Cross-Domain Data Integration for Named Entity Disambiguation in Biomedical Text

TL;DR

This paper introduces a cross-domain data integration approach that enhances biomedical named entity disambiguation by transferring structural knowledge from general text resources, significantly improving accuracy especially for rare entities.

Contribution

The work proposes a novel method for integrating structural knowledge from general to biomedical domains, creating a large dataset and achieving state-of-the-art results in medical NED.

Findings

Achieved state-of-the-art performance on MedMentions and BC5CDR datasets.

Improved disambiguation accuracy for rare entities by up to 57 points.

Generated a large biomedical NED dataset for pretraining.

Abstract

Named entity disambiguation (NED), which involves mapping textual mentions to structured entities, is particularly challenging in the medical domain due to the presence of rare entities. Existing approaches are limited by the presence of coarse-grained structural resources in biomedical knowledge bases as well as the use of training datasets that provide low coverage over uncommon resources. In this work, we address these issues by proposing a cross-domain data integration method that transfers structural knowledge from a general text knowledge base to the medical domain. We utilize our integration scheme to augment structural resources and generate a large biomedical NED dataset for pretraining. Our pretrained model with injected structural knowledge achieves state-of-the-art performance on two benchmark medical NED datasets: MedMentions and BC5CDR. Furthermore, we improve disambiguation of rare entities by up to 57 accuracy points.