Comparison of Bayesian Discriminative and Generative Models for Dialogue State Tracking
Lukáš Žilka, David Marek, Matěj Korvas, Filip Jurčíček · Annual Meeting of the Special Interest Group on Discourse and Dialogue · 2013
In this paper, we describe two dialogue state tracking models competing in the 2012 Dialogue State Tracking Challenge (DSTC). First, we detail a novel discriminative dialogue state tracker which directly estimates slot-level beliefs using deterministic state transition probability distribution. Second, we present a generative model employing a simple dependency structure to achieve fast inference. The models are evaluated on the DSTC data, and both significantly outperform the baseline DSTC tracker.