Safe transfer learning for dialogue applications

Nicolas Carrara 1, 2 Romain Laroche 3 Jean-Léon Bouraoui 4 Tanguy Urvoy 1 Olivier Pietquin 5
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille (CRIStAL) - UMR 9189
Abstract : 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.
Complete list of metadatas

Cited literature [9 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01928102
Contributor : Nicolas Carrara <>
Submitted on : Tuesday, November 20, 2018 - 1:46:18 PM
Last modification on : Thursday, October 17, 2019 - 8:57:09 AM

File

ncarrara__SLSP_2018 (1).pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01928102, version 1

Citation

Nicolas Carrara, Romain Laroche, Jean-Léon Bouraoui, Tanguy Urvoy, Olivier Pietquin. Safe transfer learning for dialogue applications. SLSP 2018 - 6th International Conference on Statistical Language and Speech Processing, Oct 2018, Mons, Belgium. ⟨hal-01928102⟩

Share

Metrics

Record views

113

Files downloads

136