Automatic Optimization of Dialogue Management

Designing the dialogue strategy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a dialogue strategy that addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We then show that our approach measurably improves performance in an experimental system.

[1]  M. Valenti,et al.  Anonymous , 1950, American Journal of International Law.

[2]  Richard S. Sutton,et al.  Planning by Incremental Dynamic Programming , 1991, ML.

[3]  Morena Danieli,et al.  Metrics for Evaluating Dialogue Strategies in a Spoken Language System , 1996, ArXiv.

[4]  Yasuhisa Niimi,et al.  A dialog control strategy based on the reliability of speech recognition , 1996, Proceeding of Fourth International Conference on Spoken Language Processing. ICSLP '96.

[5]  Egidio Giachin,et al.  Spoken language dialogue , 1997 .

[6]  Roberto Pieraccini,et al.  Learning dialogue strategies within the Markov decision process framework , 1997, 1997 IEEE Workshop on Automatic Speech Recognition and Understanding Proceedings.

[7]  L. Boves,et al.  Evaluation of the Dutch train timetable information system developed in the ARISE project , 1998, Proceedings 1998 IEEE 4th Workshop Interactive Voice Technology for Telecommunications Applications. IVTTA '98 (Cat. No.98TH8376).

[8]  Marilyn A. Walker,et al.  From novice to expert: the effect of tutorials on user expertise with spoken dialogue systems , 1998, ICSLP.

[9]  Marilyn A. Walker,et al.  Learning Optimal Dialogue Strategies: A Case Study of a Spoken Dialogue Agent for Email , 1998, COLING-ACL.

[10]  Marilyn A. Walker,et al.  Reinforcement Learning for Spoken Dialogue Systems , 1999, NIPS.

[11]  SPOKEN LANGUAGE DIALOGUE : FROM THEORY TO PRACTICE , 1999 .

[12]  Marilyn A. Walker,et al.  Empirical Evaluation of a Reinforcement Learning Spoken Dialogue System , 2000, AAAI/IAAI.

[13]  Roberto Pieraccini,et al.  A stochastic model of human-machine interaction for learning dialog strategies , 2000, IEEE Trans. Speech Audio Process..

[14]  Shimei Pan,et al.  Predicting and Adapting to Poor Speech Recognition in a Spoken Dialogue System , 2000, AAAI/IAAI.