BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses

Weihao Zeng, Keqing He, Yejie Wang, Dayuan Fu, Weiran Xu


Abstract
Pre-trained language models have been successful in many scenarios. However, their usefulness in task-oriented dialogues is limited due to the intrinsic linguistic differences between general text and task-oriented dialogues. Current task-oriented dialogue pre-training methods rely on a contrastive framework, which faces challenges such as selecting true positives and hard negatives, as well as lacking diversity. In this paper, we propose a novel dialogue pre-training model called BootTOD. It learns task-oriented dialogue representations via a self-bootstrapping framework. Unlike contrastive counterparts, BootTOD aligns context and context+response representations and dismisses the requirements of contrastive pairs. BootTOD also uses multiple appropriate response targets to model the intrinsic one-to-many diversity of human conversations. Experimental results show that BootTOD outperforms strong TOD baselines on diverse downstream dialogue tasks.
Anthology ID:
2024.lrec-main.221
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
2458–2467
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.lrec-main.221/
DOI:
Bibkey:
Cite (ACL):
Weihao Zeng, Keqing He, Yejie Wang, Dayuan Fu, and Weiran Xu. 2024. BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 2458–2467, Torino, Italia. ELRA and ICCL.
Cite (Informal):
BootTOD: Bootstrap Task-oriented Dialogue Representations by Aligning Diverse Responses (Zeng et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.lrec-main.221.pdf