Biomedical ontology alignment: An approach based on representation learning

Download Edit this record How to cite View on PhilPapers
Abstract
While representation learning techniques have shown great promise in application to a number of different NLP tasks, they have had little impact on the problem of ontology matching. Unlike past work that has focused on feature engineering, we present a novel representation learning approach that is tailored to the ontology matching task. Our approach is based on embedding ontological terms in a high-dimensional Euclidean space. This embedding is derived on the basis of a novel phrase retrofitting strategy through which semantic similarity information becomes inscribed onto fields of pre-trained word vectors. The resulting framework also incorporates a novel outlier detection mechanism based on a denoising autoencoder that is shown to improve performance. An ontology matching system derived using the proposed framework achieved an F-score of 94% on an alignment scenario involving the Adult Mouse Anatomical Dictionary and the Foundational Model of Anatomy ontology (FMA) as targets. This compares favorably with the best performing systems on the Ontology Alignment Evaluation Initiative anatomy challenge. We performed additional experiments on aligning FMA to NCI Thesaurus and to SNOMED CT based on a reference alignment extracted from the UMLS Metathesaurus. Our system obtained overall F-scores of 93.2% and 89.2% for these experiments, thus achieving state-of-the-art results.
PhilPapers/Archive ID
KOLBOA
Revision history
Archival date: 2018-08-30
View upload history
References found in this work BETA
Building Ontologies with Basic Formal Ontology.Arp, Robert; Smith, Barry & Spear, