Commit
•
080ad32
1
Parent(s):
0ae6a71
xx_cop_sigtyp_trf-0.1.0: Update SIGTYP pipeline
Browse files- README.md +19 -19
- meta.json +59 -59
- morphologizer/model +0 -0
- parser/model +0 -0
- tagger/model +0 -0
- trainable_lemmatizer/model +0 -0
- transformer/model +2 -2
- vocab/strings.json +4 -0
- xx_cop_sigtyp_trf-any-py3-none-any.whl +2 -2
README.md
CHANGED
@@ -13,21 +13,21 @@ model-index:
|
|
13 |
metrics:
|
14 |
- name: TAG (XPOS) Accuracy
|
15 |
type: accuracy
|
16 |
-
value: 0.
|
17 |
- task:
|
18 |
name: POS
|
19 |
type: token-classification
|
20 |
metrics:
|
21 |
- name: POS (UPOS) Accuracy
|
22 |
type: accuracy
|
23 |
-
value: 0.
|
24 |
- task:
|
25 |
name: MORPH
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: Morph (UFeats) Accuracy
|
29 |
type: accuracy
|
30 |
-
value: 0.
|
31 |
- task:
|
32 |
name: LEMMA
|
33 |
type: token-classification
|
@@ -41,21 +41,21 @@ model-index:
|
|
41 |
metrics:
|
42 |
- name: Unlabeled Attachment Score (UAS)
|
43 |
type: f_score
|
44 |
-
value: 0.
|
45 |
- task:
|
46 |
name: LABELED_DEPENDENCIES
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Labeled Attachment Score (LAS)
|
50 |
type: f_score
|
51 |
-
value: 0.
|
52 |
- task:
|
53 |
name: SENTS
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Sentences F-Score
|
57 |
type: f_score
|
58 |
-
value: 0.
|
59 |
---
|
60 |
| Feature | Description |
|
61 |
| --- | --- |
|
@@ -87,17 +87,17 @@ model-index:
|
|
87 |
|
88 |
| Type | Score |
|
89 |
| --- | --- |
|
90 |
-
| `DEP_UAS` | 2.
|
91 |
-
| `DEP_LAS` |
|
92 |
-
| `SENTS_P` |
|
93 |
-
| `SENTS_R` |
|
94 |
-
| `SENTS_F` |
|
95 |
| `LEMMA_ACC` | 29.43 |
|
96 |
-
| `TAG_ACC` | 28.
|
97 |
-
| `POS_ACC` | 28.
|
98 |
-
| `MORPH_ACC` |
|
99 |
-
| `TRANSFORMER_LOSS` |
|
100 |
-
| `PARSER_LOSS` |
|
101 |
-
| `TRAINABLE_LEMMATIZER_LOSS` |
|
102 |
-
| `TAGGER_LOSS` |
|
103 |
-
| `MORPHOLOGIZER_LOSS` |
|
|
|
13 |
metrics:
|
14 |
- name: TAG (XPOS) Accuracy
|
15 |
type: accuracy
|
16 |
+
value: 0.2868357488
|
17 |
- task:
|
18 |
name: POS
|
19 |
type: token-classification
|
20 |
metrics:
|
21 |
- name: POS (UPOS) Accuracy
|
22 |
type: accuracy
|
23 |
+
value: 0.2892512077
|
24 |
- task:
|
25 |
name: MORPH
|
26 |
type: token-classification
|
27 |
metrics:
|
28 |
- name: Morph (UFeats) Accuracy
|
29 |
type: accuracy
|
30 |
+
value: 0.2913647343
|
31 |
- task:
|
32 |
name: LEMMA
|
33 |
type: token-classification
|
|
|
41 |
metrics:
|
42 |
- name: Unlabeled Attachment Score (UAS)
|
43 |
type: f_score
|
44 |
+
value: 0.0242584047
|
45 |
- task:
|
46 |
name: LABELED_DEPENDENCIES
|
47 |
