A Two-Step Neural Dialog State Tracker for Task-Oriented Dialog Processing

A-Yeong Kim, Hyun-Je Song, Seong-Bae Park
2018 Computational Intelligence and Neuroscience  
Dialog state tracking in a spoken dialog system is the task that tracks the flow of a dialog and identifies accurately what a user wants from the utterance. Since the success of a dialog is influenced by the ability of the system to catch the requirements of the user, accurate state tracking is important for spoken dialog systems. This paper proposes a two-step neural dialog state tracker which is composed of an informativeness classifier and a neural tracker. The informativeness classifier
more » ... h is implemented by a CNN first filters out noninformative utterances in a dialog. Then, the neural tracker estimates dialog states from the remaining informative utterances. The tracker adopts the attention mechanism and the hierarchical softmax for its performance and fast training. To prove the effectiveness of the proposed model, we do experiments on dialog state tracking in the human-human task-oriented dialogs with the standard DSTC4 data set. Our experimental results prove the effectiveness of the proposed model by showing that the proposed model outperforms the neural trackers without the informativeness classifier, the attention mechanism, or the hierarchical softmax.
doi:10.1155/2018/5798684 pmid:30420875 pmcid:PMC6211208 dblp:journals/cin/KimSP18 fatcat:jwcuiagnvfbb3owsybuiaprh4i