model update

README.md

@@ -46,39 +46,72 @@ model-index:
     - name: MoverScore (Question Generation)
       type: moverscore_question_generation
       value: 56.5
+    - name: BLEU4 (Question & Answer Generation (with Gold Answer))
+      type: bleu4_question_answer_generation_with_gold_answer
+      value: 13.83
+    - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
+      type: rouge_l_question_answer_generation_with_gold_answer
+      value: 42.57
+    - name: METEOR (Question & Answer Generation (with Gold Answer))
+      type: meteor_question_answer_generation_with_gold_answer
+      value: 34.29
+    - name: BERTScore (Question & Answer Generation (with Gold Answer))
+      type: bertscore_question_answer_generation_with_gold_answer
+      value: 88.51
+    - name: MoverScore (Question & Answer Generation (with Gold Answer))
+      type: moverscore_question_answer_generation_with_gold_answer
+      value: 62.42
+    - 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: 88.52
+    - 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: 88.51
+    - 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: 88.53
+    - 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: 62.46
+    - 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: 62.45
+    - 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: 62.46
     - name: BLEU4 (Question & Answer Generation)
       type: bleu4_question_answer_generation
-      value: 13.83
+      value: 1.4
     - name: ROUGE-L (Question & Answer Generation)
       type: rouge_l_question_answer_generation
-      value: 42.57
+      value: 15.84
     - name: METEOR (Question & Answer Generation)
       type: meteor_question_answer_generation
-      value: 34.29
+      value: 19.29
     - name: BERTScore (Question & Answer Generation)
       type: bertscore_question_answer_generation
-      value: 88.51
+      value: 68.54
     - name: MoverScore (Question & Answer Generation)
       type: moverscore_question_answer_generation
-      value: 62.42
+      value: 51.06
     - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
-      value: 88.52
+      value: 79.72
     - name: QAAlignedRecall-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_recall_bertscore_question_answer_generation_gold_answer
-      value: 88.51
+      value: 82.06
     - name: QAAlignedPrecision-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_precision_bertscore_question_answer_generation_gold_answer
-      value: 88.53
+      value: 77.58
     - name: QAAlignedF1Score-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_f1_score_moverscore_question_answer_generation_gold_answer
-      value: 62.46
+      value: 53.94
     - name: QAAlignedRecall-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_recall_moverscore_question_answer_generation_gold_answer
-      value: 62.45
+      value: 55.32
     - name: QAAlignedPrecision-MoverScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_precision_moverscore_question_answer_generation_gold_answer
-      value: 62.46
+      value: 52.7
 ---
 
 # Model Card of `lmqg/mt5-small-frquad-qg`
@@ -132,7 +165,7 @@ output = pipe("Créateur » (Maker), lui aussi au singulier, « <hl> le Suprême
 | ROUGE_L    |   28.56 | 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/mt5-small-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/mt5-small-frquad-qg/raw/main/eval/metric.first.answer.paragraph.questions_answers.lmqg_qg_frquad.default.json)
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
@@ -152,6 +185,26 @@ output = pipe("Créateur » (Maker), lui aussi au singulier, « <hl> le Suprême
 | ROUGE_L                         |   42.57 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
 
 
+- ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/mt5-small-frquad-ae`](https://huggingface.co/lmqg/mt5-small-frquad-ae). [raw metric file](https://huggingface.co/lmqg/mt5-small-frquad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_frquad.default.lmqg_mt5-small-frquad-ae.json)
+
+|                                 |   Score | Type    | Dataset                                                          |
+|:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
+| BERTScore                       |   68.54 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_1                          |   11.49 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_2                          |    5.61 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_3                          |    2.84 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| Bleu_4                          |    1.4  | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| METEOR                          |   19.29 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| MoverScore                      |   51.06 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| QAAlignedF1Score (BERTScore)    |   79.72 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| QAAlignedF1Score (MoverScore)   |   53.94 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| QAAlignedPrecision (BERTScore)  |   77.58 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| QAAlignedPrecision (MoverScore) |   52.7  | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| QAAlignedRecall (BERTScore)     |   82.06 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| QAAlignedRecall (MoverScore)    |   55.32 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+| ROUGE_L                         |   15.84 | default | [lmqg/qg_frquad](https://huggingface.co/datasets/lmqg/qg_frquad) |
+
+
 
 ## Training hyperparameters