model update

README.md

@@ -46,39 +46,72 @@ model-index:
     - name: MoverScore (Question Generation)
       type: moverscore_question_generation
       value: 62.49
+    - name: BLEU4 (Question & Answer Generation (with Gold Answer))
+      type: bleu4_question_answer_generation_with_gold_answer
+      value: 18.61
+    - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
+      type: rouge_l_question_answer_generation_with_gold_answer
+      value: 51.04
+    - name: METEOR (Question & Answer Generation (with Gold Answer))
+      type: meteor_question_answer_generation_with_gold_answer
+      value: 43.1
+    - name: BERTScore (Question & Answer Generation (with Gold Answer))
+      type: bertscore_question_answer_generation_with_gold_answer
+      value: 90.03
+    - name: MoverScore (Question & Answer Generation (with Gold Answer))
+      type: moverscore_question_answer_generation_with_gold_answer
+      value: 67.82
+    - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
+      type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer_gold_answer
+      value: 90.17
+    - name: QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
+      type: qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer_gold_answer
+      value: 90.16
+    - name: QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
+      type: qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer_gold_answer
+      value: 90.17
+    - name: QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
+      type: qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer_gold_answer
+      value: 68.22
+    - name: QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
+      type: qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer_gold_answer
+      value: 68.21
+    - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer)) [Gold Answer]
+      type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer_gold_answer
+      value: 68.23
     - name: BLEU4 (Question & Answer Generation)
       type: bleu4_question_answer_generation
-      value: 18.61
+      value: 2.43
     - name: ROUGE-L (Question & Answer Generation)
       type: rouge_l_question_answer_generation
-      value: 51.04
+      value: 14.74
     - name: METEOR (Question & Answer Generation)
       type: meteor_question_answer_generation
-      value: 43.1
+      value: 21.27
     - name: BERTScore (Question & Answer Generation)
       type: bertscore_question_answer_generation
-      value: 90.03
+      value: 66.18
     - name: MoverScore (Question & Answer Generation)
       type: moverscore_question_answer_generation
-      value: 67.82
+      value: 51.57
     - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
-      value: 90.17
+      value: 76.96
     - name: QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer
-      value: 90.16
+      value: 81.05
     - name: QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_precision_bertscore_question_answer_generation_gold_answer
-      value: 90.17
+      value: 73.41
     - name: QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer
-      value: 68.22
+      value: 55.53
     - name: QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_recall_moverscore_question_answer_generation_gold_answer
-      value: 68.21
+      value: 58.25
     - name: QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_precision_moverscore_question_answer_generation_gold_answer
-      value: 68.23
+      value: 53.24
 ---
 
 # Model Card of `lmqg/mt5-small-ruquad-qg`
@@ -132,7 +165,7 @@ output = pipe("Нелишним будет отметить, что, разви
 | ROUGE_L    |   31.39 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
 
 
-- ***Metric (Question & Answer Generation)***: QAG metrics are computed with *the gold answer* and generated question on it for this model, as the model cannot provide an answer. [raw metric file](https://huggingface.co/lmqg/mt5-small-ruquad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_ruquad.default.json)
+- ***Metric (Question & Answer Generation, Reference Answer)***: Each question is generated from *the gold answer*. [raw metric file](https://huggingface.co/lmqg/mt5-small-ruquad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_ruquad.default.json)
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
@@ -152,6 +185,26 @@ output = pipe("Нелишним будет отметить, что, разви
 | ROUGE_L                         |   51.04 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
 
 
+- ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/mt5-small-ruquad-ae`](https://huggingface.co/lmqg/mt5-small-ruquad-ae). [raw metric file](https://huggingface.co/lmqg/mt5-small-ruquad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_ruquad.default.lmqg_mt5-small-ruquad-ae.json)
+
+|                                 |   Score | Type    | Dataset                                                          |
+|:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
+| BERTScore                       |   66.18 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_1                          |    9.81 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_2                          |    5.77 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_3                          |    3.7  | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| Bleu_4                          |    2.43 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| METEOR                          |   21.27 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| MoverScore                      |   51.57 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| QAAlignedF1Score (BERTScore)    |   76.96 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| QAAlignedF1Score (MoverScore)   |   55.53 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| QAAlignedPrecision (BERTScore)  |   73.41 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| QAAlignedPrecision (MoverScore) |   53.24 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| QAAlignedRecall (BERTScore)     |   81.05 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| QAAlignedRecall (MoverScore)    |   58.25 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+| ROUGE_L                         |   14.74 | default | [lmqg/qg_ruquad](https://huggingface.co/datasets/lmqg/qg_ruquad) |
+
+
 
 ## Training hyperparameters