Skip to Main content Skip to Navigation
Conference papers

Reward Function Learning for Dialogue Management

Layla El Asri 1 Romain Laroche 2 Olivier Pietquin 3
1 IMS - Equipe Information, Multimodalité et Signal
UMI2958 - Georgia Tech - CNRS [Metz], SUPELEC-Campus Metz, Orange Labs [Issy les Moulineaux]
3 IMS - Equipe Information, Multimodalité et Signal
UMI2958 - Georgia Tech - CNRS [Metz], SUPELEC-Campus Metz
Abstract : This paper addresses the problem of defining, from data, a reward function in a Reinforcement Learning (RL) problem. This issue is applied to the case of Spoken Dialogue Systems (SDS), which are interfaces enabling users to interact in natural language. A new methodology which, from system evaluation, apportions rewards over the system's state space, is suggested. A corpus of dialogues is collected on-line and then evaluated by experts, assigning a numerical performance score to each dialogue according to the quality of dialogue management. The approach described in this paper infers, from these scores, a locally distributed reward function which can be used on-line. Two algorithms achieving this goal are proposed. These algorithms are tested on an SDS and it is showed that in both cases, the resulting numerical rewards are close to the performance scores and thus, that it is possible to extract relevant information from performance evaluation to optimise on- line learning.
Document type :
Conference papers
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00749430
Contributor : Sébastien van Luchene <>
Submitted on : Wednesday, November 7, 2012 - 3:14:08 PM
Last modification on : Tuesday, October 27, 2020 - 2:34:45 PM

Identifiers

Collections

Citation

Layla El Asri, Romain Laroche, Olivier Pietquin. Reward Function Learning for Dialogue Management. STAIRS 2012, Aug 2012, Montpellier, France. pp.95-106, ⟨10.3233/978-1-61499-096-3-95⟩. ⟨hal-00749430⟩

Share

Metrics

Record views

295