model update

README.md

@@ -51,23 +51,38 @@ model-index:
     - name: MoverScore (Question Generation)
       type: moverscore_question_generation
       value: 57.15
-    - name: QAAlignedF1Score-BERTScore (Question & Answer Generation)
-      type: qa_aligned_f1_score_bertscore_question_answer_generation
+    - name: BLEU4 (Question & Answer Generation (with Gold Answer))
+      type: bleu4_question_answer_generation_with_gold_answer
+      value: 3.8
+    - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
+      type: rouge_l_question_answer_generation_with_gold_answer
+      value: 23.43
+    - name: METEOR (Question & Answer Generation (with Gold Answer))
+      type: meteor_question_answer_generation_with_gold_answer
+      value: 24.87
+    - name: BERTScore (Question & Answer Generation (with Gold Answer))
+      type: bertscore_question_answer_generation_with_gold_answer
+      value: 77.22
+    - name: MoverScore (Question & Answer Generation (with Gold Answer))
+      type: moverscore_question_answer_generation_with_gold_answer
+      value: 54.79
+    - name: QAAlignedF1Score-BERTScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_f1_score_bertscore_question_answer_generation_with_gold_answer
       value: 81.98
-    - name: QAAlignedRecall-BERTScore (Question & Answer Generation)
-      type: qa_aligned_recall_bertscore_question_answer_generation
+    - name: QAAlignedRecall-BERTScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_recall_bertscore_question_answer_generation_with_gold_answer
       value: 82.83
-    - name: QAAlignedPrecision-BERTScore (Question & Answer Generation)
-      type: qa_aligned_precision_bertscore_question_answer_generation
+    - name: QAAlignedPrecision-BERTScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_precision_bertscore_question_answer_generation_with_gold_answer
       value: 81.19
-    - name: QAAlignedF1Score-MoverScore (Question & Answer Generation)
-      type: qa_aligned_f1_score_moverscore_question_answer_generation
+    - name: QAAlignedF1Score-MoverScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_f1_score_moverscore_question_answer_generation_with_gold_answer
       value: 56.35
-    - name: QAAlignedRecall-MoverScore (Question & Answer Generation)
-      type: qa_aligned_recall_moverscore_question_answer_generation
+    - name: QAAlignedRecall-MoverScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_recall_moverscore_question_answer_generation_with_gold_answer
       value: 56.75
-    - name: QAAlignedPrecision-MoverScore (Question & Answer Generation)
-      type: qa_aligned_precision_moverscore_question_answer_generation
+    - name: QAAlignedPrecision-MoverScore (Question & Answer Generation (with Gold Answer))
+      type: qa_aligned_precision_moverscore_question_answer_generation_with_gold_answer
       value: 56.0
     - name: BLEU4 (Answer Extraction)
       type: bleu4_answer_extraction
@@ -152,12 +167,20 @@ question = pipe("extract answers: <hl> Il 6 ottobre 1973 , la Siria e l' Egitto,
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
+| BERTScore                       |   77.22 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| Bleu_1                          |   23.77 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| Bleu_2                          |   13.36 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| Bleu_3                          |    6.73 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| Bleu_4                          |    3.8  | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| METEOR                          |   24.87 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| MoverScore                      |   54.79 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
 | QAAlignedF1Score (BERTScore)    |   81.98 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
 | QAAlignedF1Score (MoverScore)   |   56.35 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
 | QAAlignedPrecision (BERTScore)  |   81.19 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
 | QAAlignedPrecision (MoverScore) |   56    | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
 | QAAlignedRecall (BERTScore)     |   82.83 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
 | QAAlignedRecall (MoverScore)    |   56.75 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
+| ROUGE_L                         |   23.43 | default | [lmqg/qg_itquad](https://huggingface.co/datasets/lmqg/qg_itquad) |
 
 
 - ***Metric (Answer Extraction)***: [raw metric file](https://huggingface.co/lmqg/mt5-base-itquad-qg-ae/raw/main/eval/metric.first.answer.paragraph_sentence.answer.lmqg_qg_itquad.default.json)