Co-adaptation in Spoken Dialogue Systems

Abstract : Spoken Dialogue Systems are man-machine interfaces which use spoken language as the medium of interaction. In recent years, dialogue optimization using reinforcement learning has evolved to be a state of the art technique. The primary focus of research in the dialogue optimization domain is to learn some optimal policy with regard to the task description (reward function) and the user simulation being employed. However in case human-human interaction, the parties involved in the dialogue conversation mutually evolve over the period of interaction. This very ability of humans to co-adapt attributes largely towards increasing the naturalness of the dialogue. This paper outlines a novel framework for co-adaptation in spoken dialogue systems, where the dialogue manager and user simulation evolve over a period of time; they incrementally and mutually optimize their respective behaviors.
Document type :
Conference papers
Complete list of metadatas

https://hal-supelec.archives-ouvertes.fr/hal-00778752
Contributor : Sébastien van Luchene <>
Submitted on : Monday, January 21, 2013 - 2:05:46 PM
Last modification on : Wednesday, July 31, 2019 - 4:18:03 PM

Identifiers

  • HAL Id : hal-00778752, version 1

Citation

Senthilkumar Chandramohan, Matthieu Geist, Fabrice Lefèvre, Olivier Pietquin. Co-adaptation in Spoken Dialogue Systems. IWSDS 2012, Nov 2012, Paris, France. pp.1. ⟨hal-00778752⟩

Share

Metrics

Record views

163