type: token-classification
|
48 |
metrics:
|
49 |
- name: Labeled Attachment Score (LAS)
|
50 |
type: f_score
|
51 |
+
value: 0.0218852999
|
52 |
- task:
|
53 |
name: SENTS
|
54 |
type: token-classification
|
55 |
metrics:
|
56 |
- name: Sentences F-Score
|
57 |
type: f_score
|
58 |
+
value: 0.9634703196
|
59 |
---
|
60 |
| Feature | Description |
|
61 |
| --- | --- |
|
|
|
87 |
|
88 |
| Type | Score |
|
89 |
| --- | --- |
|
90 |
+
| `DEP_UAS` | 2.43 |
|
91 |
+
| `DEP_LAS` | 2.19 |
|
92 |
+
| `SENTS_P` | 95.05 |
|
93 |
+
| `SENTS_R` | 97.69 |
|
94 |
+
| `SENTS_F` | 96.35 |
|
95 |
| `LEMMA_ACC` | 29.43 |
|
96 |
+
| `TAG_ACC` | 28.68 |
|
97 |
+
| `POS_ACC` | 28.93 |
|
98 |
+
| `MORPH_ACC` | 29.14 |
|
99 |
+
| `TRANSFORMER_LOSS` | 68087.86 |
|
100 |
+
| `PARSER_LOSS` | 43157.88 |
|
101 |
+
| `TRAINABLE_LEMMATIZER_LOSS` | 5961.08 |
|
102 |
+
| `TAGGER_LOSS` | 4684.65 |
|
103 |
+
| `MORPHOLOGIZER_LOSS` | 3294.98 |
|
meta.json
CHANGED
@@ -337,18 +337,18 @@
|
|
337 |
|
338 |
],
|
339 |
"performance":{
|
340 |
-
"dep_uas":0.
|
341 |
-
"dep_las":0.
|
342 |
"dep_las_per_type":{
|
343 |
"cc":{
|
344 |
-
"p":0.
|
345 |
-
"r":0.
|
346 |
-
"f":0.
|
347 |
},
|
348 |
"mark":{
|
349 |
-
"p":0.
|
350 |
-
"r":0.
|
351 |
-
"f":0.
|
352 |
},
|
353 |
"nsubj":{
|
354 |
"p":0.0,
|
@@ -356,19 +356,19 @@
|
|
356 |
"f":0.0
|
357 |
},
|
358 |
"root":{
|
359 |
-
"p":0.
|
360 |
-
"r":0.
|
361 |
-
"f":0.
|
362 |
},
|
363 |
"case":{
|
364 |
-
"p":0
|
365 |
"r":0.0012886598,
|
366 |
-
"f":0.
|
367 |
},
|
368 |
"obl":{
|
369 |
-
"p":0.
|
370 |
-
"r":0.
|
371 |
-
"f":0.
|
372 |
},
|
373 |
"acl:relcl":{
|
374 |
"p":0.0,
|
@@ -391,9 +391,9 @@
|
|
391 |
"f":0.0
|
392 |
},
|
393 |
"advmod":{
|
394 |
-
"p":0.
|
395 |
"r":0.0714285714,
|
396 |
-
"f":0.
|
397 |
},
|
398 |
"advcl":{
|
399 |
"p":0.0,
|
@@ -411,9 +411,9 @@
|
|
411 |
"f":0.0
|
412 |
},
|
413 |
"parataxis":{
|
414 |
-
"p":0.
|
415 |
-
"r":0.
|
416 |
-
"f":0.
|
417 |
},
|
418 |
"nmod":{
|
419 |
"p":0.0,
|
@@ -421,9 +421,9 @@
|
|
421 |
"f":0.0
|
422 |
},
|
423 |
"cop":{
|
424 |
-
"p":0.
|
425 |
"r":0.1538461538,
|
426 |
-
"f":0.
|
427 |
},
|
428 |
"appos":{
|
429 |
"p":0.0,
|
@@ -431,14 +431,14 @@
|
|
431 |
"f":0.0
|
432 |
},
|
433 |
"fixed":{
|
434 |
-
"p":
|
435 |
-
"r":0.
|
436 |
-
"f":0.
|
437 |
},
|
438 |
"conj":{
|
439 |
-
"p":0.
|
440 |
-
"r":0.
|
441 |
-
"f":0.
|
442 |
},
|
443 |
"xcomp":{
|
444 |
"p":0.0,
|
@@ -501,23 +501,23 @@
|
|
501 |
"f":0.0
|
502 |
}
|
503 |
},
|
504 |
-
"sents_p":0.
|
505 |
-
"sents_r":0.
|
506 |
-
"sents_f":0.
|
507 |
"lemma_acc":0.2942952007,
|
508 |
-
"tag_acc":0.
|
509 |
-
"pos_acc":0.
