Update spacy pipeline to 3.6.0
Browse files- README.md +24 -24
- config.cfg +6 -4
- hu_core_news_md-any-py3-none-any.whl +2 -2
- meta.json +192 -192
- 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
@@ -14,55 +14,55 @@ 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
|
@@ -76,12 +76,12 @@ Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morpholog
|
|
76 |
| Feature | Description |
|
77 |
| --- | --- |
|
78 |
| **Name** | `hu_core_news_md` |
|
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 (100 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 |
|
@@ -111,15 +111,15 @@ Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morpholog
|
|
111 |
| `SENTS_P` | 98.21 |
|
112 |
| `SENTS_R` | 97.55 |
|
113 |
| `SENTS_F` | 97.88 |
|
114 |
-
| `TAG_ACC` | 96.
|
115 |
-
| `POS_ACC` | 96.
|
116 |
-
| `MORPH_ACC` | 93.
|
117 |
-
| `MORPH_MICRO_P` | 96.
|
118 |
-
| `MORPH_MICRO_R` |
|
119 |
-
| `MORPH_MICRO_F` | 96.
|
120 |
-
| `LEMMA_ACC` | 97.
|
121 |
-
| `DEP_UAS` |
|
122 |
-
| `DEP_LAS` |
|
123 |
-
| `ENTS_P` |
|
124 |
-
| `ENTS_R` | 84.
|
125 |
-
| `ENTS_F` | 84.
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.8479221927
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.8430028129
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.8454553469
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.9640156953
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9655469423
|
38 |
- task:
|
39 |
name: MORPH
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Morph (UFeats) Accuracy
|
43 |
type: accuracy
|
44 |
+
value: 0.9339649727
|
45 |
- task:
|
46 |
name: LEMMA
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Lemma Accuracy
|
50 |
type: accuracy
|
51 |
+
value: 0.9730169362
|
52 |
- task:
|
53 |
name: UNLABELED_DEPENDENCIES
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Unlabeled Attachment Score (UAS)
|
57 |
type: f_score
|
58 |
+
value: 0.8103583867
|
59 |
- task:
|
60 |
name: LABELED_DEPENDENCIES
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Labeled Attachment Score (LAS)
|
64 |
type: f_score
|
65 |
+
value: 0.743357861
|
66 |
- task:
|
67 |
name: SENTS
|
68 |
type: token-classification
|
|
|
76 |
| Feature | Description |
|
77 |
| --- | --- |
|
78 |
| **Name** | `hu_core_news_md` |
|
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 (100 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 |
|
|
|
111 |
| `SENTS_P` | 98.21 |
|
112 |
| `SENTS_R` | 97.55 |
|
113 |
| `SENTS_F` | 97.88 |
|
114 |
+
| `TAG_ACC` | 96.40 |
|
115 |
+
| `POS_ACC` | 96.55 |
|
116 |
+
| `MORPH_ACC` | 93.40 |
|
117 |
+
| `MORPH_MICRO_P` | 96.93 |
|
118 |
+
| `MORPH_MICRO_R` | 96.11 |
|
119 |
+
| `MORPH_MICRO_F` | 96.52 |
|
120 |
+
| `LEMMA_ACC` | 97.30 |
|
121 |
+
| `DEP_UAS` | 81.04 |
|
122 |
+
| `DEP_LAS` | 74.34 |
|
123 |
+
| `ENTS_P` | 84.79 |
|
124 |
+
| `ENTS_R` | 84.30 |
|
125 |
+
| `ENTS_F` | 84.55 |
|
config.cfg
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
[paths]
|
2 |
-
parser_model = "models/hu_core_news_md-parser-3.
|
3 |
-
ner_model = "models/hu_core_news_md-ner-3.
|
4 |
-
lemmatizer_lookups = "models/hu_core_news_md-lookup-lemmatizer-3.
