Hugging Face's logo

ljvmiranda921
/
zh_lzh_sigtyp_trf

Token Classification
spaCy
Chinese
Eval Results
Model card Files Community
ljvmiranda921 commited on
Commit
a88137c
β€’
1 Parent(s): 0811cd4

zh_lzh_sigtyp_trf-0.1.0: Update SIGTYP pipeline

Browse files
Files changed (8) hide show
  1. README.md +20 -20
  2. meta.json +178 -178
  3. morphologizer/model +0 -0
  4. parser/model +1 -1
  5. tagger/model +0 -0
  6. trainable_lemmatizer/model +0 -0
  7. transformer/model +1 -1
  8. zh_lzh_sigtyp_trf-any-py3-none-any.whl +2 -2
README.md CHANGED
@@ -13,49 +13,49 @@ model-index:
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
- value: 0.7418288567
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
- value: 0.794490103
24
  - task:
25
  name: MORPH
26
  type: token-classification
27
  metrics:
28
  - name: Morph (UFeats) Accuracy
29
  type: accuracy
30
- value: 0.823496743
31
  - task:
32
  name: LEMMA
33
  type: token-classification
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
- value: 0.941164414
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
- value: 0.8227824679
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
- value: 0.7687085041
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
- value: 0.9942116231
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
@@ -88,16 +88,16 @@ model-index:
88
  | Type | Score |
89
  | --- | --- |
90
  | `DEP_UAS` | 82.28 |
91
- | `DEP_LAS` | 76.87 |
92
- | `SENTS_P` | 99.26 |
93
- | `SENTS_R` | 99.58 |
94
- | `SENTS_F` | 99.42 |
95
- | `LEMMA_ACC` | 94.12 |
96
- | `TAG_ACC` | 74.18 |
97
- | `POS_ACC` | 79.45 |
98
- | `MORPH_ACC` | 82.35 |
99
- | `TRANSFORMER_LOSS` | 3455711.53 |
100
- | `PARSER_LOSS` | 1091508.57 |
101
- | `TRAINABLE_LEMMATIZER_LOSS` | 103471.04 |
102
- | `TAGGER_LOSS` | 2743935.00 |
103
- | `MORPHOLOGIZER_LOSS` | 2387347.18 |
 
13
  metrics:
14
  - name: TAG (XPOS) Accuracy
15
  type: accuracy
16
+ value: 0.742052984
17
  - task:
18
  name: POS
19
  type: token-classification
20
  metrics:
21
  - name: POS (UPOS) Accuracy
22
  type: accuracy
23
+ value: 0.7949418685
24
  - task:
25
  name: MORPH
26
  type: token-classification
27
  metrics:
28
  - name: Morph (UFeats) Accuracy
29
  type: accuracy
30
+ value: 0.8236478744
31
  - task:
32
  name: LEMMA
33
  type: token-classification
34
  metrics:
35
  - name: Lemma Accuracy
36
  type: accuracy
37
+ value: 0.942007037
38
  - task:
39
  name: UNLABELED_DEPENDENCIES
40
  type: token-classification
41
  metrics:
42
  - name: Unlabeled Attachment Score (UAS)
43
  type: f_score
44
+ value: 0.8228271306
45
  - task:
46
  name: LABELED_DEPENDENCIES
47
  type: token-classification
48
  metrics:
49
  - name: Labeled Attachment Score (LAS)
50
  type: f_score
51
+ value: 0.7703219397
52
  - task:
53
  name: SENTS
54
  type: token-classification
55
  metrics:
56
  - name: Sentences F-Score
57
  type: f_score
58
+ value: 0.9851073655
59
  ---
60
  | Feature | Description |
61
  | --- | --- |
 
