The overview of the BioRED (Biomedical Relation Extraction Dataset) track at BioCreative VIII

Abstract

The BioRED track at BioCreative VIII calls for a community effort to identify, semantically categorize, and highlight the novelty factor of the relationships between biomedical entities in unstructured text. Relation extraction is crucial for many Natural Language Processing (NLP) applications, from drug discovery to custom medical solutions. While previous community challenges focused on identifying relationships of a single type (i.e., protein-protein interactions), categorized relationships into different semantic categories but did not require entity normalization, or worked at the sentence level, real-world applications necessitate that entities are linked to specific knowledge base records, relationships encountered in any given document generally occur between different entity types, and perusal of the whole document provides valuable additional detail. In addition, journal publications often distinguish between novel findings and background information or prior knowledge.

This article is part of the Proceedings of the BioCreative VIII Challenge and Workshop: Curation and Evaluation in the era of Generative Models.