CUED Publications database

Parameter learning for POMDP spoken dialogue models

Thomson, B and Jurčíček, F and Gašić, M and Keizer, S and Mairesse, F and Yu, K and Young, S (2010) Parameter learning for POMDP spoken dialogue models. 2010 IEEE Workshop on Spoken Language Technology, SLT 2010 - Proceedings. pp. 271-276.

Full text not available from this repository.


The partially observable Markov decision process (POMDP) provides a popular framework for modelling spoken dialogue. This paper describes how the expectation propagation algorithm (EP) can be used to learn the parameters of the POMDP user model. Various special probability factors applicable to this task are presented, which allow the parameters be to learned when the structure of the dialogue is complex. No annotations, neither the true dialogue state nor the true semantics of user utterances, are required. Parameters optimised using the proposed techniques are shown to improve the performance of both offline transcription experiments as well as simulated dialogue management performance. ©2010 IEEE.

Item Type: Article
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:30
Last Modified: 13 Apr 2021 08:21
DOI: 10.1109/SLT.2010.5700863