Trainbot: a spoken dialog system using partially observable Markov decision processes

Abstract

Due to speech recognition and understanding errors, spoken dialog systems have been suffering from inherent uncertainty in the whole conversation. Partially Observable Markov Decision Processes (POMDPs) can provide a principled mathematical framework for modeling the inherent uncertainty in spoken dialogue systems. This Paper describes a dialog system, Trainbot, which uses a POMDP statistical-based dialog model updating information states and making appropriate dialog strategies in a given situation.