Data To Text Generation On Multiwoz 2 1
Métriques
BLEU
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | BLEU |
|---|---|
| few-shot-natural-language-generation-for-task | 30.76 |
| few-shot-natural-language-generation-by | 34.96 |
| few-shot-natural-language-generation-by | 34.91 |
| text-to-text-pre-training-for-data-to-text | 35.1 |
| semantically-conditioned-dialog-response | 26.48 |