Adaptive Multimodal Dialogue Management Based on the Information State Update Approach

This paper provides an overview of the aims of the TALK project focusing on the issue of integrating Reinforcement Learning (RL) with the Information State Update (ISU) approach to dialogue management, in order to develop adaptive multimodal dialogue systems. The project will build showcases for in-car and in-home information and control, but its main aim is to advance our understanding of generic technologies that will extend the ISU approach to adaptive multimodal and multilingual dialogue.