Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations

Jingyao Zhou, Haipang Wu, Zehao Lin, Guodun Li, Yin Zhang


Abstract
Most recently proposed approaches in dialogue state tracking (DST) leverage the context and the last dialogue states to track current dialogue states, which are often slot-value pairs. Although the context contains the complete dialogue information, the information is usually indirect and even requires reasoning to obtain. The information in the lastly predicted dialogue states is direct, but when there is a prediction error, the dialogue information from this source will be incomplete or erroneous. In this paper, we propose the Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations network (FPDSC). This model extracts information of each dialogue turn by modeling interactions among each turn utterance, the corresponding last dialogue states, and dialogue slots. Then the representation of each dialogue turn is aggregated by a hierarchical structure to form the passage information, which is utilized in the current turn of DST. Experimental results validate the effectiveness of the fusion network with 55.03% and 59.07% joint accuracy on MultiWOZ 2.0 and MultiWOZ 2.1 datasets, which reaches the state-of-the-art performance. Furthermore, we conduct the deleted-value and related-slot experiments on MultiWOZ 2.1 to evaluate our model.
Anthology ID:
2021.sigdial-1.24
Volume:
Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
July
Year:
2021
Address:
Singapore and Online
Editors:
Haizhou Li, Gina-Anne Levow, Zhou Yu, Chitralekha Gupta, Berrak Sisman, Siqi Cai, David Vandyke, Nina Dethlefs, Yan Wu, Junyi Jessy Li
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
228–238
Language:
URL:
https://aclanthology.org/2021.sigdial-1.24
DOI:
10.18653/v1/2021.sigdial-1.24
Bibkey:
Cite (ACL):
Jingyao Zhou, Haipang Wu, Zehao Lin, Guodun Li, and Yin Zhang. 2021. Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations. In Proceedings of the 22nd Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 228–238, Singapore and Online. Association for Computational Linguistics.
Cite (Informal):
Dialogue State Tracking with Multi-Level Fusion of Predicted Dialogue States and Conversations (Zhou et al., SIGDIAL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.sigdial-1.24.pdf
Video:
 https://www.youtube.com/watch?v=LOC-0HQz5Lg
Code
 helloacl/DST-DCPDS
Data
MultiWOZ