Question Answering On Natural Questions Long
평가 지표
EM
평가 결과
이 벤치마크에서 각 모델의 성능 결과
비교 표
| 모델 이름 | EM |
|---|---|
| 0-8-nyquist-computational-ghost-imaging-via | 58.4 |
| learning-dense-representations-of-phrases-at | 71.9 |
| r2-d2-a-modular-baseline-for-open-domain | 55.9 |
| unitedqa-a-hybrid-approach-for-open-domain | 54.7 |
| frustratingly-easy-natural-question-answering | - |
| cluster-former-clustering-based-sparse | - |
| reading-wikipedia-to-answer-open-domain | - |
| reformer-the-efficient-transformer-1 | - |
| unified-open-domain-question-answering-with | 54.9 |
| a-bert-baseline-for-the-natural-questions | - |
| 190410509 | - |
| efficient-passage-retrieval-with-hashing-for | 41.6 |
| natural-questions-a-benchmark-for-question | - |