Question Answering On Wikihop
Métriques
Test
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Test |
|---|---|
| neural-models-for-reasoning-over-multiple | 59.3 |
| coarse-grain-fine-grain-coattention-network | 70.6 |
| commonsense-for-generative-multi-hop-question | 57.9 |
| big-bird-transformers-for-longer-sequences | 82.3 |
| constructing-datasets-for-multi-hop-reading | 42.9 |
| multi-hop-question-answering-via-reasoning | 76.5 |
| exploring-graph-structured-passage | 65.4 |
| luke-graph-a-transformer-based-approach-with | 81.0 |
| longformer-the-long-document-transformer | 81.9 |