Enhancing Task-Oriented Dialog System with Subjective Knowledge: A Large Language Model-based Data Augmentation Framework

Haein Jung, Heuiyeen Yeen, Jeehyun Lee, Minju Kim, Namo Bang, Myoung-Wan Koo

Abstract
As Task-Oriented Dialog (TOD) systems have advanced, structured DB systems, which aim to collect relevant knowledge for answering user’s questions, have also progressed. Despite these advancements, these methods face challenges when dealing with subjective questions from users. To overcome this, DSTC11 released a subjective-knowledge-based TOD (SK-TOD) dataset and benchmark. This paper introduces a framework that effectively solves SK-TOD tasks by leveraging a Large Language Model (LLM). We demonstrate the proficient use of LLM for each sub-task, including an adapters-based method and knowledge-grounded data augmentation. Our proposed methods, which utilize LLM as an efficient tool, outperform baseline performance and approaches that directly use LLM as a one-step sub-task solver, showing superior task-specific optimization.
Anthology ID:
2023.dstc-1.18
Volume:
Proceedings of The Eleventh Dialog System Technology Challenge
Month:
September
Year:
2023
Address:
Prague, Czech Republic
Editors:
Yun-Nung Chen, Paul Crook, Michel Galley, Sarik Ghazarian, Chulaka Gunasekara, Raghav Gupta, Behnam Hedayatnia, Satwik Kottur, Seungwhan Moon, Chen Zhang
Venues:
DSTC | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
150–165
Language:
URL:
https://aclanthology.org/2023.dstc-1.18
DOI:
Bibkey:
Cite (ACL):
Haein Jung, Heuiyeen Yeen, Jeehyun Lee, Minju Kim, Namo Bang, and Myoung-Wan Koo. 2023. Enhancing Task-Oriented Dialog System with Subjective Knowledge: A Large Language Model-based Data Augmentation Framework. In Proceedings of The Eleventh Dialog System Technology Challenge, pages 150–165, Prague, Czech Republic. Association for Computational Linguistics.
Cite (Informal):
Enhancing Task-Oriented Dialog System with Subjective Knowledge: A Large Language Model-based Data Augmentation Framework (Jung et al., DSTC-WS 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/add_acl24_videos/2023.dstc-1.18.pdf
PDF Search