Optimising Information Presentation for Spoken Dialogue Systems

We present a novel approach to Information Presentation (IP) in Spoken Dialogue Systems (SDS) using a data-driven statistical optimisation framework for content planning and attribute selection. First we collect data in a Wizard-of-Oz (WoZ) experiment and use it to build a supervised model of human behaviour. This forms a baseline for measuring the performance of optimised policies, developed from this data using Reinforcement Learning (RL) methods. We show that the optimised policies significantly outperform the baselines in a variety of generation scenarios: while the supervised model is able to attain up to 87.6% of the possible reward on this task, the RL policies are significantly better in 5

• Type: Journal
• Year: 2010
• Where: ACL
• Authors: Verena Rieser, Oliver Lemon, Xingkun Liu
• Keywords: ACL 2010, Computational Linguistics, Data-driven Statistical Optimisation, Spoken Dialogue Systems, Supervised Model