Paper: User Goal Change Model for Spoken Dialog State Tracking

ACL ID N13-2013
Title User Goal Change Model for Spoken Dialog State Tracking
Venue Annual Conference of the North American Chapter of the Association for Computational Linguistics
Session Student Session
Year 2013

In this paper, a Maximum Entropy Markov Model (MEMM) for dialog state tracking is proposed to efficiently handle user goal evolvement in two steps. The system first predicts the occurrence of a user goal change based on linguistic features and dialog context for each dialog turn, and then the proposed model could utilize this user goal change in- formation to infer the most probable dialog state sequence which underlies the evolve- ment of user goal during the dialog. It is believed that with the suggested various do- main independent feature functions, the pro- posed model could better exploit not only the intra-dependencies within long ASR N-best lists but also the inter-dependencies of the ob- servations across dialog turns, which leads to more efficient and accurate dialog state infer-...