Relevance Is a Guiding Light: Relevance-aware Adaptive Learning for End-to-end Task-oriented Dialogue System

Zhanpeng Chen, Zhihong Zhu, Wanshi Xu, Xianwei Zhuang, Yuexian Zou


Abstract
Retrieving accurate domain knowledge and providing helpful information are crucial in developing an effective end-to-end task-oriented dialogue system (E2ETOD). The field has witnessed numerous methods following the retrieve-then-generate paradigm and training their systems on one specific domain. However, existing approaches still suffer from the Distractive Attributes Problem (DAP): struggling to deal with false but similar knowledge (hard negative entities), which is even more intractable when countless pieces of knowledge from different domains are blended in a real-world scenario. To alleviate DAP, we propose the Relevance-aware Adaptive Learning (ReAL) method, a two-stage training framework that eliminates hard negatives step-by-step and aligns retrieval with generation. In the first stage, we introduce a top-k adaptive contrastive loss and utilize the divergence-driven feedback from the frozen generator to pre-train the retriever. In the second stage, we propose using the metric score distribution as an anchor to align retrieval with generation. Thorough experiments on three benchmark datasets demonstrate ReAL’s superiority over existing methods, with extensive analysis validating its strong capabilities of overcoming in- and cross-domain distractions.
Anthology ID:
2024.emnlp-main.309
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5410–5420
Language:
URL:
https://aclanthology.org/2024.emnlp-main.309
DOI:
Bibkey:
Cite (ACL):
Zhanpeng Chen, Zhihong Zhu, Wanshi Xu, Xianwei Zhuang, and Yuexian Zou. 2024. Relevance Is a Guiding Light: Relevance-aware Adaptive Learning for End-to-end Task-oriented Dialogue System. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 5410–5420, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Relevance Is a Guiding Light: Relevance-aware Adaptive Learning for End-to-end Task-oriented Dialogue System (Chen et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.309.pdf