End-to-end Biomedical Entity Linking with Span-based Dictionary Matching

TL;DR

This paper presents an end-to-end biomedical entity linking model that combines span-based neural representations with dictionary matching to improve recognition of unseen disease concepts in biomedical texts.

Contribution

It introduces a novel approach integrating dictionary matching with neural span representations for better handling of unseen disease concepts.

Findings

Achieved competitive results on major datasets.

Improved recognition of unseen disease concepts.

Maintained high performance with end-to-end training.

Abstract

Disease name recognition and normalization, which is generally called biomedical entity linking, is a fundamental process in biomedical text mining. Recently, neural joint learning of both tasks has been proposed to utilize the mutual benefits. While this approach achieves high performance, disease concepts that do not appear in the training dataset cannot be accurately predicted. This study introduces a novel end-to-end approach that combines span representations with dictionary-matching features to address this problem. Our model handles unseen concepts by referring to a dictionary while maintaining the performance of neural network-based models, in an end-to-end fashion. Experiments using two major datasets demonstrate that our model achieved competitive results with strong baselines, especially for unseen concepts during training.