KennethEnevoldsen
commited on
Commit
•
2ea5d62
1
Parent(s):
0dfe3fa
Updated license
Browse files
README.md
CHANGED
@@ -4,7 +4,7 @@ tags:
|
|
4 |
- token-classification
|
5 |
language:
|
6 |
- da
|
7 |
-
license: apache-2.0
|
8 |
model-index:
|
9 |
- name: da_dacy_medium_trf
|
10 |
results:
|
@@ -65,6 +65,7 @@ model-index:
|
|
65 |
value: 0.9885462555
|
66 |
---
|
67 |
|
|
|
68 |
<a href="https://github.com/centre-for-humanities-computing/Dacy"><img src="https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png" width="175" height="175" align="right" /></a>
|
69 |
|
70 |
# DaCy medium
|
|
|
4 |
- token-classification
|
5 |
language:
|
6 |
- da
|
7 |
+
license: apache-2.0
|
8 |
model-index:
|
9 |
- name: da_dacy_medium_trf
|
10 |
results:
|
|
|
65 |
value: 0.9885462555
|
66 |
---
|
67 |
|
68 |
+
|
69 |
<a href="https://github.com/centre-for-humanities-computing/Dacy"><img src="https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png" width="175" height="175" align="right" /></a>
|
70 |
|
71 |
# DaCy medium
|
meta.json
CHANGED
@@ -1,25 +1,23 @@
|
|
1 |
{
|
2 |
-
"lang":"da",
|
3 |
-
"name":"dacy_medium_trf",
|
4 |
-
"version":"0.2.0",
|
5 |
-
"description":"\n<a href=\"https://github.com/centre-for-humanities-computing/Dacy\"><img src=\"https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png\" width=\"175\" height=\"175\" align=\"right\" /></a>\n\n# DaCy medium\n\nDaCy is a Danish language processing framework with state-of-the-art pipelines as well as functionality for analysing Danish pipelines.\nDaCy's largest pipeline has achieved State-of-the-Art performance on parts-of-speech tagging and dependency \nparsing for Danish on the DaNE dataset. To read more check out the [DaCy repository](https://github.com/centre-for-humanities-computing/DaCy) for material on how to use DaCy and reproduce the results. \nDaCy also contains guides on usage of the package as well as behavioural test for biases and robustness of Danish NLP pipelines.\n",
|
6 |
-
"author":"Kenneth Enevoldsen",
|
7 |
-
"email":"Kenneth.enevoldsen@cas.au.dk",
|
8 |
-
"url":"https://chcaa.io/#/",
|
9 |
-
"license":"Apache-2.0
|
10 |
-
"spacy_version":">=3.5.2,<3.6.0",
|
11 |
-
"spacy_git_version":"Unknown",
|
12 |
-
"vectors":{
|
13 |
-
"width":0,
|
14 |
-
"vectors":0,
|
15 |
-
"keys":0,
|
16 |
-
"name":null
|
17 |
},
|
18 |
-
"labels":{
|
19 |
-
"transformer":[
|
20 |
-
|
21 |
-
],
|
22 |
-
"tagger":[
|
23 |
"ADJ",
|
24 |
"ADP",
|
25 |
"ADV",
|
@@ -38,7 +36,7 @@
|
|
38 |
"VERB",
|
39 |
"X"
|
40 |
],
|
41 |
-
"morphologizer":[
|
42 |
"AdpType=Prep|POS=ADP",
|
43 |
"Definite=Ind|Gender=Com|Number=Sing|POS=NOUN",
|
44 |
"Mood=Ind|POS=AUX|Tense=Pres|VerbForm=Fin|Voice=Act",
|
@@ -198,7 +196,7 @@
|
|
198 |
"Case=Gen|POS=NOUN",
|
199 |
"POS=AUX|Tense=Pres|VerbForm=Part"
|
200 |
],
|
201 |
-
"parser":[
|
202 |
"ROOT",
|
203 |
"acl:relcl",
|
204 |
"advcl",
|
@@ -232,23 +230,17 @@
|
|
232 |
"punct",
|
233 |
"xcomp"
|
234 |
],
|
235 |
-
"ner":[
|
236 |
"LOC",
|
237 |
"MISC",
|
238 |
"ORG",
|
239 |
"PER"
|
240 |
],
|
241 |
-
"coref":[
|
242 |
-
|
243 |
-
]
|
244 |
-
"span_resolver":[
|
245 |
-
|
246 |
-
],
|
247 |
-
"entity_linker":[
|
248 |
-
|
249 |
-
]
|
250 |
},
|
251 |
-
"pipeline":[
|
252 |
"transformer",
|
253 |
"tagger",
|
254 |
"morphologizer",
|
@@ -260,7 +252,7 @@
|
|
260 |
"span_cleaner",
