Neural Dialogue State Tracking with Temporally Expressive Networks
Beihang University（北京航空航天大学）；University of Ottawa（渥太华大学）；University of Leeds（利兹大学）
英文摘要：
Dialogue state tracking (DST) is an important part of a spoken dialogue system. Existing DST models either ignore temporal feature dependencies across dialogue turns or fail to explicitly model temporal state dependencies in a dialogue. In this work, we propose Temporally Expressive Networks (TEN) to jointly model the two types of temporal dependencies in DST. The TEN model utilizes the power of recurrent networks and probabilistic graphical models. Evaluating on standard datasets, TEN is demonstrated to be effective in improving the accuracy of turn-level-state prediction and the state aggregation.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