|
5 |
-
tagger_model = "models/hu_core_news_md-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_md-parser-3.6.0/model-best"
|
3 |
+
ner_model = "models/hu_core_news_md-ner-3.6.0/model-best"
|
4 |
+
lemmatizer_lookups = "models/hu_core_news_md-lookup-lemmatizer-3.6.0"
|
5 |
+
tagger_model = "models/hu_core_news_md-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_md-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:f9d6fccef1fb7c657e44b246f8eadd6cc6336078522b7fb4b3a61af548667728
|
3 |
+
size 126873936
|
meta.json
CHANGED
@@ -1,14 +1,14 @@
|
|
1 |
{
|
2 |
"lang":"hu",
|
3 |
"name":"core_news_md",
|
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":100,
|
14 |
"vectors":200000,
|
@@ -1271,82 +1271,82 @@
|
|
1271 |
"sents_p":0.9820627803,
|
1272 |
"sents_r":0.9755011136,
|
1273 |
"sents_f":0.9787709497,
|
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,
|
@@ -1364,114 +1364,114 @@
|
|
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":0.8105263158,
|
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,
|
@@ -1479,99 +1479,104 @@
|
|
1479 |
"f":0.0
|
1480 |
},
|
1481 |
"obj:lvc":{
|
1482 |
-
"p":0.
|
1483 |
"r":0.0833333333,
|
1484 |
-
"f":0.
|
1485 |
},
|
1486 |
"ccomp:obl":{
|
1487 |
-
"p":0.
|
1488 |
-
"r":0.
|
1489 |
-
"f":0.
|
1490 |
},
|
1491 |
"iobj":{
|
1492 |
-
"p":0.
|
1493 |
"r":0.4,
|
1494 |
-
"f":0.
|
1495 |
},
|
1496 |
"dep":{
|
1497 |
"p":0.0,
|
1498 |
"r":0.0,
|
1499 |
"f":0.0
|
1500 |
},
|
1501 |
-
"acl":{
|
1502 |
-
"p":0.2916666667,
|
1503 |
-
"r":0.1944444444,
|
1504 |
-
"f":0.2333333333
|
1505 |
-
},
|
1506 |
-
"parataxis":{
|
1507 |
-
"p":0.1428571429,
|
1508 |
-
"r":0.0273972603,
|
1509 |
-
"f":0.0459770115
|
1510 |
-
},
|
1511 |
"case":{
|
1512 |
-
"p":0.
|
1513 |
-
"r":0.
|
1514 |
-
"f":0.
|
1515 |
},
|
1516 |
"csubj":{
|
1517 |
-
"p":0.
|
1518 |
"r":0.2702702703,
|
1519 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
1520 |
},
|
1521 |
"xcomp":{
|
1522 |
-
"p":0.
|
1523 |
-
"r":0.
|
1524 |
-
"f":0.
|
1525 |
},
|
1526 |
"nummod":{
|
1527 |
-
"p":0.
|
1528 |
-
"r":0.
|
1529 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1530 |
},
|
1531 |
"advmod:tto":{
|
1532 |
"p":0.5,
|
1533 |
-
"r":0.
|
1534 |
-
"f":0.
|
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,
|
1548 |
"r":0.0,
|
1549 |
"f":0.0
|
1550 |
},
|
1551 |
-
"list":{
|
1552 |
-
"p":0.0434782609,
|
1553 |
-
"r":0.1666666667,
|
1554 |
-
"f":0.0689655172
|
1555 |
-
},
|
1556 |
"goeswith":{
|
1557 |
"p":0.0,
|
1558 |
"r":0.0,
|
1559 |
"f":0.0
|
1560 |
},
|
1561 |
"compound":{
|
1562 |
-
"p":0.
|
1563 |
-
"r":0.
|
1564 |
-
"f":0.
|
1565 |
},
|
1566 |
"obl:lvc":{
|
1567 |
"p":0.0,
|
1568 |
"r":0.0,
|
1569 |
"f":0.0
|
1570 |
},
|
1571 |
-
"
|
1572 |
-
"p":0.
|
1573 |
-
"r":0.
|
1574 |
-
"f":0.
|
1575 |
},
|
1576 |
"ccomp":{
|
1577 |
"p":0.0,
|
@@ -1584,42 +1589,37 @@
|
|
1584 |
"f":0.0
|
1585 |
},
|
1586 |
"advmod:que":{
|
1587 |
-
"p":
|
1588 |
-
"r":0.