|
261 |
"entity_linker"
|
262 |
],
|
263 |
-
"components":[
|
264 |
"transformer",
|
265 |
"tagger",
|
266 |
"morphologizer",
|
@@ -272,413 +264,411 @@
|
|
272 |
"span_cleaner",
|
273 |
"entity_linker"
|
274 |
],
|
275 |
-
"disabled":[
|
276 |
-
|
277 |
-
],
|
278 |
-
"requirements":[
|
279 |
"spacy-transformers>=1.2.3,<1.3.0",
|
280 |
"spacy-experimental>=0.6.2,<0.7.0"
|
281 |
],
|
282 |
-
"performance":{
|
283 |
-
"token_acc":0.9992023928,
|
284 |
-
"token_p":0.9970089731,
|
285 |
-
"token_r":0.9977052779,
|
286 |
-
"token_f":0.9973570039,
|
287 |
-
"sents_p":0.9842105263,
|
288 |
-
"sents_r":0.992920354,
|
289 |
-
"sents_f":0.9885462555,
|
290 |
-
"tag_acc":0.9847290149,
|
291 |
-
"pos_acc":0.985677928,
|
292 |
-
"morph_acc":0.9814371257,
|
293 |
-
"morph_micro_p":0.9910058542,
|
294 |
-
"morph_micro_r":0.9876942662,
|
295 |
-
"morph_micro_f":0.989347289,
|
296 |
-
"morph_per_feat":{
|
297 |
-
"NumType":{
|
298 |
-
"p":0.987654321,
|
299 |
-
"r":0.9302325581,
|
300 |
-
"f":0.9580838323
|
301 |
-
},
|
302 |
-
"Degree":{
|
303 |
-
"p":0.9894736842,
|
304 |
-
"r":0.9715762274,
|
305 |
-
"f":0.9804432855
|
306 |
-
},
|
307 |
-
"Number":{
|
308 |
-
"p":0.9884148064,
|
309 |
-
"r":0.9859075536,
|
310 |
-
"f":0.987159588
|
311 |
-
},
|
312 |
-
"Definite":{
|
313 |
-
"p":0.9858490566,
|
314 |
-
"r":0.9837398374,
|
315 |
-
"f":0.9847933176
|
316 |
-
},
|
317 |
-
"Gender":{
|
318 |
-
"p":0.9869901547,
|
319 |
-
"r":0.9838766211,
|
320 |
-
"f":0.9854309286
|
321 |
-
},
|
322 |
-
"Mood":{
|
323 |
-
"p":0.9971126083,
|
324 |
-
"r":0.9942418426,
|
325 |
-
"f":0.9956751562
|
326 |
-
},
|
327 |
-
"Tense":{
|
328 |
-
"p":0.9906469213,
|
329 |
-
"r":0.9906469213,
|
330 |
-
"f":0.9906469213
|
331 |
-
},
|
332 |
-
"VerbForm":{
|
333 |
-
"p":0.9924670433,
|
334 |
-
"r":0.9918444166,
|
335 |
-
"f":0.9921556323
|
336 |
-
},
|
337 |
-
"Voice":{
|
338 |
-
"p":0.997012696,
|
339 |
-
"r":0.9955257271,
|
340 |
-
"f":0.9962686567
|
341 |
-
},
|
342 |
-
"AdpType":{
|
343 |
-
"p":0.9990689013,
|
344 |
-
"r":0.9972118959,
|
345 |
-
"f":0.9981395349
|
346 |
-
},
|
347 |
-
"PronType":{
|
348 |
-
"p":0.9954914337,
|
349 |
-
"r":0.9963898917,
|
350 |
-
"f":0.9959404601
|
351 |
-
},
|
352 |
-
"Case":{
|
353 |
-
"p":0.9968652038,
|
354 |
-
"r":0.9860465116,
|
355 |
-
"f":0.9914263445
|
356 |
-
},
|
357 |
-
"Person":{
|
358 |
-
"p":0.9930555556,
|
359 |
-
"r":0.9913344887,
|
360 |
-
"f":0.9921942758
|
361 |
-
},
|
362 |
-
"Number[psor]":{
|
363 |
-
"p":0.987804878,
|
364 |
-
"r":1.0,
|
365 |
-
"f":0.9938650307
|
366 |
-
},
|
367 |
-
"Poss":{
|
368 |
-
"p":0.987804878,
|
369 |
-
"r":1.0,
|
370 |
-
"f":0.9938650307
|
371 |
-
},
|
372 |
-
"PartType":{
|
373 |
-
"p":1.0,
|
374 |
-
"r":0.9962406015,
|
375 |
-
"f":0.9981167608
|
376 |
-
},
|
377 |
-
"Polite":{
|
378 |
-
"p":0.6666666667,
|
379 |
-
"r":0.6666666667,
|
380 |
-
"f":0.6666666667
|
381 |
-
},
|
382 |
-
"Reflex":{
|
383 |
-
"p":1.0,
|
384 |
-
"r":1.0,
|
385 |
-
"f":1.0
|
386 |
-
},
|
387 |
-
"Foreign":{
|
388 |
-
"p":0.5,
|
389 |
-
"r":0.2,
|
390 |
-
"f":0.2857142857
|
391 |
-
},
|
392 |
-
"Style":{
|
393 |
-
"p":1.0,
|
394 |
-
"r":1.0,
|
395 |
-
"f":1.0
|
396 |
-
},
|
397 |
-
"Abbr":{
|
398 |
-
"p":0.6666666667,
|
399 |
-
"r":1.0,
|
400 |
-
"f":0.8
|
401 |
}
|
402 |
},
|
403 |
-
"dep_uas":0.9083920564,
|
404 |
-
"dep_las":0.883349834,
|
405 |
-
"dep_las_per_type":{
|
406 |
-
"nummod":{
|
407 |
-
"p":0.7948717949,
|
408 |
-
"r":0.8230088496,
|
409 |
-
"f":0.8086956522
|
410 |
-
},
|
411 |
-
"amod":{
|
412 |
-
"p":0.897810219,
|
413 |
-
"r":0.9027522936,
|
414 |
-
"f":0.9002744739
|
415 |
-
},
|
416 |
-
"nmod":{
|
417 |
-
"p":0.7712418301,
|
418 |
-
"r":0.7729257642,
|
419 |
-
"f":0.772082879
|
420 |
-
},
|
421 |
-
"nsubj":{
|
422 |
-
"p":0.9510638298,
|
423 |
-
"r":0.946031746,
|
424 |
-
"f":0.9485411141
|
425 |
-
},
|
426 |
-
"flat":{
|
427 |
-
"p":0.9285714286,
|
428 |
-
"r":0.9680851064,
|
429 |
-
"f":0.9479166667
|
430 |
-
},
|
431 |
-
"cc":{
|
432 |
-
"p":0.8681672026,
|
433 |
-
"r":0.8940397351,
|
434 |
-
"f":0.88091354
|
435 |
-
},
|
436 |
-
"conj":{
|
437 |
-
"p":0.8862275449,
|
438 |
-
"r":0.8554913295,
|
439 |
-
"f":0.8705882353
|
440 |
-
},
|
441 |
-
"root":{
|
442 |
-
"p":0.926056338,
|
443 |
-
"r":0.9309734513,
|
444 |
-
"f":0.9285083848
|
445 |
-
},
|
446 |
-
"advmod":{
|
447 |
-
"p":0.8871715611,
|
448 |
-
"r":0.8605697151,
|
449 |
-
"f":0.8736681887
|
450 |
-
},
|
451 |
-
"mark":{
|
452 |
-
"p":0.9148471616,
|
453 |
-
"r":0.9331848552,
|
454 |
-
"f":0.9239250276
|
455 |
-
},
|
456 |
-
"aux":{
|
457 |
-
"p":0.9875389408,
|
458 |
-
"r":0.9753846154,
|
459 |
-
"f":0.9814241486
|
460 |
-
},
|
461 |
-
"ccomp":{
|
462 |
-
"p":0.7764705882,
|
463 |
-
"r":0.835443038,
|
464 |
-
"f":0.8048780488
|
465 |
-
},
|
466 |
-
"case":{
|
467 |
-
"p":0.9348986126,
|
468 |
-
"r":0.9192025184,
|
469 |
-
"f":0.926984127
|
470 |
-
},
|
471 |
-
"det":{
|
472 |
-
"p":0.9409448819,
|
473 |
-
"r":0.9637096774,
|
474 |
-
"f":0.9521912351
|
475 |
-
},
|
476 |
-
"obl":{
|
477 |
-
"p":0.8476821192,
|
478 |
-
"r":0.8114104596,
|
479 |
-
"f":0.8291497976
|
480 |
-
},
|
481 |
-
"nmod:poss":{
|
482 |
-
"p":0.8181818182,
|
483 |
-
"r":0.8256880734,
|
484 |
-
"f":0.8219178082
|
485 |
-
},
|
486 |
-
"obj":{
|
487 |
-
"p":0.8943533698,
|
488 |
-
"r":0.9352380952,
|
489 |
-
"f":0.9143389199
|
490 |
-
},
|
491 |
-
"cop":{
|
492 |
-
"p":0.8944099379,
|
493 |
-
"r":0.8834355828,
|
494 |
-
"f":0.8888888889
|
495 |
-
},
|
496 |
-
"acl:relcl":{
|
497 |
-
"p":0.8343195266,
|
498 |
-
"r":0.7704918033,
|
499 |
-
"f":0.8011363636
|
500 |
-
},
|
501 |
-
"advcl":{
|
502 |
-
"p":0.6742857143,
|
503 |
-
"r":0.7564102564,
|
504 |
-
"f":0.7129909366
|
505 |
-
},
|
506 |
-
"dep":{
|
507 |
-
"p":0.1136363636,
|
508 |
-
"r":0.3333333333,
|
509 |
-
"f":0.1694915254
|
510 |
-
},
|
511 |
-
"compound:prt":{
|
512 |
-
"p":0.6666666667,
|
513 |
-
"r":0.5882352941,
|
514 |
-
"f":0.625
|
515 |
-
},
|
516 |
-
"fixed":{
|
517 |
-
"p":0.9473684211,
|
518 |
-
"r":0.8709677419,
|
519 |
-
"f":0.9075630252
|
520 |
-
},
|
521 |
-
"iobj":{
|
522 |
-
"p":0.7692307692,
|
523 |
-
"r":0.6666666667,
|
524 |
-
"f":0.7142857143
|
525 |
-
},
|
526 |
-
"appos":{
|
527 |
-
"p":0.8181818182,
|
528 |
-
"r":0.7105263158,
|
529 |
-
"f":0.7605633803
|
530 |
-
},
|
531 |
-
"obl:tmod":{
|
532 |
-
"p":0.5,
|
533 |
-
"r":0.3125,
|
534 |
-
"f":0.3846153846
|
535 |
-
},
|
536 |
-
"advmod:lmod":{
|
537 |
-
"p":0.7678571429,
|
538 |
-
"r":0.8958333333,
|
539 |
-
"f":0.8269230769
|
540 |
-
},
|
541 |
-
"xcomp":{
|
542 |
-
"p":0.8913043478,
|
543 |
-
"r":0.640625,
|
544 |
-
"f":0.7454545455
|
545 |
-
},
|
546 |
-
"expl":{
|
547 |
-
"p":0.9230769231,
|
548 |
-
"r":0.9230769231,
|
549 |
-
"f":0.9230769231
|
550 |
-
},
|
551 |
-
"list":{
|
552 |
-
"p":0.5714285714,
|
553 |
-
"r":0.2352941176,
|
554 |
-
"f":0.3333333333
|
555 |
-
},
|
556 |
-
"obl:lmod":{
|
557 |
-
"p":0.25,
|
558 |
-
"r":0.3333333333,
|
559 |
-
"f":0.2857142857
|
560 |
-
},
|
561 |
-
"parataxis":{
|
562 |
-
"p":0.0,
|
563 |
-
"r":0.0,
|
564 |
-
"f":0.0
|
565 |
-
},
|
566 |
-
"orphan":{
|
567 |
-
"p":0.0,
|
568 |
-
"r":0.0,
|
569 |
-
"f":0.0
|
570 |
-
},
|
571 |
-
"vocative":{
|
572 |
-
"p":0.0,
|
573 |
-
"r":0.0,
|
574 |
-
"f":0.0
|
575 |
-
},
|
576 |
-
"discourse":{
|
577 |
-
"p":0.0,
|
578 |
-
"r":0.0,
|
579 |
-
"f":0.0
|
580 |
-
},
|
581 |
-
"dislocated":{
|
582 |
-
"p":0.0,
|
583 |
-
"r":0.0,
|
584 |
-
"f":0.0
|
585 |
-
},
|
586 |
-
"compound":{
|
587 |
-
"p":0.0,
|
588 |
-
"r":0.0,
|
589 |
-
"f":0.0
|
590 |
}
|
591 |
},
|
592 |
-
"ents_p":0.8708487085,
|
593 |
-
"ents_r":0.8458781362,
|
594 |
-
"ents_f":0.8581818182,
|
595 |
-
"ents_per_type":{
|
596 |
-
"LOC":{
|
597 |
-
"p":0.854368932,
|
598 |
-
"r":0.9166666667,
|
599 |
-
"f":0.8844221106
|
600 |
-
},
|
601 |
-
"PER":{
|
602 |
-
"p":0.9100529101,
|
603 |
-
"r":0.9555555556,
|
604 |
-
"f":0.9322493225
|
605 |
-
},
|
606 |
-
"MISC":{
|
607 |
-
"p":0.8301886792,
|
608 |
-
"r":0.7272727273,
|
609 |
-
"f":0.7753303965
|
610 |
-
},
|
611 |
-
"ORG":{
|
612 |
-
"p":0.8611111111,
|
613 |
-
"r":0.7701863354,
|
614 |
-
"f":0.8131147541
|
615 |
}
|
616 |
},
|
617 |
-
"coref_lea_f1":0.4118366346,
|
618 |
-
"coref_lea_precision":0.4889169083,
|
619 |
-
"coref_lea_recall":0.3557507008,
|
620 |
-
"nel_score":0.801242236,
|
621 |
-
"nel_score_desc":"micro F",
|
622 |
-
"nel_micro_p":0.9923076923,
|
623 |
-
"nel_micro_r":0.671875,
|
624 |
-
"nel_micro_f":0.801242236,
|
625 |
-
"nel_macro_p":0.993902439,
|
626 |
-
"nel_macro_r":0.6598989464,
|
627 |
-
"nel_macro_f":0.7815238616,
|
628 |
-
"nel_f_per_type":{
|
629 |
-
"MISC":{
|
630 |
-
"p":1.0,
|
631 |
-
"r":0.4117647059,
|
632 |
-
"f":0.5833333333
|
633 |
-
},
|
634 |
-
"PER":{
|
635 |
-
"p":1.0,
|
636 |
-
"r":0.7540983607,
|
637 |
-
"f":0.8598130841
|
638 |
-
},
|
639 |
-
"LOC":{
|
640 |
-
"p":1.0,
|
641 |
-
"r":0.8285714286,
|
642 |
-
"f":0.90625
|
643 |
-
},
|
644 |
-
"ORG":{
|
645 |
-
"p":0.9756097561,
|
646 |
-
"r":0.6451612903,
|
647 |
-
"f":0.7766990291
|
648 |
}
|
649 |
}
|
650 |
},
|
651 |
-
"sources":[
|
652 |
{
|
653 |
-
"name":"UD Danish DDT v2.11",
|
654 |
-
"url":"https://github.com/UniversalDependencies/UD_Danish-DDT",
|
655 |
-
"license":"CC BY-SA 4.0",
|
656 |
-
"author":"Johannsen, Anders; Mart\u00ednez Alonso, H\u00e9ctor; Plank, Barbara"
|
657 |
},
|
658 |
{
|
659 |
-
"name":"DaNE",
|
660 |
-
"url":"https://huggingface.co/datasets/dane",
|
661 |
-
"license":"CC BY-SA 4.0",
|
662 |
-
"author":"Rasmus Hvingelby, Amalie B. Pauli, Maria Barrett, Christina Rosted, Lasse M. Lidegaard, Anders S\u00f8gaard"
|
663 |
},
|
664 |
{
|
665 |
-
"name":"DaCoref",
|
666 |
-
"url":"https://huggingface.co/datasets/alexandrainst/dacoref",
|
667 |
-
"license":"CC BY-SA 4.0",
|
668 |
-
"author":"Buch-Kromann, Matthias"
|
669 |
},
|
670 |
{
|
671 |
-
"name":"DaNED",
|
672 |
-
"url":"https://danlp-alexandra.readthedocs.io/en/stable/docs/datasets.html#daned",
|
673 |
-
"license":"CC BY-SA 4.0",
|
674 |
-
"author":"Barrett, M. J., Lam, H., Wu, M., Lacroix, O., Plank, B., & S\u00f8gaard, A."
