Update spacy pipeline to 0.4.2
Browse files- README.md +32 -24
- config.cfg +6 -4
- hu_core_news_lg-any-py3-none-any.whl +2 -2
- meta.json +195 -191
- morphologizer/model +1 -1
- ner/model +1 -1
- parser/model +1 -1
- senter/model +1 -1
- tagger/model +1 -1
- tok2vec/model +1 -1
README.md
CHANGED
@@ -14,69 +14,76 @@ 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: UNLABELED_DEPENDENCIES
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Unlabeled Attachment Score (UAS)
|
50 |
type: f_score
|
51 |
-
value: 0.
|
52 |
- task:
|
53 |
name: LABELED_DEPENDENCIES
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Labeled Attachment Score (LAS)
|
57 |
type: f_score
|
58 |
-
value: 0.
|
59 |
- task:
|
60 |
name: SENTS
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Sentences F-Score
|
64 |
type: f_score
|
65 |
-
value: 0.
|
66 |
---
|
67 |
Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner
|
68 |
|
69 |
| Feature | Description |
|
70 |
| --- | --- |
|
71 |
| **Name** | `hu_core_news_lg` |
|
72 |
-
| **Version** | `0.4.
|
73 |
| **spaCy** | `>=3.2.1,<3.3.0` |
|
74 |
| **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lemmatizer`, `parser`, `ner` |
|
75 |
| **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lemmatizer`, `parser`, `ner` |
|
76 |
| **Vectors** | 1140008 keys, 1140008 unique vectors (300 dimensions) |
|
77 |
| **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 />[hunNERwiki](http://hlt.sztaki.hu/resources/hunnerwiki.html) (Eszter Simon, Dávid Márk Nemeskey (HLT Group, Budapest University of Technology and Economics))<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 />[Webcorpuswiki word2vec model](https://github.com/oroszgy/hunlp-resources/releases/tag/webcorpuswiki_word2vec_v0.1) (György Orosz) |
|
78 |
| **License** | `cc-by-sa-4.0` |
|
79 |
-
| **Author** | [MILAB
|
80 |
|
81 |
### Label Scheme
|
82 |
|
@@ -102,17 +109,18 @@ Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morpholog
|
|
102 |
| `TOKEN_P` | 99.86 |
|
103 |
| `TOKEN_R` | 99.93 |
|
104 |
| `TOKEN_F` | 99.89 |
|
105 |
-
| `SENTS_P` | 97.
|
106 |
-
| `SENTS_R` | 97.
|
107 |
-
| `SENTS_F` | 97.
|
108 |
-
| `TAG_ACC` | 96.
|
109 |
-
| `POS_ACC` | 96.
|
110 |
-
| `MORPH_ACC` | 92.
|
111 |
-
| `MORPH_MICRO_P` | 96.
|
112 |
-
| `MORPH_MICRO_R` | 95.
|
113 |
| `MORPH_MICRO_F` | 96.02 |
|
114 |
-
| `
|
115 |
-
| `
|
116 |
-
| `
|
117 |
-
| `
|
118 |
-
| `
|
|
|
|
14 |
metrics:
|
15 |
- name: NER Precision
|
16 |
type: precision
|
17 |
+
value: 0.8543930456
|
18 |
- name: NER Recall
|
19 |
type: recall
|
20 |
+
value: 0.8369829684
|
21 |
- name: NER F Score
|
22 |
type: f_score
|
23 |
+
value: 0.8455984022
|
24 |
- task:
|
25 |
name: TAG
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: TAG (XPOS) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.9648308532
|
31 |
- task:
|
32 |
name: POS
|
33 |
type: token-classification
|
34 |
metrics:
|
35 |
- name: POS (UPOS) Accuracy
|
36 |
type: accuracy
|
37 |
+
value: 0.9652136466
|
38 |
- task:
|
39 |
name: MORPH
|
40 |
type: token-classification
|
41 |
metrics:
|
42 |
- name: Morph (UFeats) Accuracy
|
43 |
type: accuracy
|
44 |
+
value: 0.9279356876
|
45 |
+
- task:
|
46 |
+
name: LEMMA
|
47 |
+
type: token-classification
|
48 |
+
metrics:
|
49 |
+
- name: Lemma Accuracy
|
50 |
+
type: accuracy
|
51 |
+
value: 0.9543584346
|
52 |
- task:
|
53 |
name: UNLABELED_DEPENDENCIES
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Unlabeled Attachment Score (UAS)
|
57 |
type: f_score
|