|
1589 |
-
"f":0.
|
1590 |
-
},
|
1591 |
-
"ccomp:pred":{
|
1592 |
-
"p":0.0,
|
1593 |
-
"r":0.0,
|
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.
|
1614 |
-
"f":0.
|
1615 |
},
|
1616 |
"MISC":{
|
1617 |
-
"p":0.
|
1618 |
-
"r":0.
|
1619 |
-
"f":0.
|
1620 |
}
|
1621 |
},
|
1622 |
-
"speed":
|
1623 |
},
|
1624 |
"sources":[
|
1625 |
{
|
@@ -1634,17 +1634,17 @@
|
|
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",
|
1646 |
"license":"CC-BY-NC-SA-3.0",
|
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 |
"requirements":[
|
|
|
1 |
{
|
2 |
"lang":"hu",
|
3 |
"name":"core_news_md",
|
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":100,
|
14 |
"vectors":200000,
|
|
|
1271 |
"sents_p":0.9820627803,
|
1272 |
"sents_r":0.9755011136,
|
1273 |
"sents_f":0.9787709497,
|
1274 |
+
"tag_acc":0.9640156953,
|
1275 |
+
"pos_acc":0.9655469423,
|
1276 |
+
"morph_acc":0.9339649727,
|
1277 |
+
"morph_micro_p":0.9693147835,
|
1278 |
+
"morph_micro_r":0.9611087237,
|
1279 |
+
"morph_micro_f":0.965194312,
|
1280 |
"morph_per_feat":{
|
1281 |
"Definite":{
|
1282 |
+
"p":0.9694727105,
|
1283 |
+
"r":0.9780681288,
|
1284 |
+
"f":0.9737514518
|
1285 |
},
|
1286 |
"PronType":{
|
1287 |
+
"p":0.977827051,
|
1288 |
+
"r":0.9735099338,
|
1289 |
+
"f":0.9756637168
|
1290 |
},
|
1291 |
"Case":{
|
1292 |
+
"p":0.9769246071,
|
1293 |
+
"r":0.9703615886,
|
1294 |
+
"f":0.9736320381
|
1295 |
},
|
1296 |
"Degree":{
|
1297 |
+
"p":0.9202834367,
|
1298 |
+
"r":0.8643926789,
|
1299 |
+
"f":0.8914628915
|
1300 |
},
|
1301 |
"Number":{
|
1302 |
+
"p":0.985019357,
|
1303 |
+
"r":0.9807273337,
|
1304 |
+
"f":0.9828686597
|
1305 |
},
|
1306 |
"Mood":{
|
1307 |
+
"p":0.9296703297,
|
1308 |
+
"r":0.9379157428,
|
1309 |
+
"f":0.9337748344
|
1310 |
},
|
1311 |
"Person":{
|
1312 |
+
"p":0.9578163772,
|
1313 |
+
"r":0.9523026316,
|
1314 |
+
"f":0.9550515464
|
1315 |
},
|
1316 |
"Tense":{
|
1317 |
+
"p":0.9681318681,
|
1318 |
+
"r":0.973480663,
|
1319 |
+
"f":0.9707988981
|
1320 |
},
|
1321 |
"VerbForm":{
|
1322 |
+
"p":0.9611486486,
|
1323 |
+
"r":0.9125902165,
|
1324 |
+
"f":0.9362402304
|
1325 |
},
|
1326 |
"Voice":{
|
1327 |
+
"p":0.9634888438,
|
1328 |
+
"r":0.9713701431,
|
1329 |
+
"f":0.967413442
|
1330 |
},
|
1331 |
"Number[psor]":{
|
1332 |
+
"p":0.9709302326,
|
1333 |
+
"r":0.9515669516,
|
1334 |
+
"f":0.9611510791
|
1335 |
},
|
1336 |
"Person[psor]":{
|
1337 |
+
"p":0.9723837209,
|
1338 |
+
"r":0.9543509272,
|
1339 |
+
"f":0.9632829374
|
1340 |
},
|
1341 |
"NumType":{
|
1342 |
+
"p":0.9011764706,
|
1343 |
+
