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

arXiv:2402.15080v1 Announce Type: new
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 …

abstract arxiv cs.cl data discourse feature fine-tuning framework gap guidance hierarchical promotion prompt prompt tuning recognition relations space through type