Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition

Haodong Zhao, Ruifang He, Mengnan Xiao, Jing Xu


Abstract
Multi-level implicit discourse relation recognition (MIDRR) aims at identifying hierarchical discourse relations among arguments. Previous methods achieve the promotion through fine-tuning PLMs. However, due to the data scarcity and the task gap, the pre-trained feature space cannot be accurately tuned to the task-specific space, which even aggravates the collapse of the vanilla space. Besides, the comprehension of hierarchical semantics for MIDRR makes the conversion much harder. In this paper, we propose a prompt-based Parameter-Efficient Multi-level IDRR (PEMI) framework to solve the above problems. First, we leverage parameter-efficient prompt tuning to drive the inputted arguments to match the pre-trained space and realize the approximation with few parameters. Furthermore, we propose a hierarchical label refining (HLR) method for the prompt verbalizer to deeply integrate hierarchical guidance into the prompt tuning. Finally, our model achieves comparable results on PDTB 2.0 and 3.0 using about 0.1% trainable parameters compared with baselines and the visualization demonstrates the effectiveness of our HLR method.
Anthology ID:
2023.acl-long.357
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
6477–6492
Language:
URL:
https://aclanthology.org/2023.acl-long.357
DOI:
10.18653/v1/2023.acl-long.357
Bibkey:
Cite (ACL):
Haodong Zhao, Ruifang He, Mengnan Xiao, and Jing Xu. 2023. Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6477–6492, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
Infusing Hierarchical Guidance into Prompt Tuning: A Parameter-Efficient Framework for Multi-level Implicit Discourse Relation Recognition (Zhao et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.357.pdf
Video:
 https://aclanthology.org/2023.acl-long.357.mp4