model update

README.md

@@ -46,21 +46,6 @@ model-index:
     - name: MoverScore (Question Generation)
       type: moverscore_question_generation
       value: 83.36
-    - name: BLEU4 (Question & Answer Generation (with Gold Answer))
-      type: bleu4_question_answer_generation_with_gold_answer
-      value: 12.08
-    - name: ROUGE-L (Question & Answer Generation (with Gold Answer))
-      type: rouge_l_question_answer_generation_with_gold_answer
-      value: 48.7
-    - name: METEOR (Question & Answer Generation (with Gold Answer))
-      type: meteor_question_answer_generation_with_gold_answer
-      value: 38.75
-    - name: BERTScore (Question & Answer Generation (with Gold Answer))
-      type: bertscore_question_answer_generation_with_gold_answer
-      value: 88.5
-    - name: MoverScore (Question & Answer Generation (with Gold Answer))
-      type: moverscore_question_answer_generation_with_gold_answer
-      value: 85.18
     - 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: 88.8
@@ -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: 86.01
-    - name: BLEU4 (Question & Answer Generation)
-      type: bleu4_question_answer_generation
-      value: 0.65
-    - name: ROUGE-L (Question & Answer Generation)
-      type: rouge_l_question_answer_generation
-      value: 11.32
-    - name: METEOR (Question & Answer Generation)
-      type: meteor_question_answer_generation
-      value: 17.42
-    - name: BERTScore (Question & Answer Generation)
-      type: bertscore_question_answer_generation
-      value: 61.72
-    - name: MoverScore (Question & Answer Generation)
-      type: moverscore_question_answer_generation
-      value: 61.82
     - name: QAAlignedF1Score-BERTScore (Question & Answer Generation) [Gold Answer]
       type: qa_aligned_f1_score_bertscore_question_answer_generation_gold_answer
       value: 77.26
@@ -169,40 +139,24 @@ output = pipe("1990년 영화 《 <hl> 남부군 <hl> 》에서 단역으로 영
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
-| BERTScore                       |   88.5  | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_1                          |   43.95 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_2                          |   32.47 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_3                          |   20.34 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_4                          |   12.08 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| METEOR                          |   38.75 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| MoverScore                      |   85.18 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedF1Score (BERTScore)    |   88.8  | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedF1Score (MoverScore)   |   85.93 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedPrecision (BERTScore)  |   88.84 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedPrecision (MoverScore) |   86.01 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedRecall (BERTScore)     |   88.76 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedRecall (MoverScore)    |   85.87 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| ROUGE_L                         |   48.7  | 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/mt5-base-koquad-ae`](https://huggingface.co/lmqg/mt5-base-koquad-ae). [raw metric file](https://huggingface.co/lmqg/mt5-base-koquad-qg/raw/main/eval_pipeline/metric.first.answer.paragraph.questions_answers.lmqg_qg_koquad.default.lmqg_mt5-base-koquad-ae.json)
 
 |                                 |   Score | Type    | Dataset                                                          |
 |:--------------------------------|--------:|:--------|:-----------------------------------------------------------------|
-| BERTScore                       |   61.72 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_1                          |    6.83 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_2                          |    3.13 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_3                          |    1.38 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| Bleu_4                          |    0.65 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| METEOR                          |   17.42 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| MoverScore                      |   61.82 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedF1Score (BERTScore)    |   77.26 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedF1Score (MoverScore)   |   77.51 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedPrecision (BERTScore)  |   76.37 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedPrecision (MoverScore) |   76.26 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedRecall (BERTScore)     |   78.25 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
 | QAAlignedRecall (MoverScore)    |   78.95 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |
-| ROUGE_L                         |   11.32 | default | [lmqg/qg_koquad](https://huggingface.co/datasets/lmqg/qg_koquad) |