|
675 |
},
|
676 |
{
|
677 |
-
"name":"vesteinn/DanskBERT",
|
678 |
-
"author":"V\u00e9steinn Sn\u00e6bjarnarson",
|
679 |
-
"url":"https://huggingface.co/vesteinn/DanskBERT",
|
680 |
-
"license":"MIT"
|
681 |
}
|
682 |
],
|
683 |
-
"notes":"\n\n### Training\nThis model was trained using [spaCy](https://spacy.io) and logged to [Weights & Biases](https://wandb.ai/kenevoldsen/dacy-v0.2.0). You can find all the training logs [here](https://wandb.ai/kenevoldsen/dacy-v0.2.0)."
|
684 |
}
|
|
|
1 |
{
|
2 |
+
"lang": "da",
|
3 |
+
"name": "dacy_medium_trf",
|
4 |
+
"version": "0.2.0",
|
5 |
+
"description": "\n<a href=\"https://github.com/centre-for-humanities-computing/Dacy\"><img src=\"https://centre-for-humanities-computing.github.io/DaCy/_static/icon.png\" width=\"175\" height=\"175\" align=\"right\" /></a>\n\n# DaCy medium\n\nDaCy is a Danish language processing framework with state-of-the-art pipelines as well as functionality for analysing Danish pipelines.\nDaCy's largest pipeline has achieved State-of-the-Art performance on parts-of-speech tagging and dependency \nparsing for Danish on the DaNE dataset. To read more check out the [DaCy repository](https://github.com/centre-for-humanities-computing/DaCy) for material on how to use DaCy and reproduce the results. \nDaCy also contains guides on usage of the package as well as behavioural test for biases and robustness of Danish NLP pipelines.\n",
|
6 |
+
"author": "Kenneth Enevoldsen",
|
7 |
+
"email": "Kenneth.enevoldsen@cas.au.dk",
|
8 |
+
"url": "https://chcaa.io/#/",
|
9 |
+
"license": "Apache-2.0",
|
10 |
+
"spacy_version": ">=3.5.2,<3.6.0",
|
11 |
+
"spacy_git_version": "Unknown",
|
12 |
+
"vectors": {
|
13 |
+
"width": 0,
|
14 |
+
"vectors": 0,
|
15 |
+
"keys": 0,
|
16 |
+
"name": null
|
17 |
},
|
18 |
+
"labels": {
|
19 |
+
"transformer": [],
|
20 |
+
"tagger": [
|
|
|
|
|
21 |
"ADJ",
|
22 |
"ADP",
|
23 |
"ADV",
|
|
|
36 |
"VERB",
|
37 |
"X"
|
38 |
],
|
39 |
+
"morphologizer": [
|
40 |
"AdpType=Prep|POS=ADP",
|
41 |
"Definite=Ind|Gender=Com|Number=Sing|POS=NOUN",
|
42 |
"Mood=Ind|POS=AUX|Tense=Pres|VerbForm=Fin|Voice=Act",
|
|
|
196 |
"Case=Gen|POS=NOUN",
|
197 |
"POS=AUX|Tense=Pres|VerbForm=Part"
|
198 |
],
|
199 |
+
"parser": [
|
200 |
"ROOT",
|
201 |
"acl:relcl",
|
202 |
"advcl",
|
|
|
230 |
"punct",
|
231 |
"xcomp"
|
232 |
],
|
233 |
+
"ner": [
|
234 |
"LOC",
|
235 |
"MISC",
|
236 |
"ORG",
|
237 |
"PER"
|
238 |
],
|
239 |
+
"coref": [],
|
240 |
+
"span_resolver": [],
|
241 |
+
"entity_linker": []
|
|
|
|
|
|
|
|
|
|
|
|
|
242 |
},
|
243 |
+
"pipeline": [
|
244 |
"transformer",
|
245 |
"tagger",
|
246 |
"morphologizer",
|
|
|
252 |
"span_cleaner",
|
253 |
"entity_linker"
|
254 |
],
|
255 |
+
"components": [
|
256 |
"transformer",
|
257 |
"tagger",
|
258 |
"morphologizer",
|
|
|
264 |
"span_cleaner",
|
265 |
"entity_linker"
|
266 |
],
|
267 |
+
"disabled": [],
|
268 |
+
"requirements": [
|
|
|
|
|
269 |
"spacy-transformers>=1.2.3,<1.3.0",
|
270 |
"spacy-experimental>=0.6.2,<0.7.0"
|
271 |
],
|
272 |
+
"performance": {
|
273 |
+
"token_acc": 0.9992023928,
|
274 |
+
"token_p": 0.9970089731,
|
275 |
+
"token_r": 0.9977052779,
|
276 |
+
"token_f": 0.9973570039,
|
277 |
+
"sents_p": 0.9842105263,
|
278 |
+
"sents_r": 0.992920354,
|
279 |
+
"sents_f": 0.9885462555,
|
280 |
+
"tag_acc": 0.9847290149,
|
281 |
+
"pos_acc": 0.985677928,
|
