BERTMap: A BERT-based Ontology Alignment System
This addresses ontology alignment for knowledge integration, particularly in biomedical domains, with incremental improvements over existing methods.
The paper tackles the problem of ontology alignment, where existing machine learning methods underperform rule-based systems, by proposing BERTMap, a system that uses fine-tuned BERT embeddings and structural refinement, and it demonstrates improved performance over leading systems like LogMap and AML on biomedical ontology tasks.
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.