Paper: Combining POMDPs trained with User Simulations and Rule-based Dialogue Management in a Spoken Dialogue System

ACL ID P09-4011
Title Combining POMDPs trained with User Simulations and Rule-based Dialogue Management in a Spoken Dialogue System
Venue Annual Meeting of the Association of Computational Linguistics
Session System Demonstration
Year 2009
Authors

Over several years, we have developed an approach to spoken dialogue systems that includes rule-based and trainable dialogue managers, spoken language understanding and generation modules, and a compre- hensive dialogue system architecture. We present a Reinforcement Learning-based dialoguesystemthatgoesbeyondstandard rule-based models and computes on-line decisions of the best dialogue moves. The key concept of this work is that we bridge the gap between manually written dia- log models (e.g. rule-based) and adaptive computational models such as Partially Observable Markov Decision Processes (POMDP) based dialogue managers. 1 Reinforcement Learning-based Dialogue Management In recent years, Machine Learning techniques, in particular Reinforcement Learning (RL), have been applied to the ta...