Open Domain Question Answering On Eli5
평가 지표
Rouge-1
Rouge-2
Rouge-L
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | Rouge-1 | Rouge-2 | Rouge-L |
|---|---|---|---|
| closed-book-question-generation-via | 29.15 | 10.36 | 26.40 |
| using-local-knowledge-graph-construction-to | 30.0 | 5.8 | 24.0 |
| improving-conditioning-in-context-aware | 23.32 | 4.79 | 14.63 |
| fourier-transformer-fast-long-range-modeling | - | - | 26.9 |
| reducing-transformer-depth-on-demand-with-1 | 29.4 | 5.5 | 23.4 |
| bart-denoising-sequence-to-sequence-pre | 30.6 | 6.2 | 24.3 |