Sciweavers

ACL
2000

Spoken Dialogue Management Using Probabilistic Reasoning

13 years 5 months ago
Spoken Dialogue Management Using Probabilistic Reasoning
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.
Nicholas Roy, Joelle Pineau, Sebastian Thrun
Added 01 Nov 2010
Updated 01 Nov 2010
Type Conference
Year 2000
Where ACL
Authors Nicholas Roy, Joelle Pineau, Sebastian Thrun
Comments (0)