88
  | Type | Score |
89
  | --- | --- |
90
  | `DEP_UAS` | 82.28 |
91
+ | `DEP_LAS` | 77.03 |
92
+ | `SENTS_P` | 98.08 |
93
+ | `SENTS_R` | 98.94 |
94
+ | `SENTS_F` | 98.51 |
95
+ | `LEMMA_ACC` | 94.20 |
96
+ | `TAG_ACC` | 74.21 |
97
+ | `POS_ACC` | 79.49 |
98
+ | `MORPH_ACC` | 82.36 |
99
+ | `TRANSFORMER_LOSS` | 3733506.66 |
100
+ | `PARSER_LOSS` | 1170567.44 |
101
+ | `TRAINABLE_LEMMATIZER_LOSS` | 98325.33 |
102
+ | `TAGGER_LOSS` | 2806037.87 |
103
+ | `MORPHOLOGIZER_LOSS` | 2426650.00 |
meta.json CHANGED
@@ -316,193 +316,188 @@
316
 
317
  ],
318
  "performance":{
319
- "dep_uas":0.8227824679,
320
- "dep_las":0.7687085041,
321
  "dep_las_per_type":{
322
  "obl:lmod":{
323
- "p":0.7175438596,
324
- "r":0.7574074074,
325
- "f":0.7369369369
326
  },
327
  "root":{
328
- "p":0.8506410997,
329
- "r":0.8538961039,
330
- "f":0.8522654939
331
  },
332
  "obj":{
333
- "p":0.7886742612,
334
- "r":0.8133832794,
335
- "f":0.800838223
336
  },
337
  "nsubj":{
338
- "p":0.7697419859,
339
- "r":0.7765726681,
340
- "f":0.7731422401
341
  },
342
  "advmod":{
343
- "p":0.8285186041,
344
- "r":0.8366394399,
345
- "f":0.8325592197
346
  },
347
  "case":{
348
- "p":0.846727899,
349
- "r":0.853587963,
350
- "f":0.8501440922
351
  },
352
  "acl":{
353
- "p":0.6481927711,
354
- "r":0.5991091314,
355
- "f":0.6226851852
356
  },
357
  "amod":{
358
- "p":0.6948424069,
359
- "r":0.7132352941,
360
- "f":0.7039187228
361
  },
362
  "parataxis":{
363
- "p":0.5154320988,
364
- "r":0.5832363213,
365
- "f":0.5472419443
366
- },
367
- "flat":{
368
- "p":0.745471878,
369
- "r":0.7281191806,
370
- "f":0.7366933585
371
  },
372
  "conj":{
373
- "p":0.6012478729,
374
- "r":0.5617382088,
375
- "f":0.5808219178
 
 
 
 
 
376
  },
377
  "nmod":{
378
- "p":0.6947530864,
379
- "r":0.7515859766,
380
- "f":0.722052927
381
  },
382
  "cop":{
383
- "p":0.6736111111,
384
  "r":0.8049792531,
385
- "f":0.7334593573
386
  },
387
  "discourse:sp":{
388
- "p":0.8012618297,
389
- "r":0.8025276461,
390
- "f":0.8018942384
391
  },
392
  "ccomp":{
393
- "p":0.552437223,
394
- "r":0.5590433483,
395
- "f":0.5557206538
396
  },
397
  "aux":{
398
- "p":0.8916478555,
399
- "r":0.8797327394,
400
- "f":0.8856502242
401
  },
402
  "csubj":{
403
- "p":0.3918495298,
404
- "r":0.425170068,
405
- "f":0.4078303426
406
  },
407
  "clf":{
408
- "p":0.7591623037,
409
- "r":0.6651376147,
410
- "f":0.7090464548
411
- },
412
- "advcl":{
413
- "p":0.6098191214,
414
- "r":0.5400457666,
415
- "f":0.572815534
416
  },
417
  "nummod":{
418
- "p":0.7331136738,
419
- "r":0.8225508318,
420
- "f":0.775261324
421
  },
422
  "obl:tmod":{
423
- "p":0.7066974596,
424
- "r":0.7574257426,
425
- "f":0.7311827957
426
  },
427
  "det":{
428
- "p":0.8647619048,
429
- "r":0.8714011516,
430
- "f":0.8680688337
431
  },
432
  "compound":{
433
- "p":0.8644400786,
434
- "r":0.8396946565,
435
- "f":0.8518877057
436
  },
437
  "obl":{
438
- "p":0.6872427984,
439
- "r":0.5890652557,
440
- "f":0.6343779677
441
  },
442
  "flat:vv":{
443
- "p":0.5869565217,
444
- "r":0.5684210526,
445
- "f":0.577540107
446
  },
447
  "cc":{
448
- "p":0.8704581359,
449
- "r":0.8930307942,
450
- "f":0.8816
 