58 |
+
value: 0.8110496002
|
59 |
- task:
|
60 |
name: LABELED_DEPENDENCIES
|
61 |
type: token-classification
|
62 |
metrics:
|
63 |
- name: Labeled Attachment Score (LAS)
|
64 |
type: f_score
|
65 |
+
value: 0.7398792217
|
66 |
- task:
|
67 |
name: SENTS
|
68 |
type: token-classification
|
69 |
metrics:
|
70 |
- name: Sentences F-Score
|
71 |
type: f_score
|
72 |
+
value: 0.9754464286
|
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** | `0.4.2` |
|
80 |
| **spaCy** | `>=3.2.1,<3.3.0` |
|
81 |
| **Default Pipeline** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lemmatizer`, `parser`, `ner` |
|
82 |
| **Components** | `tok2vec`, `senter`, `tagger`, `morphologizer`, `lemmatizer`, `parser`, `ner` |
|
83 |
| **Vectors** | 1140008 keys, 1140008 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 />[hunNERwiki](http://hlt.sztaki.hu/resources/hunnerwiki.html) (Eszter Simon, Dávid Márk Nemeskey (HLT Group, Budapest University of Technology and Economics))<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 />[Webcorpuswiki word2vec model](https://github.com/oroszgy/hunlp-resources/releases/tag/webcorpuswiki_word2vec_v0.1) (György Orosz) |
|
85 |
| **License** | `cc-by-sa-4.0` |
|
86 |
+
| **Author** | [SzegedAI, MILAB](https://github.com/huspacy/huspacy) |
|
87 |
|
88 |
### Label Scheme
|
89 |
|
|
|
109 |
| `TOKEN_P` | 99.86 |
|
110 |
| `TOKEN_R` | 99.93 |
|
111 |
| `TOKEN_F` | 99.89 |
|
112 |
+
| `SENTS_P` | 97.76 |
|
113 |
+
| `SENTS_R` | 97.33 |
|
114 |
+
| `SENTS_F` | 97.54 |
|
115 |
+
| `TAG_ACC` | 96.48 |
|
116 |
+
| `POS_ACC` | 96.52 |
|
117 |
+
| `MORPH_ACC` | 92.79 |
|
118 |
+
| `MORPH_MICRO_P` | 96.75 |
|
119 |
+
| `MORPH_MICRO_R` | 95.29 |
|
120 |
| `MORPH_MICRO_F` | 96.02 |
|
121 |
+
| `LEMMA_ACC` | 95.44 |
|
122 |
+
| `DEP_UAS` | 81.10 |
|
123 |
+
| `DEP_LAS` | 73.99 |
|
124 |
+
| `ENTS_P` | 85.44 |
|
125 |
+
| `ENTS_R` | 83.70 |
|
126 |
+
| `ENTS_F` | 84.56 |
|
config.cfg
CHANGED
@@ -1,7 +1,7 @@
|
|
1 |
[paths]
|
2 |
-
parser_model = "../models/hu_core_news_lg-parser-0.4.
|
3 |
-
lemmy_model = "../models/lemmy-0.4.
|
4 |
-
ner_model = "../models/hu_core_news_lg-ner_merged-0.4.
|
5 |
train = null
|
6 |
dev = null
|
7 |
vectors = null
|
@@ -25,7 +25,6 @@ batch_size = 1000
|
|
25 |
|
26 |
[components.lemmatizer]
|
27 |
factory = "hu.lemmatizer"
|
28 |
-
model_path = ${paths.lemmy_model}
|
29 |
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
|
30 |
|
31 |
[components.morphologizer]
|
@@ -236,4 +235,7 @@ after_init = null
|
|
236 |
|
237 |
[initialize.components]
|
238 |
|
|
|
|
|
|
|
239 |
[initialize.tokenizer]
|
|
|
1 |
[paths]
|
2 |
+
parser_model = "../models/hu_core_news_lg-parser-0.4.2/model-best"
|
3 |
+
lemmy_model = "../models/lemmy-0.4.2.bin"
|
4 |
+
ner_model = "../models/hu_core_news_lg-ner_merged-0.4.2/model-best"
|
5 |
train = null
|
6 |
dev = null
|
7 |
vectors = null
|
|
|
25 |
|
26 |
[components.lemmatizer]
|
27 |
factory = "hu.lemmatizer"
|
|
|
28 |
scorer = {"@scorers":"spacy.lemmatizer_scorer.v1"}
|
29 |
|
30 |
[components.morphologizer]
|
|
|
235 |
|
236 |
[initialize.components]
|
237 |
|
238 |
+
[initialize.components.lemmatizer]
|
239 |
+
model_path = ${paths.lemmy_model}
|
240 |
+
|
241 |
[initialize.tokenizer]
|
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 sha256:2fc64776845dc3a42e2b8eef88d89e6d377d6bde7ef4b0ab897adff1a7cadf83
|
3 |
+
size 1419986702
|
meta.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"lang":"hu",
|
3 |
"name":"core_news_lg",
|
4 |
-
"version":"0.4.
|
5 |
"description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
|
6 |
-
"author":"MILAB
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://github.com/huspacy/huspacy",
|
9 |
"license":"cc-by-sa-4.0",
|
@@ -1192,6 +1192,9 @@
|
|
1192 |
"Case=Dat|Number=Plur|POS=PRON|Person=1|PronType=Prs",
|
1193 |
"Case=Acc|Number=Plur|Number[psor]=Sing|POS=PROPN|Person[psor]=3",
|
1194 |
"Case=All|Number=Sing|Number[psed]=Sing|POS=PRON|Person=3|PronType=Tot"
|
|
|
|
|
|
|
1195 |
],
|
1196 |
"parser":[
|
1197 |
"ROOT",
|
@@ -1271,80 +1274,85 @@
|
|
1271 |
"token_p":0.998565417,
|
1272 |
"token_r":0.9993300153,
|
1273 |
"token_f":0.9989475698,
|
1274 |
-
"sents_p":0.
|
1275 |
-
"sents_r":0.
|
1276 |
-
"sents_f":0.
|
1277 |
-
"tag_acc":0.
|
1278 |
-
"pos_acc":0.
|
1279 |
-
"morph_acc":0.
|
1280 |
-
"morph_micro_p":0.
|
1281 |
-
"morph_micro_r":0.
|
1282 |
-
"morph_micro_f":0.
|
1283 |
"morph_per_feat":{
|
1284 |
"Definite":{
|
1285 |
-
"p":0.
|
1286 |
-
"r":0.
|
1287 |
-
"f":0.
|
1288 |
},
|
1289 |
"PronType":{
|
1290 |
-
"p":0.
|
1291 |
-
"r":0.
|
1292 |
-
"f":0.
|
1293 |
},
|
1294 |
"Case":{
|
1295 |
-
"p":0.
|
1296 |
-
"r":0.
|
1297 |
-
"f":0.
|
1298 |
},
|
1299 |
"Degree":{
|
1300 |
-
"p":0.
|
1301 |
-
"r":0.
|
1302 |
-
"f":0.
|
1303 |
},
|
1304 |
"Number":{
|
1305 |
-
"p":0.
|
1306 |
-
"r":0.
|
1307 |
-
"f":0.
|
1308 |
},
|
1309 |
"Mood":{
|
1310 |
-
"p":0.
|
1311 |
-
"r":0.
|
1312 |
-
"f":0.
|
1313 |
},
|
1314 |
"Person":{
|
1315 |
-
"p":0.
|
1316 |
-
"r":0.
|
1317 |
-
"f":0.
|
1318 |
},
|
1319 |
"Tense":{
|
1320 |
-
"p":0.
|
1321 |
-
"r":0.
|
1322 |
-
"f":0.
|
1323 |
},
|
1324 |
"VerbForm":{
|
1325 |
-
"p":0.
|
1326 |
-
"r":0.
|
1327 |
-
"f":0.
|
1328 |
},
|
1329 |
"Voice":{
|
1330 |
-
"p":0.
|
1331 |
-
"r":0.
|
1332 |
-
"f":0.
|
1333 |
},
|
1334 |
"Number[psor]":{
|
1335 |
-
"p":0.
|
1336 |
-
"r":0.
|
1337 |
-
"f":0.
|
1338 |
},
|
1339 |
"Person[psor]":{
|
1340 |
-
"p":0.
|
1341 |
-
"r":0.
|
1342 |
-
"f":0.
|
1343 |
},
|
1344 |
"NumType":{
|
1345 |
-
"p":0.
|
1346 |
-
"r":0.
|
1347 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
1348 |
},
|
1349 |
"Reflex":{
|
1350 |
"p":1.0,
|
@@ -1360,120 +1368,116 @@
|
|
1360 |
"p":0.0,
|
1361 |
"r":0.0,
|
1362 |
"f":0.0
|
1363 |
-
},
|
1364 |
-
"Poss":{
|
1365 |
-
"p":1.0,
|
1366 |
-
"r":1.0,
|
1367 |
-
"f":1.0
|
1368 |
}
|
1369 |
},
|
1370 |
-
"
|
1371 |
-
"
|
|
|
1372 |
"dep_las_per_type":{
|
1373 |
"det":{
|
1374 |
-
"p":0.
|
1375 |
-
"r":0.
|
1376 |
-
"f":0.
|
1377 |
},
|
1378 |
"amod:att":{
|
1379 |
-
"p":0.
|
1380 |
-
"r":0.
|
1381 |
-
"f":0.
|
1382 |
},
|
1383 |
"nsubj":{
|
1384 |
-
"p":0.
|
1385 |
-
"r":0.
|
1386 |
-
"f":0.
|
1387 |
},
|
1388 |
"advmod:mode":{
|
1389 |
-
"p":0.
|
1390 |
-
"r":0.
|
1391 |
-
"f":0.
