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

Blaise Thomson * Steve Young
* Corresponding 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.
Document type :
Journal articles
Complete list of metadatas

Cited literature [36 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-00621617
Contributor : Hal Peer <>
Submitted on : Sunday, September 11, 2011 - 2:51:00 AM
Last modification on : Sunday, September 11, 2011 - 2:51:00 AM
Long-term archiving on : Thursday, March 30, 2017 - 2:46:57 PM

File

PEER_stage2_10.1016%2Fj.csl.20...
Files produced by the author(s)

Identifiers

Collections

Citation

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

Share

Metrics

Record views

120

Files downloads

597