Paul A. Crook, Zhuoran Wang, Xingkun Liu and Oliver Lemon. "A Statistical Spoken Dialogue System using Complex User Goals and Value Directed Compression"

Post date: Nov 26, 2012 11:38:11 PM

(A System Demonstration) Published in Proceedings of the European Chapter of Association for Computational Linguistics (EACL 2012), April 2012.


This paper presents the first demonstration of a statistical spoken dialogue system that uses automatic belief compression to reason over complex user goal sets. Reasoning over the power set of possible user goals allows complex sets of user goals to be represented, which leads to more natural dialogues. The use of the power set results in a massive expansion in the number of belief states maintained by the Partially Observable Markov Decision Process (POMDP) spoken dialogue manager. A modified form of Value Directed Compression (VDC) is applied to the POMDP belief states producing a near-lossless compression which reduces the number of bases required to represent the belief distribution.