POMDP-Based Statistical Spoken Dialog Systems: A Review

Author

Young, Stephanie ; Gasic, M. ; Thomson, B. ; Williams, John D.

Author_Institution

Dept. of Eng., Cambridge Univ., Cambridge, UK

Volume

101

Issue

5

fYear

2013

fDate

5/1/2013 12:00:00 AM

Firstpage

1160

Lastpage

1179

Abstract

Statistical dialog systems (SDSs) are motivated by the need for a data-driven framework that reduces the cost of laboriously handcrafting complex dialog managers and that provides robustness against the errors created by speech recognizers operating in noisy environments. By including an explicit Bayesian model of uncertainty and by optimizing the policy via a reward-driven process, partially observable Markov decision processes (POMDPs) provide such a framework. However, exact model representation and optimization is computationally intractable. Hence, the practical application of POMDP-based systems requires efficient algorithms and carefully constructed approximations. This review article provides an overview of the current state of the art in the development of POMDP-based spoken dialog systems.

Keywords

Bayes methods; Markov processes; optimisation; speech recognition; POMDP-based statistical spoken dialog systems; SDS; data-driven framework; exact model representation; explicit Bayesian model; noisy environments; optimization; partially observable Markov decision processes; reward-driven process; speech recognizers; statistical dialog systems; Belief propagation; Information processing; Learning systems; Markov processes; Mathematical model; Optimization; Speech processing; Speech recognition; Belief monitoring; partially observable Markov decision process (POMDP); policy optimization; reinforcement learning; spoken dialog systems (SDSs);

fLanguage

English

Journal_Title

Proceedings of the IEEE

Publisher

ieee

ISSN

0018-9219

Type

jour

DOI

10.1109/JPROC.2012.2225812

Filename

6407655