Title
Real user evaluation of a POMDP spoken dialogue system using automatic belief compression.
Abstract
This article describes an evaluation of a POMDP-based spoken dialogue system (SDS), using crowdsourced calls with real users. The evaluation compares a "Hidden Information State" POMDP system which uses a hand-crafted compression of the belief space, with the same system instead using an automatically computed belief space compression. Automatically computed compressions are a way of introducing automation into the design process of statistical SDSs and promise a principled way of reducing the size of the very large belief spaces which often make POMDP approaches intractable. This is the first empirical comparison of manual and automatic approaches on a problem of realistic scale (restaurant, pub and coffee shop domain) with real users. The evaluation took 2193 calls from 85 users. After filtering for minimal user participation the two systems were compared on more than 1000 calls. (C) 2013 Elsevier Ltd. All rights reserved.
Year
DOI
Venue
2014
10.1016/j.csl.2013.12.002
Computer Speech & Language
Keywords
Field
DocType
Spoken dialogue systems,Dialogue management,Belief compression
Empirical comparison,Dialogue management,Partially observable Markov decision process,Computer science,Filter (signal processing),Speech recognition,Automation,Artificial intelligence,Engineering design process,Machine learning
Journal
Volume
Issue
ISSN
28
4
0885-2308
Citations 
PageRank 
References 
3
0.38
15
Authors
5
Name
Order
Citations
PageRank
Paul A. Crook192.26
Simon Keizer246128.96
Zhuoran Wang38810.98
Wenshuo Tang441.08
Oliver Lemon5107286.38