|
510 |
-
"morph_acc":0.
|
511 |
"morph_per_feat":{
|
512 |
"Foreign":{
|
513 |
-
"p":0.
|
514 |
-
"r":0.
|
515 |
-
"f":0.
|
516 |
},
|
517 |
"Definite":{
|
518 |
-
"p":0
|
519 |
-
"r":0.
|
520 |
-
"f":0.
|
521 |
},
|
522 |
"Gender":{
|
523 |
"p":1.0,
|
@@ -525,24 +525,24 @@
|
|
525 |
"f":0.1027667984
|
526 |
},
|
527 |
"Number":{
|
528 |
-
"p":0
|
529 |
-
"r":0.
|
530 |
-
"f":0.
|
531 |
},
|
532 |
"Person":{
|
533 |
-
"p":0
|
534 |
-
"r":0.
|
535 |
-
"f":0.
|
536 |
},
|
537 |
"PronType":{
|
538 |
-
"p":0.
|
539 |
-
"r":0.
|
540 |
-
"f":0.
|
541 |
},
|
542 |
"VerbForm":{
|
543 |
-
"p":0.
|
544 |
-
"r":0.
|
545 |
-
"f":0.
|
546 |
},
|
547 |
"Polarity":{
|
548 |
"p":1.0,
|
@@ -575,13 +575,13 @@
|
|
575 |
"f":0.0
|
576 |
}
|
577 |
},
|
578 |
-
"transformer_loss":
|
579 |
-
"parser_loss":
|
580 |
-
"trainable_lemmatizer_loss":
|
581 |
-
"tagger_loss":
|
582 |
-
"morphologizer_loss":
|
583 |
},
|
584 |
"requirements":[
|
585 |
-
"spacy-transformers>=1.3.
|
586 |
]
|
587 |
}
|
|
|
337 |
|
338 |
],
|
339 |
"performance":{
|
340 |
+
"dep_uas":0.0242584047,
|
341 |
+
"dep_las":0.0218852999,
|
342 |
"dep_las_per_type":{
|
343 |
"cc":{
|
344 |
+
"p":0.9047619048,
|
345 |
+
"r":0.1104651163,
|
346 |
+
"f":0.1968911917
|
347 |
},
|
348 |
"mark":{
|
349 |
+
"p":0.75,
|
350 |
+
"r":0.0069444444,
|
351 |
+
"f":0.0137614679
|
352 |
},
|
353 |
"nsubj":{
|
354 |
"p":0.0,
|
|
|
356 |
"f":0.0
|
357 |
},
|
358 |
"root":{
|
359 |
+
"p":0.2705882353,
|
360 |
+
"r":0.1064814815,
|
361 |
+
"f":0.1528239203
|
362 |
},
|
363 |
"case":{
|
364 |
+
"p":1.0,
|
365 |
"r":0.0012886598,
|
366 |
+
"f":0.0025740026
|
367 |
},
|
368 |
"obl":{
|
369 |
+
"p":0.3333333333,
|
370 |
+
"r":0.0023094688,
|
371 |
+
"f":0.004587156
|
372 |
},
|
373 |
"acl:relcl":{
|
374 |
"p":0.0,
|
|
|
391 |
"f":0.0
|
392 |
},
|
393 |
"advmod":{
|
394 |
+
"p":0.6060606061,
|
395 |
"r":0.0714285714,
|
396 |
+
"f":0.1277955272
|
397 |
},
|
398 |
"advcl":{
|
399 |
"p":0.0,
|
|
|
411 |
"f":0.0
|
412 |
},
|
413 |
"parataxis":{
|
414 |
+
"p":0.0,
|
415 |
+
"r":0.0,
|
416 |
+
"f":0.0
|
417 |
},
|
418 |
"nmod":{
|
419 |
"p":0.0,
|
|
|
421 |
"f":0.0
|
422 |
},
|
423 |
"cop":{
|
424 |
+
"p":0.4705882353,
|
425 |
"r":0.1538461538,
|
426 |
+
"f":0.231884058
|
427 |
},
|
428 |
"appos":{
|
429 |
"p":0.0,
|
|
|
431 |
"f":0.0
|
432 |
},
|
433 |
"fixed":{
|
434 |
+
"p":1.0,
|
435 |
+
"r":0.0416666667,
|
436 |
+
"f":0.08
|
437 |
},
|
438 |
"conj":{
|
439 |
+
"p":0.3333333333,
|
440 |
+
"r":0.0291970803,
|
441 |
+
"f":0.0536912752
|
442 |
},
|
443 |
"xcomp":{
|
