Informatics Report Series


Report   

EDI-INF-RR-1108


Related Pages

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

Home
Title:Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System.
Authors: Diane Litman ; Satinder Singh ; Michael Kearns ; Marilyn Walker
Date: 2002
Publication Title:Journal of Artificial Intelligence Research
Publication Type:Journal Article
Volume No:16 Page Nos:105-133
Abstract:
Designing the dialogue policy of a spoken dialogue system involves many nontrivial choices. This paper presents a reinforcement learning approach for automatically optimizing a dialogue policy, which addresses the technical challenges in applying reinforcement learning to a working dialogue system with human users. We report on the design, constuction and empirical evaluation of NJFun, an experimental spoken dialogue system that provides users with access to information about fun things to do in New Jersey. Our results show that by optimizing its performance via reinforcement learning, NJFun measurably improves system performance.
Links To Paper
1st link
Bibtex format
@Article{EDI-INF-RR-1108,
author = { Diane Litman and Satinder Singh and Michael Kearns and Marilyn Walker },
title = {Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun System.},
journal = {Journal of Artificial Intelligence Research},
year = 2002,
volume = {16},
pages = {105-133},
url = {http://www.jair.org/media/859/live-859-1983-jair.pdf},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh