Informatics Report Series



Related Pages

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

Title:Learning More Effective Dialogue Strategies Using Limited Dialogue Move Features
Authors: Matthew Frampton ; Oliver Lemon
Date: 2006
Publication Title:Association for Computational Lingusitics
Publication Type:Conference Paper Publication Status:Published
Page Nos:185-192
We explore the use of restricted dialogue contexts in reinforcement learning (RL) of effective dialogue strategies for information seeking spoken dialogue systems (e.g. COMMUNICATOR). The contexts we use are richer than previous research in this area, which use only slot-based information, but are much less complex than the full dialogue ``Information States'' explored in Henderson et a. 2005, for which tractability is an issue. We explore how incrementally adding richer features allows learning of more effective dialogue strategies. We use 2 user simulations learned from COMMUNICATOR data to explore the effects of different features on learned dialogue strategies. Our results show that adding the last system and user dialogue moves increases the average reward of the automatically learned strategies by 65.9% over the original (hand-coded) COMMUNICATOR systems, and by 7.8% over a baseline RL policy that uses only slot-status features. We show that the new strategies exhibit a ``focus switching'' strategy and effective use of the `give help' action.
Links To Paper
Author homepage
Project website
Bibtex format
author = { Matthew Frampton and Oliver Lemon },
title = {Learning More Effective Dialogue Strategies Using Limited Dialogue Move Features},
book title = {Association for Computational Lingusitics},
year = 2006,
pages = {185-192},
doi = {10.3115/1220175.1220199},
url = {},

Home : Publications : Report 

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