Sixth International Conference on Spoken Language Processing (ICSLP 2000)

Beijing, China
October 16-20, 2000

DeepListener: Harnessing Expected Utility to Guide Clarification Dialog in Spoken Language Systems

Eric Horvitz, Tim Paek

Microsoft Research, Redmond, WA, USA

We describe research on endowing spoken language systems with the ability to consider the cost of misrecognition, and using that knowledge to guide clarification dialog about a userís intentions. Our approach relies on coupling utility-directed policies for dialog with the ongoing Bayesian fusion of evidence obtained from multiple utterances recognized during an interaction. After describing the methodology, we review the operation of a prototype system called DeepListener. DeepListener considers evidence gathered about utterances over time to make decisions about the optimal dialog strategy or realworld action to take given uncertainties about a userís intentions and the costs and benefits of different outcomes.


Full Paper

Bibliographic reference.  Horvitz, Eric / Paek, Tim (2000): "Deeplistener: harnessing expected utility to guide clarification dialog in spoken language systems", In ICSLP-2000, vol.1, 226-229.