DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations

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


Abstract
Language models pre-trained on general text have achieved impressive results in diverse fields. Yet, the distinct linguistic characteristics of task-oriented dialogues (TOD) compared to general text limit the practical utility of existing language models. Current task-oriented dialogue pre-training methods overlook the one-to-many property of conversations, where multiple responses can be appropriate given the same conversation context.In this paper, we propose a novel dialogue pre-training model called DivTOD, which collaborates with LLMs to learn diverse task-oriented dialogue representations. DivTOD guides LLMs in transferring diverse knowledge to smaller models while removing domain knowledge that contradicts task-oriented dialogues. Experiments show that our model outperforms strong TOD baselines on various downstream dialogue tasks and learns the intrinsic diversity of task-oriented dialogues.
Anthology ID:
2024.findings-naacl.51
Volume:
Findings of the Association for Computational Linguistics: NAACL 2024
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Kevin Duh, Helena Gomez, Steven Bethard
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
800–813
Language:
URL:
https://aclanthology.org/2024.findings-naacl.51
DOI:
10.18653/v1/2024.findings-naacl.51
Bibkey:
Cite (ACL):
Weihao Zeng, Dayuan Fu, Keqing He, Yejie Wang, Yukai Xu, and Weiran Xu. 2024. DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations. In Findings of the Association for Computational Linguistics: NAACL 2024, pages 800–813, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
DivTOD: Unleashing the Power of LLMs for Diversifying Task-Oriented Dialogue Representations (Zeng et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2024.findings-naacl.51.pdf