Enhancing Biomedical Relation Extraction with Directionality

TL;DR

This paper enhances biomedical relation extraction by annotating entity roles with directionality in the BioRED corpus and developing a multi-task language model that outperforms existing models on key benchmarks.

Contribution

It introduces directional annotations for BioRED and a novel multi-task soft-prompt learning model for relation and entity role extraction.

Findings

Enriched BioRED with 10,864 directional annotations

Proposed model outperforms GPT-4 and Llama-3 on benchmarks

Improves understanding of biological entity relationships

Abstract

Biological relation networks contain rich information for understanding the biological mechanisms behind the relationship of entities such as genes, proteins, diseases, and chemicals. The vast growth of biomedical literature poses significant challenges updating the network knowledge. The recent Biomedical Relation Extraction Dataset (BioRED) provides valuable manual annotations, facilitating the develop-ment of machine-learning and pre-trained language model approaches for automatically identifying novel document-level (inter-sentence context) relationships. Nonetheless, its annotations lack directionality (subject/object) for the entity roles, essential for studying complex biological networks. Herein we annotate the entity roles of the relationships in the BioRED corpus and subsequently propose a novel multi-task language model with soft-prompt learning to jointly identify the relationship, novel findings, and entity roles. Our results in-clude an enriched BioRED corpus with 10,864 directionality annotations. Moreover, our proposed method outperforms existing large language models such as the state-of-the-art GPT-4 and Llama-3 on two benchmarking tasks. Our source code and dataset are available at https://github.com/ncbi-nlp/BioREDirect.