|
1392 |
},
|
1393 |
"nmod:att":{
|
1394 |
-
"p":0.
|
1395 |
-
"r":0.
|
1396 |
-
"f":0.
|
1397 |
},
|
1398 |
"obl":{
|
1399 |
-
"p":0.
|
1400 |
-
"r":0.
|
1401 |
-
"f":0.
|
1402 |
},
|
1403 |
"obj":{
|
1404 |
-
"p":0.
|
1405 |
-
"r":0.
|
1406 |
-
"f":0.
|
1407 |
},
|
1408 |
"root":{
|
1409 |
-
"p":0.
|
1410 |
-
"r":0.
|
1411 |
-
"f":0.
|
1412 |
},
|
1413 |
"cc":{
|
1414 |
-
"p":0.
|
1415 |
-
"r":0.
|
1416 |
-
"f":0.
|
1417 |
},
|
1418 |
"conj":{
|
1419 |
-
"p":0.
|
1420 |
-
"r":0.
|
1421 |
-
"f":0.
|
1422 |
},
|
1423 |
"advmod":{
|
1424 |
-
"p":0.
|
1425 |
"r":0.8421052632,
|
1426 |
-
"f":0.
|
1427 |
},
|
1428 |
"flat:name":{
|
1429 |
-
"p":0.
|
1430 |
-
"r":0.
|
1431 |
-
"f":0.
|
1432 |
},
|
1433 |
"appos":{
|
1434 |
-
"p":0.
|
1435 |
-
"r":0.
|
1436 |
-
"f":0.
|
1437 |
},
|
1438 |
"advcl":{
|
1439 |
-
"p":0.
|
1440 |
-
"r":0.
|
1441 |
-
"f":0.
|
1442 |
},
|
1443 |
"advmod:tlocy":{
|
1444 |
-
"p":0.
|
1445 |
-
"r":0.
|
1446 |
-
"f":0.
|
1447 |
},
|
1448 |
"ccomp:obj":{
|
1449 |
-
"p":0.
|
1450 |
"r":0.4242424242,
|
1451 |
-
"f":0.
|
1452 |
},
|
1453 |
"mark":{
|
1454 |
-
"p":0.
|
1455 |
-
"r":0.
|
1456 |
-
"f":0.
|
1457 |
},
|
1458 |
"compound:preverb":{
|
1459 |
-
"p":0.
|
1460 |
-
"r":0.
|
1461 |
-
"f":0.
|
1462 |
},
|
1463 |
"advmod:locy":{
|
1464 |
-
"p":0.
|
1465 |
-
"r":0.
|
1466 |
-
"f":0.
|
1467 |
},
|
1468 |
"cop":{
|
1469 |
-
"p":0.
|
1470 |
-
"r":0.
|
1471 |
-
"f":0.
|
1472 |
},
|
1473 |
"nmod:obl":{
|
1474 |
-
"p":0.
|
1475 |
-
"r":0.
|
1476 |
-
"f":0.
|
1477 |
},
|
1478 |
"advmod:to":{
|
1479 |
"p":0.0,
|
@@ -1481,76 +1485,76 @@
|
|
1481 |
"f":0.0
|
1482 |
},
|
1483 |
"obj:lvc":{
|
1484 |
-
"p":0.
|
1485 |
-
"r":0.
|
1486 |
-
"f":0.
|
1487 |
},
|
1488 |
"ccomp:obl":{
|
1489 |
-
"p":0.
|
1490 |
-
"r":0.
|
1491 |
-
"f":0.
|
1492 |
},
|
1493 |
-
"
|
1494 |
-
"p":0.
|
1495 |
-
"r":0.
|
1496 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
1497 |
},
|
1498 |
"parataxis":{
|
1499 |
"p":0.1724137931,
|
1500 |
"r":0.0684931507,
|
1501 |
"f":0.0980392157
|
1502 |
},
|
1503 |
-
"case":{
|
1504 |
-
"p":0.9315789474,
|
1505 |
-
"r":0.9030612245,
|
1506 |
-
"f":0.9170984456
|
1507 |
-
},
|
1508 |
-
"csubj":{
|
1509 |
-
"p":0.5416666667,
|
1510 |
-
"r":0.3513513514,
|
1511 |
-
"f":0.4262295082
|
1512 |
-
},
|
1513 |
"xcomp":{
|
1514 |
-
"p":0.
|
1515 |
-
"r":0.
|
1516 |
-
"f":0.
|
1517 |
},
|
1518 |
"nummod":{
|
1519 |
-
"p":0.
|
1520 |
-
"r":0.
|
1521 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
1522 |
},
|
1523 |
"acl":{
|
1524 |
-
"p":0.
|
1525 |
-
"r":0.
|
1526 |
-
"f":0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1527 |
},
|
1528 |
"advmod:tto":{
|
1529 |
-
"p":0.
