The Hidden Information State Model: a practical framework for POMDP-based spoken dialogue management

Abstract : This paper explains how Partially Observable Markov Decision Processes (POMDPs) can provide a principled mathematical framework for modelling the inherent uncertainty in spoken dialogue systems. It briefly summarises the basic mathematics and explains why exact optimisation is intractable. It then describes in some detail a form of approximation called the which does scale and which can be used to build practical systems. A prototype HIS system for the tourist information domain is evaluated and compared with a baseline MDP system using both user simulations and a live user trial. The results give strong support to the central contention that the POMDP-based framework is both a tractable and powerful approach to building more robust spoken dialogue systems.
Type de document :
Article dans une revue
Computer Speech and Language, Elsevier, 2009, 24 (2), pp.150. 〈10.1016/j.csl.2009.04.001〉
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00598186
Contributeur : Hal Peer <>
Soumis le : dimanche 5 juin 2011 - 02:54:11
Dernière modification le : dimanche 5 juin 2011 - 02:54:11
Document(s) archivé(s) le : dimanche 4 décembre 2016 - 09:09:32

Fichier

PEER_stage2_10.1016%2Fj.csl.20...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Steve Young, Milica Gašić, Simon Keizer, François Mairesse, Jost Schatzmann, et al.. The Hidden Information State Model: a practical framework for POMDP-based spoken dialogue management. Computer Speech and Language, Elsevier, 2009, 24 (2), pp.150. 〈10.1016/j.csl.2009.04.001〉. 〈hal-00598186〉

Partager

Métriques

Consultations de la notice

268

Téléchargements de fichiers

797