"r":0.9341463415,
|
1344 |
+
"f":0.9173652695
|
1345 |
},
|
1346 |
"Reflex":{
|
1347 |
"p":1.0,
|
1348 |
+
"r":0.875,
|
1349 |
+
"f":0.9333333333
|
1350 |
},
|
1351 |
"Aspect":{
|
1352 |
"p":0.0,
|
|
|
1364 |
"f":1.0
|
1365 |
}
|
1366 |
},
|
1367 |
+
"lemma_acc":0.9730169362,
|
1368 |
+
"dep_uas":0.8103583867,
|
1369 |
+
"dep_las":0.743357861,
|
1370 |
"dep_las_per_type":{
|
1371 |
"det":{
|
1372 |
+
"p":0.8618524333,
|
1373 |
+
"r":0.8742038217,
|
1374 |
+
"f":0.8679841897
|
1375 |
},
|
1376 |
"amod:att":{
|
1377 |
+
"p":0.8163580247,
|
1378 |
+
"r":0.8650858545,
|
1379 |
+
"f":0.8400158793
|
1380 |
},
|
1381 |
"nsubj":{
|
1382 |
+
"p":0.7198748044,
|
1383 |
+
"r":0.71875,
|
1384 |
+
"f":0.7193119625
|
1385 |
},
|
1386 |
"advmod:mode":{
|
1387 |
+
"p":0.5789473684,
|
1388 |
+
"r":0.5392156863,
|
1389 |
+
"f":0.5583756345
|
1390 |
},
|
1391 |
"nmod:att":{
|
1392 |
+
"p":0.7376788553,
|
1393 |
+
"r":0.786440678,
|
1394 |
+
"f":0.7612797375
|
1395 |
},
|
1396 |
"obl":{
|
1397 |
+
"p":0.7789954338,
|
1398 |
+
"r":0.7677767777,
|
1399 |
+
"f":0.7733454216
|
1400 |
},
|
1401 |
"obj":{
|
1402 |
+
"p":0.8280542986,
|
1403 |
+
"r":0.8224719101,
|
1404 |
+
"f":0.825253664
|
1405 |
},
|
1406 |
"root":{
|
1407 |
+
"p":0.8183856502,
|
1408 |
+
"r":0.8129175947,
|
1409 |
+
"f":0.8156424581
|
1410 |
},
|
1411 |
"cc":{
|
1412 |
+
"p":0.7096774194,
|
1413 |
+
"r":0.6947368421,
|
1414 |
+
"f":0.7021276596
|
1415 |
},
|
1416 |
"conj":{
|
1417 |
+
"p":0.4771784232,
|
1418 |
+
"r":0.4791666667,
|
1419 |
+
"f":0.4781704782
|
1420 |
},
|
1421 |
"advmod":{
|
1422 |
+
"p":0.8279569892,
|
1423 |
"r":0.8105263158,
|
1424 |
+
"f":0.8191489362
|
1425 |
},
|
1426 |
"flat:name":{
|
1427 |
+
"p":0.8451327434,
|
1428 |
+
"r":0.8925233645,
|
1429 |
+
"f":0.8681818182
|
1430 |
},
|
1431 |
"appos":{
|
1432 |
+
"p":0.3837209302,
|
1433 |
+
"r":0.3510638298,
|
1434 |
+
"f":0.3666666667
|
1435 |
},
|
1436 |
"advcl":{
|
1437 |
+
"p":0.2941176471,
|
1438 |
+
"r":0.306122449,
|
1439 |
+
"f":0.3
|
1440 |
},
|
1441 |
"advmod:tlocy":{
|
1442 |
+
"p":0.688034188,
|
1443 |
+
"r":0.7,
|
1444 |
+
"f":0.6939655172
|
1445 |
},
|
1446 |
"ccomp:obj":{
|
1447 |
+
"p":0.3513513514,
|
1448 |
+
"r":0.3939393939,
|
1449 |
+
"f":0.3714285714
|
1450 |
},
|
1451 |
"mark":{
|
1452 |
+
"p":0.8113207547,
|
1453 |
+
"r":0.8164556962,
|
1454 |
+
"f":0.8138801262
|
1455 |
},
|
1456 |
"compound:preverb":{
|
1457 |
+
"p":0.9203539823,
|
1458 |
+
"r":0.9541284404,
|
1459 |
+
"f":0.9369369369
|
1460 |
},
|
1461 |
"advmod:locy":{
|
1462 |
+
"p":0.8235294118,
|
1463 |
