1530 |
},
|
1531 |
"advmod:tto":{
|
1532 |
"p":0.6666666667,
|
|
|
1534 |
"f":0.3076923077
|
1535 |
},
|
1536 |
"nmod":{
|
1537 |
+
"p":0.1666666667,
|
1538 |
"r":0.0909090909,
|
1539 |
+
"f":0.1176470588
|
1540 |
},
|
1541 |
"aux":{
|
1542 |
+
"p":1.0,
|
1543 |
+
"r":0.6666666667,
|
1544 |
+
"f":0.8
|
1545 |
},
|
1546 |
"advmod:tfrom":{
|
1547 |
"p":0.0,
|
|
|
1554 |
"f":0.0
|
1555 |
},
|
1556 |
"compound":{
|
1557 |
+
"p":0.8666666667,
|
1558 |
+
"r":0.975,
|
1559 |
+
"f":0.9176470588
|
1560 |
},
|
1561 |
"obl:lvc":{
|
1562 |
"p":0.0,
|
|
|
1584 |
"f":0.0
|
1585 |
},
|
1586 |
"advmod:que":{
|
1587 |
+
"p":0.0,
|
1588 |
+
"r":0.0,
|
1589 |
+
"f":0.0
|
1590 |
},
|
1591 |
"ccomp:pred":{
|
1592 |
"p":0.0,
|
|
|
1594 |
"f":0.0
|
1595 |
}
|
1596 |
},
|
1597 |
+
"ents_p":0.8636042403,
|
1598 |
+
"ents_r":0.8593530239,
|
1599 |
+
"ents_f":0.8614733874,
|
1600 |
"ents_per_type":{
|
1601 |
"ORG":{
|
1602 |
+
"p":0.8953974895,
|
1603 |
+
"r":0.892906815,
|
1604 |
+
"f":0.8941504178
|
1605 |
},
|
1606 |
"PER":{
|
1607 |
+
"p":0.8699830413,
|
1608 |
+
"r":0.9193548387,
|
1609 |
+
"f":0.8939878013
|
1610 |
},
|
1611 |
"LOC":{
|
1612 |
+
"p":0.8781362007,
|
1613 |
"r":0.8506944444,
|
1614 |
+
"f":0.8641975309
|
1615 |
},
|
1616 |
"MISC":{
|
1617 |
+
"p":0.7099358974,
|
1618 |
+
"r":0.6283687943,
|
1619 |
+
"f":0.6666666667
|
1620 |
}
|
1621 |
},
|
1622 |
+
"speed":901.0325291331
|
1623 |
},
|
1624 |
"sources":[
|
1625 |
{
|
|
|
1634 |
"license":"CC BY-SA 4.0",
|
1635 |
"author":"Eszter Simon, No\u00e9mi Vad\u00e1sz (Department of Language Technology and Applied Linguistics)"
|
1636 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
1637 |
{
|
1638 |
"name":"Szeged NER Corpus",
|
1639 |
"url":"https://rgai.inf.u-szeged.hu/node/130",
|
|
|
1641 |
"author":"Gy\u00f6rgy Szarvas, Rich\u00e1rd Farkas, L\u00e1szl\u00f3 Felf\u00f6ldi, Andr\u00e1s Kocsor, J\u00e1nos Csirik (MTA-SZTE Research Group on Artificial Intelligence)"
|
1642 |
},
|
1643 |
{
|
1644 |
+
"name":"Hungarian lg Floret vectors",
|
1645 |
+
"url":"https://huggingface.co/huspacy/hu_vectors_web_lg",
|
1646 |
"license":"CC-BY-SA-4.0",
|
1647 |
+
"author":"Szeged AI"
|
1648 |
}
|
1649 |
],
|
1650 |
"requirements":[
|
morphologizer/cfg
CHANGED
@@ -1,5 +1,6 @@
|
|
1 |
{
|
2 |
"extend":false,
|
|
|
3 |
"labels_morph":{
|
4 |
"Definite=Def|POS=DET|PronType=Art":"Definite=Def|PronType=Art",
|
5 |
"Case=Ine|Number=Sing|POS=NOUN":"Case=Ine|Number=Sing",
|
|
|
1 |
{
|
2 |
"extend":false,
|
3 |
+
"label_smoothing":0.0,
|
4 |
"labels_morph":{
|
5 |
"Definite=Def|POS=DET|PronType=Art":"Definite=Def|PronType=Art",
|
6 |
"Case=Ine|Number=Sing|POS=NOUN":"Case=Ine|Number=Sing",
|
morphologizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1379030
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:19646b3038a0758c374f45ec4672ed54cdc468fbeacbad4d3b9075092a5c8529
|
3 |
size 1379030
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56989063
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a2ea09876719885709fb906c812cbfcc4ed4549056b415d6ab627f3811dbaa1
|
3 |
size 56989063
|
parser/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 26010735
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c9faebc55d312e2e1b98b2b118e47145563123f788c619cf3c6301c7ddd31e0
|
3 |
size 26010735
|
senter/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2845
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f028f27d316a6a9d513f27769200316f1d691a112a4b16253592dbd10789158d
|
3 |
size 2845
|
tagger/cfg
CHANGED
@@ -1,4 +1,5 @@
|
|
1 |
{
|
|
|
2 |
"labels":[
|
3 |
"ADJ",
|
4 |
"ADP",
|
|
|
1 |
{
|
2 |
+
"label_smoothing":0.0,
|
3 |
"labels":[
|
4 |
"ADJ",
|
5 |
"ADP",
|
tagger/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20905
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5343a2575e4e3f902f4753fd6a6b8bc61258b2d83f47d57baba684f1b71084e3
|
3 |
size 20905
|
tok2vec/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56806299
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55093574bbfc26486020ca0de33e8e1e92f6f58ea68e58b086d20eb79fa55ac5
|
3 |
size 56806299
|
trainable_lemmatizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 61643136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9b88a18f7e6e0950d64532696fbeb0da25566cc4a4c2a6370bd333b26980377d
|
3 |
size 61643136
|
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 sha256:578a7114ebd95230499087da9ca620a5ddfb83a4d47155461531e1871435a3a6
|
3 |
+
size 6402680
|
vocab/vectors.cfg
CHANGED
@@ -5,5 +5,6 @@
|
|
5 |
"hash_count":2,
|
6 |
"hash_seed":2166136261,
|
7 |
"bow":"<",
|
8 |
-
"eow":">"
|
|
|
9 |
}
|
|
|
5 |
"hash_count":2,
|
6 |
"hash_seed":2166136261,
|
7 |
"bow":"<",
|
8 |
+
"eow":">",
|
9 |
+
"attr":65
|
10 |
}
|