444 |
"p":0.0,
|
|
|
501 |
"f":0.0
|
502 |
}
|
503 |
},
|
504 |
+
"sents_p":0.9504504505,
|
505 |
+
"sents_r":0.9768518519,
|
506 |
+
"sents_f":0.9634703196,
|
507 |
"lemma_acc":0.2942952007,
|
508 |
+
"tag_acc":0.2868357488,
|
509 |
+
"pos_acc":0.2892512077,
|
510 |
+
"morph_acc":0.2913647343,
|
511 |
"morph_per_feat":{
|
512 |
"Foreign":{
|
513 |
+
"p":0.9898477157,
|
514 |
+
"r":0.40625,
|
515 |
+
"f":0.576070901
|
516 |
},
|
517 |
"Definite":{
|
518 |
+
"p":1.0,
|
519 |
+
"r":0.029318037,
|
520 |
+
"f":0.0569659443
|
521 |
},
|
522 |
"Gender":{
|
523 |
"p":1.0,
|
|
|
525 |
"f":0.1027667984
|
526 |
},
|
527 |
"Number":{
|
528 |
+
"p":1.0,
|
529 |
+
"r":0.053030303,
|
530 |
+
"f":0.1007194245
|
531 |
},
|
532 |
"Person":{
|
533 |
+
"p":1.0,
|
534 |
+
"r":0.0326659642,
|
535 |
+
"f":0.0632653061
|
536 |
},
|
537 |
"PronType":{
|
538 |
+
"p":0.9577464789,
|
539 |
+
"r":0.0417947142,
|
540 |
+
"f":0.0800942285
|
541 |
},
|
542 |
"VerbForm":{
|
543 |
+
"p":0.9166666667,
|
544 |
+
"r":0.0995475113,
|
545 |
+
"f":0.1795918367
|
546 |
},
|
547 |
"Polarity":{
|
548 |
"p":1.0,
|
|
|
575 |
"f":0.0
|
576 |
}
|
577 |
},
|
578 |
+
"transformer_loss":680.8785867814,
|
579 |
+
"parser_loss":431.5788031977,
|
580 |
+
"trainable_lemmatizer_loss":59.610784068,
|
581 |
+
"tagger_loss":46.8465012404,
|
582 |
+
"morphologizer_loss":32.949805721
|
583 |
},
|
584 |
"requirements":[
|
585 |
+
"spacy-transformers>=1.3.4,<1.4.0"
|
586 |
]
|
587 |
}
|
morphologizer/model
CHANGED
Binary files a/morphologizer/model and b/morphologizer/model differ
|
|
parser/model
CHANGED
Binary files a/parser/model and b/parser/model differ
|
|
tagger/model
CHANGED
Binary files a/tagger/model and b/tagger/model differ
|
|
trainable_lemmatizer/model
CHANGED
Binary files a/trainable_lemmatizer/model and b/trainable_lemmatizer/model differ
|
|
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:e2e76a9d38793e359a442166ae74a7d55f23957e4c44432deaf3cf7ae08a2abe
|
3 |
+
size 508592662
|
vocab/strings.json
CHANGED
@@ -8560,6 +8560,7 @@
|
|
8560 |
"\u2c99\u2cb1\u2c81\u2c83",
|
8561 |
"\u2c99\u2cb1\u2c81\u2c83\u2c93\u2ca7\u2c8f\u2ca5",
|
8562 |
"\u2c99\u2cb1\u2c85\u2c93\u2ca5",
|
|
|
8563 |
"\u2c99\u2cb1\u2c9b",
|
8564 |
"\u2c99\u2cb1\u2c9b\u2c9f\u2c9b",
|
8565 |
"\u2c99\u2cb1\u2ca5",
|
@@ -10785,6 +10786,7 @@
|
|
10785 |
"\u2c9b\u2cb1\u2c9b\u2c89",
|
10786 |
"\u2c9b\u2cb1\u2ca3\u03e3",
|
10787 |
"\u2c9b\u2cb1\u2ca5",
|
|
|
10788 |
"\u2c9d",
|
10789 |
"\u2c9d\u2c89\u2ca5\u2ca7\u2c8f\u2ca5",
|
10790 |
"\u2c9d\u2c93\u2c81",
|
