Open-Domain Question Answering on Quasar
Metric: F1 (Quasar-T) (higher is better)
Metric: F1 (Quasar-T) (higher is better)
| # | Model↕ | F1 (Quasar-T)▼ | Extra Data | Paper | Date↕ | Code |
|---|---|---|---|---|---|---|
| 1 | Evidence Aggregation via R^3 Re-Ranking | 49.6 | No | Evidence Aggregation for Answer Re-Ranking in Op... | 2017-11-14 | Code |
| 2 | Denoising QA | 49.3 | No | - | - | Code |
| 3 | DecaProp | 46.9 | No | Densely Connected Attention Propagation for Read... | 2018-11-10 | Code |
| 4 | R^3 | 41.7 | No | R$^3$: Reinforced Reader-Ranker for Open-Domain ... | 2017-08-31 | Code |
| 5 | BiDAF | 28.5 | No | Bidirectional Attention Flow for Machine Compreh... | 2016-11-05 | Code |
| 6 | GA | 26.4 | No | Gated-Attention Readers for Text Comprehension | 2016-06-05 | Code |