model update

README.md

@@ -46,23 +46,38 @@ model-index:
     - name: MoverScore (Question Generation)
       type: moverscore_question_generation
       value: 50.35
-    - name: QAAlignedF1Score-BERTScore (Gold Answer)
-      type: qa_aligned_f1_score_bertscore_gold_answer
+    - name: BLEU4 (Question & Answer Generation (with Gold Answer))
+      type: bleu4_question_answer_generation_with_gold_answer
+      value: 9.7
+    - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
+      type: rouge_l_question_answer_generation_with_gold_answer
+      value: 33.61
+    - name: METEOR (Question & Answer Generation (with Gold Answer))
+      type: meteor_question_answer_generation_with_gold_answer
+      value: 26.31
+    - name: BERTScore (Question & Answer Generation (with Gold Answer))
+      type: bertscore_question_answer_generation_with_gold_answer
+      value: 80.27
+    - name: MoverScore (Question & Answer Generation (with Gold Answer))
+      type: moverscore_question_answer_generation_with_gold_answer
+      value: 55.65
+    - 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: 81.27
-    - name: QAAlignedRecall-BERTScore (Gold Answer)
-      type: qa_aligned_recall_bertscore_gold_answer
+    - 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: 81.25
-    - name: QAAlignedPrecision-BERTScore (Gold Answer)
-      type: qa_aligned_precision_bertscore_gold_answer
+    - 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: 81.29
-    - name: QAAlignedF1Score-MoverScore (Gold Answer)
-      type: qa_aligned_f1_score_moverscore_gold_answer
+    - 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: 55.61
-    - name: QAAlignedRecall-MoverScore (Gold Answer)
-      type: qa_aligned_recall_moverscore_gold_answer
+    - 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: 55.6
-    - name: QAAlignedPrecision-MoverScore (Gold Answer)
-      type: qa_aligned_precision_moverscore_gold_answer
+    - 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: 55.61
 ---
 
@@ -117,16 +132,24 @@ output = pipe("Créateur » (Maker), lui aussi au singulier, « <hl> le Suprême
 | ROUGE_L    |   16.4  | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 
 
-- ***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/mbart-large-cc25-frquad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_frquad.default.json)
+- ***Metric (Question & Answer Generation, Reference Answer)***: Each question is generated from *the gold answer*. [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-frquad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_frquad.default.json)
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
+| BERTScore                       |   80.27 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_1                          |   29.47 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_2                          |   19.07 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_3                          |   13.39 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_4                          |    9.7  | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| METEOR                          |   26.31 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| MoverScore                      |   55.65 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 | QAAlignedF1Score (BERTScore)    |   81.27 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 | QAAlignedF1Score (MoverScore)   |   55.61 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 | QAAlignedPrecision (BERTScore)  |   81.29 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 | QAAlignedPrecision (MoverScore) |   55.61 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 | QAAlignedRecall (BERTScore)     |   81.25 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 | QAAlignedRecall (MoverScore)    |   55.6  | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| ROUGE_L                         |   33.61 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |