Abstract:
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.
copied = false, 2000);
">
@conference{Roy-2000-8120,
author = {Nicholas Roy And Joelle Pineau And Sebastian Thrun},
title = {Spoken Dialog Management for Robots},
booktitle = {Proceedings of 39th Annual Meeting of the Association for Computational Linguistics (ACL '00)},
year = {2000},
month = {October},
keywords = {POMDP, dialogue, robotics},
}
author = {Nicholas Roy And Joelle Pineau And Sebastian Thrun},
title = {Spoken Dialog Management for Robots},
booktitle = {Proceedings of 39th Annual Meeting of the Association for Computational Linguistics (ACL '00)},
year = {2000},
month = {October},
keywords = {POMDP, dialogue, robotics},
}