A Simple and Generic Belief Tracking Mechanism for the Dialog State Tracking Challenge: On the believability of observed information

This paper presents a generic dialogue state tracker that maintains beliefs over user goals based on a few simple domainindependent rules, using basic probability operations. The rules apply to observed system actions and partially observable user acts, without using any knowledge obtained from external resources (i.e. without requiring training data). The core insight is to maximise the amount of information directly gainable from an errorprone dialogue itself, so as to better lowerbound one’s expectations on the performance of more advanced statistical techniques for the task. The proposed method is evaluated in the Dialog State Tracking Challenge, where it achieves comparable performance in hypothesis accuracy to machine learning based systems. Consequently, with respect to different scenarios for the belief tracking problem, the potential superiority and weakness of machine learning approaches in general are investigated.