Abstract
This work shows how a spoken dialogue system can be represented as a Partially Observable Markov Decision Process (POMDP) with composite observations consisting of discrete elements representing dialogue acts and continuous components representing confidence scores. Using a testbed simulated dialogue management problem and recently developed optimisation techniques, we demonstrate that this continuous POMDP can outperform traditional approaches in which confidence score is tracked discretely. Further, we present a method for automatically improving handcrafted dialogue managers by incorporating POMDP belief state monitoring, including confidence score information. Experiments on the test-bed system show significant improvements for several example handcrafted dialogue managers across a range of operating conditions.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2008 Springer Science + Business Media B.V.
About this chapter
Cite this chapter
Williams, J.D., Poupart, P., Young, S. (2008). Partially Observable Markov Decision Processes with Continuous Observations for Dialogue Management. In: Dybkjær, L., Minker, W. (eds) Recent Trends in Discourse and Dialogue. Text, Speech and Language Technology, vol 39. Springer, Dordrecht. https://doi.org/10.1007/978-1-4020-6821-8_8
Download citation
DOI: https://doi.org/10.1007/978-1-4020-6821-8_8
Publisher Name: Springer, Dordrecht
Print ISBN: 978-1-4020-6820-1
Online ISBN: 978-1-4020-6821-8
eBook Packages: Humanities, Social Sciences and LawSocial Sciences (R0)