 
 
 
 
 
 
 
 
 
451
  },
452
  "fixed":{
453
- "p":0.7808219178,
454
- "r":0.6705882353,
455
- "f":0.7215189873
456
  },
457
  "xcomp":{
458
- "p":0.8550724638,
459
- "r":0.8613138686,
460
- "f":0.8581818182
461
  },
462
  "dislocated":{
463
- "p":0.2857142857,
464
  "r":0.2105263158,
465
- "f":0.2424242424
466
  },
467
  "mark":{
468
- "p":0.6096654275,
469
- "r":0.6356589147,
470
- "f":0.6223908918
471
  },
472
- "iobj":{
473
- "p":0.5871559633,
474
- "r":0.5663716814,
475
- "f":0.5765765766
476
- },
477
- "dep":{
478
- "p":0.0,
479
- "r":0.0,
480
- "f":0.0
481
  },
482
  "compound:redup":{
483
- "p":0.5571428571,
484
- "r":0.52,
485
- "f":0.5379310345
486
- },
487
- "nsubj:outer":{
488
- "p":0.4343434343,
489
- "r":0.309352518,
490
- "f":0.3613445378
491
  },
492
  "discourse":{
493
- "p":0.4719101124,
494
- "r":0.5,
495
- "f":0.4855491329
496
  },
497
  "expl":{
498
- "p":0.7948717949,
499
- "r":0.5535714286,
500
- "f":0.6526315789
501
  },
502
  "vocative":{
503
  "p":0.5,
504
- "r":0.3125,
505
- "f":0.3846153846
506
  },
507
  "list":{
508
  "p":0.0,
@@ -518,102 +513,107 @@
518
  "p":0.0,
519
  "r":0.0,
520
  "f":0.0
 
 
 
 
 
