Learning to Match Representations is Better for End-to-End Task-Oriented Dialog System

Wanshi Xu, Xuxin Cheng, Zhihong Zhu, Zhanpeng Chen, Yuexian Zou


Abstract
Due to the rapid development with pre-trained language models, fully end-to-end Task-Oriented Dialogue (TOD) systems exhibit superior performance. How to achieve the ability to efficiently retrieve entities in cross-domain large-scale databases is a key issue. Most existing end-to-end Task-Oriented Dialogue systems suffer from the following problems: The ability to handle erroneous but easily confused entities needs to be improved; Matching information between contexts and entities is not captured, leading to weak modeling of domain-invariant and interpretable features, making it difficult to generalize to unseen domains. In this paper, we propose a method for knowledge retrieval driven by matching representations. The approach consists of a matching signal extractor for extracting matching representations between contexts and entities that have generic conceptual features and hence domain invariant properties, and an Attribute Filter for filtering irrelevant information to facilitate the re-selection of entities. Experiments on three standard benchmarks at the dialogue level and on large knowledge bases show that our retriever performs knowledge retrieval more efficiently than existing approaches.
Anthology ID:
2024.findings-emnlp.609
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2024
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10409–10419
Language:
URL:
https://aclanthology.org/2024.findings-emnlp.609/
DOI:
10.18653/v1/2024.findings-emnlp.609
Bibkey:
Cite (ACL):
Wanshi Xu, Xuxin Cheng, Zhihong Zhu, Zhanpeng Chen, and Yuexian Zou. 2024. Learning to Match Representations is Better for End-to-End Task-Oriented Dialog System. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 10409–10419, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
Learning to Match Representations is Better for End-to-End Task-Oriented Dialog System (Xu et al., Findings 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.findings-emnlp.609.pdf