DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation

Mengyi Huang, Meng Xiao, Ludi Wang, Yi Du

Abstract
Continuous Relation Extraction (CRE) aims to incrementally learn relation knowledge from a non-stationary stream of data. Since the introduction of new relational tasks can overshadow previously learned information, catastrophic forgetting becomes a significant challenge in this domain. Current replay-based training paradigms prioritize all data uniformly and train memory samples through multiple rounds, which would result in overfitting old tasks and pronounced bias towards new tasks because of the imbalances of the replay set. To handle the problem, we introduce the DecouPled CRE (DP-CRE) framework that decouples the process of prior information preservation and new knowledge acquisition. This framework examines alterations in the embedding space as new relation classes emerge, distinctly managing the preservation and acquisition of knowledge. Extensive experiments show that DP-CRE significantly outperforms other CRE baselines across two datasets.
Anthology ID:
2024.lrec-main.475
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:
5338–5349
Language:
URL:
https://aclanthology.org/2024.lrec-main.475
DOI:
Bibkey:
Cite (ACL):
Mengyi Huang, Meng Xiao, Ludi Wang, and Yi Du. 2024. DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5338–5349, Torino, Italia. ELRA and ICCL.
Cite (Informal):
DP-CRE: Continual Relation Extraction via Decoupled Contrastive Learning and Memory Structure Preservation (Huang et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-2/2024.lrec-main.475.pdf
PDF Search