Informatics Report Series



Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Title:Cluster-based User Simulations for Learning Dialogue Strategies.
Authors: Verena Rieser ; Oliver Lemon
Date:Sep 2006
Publication Title:Ninth International Conference on Spoken Language Processing
Publication Type:Conference Paper Publication Status:Pre-print
Good dialogue strategies in spoken dialogue systems help to ensure and maintain mutual understanding and thus play a crucial role in robust conversational interaction. We focus on clarification strategies and build user simulations which are critical for reinforcement learning, which is a cheap and principled way to automatically optimise dialogue management. In this paper we present a novel cluster-based technique for building user simulations which show varying, but complete and consistent behaviour with respect to real users. We use this technique to build user simulations and we also introduce the super evaluation metric which allows us to evaluate user simulations with respect to these desiderata. We show that the cluster-based user simulation technique performs significantly better (at P < 0.01) than decisions made using either the one most likely action or a random baseline. The cluster-based user simulations reduce the average error of these other models by 53% and 34% respectively.
Links To Paper
ISCA archive
Bibtex format
author = { Verena Rieser and Oliver Lemon },
title = {Cluster-based User Simulations for Learning Dialogue Strategies.},
book title = {Ninth International Conference on Spoken Language Processing},
publisher = {ISCA},
year = 2006,
month = {Sep},
url = {},

Home : Publications : Report 

Please mail <> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh