Open Domain Question Answering On Quasar
Métriques
EM (Quasar-T)
F1 (Quasar-T)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Nom du modèle | EM (Quasar-T) | F1 (Quasar-T) | Paper Title | Repository |
|---|---|---|---|---|
| R^3 | 35.3 | 41.7 | R$^3$: Reinforced Reader-Ranker for Open-Domain Question Answering | |
| BiDAF | 25.9 | 28.5 | Bidirectional Attention Flow for Machine Comprehension | |
| DecaProp | 38.6 | 46.9 | Densely Connected Attention Propagation for Reading Comprehension | |
| Evidence Aggregation via R^3 Re-Ranking | 42.3 | 49.6 | Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering | |
| Denoising QA | 42.2 | 49.3 | Denoising Distantly Supervised Open-Domain Question Answering | |
| GA | 26.4 | 26.4 | Gated-Attention Readers for Text Comprehension |
0 of 6 row(s) selected.