282 |
+
"morph_acc": 0.9814371257,
|
283 |
+
"morph_micro_p": 0.9910058542,
|
284 |
+
"morph_micro_r": 0.9876942662,
|
285 |
+
"morph_micro_f": 0.989347289,
|
286 |
+
"morph_per_feat": {
|
287 |
+
"NumType": {
|
288 |
+
"p": 0.987654321,
|
289 |
+
"r": 0.9302325581,
|
290 |
+
"f": 0.9580838323
|
291 |
+
},
|
292 |
+
"Degree": {
|
293 |
+
"p": 0.9894736842,
|
294 |
+
"r": 0.9715762274,
|
295 |
+
"f": 0.9804432855
|
296 |
+
},
|
297 |
+
"Number": {
|
298 |
+
"p": 0.9884148064,
|
299 |
+
"r": 0.9859075536,
|
300 |
+
"f": 0.987159588
|
301 |
+
},
|
302 |
+
"Definite": {
|
303 |
+
"p": 0.9858490566,
|
304 |
+
"r": 0.9837398374,
|
305 |
+
"f": 0.9847933176
|
306 |
+
},
|
307 |
+
"Gender": {
|
308 |
+
"p": 0.9869901547,
|
309 |
+
"r": 0.9838766211,
|
310 |
+
"f": 0.9854309286
|
311 |
+
},
|
312 |
+
"Mood": {
|
313 |
+
"p": 0.9971126083,
|
314 |
+
"r": 0.9942418426,
|
315 |
+
"f": 0.9956751562
|
316 |
+
},
|
317 |
+
"Tense": {
|
318 |
+
"p": 0.9906469213,
|
319 |
+
"r": 0.9906469213,
|
320 |
+
"f": 0.9906469213
|
321 |
+
},
|
322 |
+
"VerbForm": {
|
323 |
+
"p": 0.9924670433,
|
324 |
+
"r": 0.9918444166,
|
325 |
+
"f": 0.9921556323
|
326 |
+
},
|
327 |
+
"Voice": {
|
328 |
+
"p": 0.997012696,
|
329 |
+
"r": 0.9955257271,
|
330 |
+
"f": 0.9962686567
|
331 |
+
},
|
332 |
+
"AdpType": {
|
333 |
+
"p": 0.9990689013,
|
334 |
+
"r": 0.9972118959,
|
335 |
+
"f": 0.9981395349
|
336 |
+
},
|
337 |
+
"PronType": {
|
338 |
+
"p": 0.9954914337,
|
339 |
+
"r": 0.9963898917,
|
340 |
+
"f": 0.9959404601
|
341 |
+
},
|
342 |
+
"Case": {
|
343 |
+
"p": 0.9968652038,
|
344 |
+
"r": 0.9860465116,
|
345 |
+
"f": 0.9914263445
|
346 |
+
},
|
347 |
+
"Person": {
|
348 |
+
"p": 0.9930555556,
|
349 |
+
"r": 0.9913344887,
|
350 |
+
"f": 0.9921942758
|
351 |
+
},
|
352 |
+
"Number[psor]": {
|
353 |
+
"p": 0.987804878,
|
354 |
+
"r": 1.0,
|
355 |
+
"f": 0.9938650307
|
356 |
+
},
|
357 |
+
"Poss": {
|
358 |
+
"p": 0.987804878,
|
359 |
+
"r": 1.0,
|
360 |
+
"f": 0.9938650307
|
361 |
+
},
|
362 |
+
"PartType": {
|
363 |
+
"p": 1.0,
|
364 |
+
"r": 0.9962406015,
|
365 |
+
"f": 0.9981167608
|
366 |
+
},
|
367 |
+
"Polite": {
|
368 |
+
"p": 0.6666666667,
|
369 |
+
"r": 0.6666666667,
|
370 |
+
"f": 0.6666666667
|
371 |
+
},
|
372 |
+
"Reflex": {
|
373 |
+
"p": 1.0,
|
374 |
+
"r": 1.0,
|
375 |
+
"f": 1.0
|
376 |
+
},
|
377 |
+
"Foreign": {
|
378 |
+
"p": 0.5,
|
379 |
+
"r": 0.2,
|
380 |
+
"f": 0.2857142857
|
381 |
+
},
|
382 |
+
"Style": {
|
383 |
+
"p": 1.0,
|
384 |
+
"r": 1.0,
|
385 |
+
"f": 1.0
|
386 |
+
},
|
387 |
+
"Abbr": {
|
388 |
+
"p": 0.6666666667,
|
389 |
+
"r": 1.0,
|
390 |
+
"f": 0.8
|
391 |
}
|
392 |
},
|
393 |
+
"dep_uas": 0.9083920564,
|
394 |
+
"dep_las": 0.883349834,
|
395 |
+
"dep_las_per_type": {
|
396 |
+
"nummod": {
|
397 |
+
"p": 0.7948717949,
|
398 |
+
"r": 0.8230088496,
|
399 |
+
"f": 0.8086956522
|
400 |
+
},
|
401 |
+
"amod": {
|
402 |
+
"p": 0.897810219,
|
403 |
+
"r": 0.9027522936,
|
404 |
+
"f": 0.9002744739
|
405 |
+
},
|
406 |
+
"nmod": {
|
407 |
+
"p": 0.7712418301,
|
408 |
+
"r": 0.7729257642,
|
409 |
+
"f": 0.772082879
|
410 |
+
},
|
411 |
+
"nsubj": {
|
412 |
+
"p": 0.9510638298,
|
413 |
+
"r": 0.946031746,
|
414 |
+
"f": 0.9485411141
|
415 |
+
},
|
416 |
+
"flat": {
|
417 |
+
"p": 0.9285714286,
|
418 |
+
"r": 0.9680851064,
|
419 |
+
"f": 0.9479166667
|
420 |
+
},
|
421 |
+
"cc": {
|
422 |
+