|
1530 |
-
"r":0.
|
1531 |
-
"f":0.
|
1532 |
},
|
1533 |
"nmod":{
|
1534 |
-
"p":0.
|
1535 |
"r":0.0909090909,
|
1536 |
-
"f":0.
|
1537 |
-
},
|
1538 |
-
"ccomp":{
|
1539 |
-
"p":0.1,
|
1540 |
-
"r":0.0769230769,
|
1541 |
-
"f":0.0869565217
|
1542 |
},
|
1543 |
"aux":{
|
1544 |
-
"p":0.
|
1545 |
-
"r":0.
|
1546 |
-
"f":0.
|
1547 |
},
|
1548 |
"advmod:tfrom":{
|
1549 |
-
"p":0.3333333333,
|
1550 |
-
"r":0.1666666667,
|
1551 |
-
"f":0.2222222222
|
1552 |
-
},
|
1553 |
-
"dep":{
|
1554 |
"p":0.0,
|
1555 |
"r":0.0,
|
1556 |
"f":0.0
|
@@ -1561,9 +1565,9 @@
|
|
1561 |
"f":0.0
|
1562 |
},
|
1563 |
"compound":{
|
1564 |
-
"p":
|
1565 |
-
"r":0.
|
1566 |
-
"f":0.
|
1567 |
},
|
1568 |
"obl:lvc":{
|
1569 |
"p":0.0,
|
@@ -1581,47 +1585,47 @@
|
|
1581 |
"f":0.0
|
1582 |
},
|
1583 |
"list":{
|
1584 |
-
"p":0.2,
|
1585 |
-
"r":0.1666666667,
|
1586 |
-
"f":0.1818181818
|
1587 |
-
},
|
1588 |
-
"advmod:que":{
|
1589 |
"p":1.0,
|
1590 |
-
"r":0.
|
1591 |
-
"f":0.
|
1592 |
},
|
1593 |
"ccomp:pred":{
|
1594 |
"p":0.0,
|
1595 |
"r":0.0,
|
1596 |
"f":0.0
|
|
|
|
|
|
|
|
|
|
|
1597 |
}
|
1598 |
},
|
1599 |
-
"ents_p":0.
|
1600 |
-
"ents_r":0.
|
1601 |
-
"ents_f":0.
|
1602 |
"ents_per_type":{
|
1603 |
"ORG":{
|
1604 |
-
"p":0.
|
1605 |
-
"r":0.
|
1606 |
-
"f":0.
|
1607 |
},
|
1608 |
"LOC":{
|
1609 |
-
"p":0.
|
1610 |
-
"r":0.
|
1611 |
-
"f":0.
|
1612 |
},
|
1613 |
"MISC":{
|
1614 |
-
"p":0.
|
1615 |
-
"r":0.
|
1616 |
-
"f":0.
|
1617 |
},
|
1618 |
"PER":{
|
1619 |
-
"p":0.
|
1620 |
-
"r":0.
|
1621 |
-
"f":0.
|
1622 |
}
|
1623 |
},
|
1624 |
-
"speed":
|
1625 |
},
|
1626 |
"sources":[
|
1627 |
{
|
|
|
1 |
{
|
2 |
"lang":"hu",
|
3 |
"name":"core_news_lg",
|
4 |
+
"version":"0.4.2",
|
5 |
"description":"Core Hungarian model for HuSpaCy. Components: tok2vec, senter, tagger, morphologizer, lemmatizer, parser, ner",
|
6 |
+
"author":"SzegedAI, MILAB",
|
7 |
"email":"[email protected]",
|
8 |
"url":"https://github.com/huspacy/huspacy",
|
9 |
"license":"cc-by-sa-4.0",
|
|
|
1192 |
"Case=Dat|Number=Plur|POS=PRON|Person=1|PronType=Prs",
|
1193 |
"Case=Acc|Number=Plur|Number[psor]=Sing|POS=PROPN|Person[psor]=3",
|
1194 |
"Case=All|Number=Sing|Number[psed]=Sing|POS=PRON|Person=3|PronType=Tot"
|
1195 |
+
],
|
1196 |
+
"lemmatizer":[
|
1197 |
+
|
1198 |
],
|
1199 |
"parser":[
|
1200 |
"ROOT",
|
|
|
1274 |
"token_p":0.998565417,
|
1275 |
"token_r":0.9993300153,
|
1276 |
"token_f":0.9989475698,
|
1277 |
+
"sents_p":0.9776286353,
|
1278 |
+
"sents_r":0.9732739421,
|
1279 |
+
"sents_f":0.9754464286,
|
1280 |
+
"tag_acc":0.9648308532,
|
1281 |
+
"pos_acc":0.9652136466,
|
1282 |
+
"morph_acc":0.9279356876,
|
1283 |
+
"morph_micro_p":0.9675378507,
|
1284 |
+
"morph_micro_r":0.9529437043,
|
1285 |
+
"morph_micro_f":0.9601853255,
|
1286 |
"morph_per_feat":{
|
1287 |
"Definite":{
|
1288 |
+
"p":0.9650092081,
|
1289 |
+
