Title :

Safe transfer learning for dialogue applications

Author(s) :

Carrara, Nicolas [Auteur]
Sequential Learning [SEQUEL]
Orange Labs [Lannion]
Laroche, Romain [Auteur]
Maluuba
Bouraoui, Jean-Léon [Auteur]
Orange Labs [Lannion]
Urvoy, Tanguy [Auteur]
Orange Labs [Lannion]
Pietquin, Olivier [Auteur]
Google Inc

Conference title :

SLSP 2018 - 6th International Conference on Statistical Language and Speech Processing

City :

Mons

Country :

Belgique

Start date of the conference :

2018-10-15

Publication date :

2018-10-15

English keyword(s) :

Safety
Transfer Learning
Dialogue

HAL domain(s) :

Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]
Informatique [cs]/Apprentissage [cs.LG]

English abstract : [en]

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 ...
Show more >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.Show less >

Language :

Anglais

Peer reviewed article :

Oui

Audience :

Internationale

Popular science :

Non

Collections :

• Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189

Source :

Harvested from HAL