"p": 0.8681672026,
|
423 |
+
"r": 0.8940397351,
|
424 |
+
"f": 0.88091354
|
425 |
+
},
|
426 |
+
"conj": {
|
427 |
+
"p": 0.8862275449,
|
428 |
+
"r": 0.8554913295,
|
429 |
+
"f": 0.8705882353
|
430 |
+
},
|
431 |
+
"root": {
|
432 |
+
"p": 0.926056338,
|
433 |
+
"r": 0.9309734513,
|
434 |
+
"f": 0.9285083848
|
435 |
+
},
|
436 |
+
"advmod": {
|
437 |
+
"p": 0.8871715611,
|
438 |
+
"r": 0.8605697151,
|
439 |
+
"f": 0.8736681887
|
440 |
+
},
|
441 |
+
"mark": {
|
442 |
+
"p": 0.9148471616,
|
443 |
+
"r": 0.9331848552,
|
444 |
+
"f": 0.9239250276
|
445 |
+
},
|
446 |
+
"aux": {
|
447 |
+
"p": 0.9875389408,
|
448 |
+
"r": 0.9753846154,
|
449 |
+
"f": 0.9814241486
|
450 |
+
},
|
451 |
+
"ccomp": {
|
452 |
+
"p": 0.7764705882,
|
453 |
+
"r": 0.835443038,
|
454 |
+
"f": 0.8048780488
|
455 |
+
},
|
456 |
+
"case": {
|
457 |
+
"p": 0.9348986126,
|
458 |
+
"r": 0.9192025184,
|
459 |
+
"f": 0.926984127
|
460 |
+
},
|
461 |
+
"det": {
|
462 |
+
"p": 0.9409448819,
|
463 |
+
"r": 0.9637096774,
|
464 |
+
"f": 0.9521912351
|
465 |
+
},
|
466 |
+
"obl": {
|
467 |
+
"p": 0.8476821192,
|
468 |
+
"r": 0.8114104596,
|
469 |
+
"f": 0.8291497976
|
470 |
+
},
|
471 |
+
"nmod:poss": {
|
472 |
+
"p": 0.8181818182,
|
473 |
+
"r": 0.8256880734,
|
474 |
+
"f": 0.8219178082
|
475 |
+
},
|
476 |
+
"obj": {
|
477 |
+
"p": 0.8943533698,
|
478 |
+
"r": 0.9352380952,
|
479 |
+
"f": 0.9143389199
|
480 |
+
},
|
481 |
+
"cop": {
|
482 |
+
"p": 0.8944099379,
|
483 |
+
"r": 0.8834355828,
|
484 |
+
"f": 0.8888888889
|
485 |
+
},
|
486 |
+
"acl:relcl": {
|
487 |
+
"p": 0.8343195266,
|
488 |
+
"r": 0.7704918033,
|
489 |
+
"f": 0.8011363636
|
490 |
+
},
|
491 |
+
"advcl": {
|
492 |
+
"p": 0.6742857143,
|
493 |
+
"r": 0.7564102564,
|
494 |
+
"f": 0.7129909366
|
495 |
+
},
|
496 |
+
"dep": {
|
497 |
+
"p": 0.1136363636,
|
498 |
+
"r": 0.3333333333,
|
499 |
+
"f": 0.1694915254
|
500 |
+
},
|
501 |
+
"compound:prt": {
|
502 |
+
"p": 0.6666666667,
|
503 |
+
"r": 0.5882352941,
|
504 |
+
"f": 0.625
|
505 |
+
},
|
506 |
+
"fixed": {
|
507 |
+
"p": 0.9473684211,
|
508 |
+
"r": 0.8709677419,
|
509 |
+
"f": 0.9075630252
|
510 |
+
},
|
511 |
+
"iobj": {
|
512 |
+
"p": 0.7692307692,
|
513 |
+
"r": 0.6666666667,
|
514 |
+
"f": 0.7142857143
|
515 |
+
},
|
516 |
+
"appos": {
|
517 |
+
"p": 0.8181818182,
|
518 |
+
"r": 0.7105263158,
|
519 |
+
"f": 0.7605633803
|
520 |
+
},
|
521 |
+
"obl:tmod": {
|
522 |
+
"p": 0.5,
|
523 |
+
"r": 0.3125,
|
524 |
+
"f": 0.3846153846
|
525 |
+
},
|
526 |
+
"advmod:lmod": {
|
527 |
+
"p": 0.7678571429,
|
528 |
+
"r": 0.8958333333,
|
529 |
+
"f": 0.8269230769
|
530 |
+
},
|
531 |
+
"xcomp": {
|
532 |
+
"p": 0.8913043478,
|
533 |
+
"r": 0.640625,
|
534 |
+
"f": 0.7454545455
|
535 |
+
},
|
536 |
+
"expl": {
|
537 |
+
"p": 0.9230769231,
|
538 |
+
"r": 0.9230769231,
|
539 |
+
"f": 0.9230769231
|
540 |
+
},
|
541 |
+
"list": {
|
542 |
+
"p": 0.5714285714,
|
543 |
+
"r": 0.2352941176,
|
544 |
+
"f": 0.3333333333
|
545 |
+
},
|
546 |
+
"obl:lmod": {
|
547 |
+
"p": 0.25,
|
548 |
+
"r": 0.3333333333,
|
549 |
+
"f": 0.2857142857
|
550 |
+
},
|
551 |
+
"parataxis": {
|
552 |
+
"p": 0.0,
|
553 |
+
"r": 0.0,
|
554 |
+
"f": 0.0
|
555 |
+
},
|
556 |
+
"orphan": {
|
557 |
+
"p": 0.0,
|
558 |
+
"r": 0.0,
|
559 |
+
"f": 0.0
|
560 |
+
},
|
561 |
+
"vocative": {
|
562 |
+
"p": 0.0,
|
563 |
+
"r": 0.0,
|
564 |
+
"f": 0.0
|
565 |
+
},
|
566 |
