Ontology Alignment in the Biomedical Domain Using Entity Definitions and Context

TL;DR

This paper introduces a neural method for ontology alignment in biomedicine that leverages external entity definitions and context, achieving competitive F1 scores on a standard benchmark.

Contribution

It proposes enriching ontology entities with external information and developing a neural encoder to improve alignment accuracy.

Findings

Achieved an F1-score of 0.69 on OAEI largebio SNOMED-NCI subtask.

Comparable performance to state-of-the-art entity matchers.

Demonstrated the benefit of external definitions and context in ontology alignment.

Abstract

Ontology alignment is the task of identifying semantically equivalent entities from two given ontologies. Different ontologies have different representations of the same entity, resulting in a need to de-duplicate entities when merging ontologies. We propose a method for enriching entities in an ontology with external definition and context information, and use this additional information for ontology alignment. We develop a neural architecture capable of encoding the additional information when available, and show that the addition of external data results in an F1-score of 0.69 on the Ontology Alignment Evaluation Initiative (OAEI) largebio SNOMED-NCI subtask, comparable with the entity-level matchers in a SOTA system.