Ontology Alignment in the Biomedical Domain Using Entity Definitions and Context
This work addresses the need for accurate entity deduplication when merging biomedical ontologies, but it is incremental as it builds on existing methods with external data.
The paper tackles the problem of ontology alignment in the biomedical domain by enriching entities with external definition and context information, achieving an F1-score of 0.69 on the OAEI largebio SNOMED-NCI subtask, which is comparable to state-of-the-art entity-level matchers.
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.