Question Answering On Ms Marco
평가 지표
BLEU-1
Rouge-L
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | BLEU-1 | Rouge-L | Paper Title | Repository |
|---|---|---|---|---|
| Masque Q&A Style | 43.77 | 52.2 | Multi-style Generative Reading Comprehension | - |
| BiDaF Baseline | 10.64 | 23.96 | Bidirectional Attention Flow for Machine Comprehension | |
| Deep Cascade QA | 54.64 | 52.01 | A Deep Cascade Model for Multi-Document Reading Comprehension | - |
| VNET | 54.37 | 51.63 | Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification | - |
0 of 4 row(s) selected.