The Hidden Information State Model: a practical framework for POMDP-based spoken dialogue management - Archive ouverte HAL Access content directly
Journal Articles Computer Speech and Language Year : 2009

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

Steve Young
  • Function : Correspondent author
  • PersonId : 873407

Connectez-vous pour contacter l'auteur
Milica Gašić
  • Function : Author
Simon Keizer
  • Function : Author
François Mairesse
Jost Schatzmann
  • Function : Author
Blaise Thomson
  • Function : Author
Kai Yu
  • Function : Author

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.
Fichier principal
Vignette du fichier
PEER_stage2_10.1016%2Fj.csl.2009.04.001.pdf (636.35 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00598186 , version 1 (05-06-2011)

Identifiers

Cite

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, 2009, 24 (2), pp.150. ⟨10.1016/j.csl.2009.04.001⟩. ⟨hal-00598186⟩

Collections

PEER
599 View
1334 Download

Altmetric

Share

Gmail Facebook X LinkedIn More