Informatics Report Series



Related Pages

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

Title:Learning Effective Multimodal Dialogue Strategies from Wizard-of-Oz data: Bootstrapping and Evaluation
Authors: Verena Rieser ; Oliver Lemon
Date:Jun 2008
Publication Title:Proceedings of ACL-08: HLT
Publisher:Association for Computational Linguistics
Publication Type:Conference Paper Publication Status:Published
Page Nos:638--646
We address two problems in the field of automatic optimization of dialogue strategies: learning effective dialogue strategies when no initial data or system exists, and evaluating the result with real users. We use Reinforcement Learning (RL) to learn multimodal dialogue strategies by interaction with a simulated environment which is "bootstrapped'' from small amounts of Wizard-of-Oz (WOZ) data. This use of WOZ data allows development of optimal strategies for domains where no working prototype is available. We compare the RL-based strategy against a supervised strategy which mimics the wizards' policies. This comparison allows us to measure relative improvement over the training data. Our results show that RL significantly outperforms Supervised Learning when interacting in simulation as well as for interactions with real users. The RL-based policy gains on average 50-times more reward when tested in simulation, and almost 18-times more reward when interacting with real users. Users also subjectively rate the RL-based policy on average 10% higher.
2008 by The University of Edinburgh. All Rights Reserved
Links To Paper
ACL Anthology
Bibtex format
author = { Verena Rieser and Oliver Lemon },
title = {Learning Effective Multimodal Dialogue Strategies from Wizard-of-Oz data: Bootstrapping and Evaluation},
book title = {Proceedings of ACL-08: HLT},
publisher = {Association for Computational Linguistics},
year = 2008,
month = {Jun},
pages = {638--646},
url = {},

Home : Publications : Report 

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