+
"r":0.4375,
|
1464 |
+
"f":0.5714285714
|
1465 |
},
|
1466 |
"cop":{
|
1467 |
+
"p":0.6666666667,
|
1468 |
+
"r":0.5365853659,
|
1469 |
+
"f":0.5945945946
|
1470 |
},
|
1471 |
"nmod:obl":{
|
1472 |
+
"p":0.2162162162,
|
1473 |
+
"r":0.2,
|
1474 |
+
"f":0.2077922078
|
1475 |
},
|
1476 |
"advmod:to":{
|
1477 |
"p":0.0,
|
|
|
1479 |
"f":0.0
|
1480 |
},
|
1481 |
"obj:lvc":{
|
1482 |
+
"p":0.5,
|
1483 |
"r":0.0833333333,
|
1484 |
+
"f":0.1428571429
|
1485 |
},
|
1486 |
"ccomp:obl":{
|
1487 |
+
"p":0.28,
|
1488 |
+
"r":0.21875,
|
1489 |
+
"f":0.2456140351
|
1490 |
},
|
1491 |
"iobj":{
|
1492 |
+
"p":0.3157894737,
|
1493 |
"r":0.4,
|
1494 |
+
"f":0.3529411765
|
1495 |
},
|
1496 |
"dep":{
|
1497 |
"p":0.0,
|
1498 |
"r":0.0,
|
1499 |
"f":0.0
|
1500 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1501 |
"case":{
|
1502 |
+
"p":0.9432989691,
|
1503 |
+
"r":0.9336734694,
|
1504 |
+
"f":0.9384615385
|
1505 |
},
|
1506 |
"csubj":{
|
1507 |
+
"p":0.5882352941,
|
1508 |
"r":0.2702702703,
|
1509 |
+
"f":0.3703703704
|
1510 |
+
},
|
1511 |
+
"parataxis":{
|
1512 |
+
"p":0.2727272727,
|
1513 |
+
"r":0.0410958904,
|
1514 |
+
"f":0.0714285714
|
1515 |
},
|
1516 |
"xcomp":{
|
1517 |
+
"p":0.8985507246,
|
1518 |
+
"r":0.8378378378,
|
1519 |
+
"f":0.8671328671
|
1520 |
},
|
1521 |
"nummod":{
|
1522 |
+
"p":0.6282051282,
|
1523 |
+
"r":0.5268817204,
|
1524 |
+
"f":0.5730994152
|
1525 |
+
},
|
1526 |
+
"acl":{
|
1527 |
+
"p":0.3846153846,
|
1528 |
+
"r":0.2777777778,
|
1529 |
+
"f":0.3225806452
|
1530 |
+
},
|
1531 |
+
"orphan":{
|
1532 |
+
"p":0.0,
|
1533 |
+
"r":0.0,
|
1534 |
+
"f":0.0
|
1535 |
},
|
1536 |
"advmod:tto":{
|
1537 |
"p":0.5,
|
1538 |
+
"r":0.1,
|
1539 |
+
"f":0.1666666667
|
1540 |
},
|
1541 |
"nmod":{
|
1542 |
+
"p":1.0,
|
1543 |
"r":0.0909090909,
|
1544 |
+
"f":0.1666666667
|
1545 |
+
},
|
1546 |
+
"ccomp:pred":{
|
1547 |
+
"p":0.0,
|
1548 |
+
"r":0.0,
|
1549 |
+
"f":0.0
|
1550 |
},
|
1551 |
"aux":{
|
1552 |
+
"p":0.9,
|
1553 |
+
"r":0.75,
|
1554 |
+
"f":0.8181818182
|
1555 |
},
|
1556 |
"advmod:tfrom":{
|
1557 |
"p":0.0,
|
1558 |
"r":0.0,
|
1559 |
"f":0.0
|
1560 |
},
|
|
|
|
|
|
|
|
|
|
|
1561 |
"goeswith":{
|
1562 |
"p":0.0,
|
1563 |
"r":0.0,
|
1564 |
"f":0.0
|
1565 |
},
|
1566 |
"compound":{
|
1567 |
+
"p":0.9487179487,
|
1568 |
+
"r":0.925,
|
1569 |
+
"f":0.9367088608
|
1570 |
},
|
1571 |
"obl:lvc":{
|
1572 |
"p":0.0,
|
1573 |
"r":0.0,
|
1574 |
"f":0.0
|
1575 |
},
|
1576 |
+
"list":{
|
1577 |
+
"p":0.2,
|
1578 |
+
"r":0.1666666667,
|
1579 |
+
"f":0.1818181818
|
1580 |
},
|
1581 |
"ccomp":{
|
