Repository logo
 

Policy committee for adaptation in multi-domain spoken dialogue systems

Accepted version
Peer-reviewed

Repository DOI


Type

Conference Object

Change log

Authors

Mrksic, N 
Su, PH 
Vandyke, D 
Wen, TH 

Abstract

Moving from limited-domain dialogue systems to open domain dialogue systems raises a number of challenges. One of them is the ability of the system to utilise small amounts of data from disparate domains to build a dialogue manager policy. Previous work has focused on using data from different domains to adapt a generic policy to a specific domain. Inspired by Bayesian committee machines, this paper proposes the use of a committee of dialogue policies. The results show that such a model is particularly beneficial for adaptation in multi-domain dialogue systems. The use of this model significantly improves performance compared to a single policy baseline, as confirmed by the performed real-user trial. This is the first time a dialogue policy has been trained on multiple domains on-line in interaction with real users.

Description

Keywords

Bayesian committee machines, Gaussian processes, reinforcement learning

Journal Title

2015 IEEE Workshop on Automatic Speech Recognition and Understanding, ASRU 2015 - Proceedings

Conference Name

2015 IEEE Workshop on Automatic Speech Recognition and Understanding (ASRU)

Journal ISSN

Volume Title

Publisher

IEEE
Sponsorship
Engineering and Physical Sciences Research Council (EP/M018946/1)
The research leading to this work was funded by the EPSRC grant EP/M018946/1 ”Open Domain Statistical Spoken Dialogue Systems”.