2017/09/30 by Po-Chun Chen, Chen, Po-Chun, Ta-Chung Chi +6
Computer Science · #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Speech and dialogue systems #Topic Modeling #cs.CL
paper · pdf · doi:10.48550/arxiv.1710.00165
Accepted by ASRU 2017. arXiv admin note: text overlap with arXiv:1710.00164
openalex publication_date 2017/09/30 · arxiv created 2017/12/08 · arxiv updated 2017/12/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Spoken language understanding (SLU) is an essential component in conversational systems. Most SLU component treats each utterance independently, and then the following components aggregate the multi-turn information in the separate phases. In order to avoid error propagation and effectively utilize contexts, prior work leveraged history for contextual SLU. However, the previous model only paid attention to the content in history utterances without considering their temporal information and speaker roles. In the dialogues, the most recent utterances should be more important than the least recent ones. Furthermore, users usually pay attention to 1) self history for reasoning and 2) others' utterances for listening, the speaker of the utterances may provides informative cues to help understanding. Therefore, this paper proposes an attention-based network that additionally leverages temporal information and speaker role for better SLU, where the attention to contexts and speaker roles can be automatically learned in an end-to-end manner. The experiments on the benchmark Dialogue State Tracking Challenge 4 (DSTC4) dataset show that the time-aware dynamic role attention networks significantly improve the understanding performance.