Safe transfer learning for dialogue applications
Résumé
In this paper, we formulate the hypothesis that the first dialogues with a new user should be handle in a very conservative way, for two reasons : avoid user dropout; gather more successful dialogues to speedup the learning of the asymptotic strategy. To this extend, we propose to transfer a safe strategy to initiate the first dialogues.
| Origine | Fichiers produits par l'(les) auteur(s) |
|---|
Loading...