model update

README.md

@@ -46,39 +46,72 @@ model-index:
     - name: MoverScore (Question Generation)
       type: moverscore_question_generation
       value: 54.64
+    - name: BLEU4 (Question & Answer Generation (with Gold Answer))
+      type: bleu4_question_answer_generation_with_gold_answer
+      value: 0.08
+    - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
+      type: rouge_l_question_answer_generation_with_gold_answer
+      value: 16.17
+    - name: METEOR (Question & Answer Generation (with Gold Answer))
+      type: meteor_question_answer_generation_with_gold_answer
+      value: 18.96
+    - name: BERTScore (Question & Answer Generation (with Gold Answer))
+      type: bertscore_question_answer_generation_with_gold_answer
+      value: 74.29
+    - name: MoverScore (Question & Answer Generation (with Gold Answer))
+      type: moverscore_question_answer_generation_with_gold_answer
+      value: 52.45
+    - 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: 90.55
+    - 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: 90.51
+    - 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: 90.59
+    - 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: 64.33
+    - 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: 64.29
+    - 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: 64.37
     - name: BLEU4 (Question & Answer Generation)
       type: bleu4_question_answer_generation
-      value: 0.08
+      value: 0.89
     - name: ROUGE-L (Question & Answer Generation)
       type: rouge_l_question_answer_generation
-      value: 16.17
+      value: 16.85
     - name: METEOR (Question & Answer Generation)
       type: meteor_question_answer_generation
-      value: 18.96
+      value: 20.32
     - name: BERTScore (Question & Answer Generation)
       type: bertscore_question_answer_generation
-      value: 74.29
+      value: 73.16
     - name: MoverScore (Question & Answer Generation)
       type: moverscore_question_answer_generation
-      value: 52.45
+      value: 52.63
     - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
-      value: 90.55
+      value: 81.19
     - name: QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer
-      value: 90.51
+      value: 82.46
     - name: QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_precision_bertscore_question_answer_generation_gold_answer
-      value: 90.59
+      value: 80.0
     - name: QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer
-      value: 64.33
+      value: 54.3
     - name: QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_recall_moverscore_question_answer_generation_gold_answer
-      value: 64.29
+      value: 54.59
     - name: QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_precision_moverscore_question_answer_generation_gold_answer
-      value: 64.37
+      value: 54.04
 ---
 
 # Model Card of `lmqg/mt5-small-dequad-qg`
@@ -132,7 +165,7 @@ output = pipe("Empfangs- und Sendeantenne sollen in ihrer Polarisation übereins
 | ROUGE_L    |   10.08 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
 
 
-- ***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-dequad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.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-dequad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.json)
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
@@ -152,6 +185,26 @@ output = pipe("Empfangs- und Sendeantenne sollen in ihrer Polarisation übereins
 | ROUGE_L                         |   16.17 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
 
 
+- ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/mt5-small-dequad-ae`](https://huggingface.co/lmqg/mt5-small-dequad-ae). [raw metric file](https://huggingface.co/lmqg/mt5-small-dequad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_dequad.default.lmqg_mt5-small-dequad-ae.json)
+
+|                                 |   Score | Type    | Dataset                                                          |
+|:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
+| BERTScore                       |   73.16 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| Bleu_1                          |   14.65 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| Bleu_2                          |    7.15 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| Bleu_3                          |    2.23 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| Bleu_4                          |    0.89 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| METEOR                          |   20.32 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| MoverScore                      |   52.63 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| QAAlignedF1Score (BERTScore)    |   81.19 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| QAAlignedF1Score (MoverScore)   |   54.3  | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| QAAlignedPrecision (BERTScore)  |   80    | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| QAAlignedPrecision (MoverScore) |   54.04 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| QAAlignedRecall (BERTScore)     |   82.46 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| QAAlignedRecall (MoverScore)    |   54.59 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+| ROUGE_L                         |   16.85 | default | [lmqg/qg_dequad](https://huggingface.co/datasets/lmqg/qg_dequad) |
+
+
 
 ## Training hyperparameters