model update

README.md

@@ -31,37 +31,37 @@ model-index:
       type: default
       args: default
     metrics:
-    - name: BLEU4
-      type: bleu4
+    - name: BLEU4 (Question Generation)
+      type: bleu4_question_generation
       value: 0.75
-    - name: ROUGE-L
-      type: rouge-l
+    - name: ROUGE-L (Question Generation)
+      type: rouge_l_question_generation
       value: 11.19
-    - name: METEOR
-      type: meteor
+    - name: METEOR (Question Generation)
+      type: meteor_question_generation
       value: 13.71
-    - name: BERTScore
-      type: bertscore
+    - name: BERTScore (Question Generation)
+      type: bertscore_question_generation
       value: 80.77
-    - name: MoverScore
-      type: moverscore
+    - name: MoverScore (Question Generation)
+      type: moverscore_question_generation
       value: 55.88
-    - name: QAAlignedF1Score (BERTScore) [Gold Answer]
+    - name: QAAlignedF1Score-BERTScore (Gold Answer)
       type: qa_aligned_f1_score_bertscore_gold_answer
       value: 90.66
-    - name: QAAlignedRecall (BERTScore) [Gold Answer]
+    - name: QAAlignedRecall-BERTScore (Gold Answer)
       type: qa_aligned_recall_bertscore_gold_answer
       value: 90.69
-    - name: QAAlignedPrecision (BERTScore) [Gold Answer]
+    - name: QAAlignedPrecision-BERTScore (Gold Answer)
       type: qa_aligned_precision_bertscore_gold_answer
       value: 90.64
-    - name: QAAlignedF1Score (MoverScore) [Gold Answer]
+    - name: QAAlignedF1Score-MoverScore (Gold Answer)
       type: qa_aligned_f1_score_moverscore_gold_answer
       value: 65.36
-    - name: QAAlignedRecall (MoverScore) [Gold Answer]
+    - name: QAAlignedRecall-MoverScore (Gold Answer)
       type: qa_aligned_recall_moverscore_gold_answer
       value: 65.36
-    - name: QAAlignedPrecision (MoverScore) [Gold Answer]
+    - name: QAAlignedPrecision-MoverScore (Gold Answer)
       type: qa_aligned_precision_moverscore_gold_answer
       value: 65.37
 ---