Machine Learning for Spoken Dialogue Management: An Experiment with Speech-Based Database Querying

Abstract : Although speech and language processing techniques achieved a relative maturity during the last decade, designing a spoken dialogue system is still a tailoring task because of the great variability of factors to take into account. Rapid design and reusability across tasks of previous work is made very difficult. For these reasons, machine learning methods applied to dialogue strategy optimization has become a leading subject of researches since the mid 90's. In this paper, we describe an experiment of reinforcement learning applied to the optimization of speech-based database querying. We will especially emphasize on the sensibility of the method relatively to the dialogue modeling parameters in the framework of the Markov decision processes, namely the state space and the reinforcement signal. The evolution of the design will be exposed as well as results obtained on a simple real application.
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00208016
Contributor : Sébastien van Luchene <>
Submitted on : Friday, January 18, 2008 - 10:30:54 PM
Last modification on : Thursday, March 29, 2018 - 11:06:04 AM

Links full text

Identifiers

Collections

Citation

Olivier Pietquin. Machine Learning for Spoken Dialogue Management: An Experiment with Speech-Based Database Querying. The 12th International Conference on Artificial Intelligence: Methodology, Systems, Applications (AIMSA 2006), Sep 2006, Varna, Bulgaria. pp.172-180, ⟨10.1007/11861461_19⟩. ⟨hal-00208016⟩

Share

Metrics

Record views

68