"r":0.9780681288,
|
1290 |
+
"f":0.9714947856
|
1291 |
},
|
1292 |
"PronType":{
|
1293 |
+
"p":0.9729878721,
|
1294 |
+
"r":0.9740618102,
|
1295 |
+
"f":0.973524545
|
1296 |
},
|
1297 |
"Case":{
|
1298 |
+
"p":0.9694915254,
|
1299 |
+
"r":0.9606797076,
|
1300 |
+
"f":0.9650655022
|
1301 |
},
|
1302 |
"Degree":{
|
1303 |
+
"p":0.9205357143,
|
1304 |
+
"r":0.8577371048,
|
1305 |
+
"f":0.8880275624
|
1306 |
},
|
1307 |
"Number":{
|
1308 |
+
"p":0.98056119,
|
1309 |
+
"r":0.9721803251,
|
1310 |
+
"f":0.9763527729
|
1311 |
},
|
1312 |
"Mood":{
|
1313 |
+
"p":0.9442586399,
|
1314 |
+
"r":0.9390243902,
|
1315 |
+
"f":0.9416342412
|
1316 |
},
|
1317 |
"Person":{
|
1318 |
+
"p":0.9671440607,
|
1319 |
+
"r":0.9440789474,
|
1320 |
+
"f":0.9554723263
|
1321 |
},
|
1322 |
"Tense":{
|
1323 |
+
"p":0.9754738016,
|
1324 |
+
"r":0.9668508287,
|
1325 |
+
"f":0.9711431743
|
1326 |
},
|
1327 |
"VerbForm":{
|
1328 |
+
"p":0.966977138,
|
1329 |
+
"r":0.915797915,
|
1330 |
+
"f":0.9406919275
|
1331 |
},
|
1332 |
"Voice":{
|
1333 |
+
"p":0.9701952724,
|
1334 |
+
"r":0.9652351738,
|
1335 |
+
"f":0.9677088672
|
1336 |
},
|
1337 |
"Number[psor]":{
|
1338 |
+
"p":0.9610778443,
|
1339 |
+
"r":0.9145299145,
|
1340 |
+
"f":0.9372262774
|
1341 |
},
|
1342 |
"Person[psor]":{
|
1343 |
+
"p":0.9610778443,
|
1344 |
+
"r":0.9158345221,
|
1345 |
+
"f":0.9379108839
|
1346 |
},
|
1347 |
"NumType":{
|
1348 |
+
"p":0.9296482412,
|
1349 |
+
"r":0.9024390244,
|
1350 |
+
"f":0.9158415842
|
1351 |
+
},
|
1352 |
+
"Poss":{
|
1353 |
+
"p":0.6,
|
1354 |
+
"r":1.0,
|
1355 |
+
"f":0.75
|
1356 |
},
|
1357 |
"Reflex":{
|
1358 |
"p":1.0,
|
|
|
1368 |
"p":0.0,
|
1369 |
"r":0.0,
|
1370 |
"f":0.0
|
|
|
|
|
|
|
|
|
|
|
1371 |
}
|
1372 |
},
|
1373 |
+
"lemma_acc":0.9543584346,
|
1374 |
+
"dep_uas":0.8110496002,
|
1375 |
+
"dep_las":0.7398792217,
|
1376 |
"dep_las_per_type":{
|
1377 |
"det":{
|
1378 |
+
"p":0.8394875659,
|
1379 |
+
"r":0.8869426752,
|
1380 |
+
"f":0.8625629113
|
1381 |
},
|
1382 |
"amod:att":{
|
1383 |
+
"p":0.8847549909,
|
1384 |
+
"r":0.7972199509,
|
1385 |
+
"f":0.8387096774
|
1386 |
},
|
1387 |
"nsubj":{
|
1388 |
+
"p":0.7160305344,
|
1389 |
+
"r":0.7328125,
|
1390 |
+
"f":0.7243243243
|
1391 |
},
|
1392 |
"advmod:mode":{
|
1393 |
+
"p":0.5522041763,
|
1394 |
+
"r":0.5833333333,
|
1395 |
+
"f":0.5673420739
|
1396 |
},
|
1397 |
"nmod:att":{
|
1398 |
+
"p":0.7521222411,
|
1399 |
+
"r":0.7508474576,
|
1400 |
+
"f":0.7514843087
|
1401 |
},
|
1402 |
"obl":{
|
1403 |
+
"p":0.7796143251,
|
1404 |
+
"r":0.7641764176,
|
1405 |
+
"f":0.7718181818
|
1406 |
},
|
1407 |
"obj":{
|
1408 |
+
"p":0.8564920273,
|
1409 |
+
"r":0.8449438202,
|
1410 |
+
"f":0.850678733
|
1411 |
},
|
1412 |
"root":{
|
1413 |
+
"p":0.8210290828,
|
1414 |
+
"r":0.8173719376,
|
1415 |
+
"f":0.8191964286
|
1416 |
},
|
1417 |
"cc":{
|
1418 |
+
