model update

README.md

@@ -46,21 +46,6 @@ model-index:
     - name: MoverScore (Question Generation)
       type: moverscore_question_generation
       value: 82.95
-    - name: BLEU4 (Question & Answer Generation (with Gold Answer))
-      type: bleu4_question_answer_generation_with_gold_answer
-      value: 11.25
-    - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
-      type: rouge_l_question_answer_generation_with_gold_answer
-      value: 47.9
-    - name: METEOR (Question & Answer Generation (with Gold Answer))
-      type: meteor_question_answer_generation_with_gold_answer
-      value: 39.03
-    - name: BERTScore (Question & Answer Generation (with Gold Answer))
-      type: bertscore_question_answer_generation_with_gold_answer
-      value: 87.88
-    - name: MoverScore (Question & Answer Generation (with Gold Answer))
-      type: moverscore_question_answer_generation_with_gold_answer
-      value: 84.85
     - 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: 88.18
@@ -79,21 +64,6 @@ model-index:
     - 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: 85.62
-    - name: BLEU4 (Question & Answer Generation)
-      type: bleu4_question_answer_generation
-      value: 0.96
-    - name: ROUGE-L (Question & Answer Generation)
-      type: rouge_l_question_answer_generation
-      value: 12.88
-    - name: METEOR (Question & Answer Generation)
-      type: meteor_question_answer_generation
-      value: 23.62
-    - name: BERTScore (Question & Answer Generation)
-      type: bertscore_question_answer_generation
-      value: 67.72
-    - name: MoverScore (Question & Answer Generation)
-      type: moverscore_question_answer_generation
-      value: 62.37
     - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
       value: 80.64
@@ -169,40 +139,24 @@ output = pipe("1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
-| BERTScore                       |   87.88 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_1                          |   42.94 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_2                          |   31.44 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_3                          |   19.38 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_4                          |   11.25 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| METEOR                          |   39.03 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| MoverScore                      |   84.85 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedF1Score (BERTScore)    |   88.18 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedF1Score (MoverScore)   |   85.53 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedPrecision (BERTScore)  |   88.22 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedPrecision (MoverScore) |   85.62 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedRecall (BERTScore)     |   88.15 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedRecall (MoverScore)    |   85.46 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| ROUGE_L                         |   47.9  | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 
 
 - ***Metric (Question & Answer Generation, Pipeline Approach)***: Each question is generated on the answer generated by [`lmqg/mbart-large-cc25-koquad-ae`](https://huggingface.co/lmqg/mbart-large-cc25-koquad-ae). [raw metric file](https://huggingface.co/lmqg/mbart-large-cc25-koquad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_koquad.default.lmqg_mbart-large-cc25-koquad-ae.json)
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
-| BERTScore                       |   67.72 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_1                          |    8.03 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_2                          |    4.3  | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_3                          |    2.04 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_4                          |    0.96 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| METEOR                          |   23.62 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| MoverScore                      |   62.37 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedF1Score (BERTScore)    |   80.64 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedF1Score (MoverScore)   |   82.74 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedPrecision (BERTScore)  |   77.67 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedPrecision (MoverScore) |   78.99 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedRecall (BERTScore)     |   83.95 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedRecall (MoverScore)    |   87.04 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| ROUGE_L                         |   12.88 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |