asahi417 commited on
Commit
177afce
1 Parent(s): 6ef12bd

model update

Browse files
Files changed (1) hide show
  1. README.md +0 -46
README.md CHANGED
@@ -46,21 +46,6 @@ model-index:
46
  - name: MoverScore (Question Generation)
47
  type: moverscore_question_generation
48
  value: 64.99
49
- - name: BLEU4 (Question & Answer Generation (with Gold Answer))
50
- type: bleu4_question_answer_generation_with_gold_answer
51
- value: 13.96
52
- - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
53
- type: rouge_l_question_answer_generation_with_gold_answer
54
- value: 42.37
55
- - name: METEOR (Question & Answer Generation (with Gold Answer))
56
- type: meteor_question_answer_generation_with_gold_answer
57
- value: 40.22
58
- - name: BERTScore (Question & Answer Generation (with Gold Answer))
59
- type: bertscore_question_answer_generation_with_gold_answer
60
- value: 94.63
61
- - name: MoverScore (Question & Answer Generation (with Gold Answer))
62
- type: moverscore_question_answer_generation_with_gold_answer
63
- value: 69.72
64
  - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
65
  type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer_gold_answer
66
  value: 95.54
@@ -79,21 +64,6 @@ model-index:
79
  - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
80
  type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer_gold_answer
81
  value: 71.13
82
- - name: BLEU4 (Question & Answer Generation)
83
- type: bleu4_question_answer_generation
84
- value: 3.95
85
- - name: ROUGE-L (Question & Answer Generation)
86
- type: rouge_l_question_answer_generation
87
- value: 25.63
88
- - name: METEOR (Question & Answer Generation)
89
- type: meteor_question_answer_generation
90
- value: 25.64
91
- - name: BERTScore (Question & Answer Generation)
92
- type: bertscore_question_answer_generation
93
- value: 90.91
94
- - name: MoverScore (Question & Answer Generation)
95
- type: moverscore_question_answer_generation
96
- value: 61.98
97
  - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer]
98
  type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
99
  value: 93.23
@@ -399,40 +369,24 @@ output = pipe("<hl> Beyonce <hl> further expanded her acting career, starring as
399
 
400
  | | Score | Type | Dataset |
401
  |:--------------------------------|--------:|:--------|:---------------------------------------------------------------|
402
- | BERTScore | 94.63 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
403
- | Bleu_1 | 43.22 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
404
- | Bleu_2 | 29.09 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
405
- | Bleu_3 | 19.77 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
406
- | Bleu_4 | 13.96 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
407
- | METEOR | 40.22 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
408
- | MoverScore | 69.72 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
409
  | QAAlignedF1Score (BERTScore) | 95.54 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
410
  | QAAlignedF1Score (MoverScore) | 70.82 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
411
  | QAAlignedPrecision (BERTScore) | 95.59 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
412
  | QAAlignedPrecision (MoverScore) | 71.13 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
413
  | QAAlignedRecall (BERTScore) | 95.49 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
414
  | QAAlignedRecall (MoverScore) | 70.54 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
415
- | ROUGE_L | 42.37 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
416
 
417
 
418
  - ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/bart-large-squad-ae`](https://huggingface.co/lmqg/bart-large-squad-ae). [raw metric file](https://huggingface.co/lmqg/bart-large-squad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_squad.default.lmqg_bart-large-squad-ae.json)
419
 
420
  | | Score | Type | Dataset |
421
  |:--------------------------------|--------:|:--------|:---------------------------------------------------------------|
422
- | BERTScore | 90.91 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
423
- | Bleu_1 | 26.04 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
424
- | Bleu_2 | 14.51 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
425
- | Bleu_3 | 7.13 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
426
- | Bleu_4 | 3.95 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
427
- | METEOR | 25.64 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
428
- | MoverScore | 61.98 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
429
  | QAAlignedF1Score (BERTScore) | 93.23 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
430
  | QAAlignedF1Score (MoverScore) | 64.76 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
431
  | QAAlignedPrecision (BERTScore) | 93.13 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
432
  | QAAlignedPrecision (MoverScore) | 64.98 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
433
  | QAAlignedRecall (BERTScore) | 93.35 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
434
  | QAAlignedRecall (MoverScore) | 64.63 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
435
- | ROUGE_L | 25.63 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
436
 
437
 
438
  - ***Metrics (Question Generation, Out-of-Domain)***
 
46
  - name: MoverScore (Question Generation)
47
  type: moverscore_question_generation
48
  value: 64.99
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
49
  - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
50
  type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer_gold_answer
51
  value: 95.54
 
64
  - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
65
  type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer_gold_answer
66
  value: 71.13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
67
  - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer]
68
  type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
69
  value: 93.23
 
369
 
370
  | | Score | Type | Dataset |
371
  |:--------------------------------|--------:|:--------|:---------------------------------------------------------------|
 
 
 
 
 
 
 
372
  | QAAlignedF1Score (BERTScore) | 95.54 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
373
  | QAAlignedF1Score (MoverScore) | 70.82 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
374
  | QAAlignedPrecision (BERTScore) | 95.59 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
375
  | QAAlignedPrecision (MoverScore) | 71.13 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
376
  | QAAlignedRecall (BERTScore) | 95.49 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
377
  | QAAlignedRecall (MoverScore) | 70.54 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
 
378
 
379
 
380
  - ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/bart-large-squad-ae`](https://huggingface.co/lmqg/bart-large-squad-ae). [raw metric file](https://huggingface.co/lmqg/bart-large-squad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_squad.default.lmqg_bart-large-squad-ae.json)
381
 
382
  | | Score | Type | Dataset |
383
  |:--------------------------------|--------:|:--------|:---------------------------------------------------------------|
 
 
 
 
 
 
 
384
  | QAAlignedF1Score (BERTScore) | 93.23 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
385
  | QAAlignedF1Score (MoverScore) | 64.76 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
386
  | QAAlignedPrecision (BERTScore) | 93.13 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
387
  | QAAlignedPrecision (MoverScore) | 64.98 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
388
  | QAAlignedRecall (BERTScore) | 93.35 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
389
  | QAAlignedRecall (MoverScore) | 64.63 | default | [lmqg/qg_squad](https://huggingface.co/datasets/lmqg/qg_squad) |
 
390
 
391
 
392
  - ***Metrics (Question Generation, Out-of-Domain)***