Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System

Jianguo Zhang, Stephen Roller, Kun Qian, Zhiwei Liu, Rui Meng, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong


Abstract
End-to-end task-oriented dialogue (TOD) systems have achieved promising performance by leveraging sophisticated natural language understanding and natural language generation capabilities of pre-trained models. This work enables the TOD systems with more flexibility through a simple cache. The cache provides the flexibility to dynamically update the TOD systems and handle both existing and unseen dialogue scenarios. Towards this end, we first fine-tune a retrieval module to effectively retrieve the most relevant information entries from the cache. We then train end-to-end TOD models that can refer to and ground on both dialogue history and retrieved information during TOD generation. The introduced cache is straightforward to construct, and the backbone models of TOD systems are compatible with existing pre-trained generative models. Extensive experiments demonstrate the superior performance of our framework, with a notable improvement in non-empty joint goal accuracy by 6.7% compared to strong baselines.
Anthology ID:
2023.sigdial-1.47
Volume:
Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
September
Year:
2023
Address:
Prague, Czechia
Editors:
Svetlana Stoyanchev, Shafiq Joty, David Schlangen, Ondrej Dusek, Casey Kennington, Malihe Alikhani
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
509–518
Language:
URL:
https://aclanthology.org/2023.sigdial-1.47
DOI:
10.18653/v1/2023.sigdial-1.47
Bibkey:
Cite (ACL):
Jianguo Zhang, Stephen Roller, Kun Qian, Zhiwei Liu, Rui Meng, Shelby Heinecke, Huan Wang, Silvio Savarese, and Caiming Xiong. 2023. Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System. In Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 509–518, Prague, Czechia. Association for Computational Linguistics.
Cite (Informal):
Enhancing Performance on Seen and Unseen Dialogue Scenarios using Retrieval-Augmented End-to-End Task-Oriented System (Zhang et al., SIGDIAL 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.sigdial-1.47.pdf