Continual Contrastive Finetuning Improves Low-Resource Relation Extraction
This work addresses low-resource relation extraction for domains like biomedical text, offering a novel approach to improve performance with minimal labeled data.
The paper tackles the challenge of low-resource relation extraction by bridging the gap between pretraining and finetuning objectives, using consistent contrastive learning and a multi-center loss to improve representation alignment. The method outperforms a PLM-based classifier by 10.5% and 6.1% on two datasets with only 1% training data.
Relation extraction (RE), which has relied on structurally annotated corpora for model training, has been particularly challenging in low-resource scenarios and domains. Recent literature has tackled low-resource RE by self-supervised learning, where the solution involves pretraining the entity pair embedding by RE-based objective and finetuning on labeled data by classification-based objective. However, a critical challenge to this approach is the gap in objectives, which prevents the RE model from fully utilizing the knowledge in pretrained representations. In this paper, we aim at bridging the gap and propose to pretrain and finetune the RE model using consistent objectives of contrastive learning. Since in this kind of representation learning paradigm, one relation may easily form multiple clusters in the representation space, we further propose a multi-center contrastive loss that allows one relation to form multiple clusters to better align with pretraining. Experiments on two document-level RE datasets, BioRED and Re-DocRED, demonstrate the effectiveness of our method. Particularly, when using 1% end-task training data, our method outperforms PLM-based RE classifier by 10.5% and 6.1% on the two datasets, respectively.