TL-BERT: A Novel Biomedical Relation Extraction Approach

Automatically extracting entity-pair interactions from biomedical literature plays an important role in promoting the development of the biomedical field. For instance, the interactions between drugs can guide patients to take drugs correctly and avoid clinical adverse drug reactions; The interactions between proteins can help researchers design therapeutic drugs and discover disease mechanisms. However, it is found that relation instances of different classes generated from the same sentence are easily classified into the same class since their context information is almost the same. To address this issue, Triplet Loss based BERT (TL-BERT) approach is proposed in this paper, where the Triplet Loss training strategy is first introduced into the biomedical relation extraction field. Triplet Loss training strategy will increase the distances between these instances generated from the same sentence but belonging to different classes, and decrease the distances between these instances generated from different sentences but belonging to the same class. As a result, our approach can classify these instances generated from the same sentence more correctly. TL-BERT was evaluated on AIMed, BioInfer, and DDI Extraction-2013 corpus, the experimental results demonstrate that the Triplet Loss training strategy can improve the performance on both Protein-Protein interactions extraction tasks and Drug-Drug interactions detection tasks.

I. Introduction

The interactions between biomedical entities contain rich information, which is of significance to the biomedical research field. Drug-Drug Interaction (DDI) refers to the phenomenon that the effect of one drug is changed by another drug. The mining of the interactions between drugs can guide patients to take drugs correctly and avoid the Adverse Drug Reactions caused by taking two or more drugs at the same time. Protein-Protein Interactions (PPIs) can be used to design therapeutic drugs, help researchers to recognize protein complexes and discover disease mechanisms. Therefore, there is an urgent need to automatically extract relations (like DDIs, PPIs) from the massive biomedical literature.