"p":0.6175298805,
|
1419 |
+
"r":0.6526315789,
|
1420 |
+
"f":0.6345957011
|
1421 |
},
|
1422 |
"conj":{
|
1423 |
+
"p":0.4725274725,
|
1424 |
+
"r":0.5375,
|
1425 |
+
"f":0.5029239766
|
1426 |
},
|
1427 |
"advmod":{
|
1428 |
+
"p":0.7920792079,
|
1429 |
"r":0.8421052632,
|
1430 |
+
"f":0.8163265306
|
1431 |
},
|
1432 |
"flat:name":{
|
1433 |
+
"p":0.8488888889,
|
1434 |
+
"r":0.8925233645,
|
1435 |
+
"f":0.8701594533
|
1436 |
},
|
1437 |
"appos":{
|
1438 |
+
"p":0.3274336283,
|
1439 |
+
"r":0.3936170213,
|
1440 |
+
"f":0.3574879227
|
1441 |
},
|
1442 |
"advcl":{
|
1443 |
+
"p":0.3829787234,
|
1444 |
+
"r":0.1836734694,
|
1445 |
+
"f":0.2482758621
|
1446 |
},
|
1447 |
"advmod:tlocy":{
|
1448 |
+
"p":0.7004405286,
|
1449 |
+
"r":0.6913043478,
|
1450 |
+
"f":0.6958424508
|
1451 |
},
|
1452 |
"ccomp:obj":{
|
1453 |
+
"p":0.2857142857,
|
1454 |
"r":0.4242424242,
|
1455 |
+
"f":0.3414634146
|
1456 |
},
|
1457 |
"mark":{
|
1458 |
+
"p":0.8176100629,
|
1459 |
+
"r":0.8227848101,
|
1460 |
+
"f":0.8201892744
|
1461 |
},
|
1462 |
"compound:preverb":{
|
1463 |
+
"p":0.8888888889,
|
1464 |
+
"r":0.9541284404,
|
1465 |
+
"f":0.9203539823
|
1466 |
},
|
1467 |
"advmod:locy":{
|
1468 |
+
"p":0.6956521739,
|
1469 |
+
"r":0.5,
|
1470 |
+
"f":0.5818181818
|
1471 |
},
|
1472 |
"cop":{
|
1473 |
+
"p":0.9,
|
1474 |
+
"r":0.6585365854,
|
1475 |
+
"f":0.7605633803
|
1476 |
},
|
1477 |
"nmod:obl":{
|
1478 |
+
"p":0.15,
|
1479 |
+
"r":0.075,
|
1480 |
+
"f":0.1
|
1481 |
},
|
1482 |
"advmod:to":{
|
1483 |
"p":0.0,
|
|
|
1485 |
"f":0.0
|
1486 |
},
|
1487 |
"obj:lvc":{
|
1488 |
+
"p":0.0,
|
1489 |
+
"r":0.0,
|
1490 |
+
"f":0.0
|
1491 |
},
|
1492 |
"ccomp:obl":{
|
1493 |
+
"p":0.56,
|
1494 |
+
"r":0.4375,
|
1495 |
+
"f":0.4912280702
|
1496 |
},
|
1497 |
+
"case":{
|
1498 |
+
"p":0.9068627451,
|
1499 |
+
"r":0.943877551,
|
1500 |
+
"f":0.925
|
1501 |
+
},
|
1502 |
+
"csubj":{
|
1503 |
+
"p":0.7368421053,
|
1504 |
+
"r":0.3783783784,
|
1505 |
+
"f":0.5
|
1506 |
},
|
1507 |
"parataxis":{
|
1508 |
"p":0.1724137931,
|
1509 |
"r":0.0684931507,
|
1510 |
"f":0.0980392157
|
1511 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1512 |
"xcomp":{
|
1513 |
+
"p":0.9166666667,
|
1514 |
+
"r":0.8918918919,
|
1515 |
+
"f":0.904109589
|
1516 |
},
|
1517 |
"nummod":{
|
1518 |
+
"p":0.4671052632,
|
1519 |
+
"r":0.7634408602,
|
1520 |
+
"f":0.5795918367
|
1521 |
+
},
|
1522 |
+
"ccomp":{
|
1523 |
+
"p":0.0,
|
1524 |
+
"r":0.0,
|
1525 |
+
"f":0.0
|
1526 |
},
|
1527 |
"acl":{
|
1528 |
+
"p":0.4029850746,
|
1529 |
+
"r":0.375,
|
1530 |
+
"f":0.3884892086
|
1531 |
+
},
|
1532 |
+
"iobj":{
|
1533 |
+
"p":0.2857142857,
|
1534 |
+
"r":0.1333333333,
|
1535 |
+
"f":0.1818181818
|
1536 |
+
},
|
1537 |
+
"dep":{
|
1538 |
+
"p":0.0,
|
1539 |
+
"r":0.0,
|
1540 |
+
"f":0.0
|
1541 |
},
|
1542 |
"advmod:tto":{
|
1543 |
+
"p":0.3571428571,