521
  }
522
  },
523
- "sents_p":0.9926028664,
524
- "sents_r":0.995825603,
525
- "sents_f":0.9942116231,
526
- "lemma_acc":0.941164414,
527
- "tag_acc":0.7418288567,
528
- "pos_acc":0.794490103,
529
- "morph_acc":0.823496743,
530
  "morph_per_feat":{
531
  "Case":{
532
- "p":0.9477834612,
533
- "r":0.8454372624,
534
- "f":0.8936897106
535
  },
536
  "NameType":{
537
- "p":0.8578779711,
538
- "r":0.7701275847,
539
- "f":0.8116378811
540
  },
541
  "PronType":{
542
- "p":0.9238548483,
543
- "r":0.7434179033,
544
- "f":0.823872679
545
  },
546
  "AdvType":{
547
- "p":0.8995756719,
548
- "r":0.8796680498,
549
- "f":0.8895104895
550
  },
551
  "Degree":{
552
- "p":0.9132757912,
553
- "r":0.7709923664,
554
- "f":0.8361241769
555
  },
556
  "VerbForm":{
557
- "p":0.8349834983,
558
- "r":0.6042993631,
559
- "f":0.7011547344
560
  },
561
  "Polarity":{
562
- "p":0.8795986622,
563
- "r":0.7535816619,
564
- "f":0.8117283951
565
  },
566
  "Person":{
567
- "p":0.9634025717,
568
- "r":0.7257824143,
569
- "f":0.827879303
570
  },
571
  "VerbType":{
572
- "p":0.815,
573
- "r":0.6763485477,
574
- "f":0.7392290249
575
  },
576
  "Mood":{
577
- "p":0.7323651452,
578
- "r":0.772428884,
579
- "f":0.7518636848
580
  },
581
  "NounType":{
582
- "p":0.9014084507,
583
- "r":0.6336633663,
584
- "f":0.7441860465
585
  },
586
  "Tense":{
587
- "p":0.8804347826,
588
- "r":0.7941176471,
589
- "f":0.8350515464
590
  },
591
  "Aspect":{
592
- "p":0.9701492537,
593
- "r":0.8783783784,
594
- "f":0.9219858156
595
  },
596
  "Reflex":{
597
- "p":0.9603960396,
598
- "r":0.7886178862,
599
- "f":0.8660714286
600
  },
601
  "Voice":{
602
  "p":1.0,
603
- "r":0.625,
604
- "f":0.7692307692
605
  },
606
  "NumType":{
607
- "p":1.0,
608
- "r":0.85,
609
- "f":0.9189189189
610
  }
611
  },
612
- "transformer_loss":34557.1153369261,
613
- "parser_loss":10915.0856971908,
614
- "trainable_lemmatizer_loss":1034.7104087231,
615
- "tagger_loss":27439.3499745419,
616
- "morphologizer_loss":23873.4718287597
617
  },
618
  "requirements":[
619
  "spacy-transformers>=1.3.4,<1.4.0"
 
316
 
317
  ],
318
  "performance":{
319
+ "dep_uas":0.8228271306,
320
+ "dep_las":0.7703219397,
321
  "dep_las_per_type":{
322
  "obl:lmod":{
323
+ "p":0.724738676,
324
+ "r":0.7703703704,
325
+ "f":0.7468581688
326
  },
327
  "root":{
328
+ "p":0.8493056353,
329
+ "r":0.8580705009,
330
+ "f":0.8536655707
331
  },
332
  "obj":{
333
+ "p":0.7878246753,
334
+ "r":0.8263238549,
335
+ "f":0.8066151417
336
  },
337
  "nsubj":{
338
+ "p":0.7660703755,
339
+ "r":0.7684874778,
340
+ "f":0.767277023
341
  },
342
  "advmod":{
343
+ "p":0.834625323,
344
+ "r":0.8291715286,
345
+ "f":0.8318894872
346
  },
347
  "case":{
348
+ "p":0.8498273878,
349
+ "r":0.8547453704,
350
+ "f":0.8522792845
351
  },
352
  "acl":{
353
+ "p":0.6804878049,
354
+ "r":0.6213808463,
355
+ "f":0.6495925495
356
  },
357
  "amod":{
358
+ "p":0.7589359933,
359
+ "r":0.6713235294,
360
+ "f":0.7124463519
361
  },
362
  "parataxis":{
363
+ "p":0.5093596059,
364
+ "r":0.601862631,
365
+ "f":0.5517609392
 
 
 
 
 
366
  },
367
  "conj":{
368
+ "p":0.5870056497,
369
+ "r":0.550609433,
370
+ "f":0.5682253213
371
+ },
372
+ "iobj":{
373
+ "p":0.5102040816,
374
+ "r":0.6637168142,
375
+ "f":0.5769230769
376
  },
377
  "nmod":{
378
+ "p":0.698358625,
379
+ "r":0.7529215359,
380
+ "f":0.7246143959
381
  },
382
  "cop":{
383
+ "p":0.6689655172,
384
  "r":0.8049792531,
385
+ "f":0.7306967985
386
  },
387
  "discourse:sp":{
388
+ "p":0.8123028391,
389
+ "r":0.8135860979,
390
+ "f":0.8129439621
391
  },
392
  "ccomp":{
393
+ "p":0.5366197183,
394
+ "r":0.5695067265,
395
+ "f":0.5525743292
396
  },
397
  "aux":{
398
+ "p":0.8967889908,
399
+ "r":0.8708240535,
400
+ "f":0.8836158192
401
  },
402
  "csubj":{
403
+ "p":0.5193133047,
404
+ "r":0.4115646259,
405
+ "f":0.4592030361
406
  },
407
  "clf":{
408
+ "p":0.7727272727,
409
+ "r":0.623853211,
410
+ "f":0.6903553299
 
