CUED Publications database

Quality-adaptive Spoken Dialogue initiative selection and implications on reward modelling

Ultes, S and Kraus, M and Schmitt, A and Minker, W (2015) Quality-adaptive Spoken Dialogue initiative selection and implications on reward modelling. In: UNSPECIFIED pp. 374-383..

Full text not available from this repository.

Abstract

© 2015 Association for Computational Linguistics. Adapting Spoken Dialogue Systems to the user is supposed to result in more efficient and successful dialogues. In this work, we present an evaluation of a quality-adaptive strategy with a user simulator adapting the dialogue initiative dynamically during the ongoing interaction and show that it outperforms conventional non-adaptive strategies and a random strategy. Furthermore, we indicate a correlation between Interaction Quality and dialogue completion rate, task success rate, and average dialogue length. Finally, we analyze the correlation between task success and interaction quality in more detail identifying the usefulness of interaction quality for modelling the reward of reinforcement learning strategy optimization.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:31
Last Modified: 03 Aug 2017 03:04
DOI: