Using Markov decision process for learning dialogue strategies

Author

Levin, Esther ; Pieraccini, Roberto ; Eckert, Wieland

Author_Institution

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

Volume

1

fYear

1998

fDate

12-15 May 1998

Firstpage

201

Abstract

We introduce a stochastic model for dialogue systems based on 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

Markov processes; decision theory; interactive systems; learning systems; optimisation; speech recognition; traffic information systems; Markov decision process; air travel information system; dialogue systems; interactive system; optimization; reinforcement learning; speech understanding; stochastic model; Computational modeling; Databases; Design optimization; Hidden Markov models; History; Information systems; Learning; Natural languages; Speech recognition; Stochastic systems;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech and Signal Processing, 1998. Proceedings of the 1998 IEEE International Conference on

Conference_Location

Seattle, WA

ISSN

1520-6149

Print_ISBN

0-7803-4428-6

Type

conf

DOI

10.1109/ICASSP.1998.674402

Filename

674402