Learning dialogue strategies within the Markov decision process framework

Author

Levin, Esther ; Pieraccini, Roberto ; Eckert, Wieland

Author_Institution

AT&T Labs., Florham Park, NJ, USA

fYear

1997

fDate

14-17 Dec 1997

Firstpage

72

Lastpage

79

Abstract

We introduce a stochastic model for dialogue systems based on the Markov decision process. Within this framework we show that the problem of dialogue strategy design can be stated as an optimization problem, and solved by a variety of methods, including the reinforcement learning approach. The advantages of this new paradigm include objective evaluation of dialogue systems and their automatic design and adaptation. We show some preliminary results on learning a dialogue strategy for an air travel information system

Keywords

interactive systems; Markov decision process framework; air travel information system; automatic design; dialogue strategies; dialogue systems evaluation; optimization problem; reinforcement learning; speech recognition; stochastic model; Databases; Design optimization; Hidden Markov models; History; Information systems; Learning; Natural languages; Speech recognition; State-space methods; Stochastic systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Automatic Speech Recognition and Understanding, 1997. Proceedings., 1997 IEEE Workshop on

Conference_Location

Santa Barbara, CA

Print_ISBN

0-7803-3698-4

Type

conf

DOI

10.1109/ASRU.1997.658989

Filename

658989