Comprehensive study: How the context information of different granularity affects dialogue state tracking?

Puhai Yang, Heyan Huang*, Xian Ling Mao

*此作品的通讯作者

科研成果: 书/报告/会议事项章节会议稿件同行评审

9 引用 (Scopus)

摘要

Dialogue state tracking (DST) plays a key role in task-oriented dialogue systems to monitor the user's goal. In general, there are two strategies to track a dialogue state: predicting it from scratch and updating it from previous state. The scratch-based strategy obtains each slot value by inquiring all the dialogue history, and the previous-based strategy relies on the current turn dialogue to update the previous dialogue state. However, it is hard for the scratch-based strategy to correctly track short-dependency dialogue state because of noise; meanwhile, the previous-based strategy is not very useful for long-dependency dialogue state tracking. Obviously, it plays different roles for the context information of different granularity to track different kinds of dialogue states. Thus, in this paper, we will study and discuss how the context information of different granularity affects dialogue state tracking. First, we explore how greatly different granularities affect dialogue state tracking. Then, we further discuss how to combine multiple granularities for dialogue state tracking. Finally, we apply the findings about context granularity to few-shot learning scenario. Besides, we have publicly released all codes.

源语言英语
主期刊名ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference
出版商Association for Computational Linguistics (ACL)
2481-2491
页数11
ISBN(电子版)9781954085527
出版状态已出版 - 2021
活动Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021 - Virtual, Online
期限: 1 8月 20216 8月 2021

出版系列

姓名ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference

会议

会议Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, ACL-IJCNLP 2021
Virtual, Online
时期1/08/216/08/21

指纹

探究 'Comprehensive study: How the context information of different granularity affects dialogue state tracking?' 的科研主题。它们共同构成独一无二的指纹。

引用此

Yang, P., Huang, H., & Mao, X. L. (2021). Comprehensive study: How the context information of different granularity affects dialogue state tracking?ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference (页码 2481-2491). (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the Conference). Association for Computational Linguistics (ACL).