Leveraging POMDPs trained with User Simulations and Rule-based Dialogue Management in a Spoken Dialogue System

Sebastian Varges, Giuseppe Riccardi, Silvia Quarteroni and Alexei V. Ivanov

SIGDIAL Workshop on Discourse and Dialogue (SIGDIAL 2009)
Queen Mary University of London, September 11-12, 2009

Summary

We have developed a complete spoken dialogue framework that includes rule-based and trainable dialogue managers, speech recognition, spoken language understanding and generation modules, and a comprehensive web visualization interface.

We will present a spoken dialogue system based on Reinforcement Learning that goes beyond standard rule based models and computes on-line decisions of the best dialogue moves. Bridging the gap between handcrafted (e.g. rule-based) and adaptive (e.g. based on Partially Observable Markov Decision Processes - POMDP) dialogue models, this prototype is able to learn high rewarding policies in a number of dialogue situations.