Evolving optimal inspectable strategies for spoken dialogue systems

Authors:
Dave Toney;Johanna Moore;Oliver Lemon
Affiliations:
Edinburgh University, Edinburgh;Edinburgh University, Edinburgh;Edinburgh University, Edinburgh
Venue:
NAACL-Short '06 Proceedings of the Human Language Technology Conference of the NAACL, Companion Volume: Short Papers
Year:
2006

Citing 4
Cited 1

Applications of Learning Classifier Systems

Applications of Learning Classifier Systems
Learning optimal dialogue management rules by using reinforcement learning and inductive logic programming

NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
Probabilistic simulation of human-machine dialogues

ICASSP '00 Proceedings of the Acoustics, Speech, and Signal Processing, 2000. on IEEE International Conference - Volume 02
Classifier fitness based on accuracy

Evolutionary Computation

Learning automata-based approach to learn dialogue policies in large state space

International Journal of Intelligent Information and Database Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

We report on a novel approach to generating strategies for spoken dialogue systems. We present a series of experiments that illustrate how an evolutionary reinforcement learning algorithm can produce strategies that are both optimal and easily inspectable by human developers. Our experimental strategies achieve a mean performance of 98.9% with respect to a predefined evaluation metric. Our approach also produces a dramatic reduction in strategy size when compared with conventional reinforcement learning techniques (87% in one experiment). We conclude that this algorithm can be used to evolve optimal inspectable dialogue strategies.