 
 
 
 
411
  },
412
  "nummod":{
413
+ "p":0.7285945073,
414
+ "r":0.8336414048,
415
+ "f":0.7775862069
416
  },
417
  "obl:tmod":{
418
+ "p":0.7013888889,
419
+ "r":0.75,
420
+ "f":0.7248803828
421
  },
422
  "det":{
423
+ "p":0.8565965583,
424
+ "r":0.8598848369,
425
+ "f":0.8582375479
426
  },
427
  "compound":{
428
+ "p":0.8364661654,
429
+ "r":0.8492366412,
430
+ "f":0.8428030303
431
  },
432
  "obl":{
433
+ "p":0.6679920477,
434
+ "r":0.5925925926,
435
+ "f":0.6280373832
436
  },
437
  "flat:vv":{
438
+ "p":0.5630252101,
439
+ "r":0.5877192982,
440
+ "f":0.5751072961
441
  },
442
  "cc":{
443
+ "p":0.8785942492,
444
+ "r":0.8914100486,
445
+ "f":0.8849557522
446
+ },
447
+ "advcl":{
448
+ "p":0.6465753425,
449
+ "r":0.5400457666,
450
+ "f":0.5885286783
451
+ },
452
+ "flat":{
453
+ "p":0.7286476868,
454
+ "r":0.7625698324,
455
+ "f":0.7452229299
456
  },
457
  "fixed":{
458
+ "p":0.7534246575,
459
+ "r":0.6470588235,
460
+ "f":0.6962025316
461
  },
462
  "xcomp":{
463
+ "p":0.8357142857,
464
+ "r":0.8540145985,
465
+ "f":0.844765343
466
  },
467
  "dislocated":{
468
+ "p":0.4444444444,
469
  "r":0.2105263158,
470
+ "f":0.2857142857
471
  },
472
  "mark":{
473
+ "p":0.6396761134,
474
+ "r":0.6124031008,
475
+ "f":0.6257425743
476
  },
477
+ "nsubj:outer":{
478
+ "p":0.4607843137,
479
+ "r":0.3381294964,
480
+ "f":0.3900414938
 
 
 
 
 
481
  },
482
  "compound:redup":{
483
+ "p":0.5806451613,
484
+ "r":0.48,
485
+ "f":0.5255474453
 
 
 
 
 
486
  },
487
  "discourse":{
488
+ "p":0.5657894737,
489
+ "r":0.5119047619,
490
+ "f":0.5375
491
  },
492
  "expl":{
493
+ "p":0.8181818182,
494
+ "r":0.4821428571,
495
+ "f":0.606741573
496
  },
497
  "vocative":{
498
  "p":0.5,
499
+ "r":0.375,
500
+ "f":0.4285714286
501
  },
502
  "list":{
503
  "p":0.0,
 
513
  "p":0.0,
514
  "r":0.0,
515
  "f":0.0
516
+ },
517
+ "dep":{
518
+ "p":0.0,
519
+ "r":0.0,
520
+ "f":0.0
521
  }
522
  },
523
+ "sents_p":0.9808045977,
524
+ "sents_r":0.9894480519,
525
+ "sents_f":0.9851073655,
526
+ "lemma_acc":0.942007037,
527
+ "tag_acc":0.742052984,
528
+ "pos_acc":0.7949418685,
529
+ "morph_acc":0.8236478744,
530
  "morph_per_feat":{
531
  "Case":{
532
+ "p":0.9428028704,
533
+ "r":0.8492395437,
534
+ "f":0.8935787157
535
  },
536
  "NameType":{
537
+ "p":0.8543936935,
538
+ "r":0.8106027277,
539
+ "f":0.8319223389
540
  },
541
  "PronType":{
542
+ "p":0.918753478,
543
+ "r":0.7903303016,
544
+ "f":0.8497169326
545
  },
546
  "AdvType":{
547
+ "p":0.8959212377,
548
+ "r":0.8810511757,
549
+ "f":0.8884239888
550
  },
551
  "Degree":{
552
+ "p":0.9257469244,
553
+ "r":0.7310895212,
554
+ "f":0.8169833269
555
  },
556
  "VerbForm":{
557
+ "p":0.8499384994,
558
+ "r":0.5501592357,
559
+ "f":0.6679555341
560
  },
561
  "Polarity":{
562
+ "p":0.8815261044,
563
+ "r":0.6289398281,
564
+ "f":0.7341137124
565
  },
566
  "Person":{
567
+ "p":0.9484629295,
568
+ "r":0.7816691505,
569
+ "f":0.8570261438
570
  },
571
  "VerbType":{
572
+ "p":0.7818181818,
573
+ "r":0.7136929461,
574
+ "f":0.7462039046
575
  },
576
  "Mood":{
577
+ "p":0.7377777778,
578
+ "r":0.7264770241,
579
+ "f":0.7320837927
580
  },
581
  "NounType":{
582
+ "p":0.8939393939,
583
+ "r":0.5841584158,
584
+ "f":0.7065868263
585
  },
586
  "Tense":{
587
+ "p":0.8529411765,
588
+ "r":0.8529411765,
589
+ "f":0.8529411765
590
  },
591
  "Aspect":{
592
+ "p":0.9705882353,
593
+ "r":0.8918918919,
594
+ "f":0.9295774648
595
  },
596
  "Reflex":{
597
+ "p":0.9482758621,
598
+ "r":0.8943089431,
599
+ "f":0.9205020921
600
  },
601
  "Voice":{
602
  "p":1.0,
603
+ "r":0.5,
604
+ "f":0.6666666667
605
  },
606
  "NumType":{
607
+ "p":0.9411764706,
608
+ "r":0.8,
609
+ "f":0.8648648649
610
  }
611
  },
612
+ "transformer_loss":37335.0666093492,
613
+ "parser_loss":11705.6744064605,
614
+ "trainable_lemmatizer_loss":983.2532583296,
615
+ "tagger_loss":28060.3787321919,
616
+ "morphologizer_loss":24266.5000275219
617
  },
618
  "requirements":[
619
  "spacy-transformers>=1.3.4,<1.4.0"
morphologizer/model CHANGED
Binary files a/morphologizer/model and b/morphologizer/model differ
 
parser/model CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d5c3be9e68cdcb62862ed9075a3f5c4638a61256d194f680e6f49a42ac5e9c4
3
  size 1088787
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68dd2415807572b6e926e90f6b5a09a3db26b4fd898d7dbb008970c7d3c4e8e5
3
  size 1088787
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 sha256:91c6e14d642ad93df7d91b57babdc479e88a38c97ec1c2d2c2589cf52acaf646
3
  size 508592662
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6e6f114d6f3e284022973d8c75947cb9397f9206d045b15cbe515be3720c7551
3
  size 508592662
zh_lzh_sigtyp_trf-any-py3-none-any.whl CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fb98c051560cdfde267b69cf522c606e6b16ba69dd599bbafbc4eda5dd6f92e3
3
- size 469155020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7229db32542c9494a75430c7d5e9884c00bc5a554c7e5a5db06de9449d085798
3
+ size 469151931