@@ -11420,6 +11422,7 @@
|
|
11420 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2c97\u2c89\u2c85\u2c93\u2cb1\u2c9b",
|
11421 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca1\u2ca7\u2c8f\u2ca3\u03e5",
|
11422 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca9\u03eb\u2c9f\u2c9f\u2ca5",
|
|
|
11423 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca9\u2ca5\u2ca7\u2c81\u2ca9\u2ca3\u2c9f\u2ca9",
|
11424 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca9\u2ca7\u2c9f\u03ed\u2c9b\u2c89\u03e5",
|
11425 |
"\u2ca1\u2c89\u2c9f\u2c9f\u2ca9",
|
@@ -11721,6 +11724,7 @@
|
|
11721 |
"\u2ca1\u2ca5\u2cb1\u2c99\u2c81",
|
11722 |
"\u2ca1\u2ca5\u2cb1\u2ca7\u2c89",
|
11723 |
"\u2ca1\u2ca5\u2cb1\u2ca7\u2c8f\u2ca3",
|
|
|
11724 |
"\u2ca1\u2ca7\u2c81\u03eb\u2ca3\u2c9f",
|
11725 |
"\u2ca1\u2ca7\u2c81\u2c89\u2c93\u2c9f",
|
11726 |
"\u2ca1\u2ca7\u2c83\u2c83\u2c9f",
|
|
|
8560 |
"\u2c99\u2cb1\u2c81\u2c83",
|
8561 |
"\u2c99\u2cb1\u2c81\u2c83\u2c93\u2ca7\u2c8f\u2ca5",
|
8562 |
"\u2c99\u2cb1\u2c85\u2c93\u2ca5",
|
8563 |
+
"\u2c99\u2cb1\u2c95\u03e9",
|
8564 |
"\u2c99\u2cb1\u2c9b",
|
8565 |
"\u2c99\u2cb1\u2c9b\u2c9f\u2c9b",
|
8566 |
"\u2c99\u2cb1\u2ca5",
|
|
|
10786 |
"\u2c9b\u2cb1\u2c9b\u2c89",
|
10787 |
"\u2c9b\u2cb1\u2ca3\u03e3",
|
10788 |
"\u2c9b\u2cb1\u2ca5",
|
10789 |
+
"\u2c9b\u2cb1\u2ca9\u2ca5\u2c9f\u2ca1",
|
10790 |
"\u2c9d",
|
10791 |
"\u2c9d\u2c89\u2ca5\u2ca7\u2c8f\u2ca5",
|
10792 |
"\u2c9d\u2c93\u2c81",
|
|
|
11422 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2c97\u2c89\u2c85\u2c93\u2cb1\u2c9b",
|
11423 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca1\u2ca7\u2c8f\u2ca3\u03e5",
|
11424 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca9\u03eb\u2c9f\u2c9f\u2ca5",
|
11425 |
+
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca9\u2c9b\u2c81\u2ca9",
|
11426 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca9\u2ca5\u2ca7\u2c81\u2ca9\u2ca3\u2c9f\u2ca9",
|
11427 |
"\u2ca1\u2c89\u2c9b\u2ca7\u2c81\u2ca9\u2ca7\u2c9f\u03ed\u2c9b\u2c89\u03e5",
|
11428 |
"\u2ca1\u2c89\u2c9f\u2c9f\u2ca9",
|
|
|
11724 |
"\u2ca1\u2ca5\u2cb1\u2c99\u2c81",
|
11725 |
"\u2ca1\u2ca5\u2cb1\u2ca7\u2c89",
|
11726 |
"\u2ca1\u2ca5\u2cb1\u2ca7\u2c8f\u2ca3",
|
11727 |
+
"\u2ca1\u2ca7\u03e9\u2c89",
|
11728 |
"\u2ca1\u2ca7\u2c81\u03eb\u2ca3\u2c9f",
|
11729 |
"\u2ca1\u2ca7\u2c81\u2c89\u2c93\u2c9f",
|
11730 |
"\u2ca1\u2ca7\u2c83\u2c83\u2c9f",
|
xx_cop_sigtyp_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:a1f898d58be260f07531ebac42e4ae188b03a5745ca4f59834592b8b091fc641
|
3 |
+
size 468539341
|