BERTMap: A BERT-based Ontology Alignment System

TL;DR

BERTMap is a novel ontology matching system that leverages fine-tuned BERT embeddings to improve alignment accuracy in biomedical ontologies, supporting both unsupervised and semi-supervised settings.

Contribution

It introduces a BERT-based classifier for ontology mapping and a refinement process utilizing ontology structure, outperforming existing systems in biomedical ontology alignment.

Findings

BERTMap outperforms LogMap and AML in biomedical ontology tasks.

Supports both unsupervised and semi-supervised ontology alignment.

Refines mappings using ontology structure and logic.

Abstract

Ontology alignment (a.k.a ontology matching (OM)) plays a critical role in knowledge integration. Owing to the success of machine learning in many domains, it has been applied in OM. However, the existing methods, which often adopt ad-hoc feature engineering or non-contextual word embeddings, have not yet outperformed rule-based systems especially in an unsupervised setting. In this paper, we propose a novel OM system named BERTMap which can support both unsupervised and semi-supervised settings. It first predicts mappings using a classifier based on fine-tuning the contextual embedding model BERT on text semantics corpora extracted from ontologies, and then refines the mappings through extension and repair by utilizing the ontology structure and logic. Our evaluation with three alignment tasks on biomedical ontologies demonstrates that BERTMap can often perform better than the leading OM systems LogMap and AML.