|
1544 |
+
"r":0.5,
|
1545 |
+
"f":0.4166666667
|
1546 |
},
|
1547 |
"nmod":{
|
1548 |
+
"p":0.1666666667,
|
1549 |
"r":0.0909090909,
|
1550 |
+
"f":0.1176470588
|
|
|
|
|
|
|
|
|
|
|
1551 |
},
|
1552 |
"aux":{
|
1553 |
+
"p":0.8888888889,
|
1554 |
+
"r":0.6666666667,
|
1555 |
+
"f":0.7619047619
|
1556 |
},
|
1557 |
"advmod:tfrom":{
|
|
|
|
|
|
|
|
|
|
|
1558 |
"p":0.0,
|
1559 |
"r":0.0,
|
1560 |
"f":0.0
|
|
|
1565 |
"f":0.0
|
1566 |
},
|
1567 |
"compound":{
|
1568 |
+
"p":0.9268292683,
|
1569 |
+
"r":0.95,
|
1570 |
+
"f":0.9382716049
|
1571 |
},
|
1572 |
"obl:lvc":{
|
1573 |
"p":0.0,
|
|
|
1585 |
"f":0.0
|
1586 |
},
|
1587 |
"list":{
|
|
|
|
|
|
|
|
|
|
|
1588 |
"p":1.0,
|
1589 |
+
"r":0.1666666667,
|
1590 |
+
"f":0.2857142857
|
1591 |
},
|
1592 |
"ccomp:pred":{
|
1593 |
"p":0.0,
|
1594 |
"r":0.0,
|
1595 |
"f":0.0
|
1596 |
+
},
|
1597 |
+
"advmod:que":{
|
1598 |
+
"p":1.0,
|
1599 |
+
"r":0.25,
|
1600 |
+
"f":0.4
|
1601 |
}
|
1602 |
},
|
1603 |
+
"ents_p":0.8543930456,
|
1604 |
+
"ents_r":0.8369829684,
|
1605 |
+
"ents_f":0.8455984022,
|
1606 |
"ents_per_type":{
|
1607 |
"ORG":{
|
1608 |
+
"p":0.8789659224,
|
1609 |
+
"r":0.8786217698,
|
1610 |
+
"f":0.8787938124
|
1611 |
},
|
1612 |
"LOC":{
|
1613 |
+
"p":0.8245981831,
|
1614 |
+
"r":0.8898944193,
|
1615 |
+
"f":0.8560029017
|
1616 |
},
|
1617 |
"MISC":{
|
1618 |
+
"p":0.6983606557,
|
1619 |
+
"r":0.5461538462,
|
1620 |
+
"f":0.6129496403
|
1621 |
},
|
1622 |
"PER":{
|
1623 |
+
"p":0.895021645,
|
1624 |
+
"r":0.863256785,
|
1625 |
+
"f":0.8788522848
|
1626 |
}
|
1627 |
},
|
1628 |
+
"speed":1576.1377252055
|
1629 |
},
|
1630 |
"sources":[
|
1631 |
{
|
morphologizer/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1383794
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:419afa1fa20c17c7ebdf36d9d16bb529c59af77f4a85a7e33feef6df06d99f6b
|
3 |
size 1383794
|
ner/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56989356
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dcfdc7eb9e7ccb82c22bea8582667773a93a7ad2786c323ac6dadeedafe1878c
|
3 |
size 56989356
|
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 sha256:4d253b22f1fc99cae9567cd03a04470b5d191d2dd9c0937890f36d4a6d55b45d
|
3 |
size 26010735
|
senter/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 2793
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:49a7d066ca7a7f8a029d9010dc7038016067caf4e9926b4d58bf4be7651cb6f0
|
3 |
size 2793
|
tagger/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20853
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c2554af41b1dc7c6b8c86bbfaec8617ea11a09037db0ecdd4ca83bdbdc62364
|
3 |
size 20853
|
tok2vec/model
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 56806592
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:261fde9b3cc88d5bd398b95d6b078a4bf54c350a510d18705c9420da15f05e8c
|
3 |
size 56806592
|