+
"discourse": {
|
567 |
+
"p": 0.0,
|
568 |
+
"r": 0.0,
|
569 |
+
"f": 0.0
|
570 |
+
},
|
571 |
+
"dislocated": {
|
572 |
+
"p": 0.0,
|
573 |
+
"r": 0.0,
|
574 |
+
"f": 0.0
|
575 |
+
},
|
576 |
+
"compound": {
|
577 |
+
"p": 0.0,
|
578 |
+
"r": 0.0,
|
579 |
+
"f": 0.0
|
580 |
}
|
581 |
},
|
582 |
+
"ents_p": 0.8708487085,
|
583 |
+
"ents_r": 0.8458781362,
|
584 |
+
"ents_f": 0.8581818182,
|
585 |
+
"ents_per_type": {
|
586 |
+
"LOC": {
|
587 |
+
"p": 0.854368932,
|
588 |
+
"r": 0.9166666667,
|
589 |
+
"f": 0.8844221106
|
590 |
+
},
|
591 |
+
"PER": {
|
592 |
+
"p": 0.9100529101,
|
593 |
+
"r": 0.9555555556,
|
594 |
+
"f": 0.9322493225
|
595 |
+
},
|
596 |
+
"MISC": {
|
597 |
+
"p": 0.8301886792,
|
598 |
+
"r": 0.7272727273,
|
599 |
+
"f": 0.7753303965
|
600 |
+
},
|
601 |
+
"ORG": {
|
602 |
+
"p": 0.8611111111,
|
603 |
+
"r": 0.7701863354,
|
604 |
+
"f": 0.8131147541
|
605 |
}
|
606 |
},
|
607 |
+
"coref_lea_f1": 0.4118366346,
|
608 |
+
"coref_lea_precision": 0.4889169083,
|
609 |
+
"coref_lea_recall": 0.3557507008,
|
610 |
+
"nel_score": 0.801242236,
|
611 |
+
"nel_score_desc": "micro F",
|
612 |
+
"nel_micro_p": 0.9923076923,
|
613 |
+
"nel_micro_r": 0.671875,
|
614 |
+
"nel_micro_f": 0.801242236,
|
615 |
+
"nel_macro_p": 0.993902439,
|
616 |
+
"nel_macro_r": 0.6598989464,
|
617 |
+
"nel_macro_f": 0.7815238616,
|
618 |
+
"nel_f_per_type": {
|
619 |
+
"MISC": {
|
620 |
+
"p": 1.0,
|
621 |
+
"r": 0.4117647059,
|
622 |
+
"f": 0.5833333333
|
623 |
+
},
|
624 |
+
"PER": {
|
625 |
+
"p": 1.0,
|
626 |
+
"r": 0.7540983607,
|
627 |
+
"f": 0.8598130841
|
628 |
+
},
|
629 |
+
"LOC": {
|
630 |
+
"p": 1.0,
|
631 |
+
"r": 0.8285714286,
|
632 |
+
"f": 0.90625
|
633 |
+
},
|
634 |
+
"ORG": {
|
635 |
+
"p": 0.9756097561,
|
636 |
+
"r": 0.6451612903,
|
637 |
+
"f": 0.7766990291
|
638 |
}
|
639 |
}
|
640 |
},
|
641 |
+
"sources": [
|
642 |
{
|
643 |
+
"name": "UD Danish DDT v2.11",
|
644 |
+
"url": "https://github.com/UniversalDependencies/UD_Danish-DDT",
|
645 |
+
"license": "CC BY-SA 4.0",
|
646 |
+
"author": "Johannsen, Anders; Mart\u00ednez Alonso, H\u00e9ctor; Plank, Barbara"
|
647 |
},
|
648 |
{
|
649 |
+
"name": "DaNE",
|
650 |
+
"url": "https://huggingface.co/datasets/dane",
|
651 |
+
"license": "CC BY-SA 4.0",
|
652 |
+
"author": "Rasmus Hvingelby, Amalie B. Pauli, Maria Barrett, Christina Rosted, Lasse M. Lidegaard, Anders S\u00f8gaard"
|
653 |
},
|
654 |
{
|
655 |
+
"name": "DaCoref",
|
656 |
+
"url": "https://huggingface.co/datasets/alexandrainst/dacoref",
|
657 |
+
"license": "CC BY-SA 4.0",
|
658 |
+
"author": "Buch-Kromann, Matthias"
|
659 |
},
|
660 |
{
|
661 |
+
"name": "DaNED",
|
662 |
+
"url": "https://danlp-alexandra.readthedocs.io/en/stable/docs/datasets.html#daned",
|
663 |
+
"license": "CC BY-SA 4.0",
|
664 |
+
"author": "Barrett, M. J., Lam, H., Wu, M., Lacroix, O., Plank, B., & S\u00f8gaard, A."
|
665 |
},
|
666 |
{
|
667 |
+
"name": "vesteinn/DanskBERT",
|
668 |
+
"author": "V\u00e9steinn Sn\u00e6bjarnarson",
|
669 |
+
"url": "https://huggingface.co/vesteinn/DanskBERT",
|
670 |
+
"license": "MIT"
|
671 |
}
|
672 |
],
|
673 |
+
"notes": "\n\n### Training\nThis model was trained using [spaCy](https://spacy.io) and logged to [Weights & Biases](https://wandb.ai/kenevoldsen/dacy-v0.2.0). You can find all the training logs [here](https://wandb.ai/kenevoldsen/dacy-v0.2.0)."
|
674 |
}
|