Question Answering On Friendsqa
Métriques
EM
F1
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | EM | F1 |
|---|---|---|
| enhanced-speaker-aware-multi-party-multi-turn | 58.7 | 75.4 |
| self-and-pseudo-self-supervised-prediction-of | 55.8 | 72.3 |
| transformers-to-learn-hierarchical-contexts | 46.8 | 63.1 |
| graph-based-knowledge-integration-for | 46.4 | 64.3 |
| self-and-pseudo-self-supervised-prediction-of | 46.9 | 63.9 |
| transformers-to-learn-hierarchical-contexts | 53.5 | 69.6 |