Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling

Yiyang Li, Hai Zhao, Zhuosheng Zhang


Abstract
Multi-turn dialogue modeling as a challenging branch of natural language understanding (NLU), aims to build representations for machines to understand human dialogues, which provides a solid foundation for multiple downstream tasks. Recent studies of dialogue modeling commonly employ pre-trained language models (PrLMs) to encode the dialogue history as successive tokens, which is insufficient in capturing the temporal characteristics of dialogues. Therefore, we propose Bidirectional Information Decoupling Network (BiDeN) as a universal dialogue encoder, which explicitly incorporates both the past and future contexts and can be generalized to a wide range of dialogue-related tasks. Experimental results on datasets of different downstream tasks demonstrate the universality and effectiveness of our BiDeN.
Anthology ID:
2022.emnlp-main.177
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2761–2774
Language:
URL:
https://aclanthology.org/2022.emnlp-main.177
DOI:
10.18653/v1/2022.emnlp-main.177
Bibkey:
Cite (ACL):
Yiyang Li, Hai Zhao, and Zhuosheng Zhang. 2022. Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 2761–2774, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Back to the Future: Bidirectional Information Decoupling Network for Multi-turn Dialogue Modeling (Li et al., EMNLP 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.emnlp-main.177.pdf