FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue

Weihao Zeng, Keqing He, Yejie Wang, Chen Zeng, Jingang Wang, Yunsen Xian, Weiran Xu


Abstract
Pre-trained language models based on general text enable huge success in the NLP scenario. But the intrinsical difference of linguistic patterns between general text and task-oriented dialogues makes existing pre-trained language models less useful in practice. Current dialogue pre-training methods rely on a contrastive framework and face the challenges of both selecting true positives and hard negatives. In this paper, we propose a novel dialogue pre-training model, FutureTOD, which distills future knowledge to the representation of the previous dialogue context using a self-training framework. Our intuition is that a good dialogue representation both learns local context information and predicts future information. Extensive experiments on diverse downstream dialogue tasks demonstrate the effectiveness of our model, especially the generalization, robustness, and learning discriminative dialogue representations capabilities.
Anthology ID:
2023.acl-long.360
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6532–6546
Language:
URL:
https://aclanthology.org/2023.acl-long.360
DOI:
10.18653/v1/2023.acl-long.360
Bibkey:
Cite (ACL):
Weihao Zeng, Keqing He, Yejie Wang, Chen Zeng, Jingang Wang, Yunsen Xian, and Weiran Xu. 2023. FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6532–6546, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
FutureTOD: Teaching Future Knowledge to Pre-trained Language Model for Task-Oriented Dialogue (Zeng et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.360.pdf
Video:
 https://aclanthology.org/2023.acl-long.360.mp4