Global and Local Hierarchical Prompt Tuning Framework for Multi-level Implicit Discourse Relation Recognition

Lei Zeng, Ruifang He, Haowen Sun, Jing Xu, Chang Liu, Bo Wang


Abstract
Multi-level implicit discourse relation recognition (MIDRR) is a challenging task to recognize the hierarchical discourse relations between the arguments with the absence of connectives. Recent methods tend to incorporate the static hierarchical structure containing all senses (defined as global hierarchy) into prompt tuning through a path prompt template or hierarchical label refining. Howerver, hierarchical modeling is independent of the verbalizer, resulting in a failure to effectively utilize the output probability distribution information of verbalizer. Besides, they ignore the utilization of the dynamic hierarchical label sequence for each instance (defined as local hierarchy) in prompt tuning. In this paper, we propose a global and local hierarchical prompt tuning (GLHPT) framework, which utilize prior knowledge of PLMs while better incorporating hierarchical information from two aspects. We leverage bottom-up propagated probability as the global hierarchy to inject it into multi-level verbalizer (MLV). Furthermore, we design a local hierarchy-driven contrastive learning (LHCL) to improve the probability distribution of MLV. Finally, our model achieves competitive results on two benchmacks.
Anthology ID:
2024.lrec-main.686
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
7760–7773
Language:
URL:
https://aclanthology.org/2024.lrec-main.686
DOI:
Bibkey:
Cite (ACL):
Lei Zeng, Ruifang He, Haowen Sun, Jing Xu, Chang Liu, and Bo Wang. 2024. Global and Local Hierarchical Prompt Tuning Framework for Multi-level Implicit Discourse Relation Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 7760–7773, Torino, Italia. ELRA and ICCL.
Cite (Informal):
Global and Local Hierarchical Prompt Tuning Framework for Multi-level Implicit Discourse Relation Recognition (Zeng et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.lrec-main.686.pdf