What are the Generator Preferences for End-to-end Task-Oriented Dialog System?

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


Abstract
Fully end-to-end task-oriented dialogue (EToD) systems have shown excellent performance, which requires the ability to retrieve entities accurately for generation. Existing methods improve the accuracy of entity retrieval and construct data flows between retrieval results and response generator, achieving promising results. However, most of them suffer from the following issues: (1) The entity is retrieved by directly interacting with the context at a coarse-grained level, so the similarity score may be disturbed by irrelevant attributes; (2) The generator pays equal attention to retrieved entities and the context and does not learn the generation preferences for the current turn. In this paper, we propose a framework called Regulating Preferences of Generator (RPG) based on retrieval results, which includes a generator preference extractor, an entity retriever, and a generator with the gate-controlled preference regulator. The generator preference extractor not only improves the entity retriever by filtering the interference of irrelevant attributes but also provides more focused guidance to the generator by performing inter-turn attribute prediction. Experiments and analyses on three standard benchmarks show that our framework outperforms existing methods and improves the quality of the dialogue.
Anthology ID:
2024.emnlp-main.616
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:
10992–11003
Language:
URL:
https://aclanthology.org/2024.emnlp-main.616/
DOI:
10.18653/v1/2024.emnlp-main.616
Bibkey:
Cite (ACL):
Wanshi Xu, Xianwei Zhuang, Zhanpeng Chen, Zhihong Zhu, Xuxin Cheng, and Yuexian Zou. 2024. What are the Generator Preferences for End-to-end Task-Oriented Dialog System?. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 10992–11003, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
What are the Generator Preferences for End-to-end Task-Oriented Dialog System? (Xu et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.616.pdf