Clustering-based Inference for Biomedical Entity Linking

TL;DR

This paper introduces a clustering-based inference model for biomedical entity linking that leverages relationships between mentions to improve linking accuracy, especially for unseen entities, outperforming previous independent prediction methods.

Contribution

The paper presents a novel clustering-based inference approach that jointly links mentions by considering their relationships, enhancing accuracy over traditional independent models.

Findings

Improved entity linking accuracy by 3.0 points over the best independent methods.

Further accuracy improvement of 2.3 points using clustering-based inference.

Effective handling of unseen entities in biomedical text.

Abstract

Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unseen entities using learned representations of entities. Previous approaches link each mention independently, ignoring the relationships within and across documents between the entity mentions. These relations can be very useful for linking mentions in biomedical text where linking decisions are often difficult due mentions having a generic or a highly specialized form. In this paper, we introduce a model in which linking decisions can be made not merely by linking to a knowledge base entity but also by grouping multiple mentions together via clustering and jointly making linking predictions. In experiments on the largest publicly available biomedical dataset, we improve the best independent prediction for entity linking by 3.0 points of accuracy, and our clustering-based inference model further improves entity linking by 2.3 points.