Comparing User Simulation Models For Dialog Strategy Learning

This paper explores what kind of user simulation model is suitable for developing a training corpus for using Markov Decision Processes (MDPs) to automatically learn dialog strategies. Our results suggest that with sparse training data, a model that aims to randomly explore more dialog state spaces with certain constraints actually performs at the same or better than a more complex model that simulates realistic user behaviors in a statistical way.

• Type: Conference
• Year: 2007
• Where: NAACL
• Authors: Hua Ai, Joel R. Tetreault, Diane J. Litman
• Keywords: Computational Linguistics, Dialog Strategies, NAACL 2007, Realistic User Behaviors, User Simulation Model