Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System

Namo Bang, Jeehyun Lee, Myoung-Wan Koo


Abstract
Task-Oriented Dialogue (TOD) systems are designed to carry out specific tasks by tracking dialogue states and generating appropriate responses to help users achieve defined goals. Recently, end-to-end dialogue models pre-trained based on large datasets have shown promising performance in the conversational system. However, they share the same parameters to train tasks of the dialogue system (NLU, DST, NLG), so debugging each task is challenging. Also, they require a lot of effort to fine-tune large parameters to create a task-oriented chatbot, making it difficult for non-experts to handle. Therefore, we intend to train relatively lightweight and fast models compared to PLM. In this paper, we propose an End-to-end TOD system with Task-Optimized Adapters which learn independently per task, adding only small number of parameters after fixed layers of pre-trained network. We also enhance the performance of the DST and NLG modules through reinforcement learning, overcoming the learning curve that has lacked at the adapter learning and enabling the natural and consistent response generation that is appropriate for the goal. Our method is a model-agnostic approach and does not require prompt-tuning as only input data without a prompt. As results of the experiment, our method shows competitive performance on the MultiWOZ benchmark compared to the existing end-to-end models. In particular, we attain state-of-the-art performance on the DST task of 2.2 dataset.
Anthology ID:
2023.findings-acl.464
Volume:
Findings of the Association for Computational Linguistics: ACL 2023
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7355–7369
Language:
URL:
https://aclanthology.org/2023.findings-acl.464
DOI:
10.18653/v1/2023.findings-acl.464
Bibkey:
Cite (ACL):
Namo Bang, Jeehyun Lee, and Myoung-Wan Koo. 2023. Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System. In Findings of the Association for Computational Linguistics: ACL 2023, pages 7355–7369, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System (Bang et al., Findings 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.findings-acl.464.pdf
Video:
 https://aclanthology.org/2023.findings-acl.464.mp4