1582 |
"p":0.0,
|
|
|
1589 |
"f":0.0
|
1590 |
},
|
1591 |
"advmod:que":{
|
1592 |
+
"p":1.0,
|
1593 |
+
"r":0.25,
|
1594 |
+
"f":0.4
|
|
|
|
|
|
|
|
|
|
|
1595 |
}
|
1596 |
},
|
1597 |
+
"ents_p":0.8479221927,
|
1598 |
+
"ents_r":0.8430028129,
|
1599 |
+
"ents_f":0.8454553469,
|
1600 |
"ents_per_type":{
|
1601 |
"ORG":{
|
1602 |
+
"p":0.882924572,
|
1603 |
+
"r":0.8845618915,
|
1604 |
+
"f":0.8837424734
|
1605 |
},
|
1606 |
"PER":{
|
1607 |
+
"p":0.8772969769,
|
1608 |
+
"r":0.8841099164,
|
1609 |
+
"f":0.8806902708
|
1610 |
},
|
1611 |
"LOC":{
|
1612 |
+
"p":0.84,
|
1613 |
+
"r":0.8567708333,
|
1614 |
+
"f":0.8483025355
|
1615 |
},
|
1616 |
"MISC":{
|
1617 |
+
"p":0.664556962,
|
1618 |
+
"r":0.5957446809,
|
1619 |
+
"f":0.6282722513
|
1620 |
}
|
1621 |
},
|
1622 |
+
"speed":2618.8542210874
|
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",
|
1640 |
"license":"CC-BY-NC-SA-3.0",
|
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 463022
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d43683d554c8c726ef065c0db115d588004bf892c00d7032b65456ddb0fa6d9
|
3 |
size 463022
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9791307
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:364eda709e2edbfac89812efe2353bb8cecd2854ea39f900e1bd98ce6751ea66
|
3 |
size 9791307
|
parser/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 25601129
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fee779591ece0e3d7caf9277c67269f4ec014108863356ede7f37ad457ad384f
|
3 |
size 25601129
|
senter/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1237
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfb4dcfe2a876d6bade5bf405e9835efe65bb71092aaa1aa86d1ccdc2b255e0a
|
3 |
size 1237
|
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 7297
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:632c6f38ad97c0336e65a15ee41d097f45d71233914ea41f2e7010d6af4c89f6
|
3 |
size 7297
|
tok2vec/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9659749
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7092f2f38ddf3e799dadff6a131296038901b22d90c44940a6a453104db5fc2e
|
3 |
size 9659749
|
trainable_lemmatizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 11282980
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:034f6cf0204dd1b27ebac3b5d66fa99ea8cd96e3df746325e228949186826a20
|
3 |
size 11282980
|
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 sha256:8d5610c17288cd7c1db421eb081e29b13e79705966a21722c748c310f2f1f905
|
3 |
+
size 6406437
|
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 |
}
|