Spoken dialogue management using probabilistic reasoning.

N. Roy, J. Pineau, and S. Thrun.

Spoken dialogue managers have benefited from using stochastic planners such as Markov Decision Processes (MDPs). However, so far, MDPs do not handle well noisy and ambiguous speech utterances. We use a Partially Observable Markov Decision Process (POMDP)-style approach to generate dialogue strategies by inverting the notion of dialogue state; the state represents the user's intentions, rather than the system state. We demonstrate that under the same noisy conditions, a POMDP dialogue manager makes fewer mistakes than an MDP dialogue manager. Furthermore, as the quality of speech recognition degrades, the POMDP dialogue manager automatically adjusts the policy.

The full paper is available in PDF and gzipped Postscript

@INPROCEEDINGS{Roy00b,
  AUTHOR	= {Roy, N. and Pineau, J. and Thrun, S.},
  TITLE		= {Spoken Dialogue Management Using Probabilistic Reasoning},
  YEAR		= {2000},
  BOOKTITLE	= {Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics (ACL-2000)},
  ADDRESS	= {Hong Kong}
}