Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems - Archive ouverte HAL Access content directly
Journal Articles Computer Speech and Language Year : 2010

Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems

,
Blaise Thomson
  • Function : Correspondent author
  • PersonId : 909566

Connectez-vous pour contacter l'auteur
Steve Young
  • Function : Author

Abstract

This paper describes a statistically motivated framework for performing real-time dialogue state updates and policy learning in a spoken dialogue system. The framework is based on the partially observable Markov decision process (POMDP), which provides a well-founded, statistical model of spoken dialogue management. However, exact belief state updates in a POMDP model are computationally intractable so approximate methods must be used. This paper presents a tractable method based on the loopy belief propagation algorithm. Various simplifications are made, which improve the efficiency significantly compared to the original algorithm as well as compared to other POMDP-based dialogue state updating approaches. A second contribution of this paper is a method for learning in spoken dialogue systems which uses a component-based policy with the episodic Natural Actor Critic algorithm.
Fichier principal
Vignette du fichier
PEER_stage2_10.1016%2Fj.csl.2009.07.003.pdf (714.22 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00621617 , version 1 (11-09-2011)

Identifiers

Cite

Blaise Thomson, Steve Young. Bayesian update of dialogue state: A POMDP framework for spoken dialogue systems. Computer Speech and Language, 2010, 24 (4), pp.562. ⟨10.1016/j.csl.2009.07.003⟩. ⟨hal-00621617⟩

Collections

PEER
130 View
482 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More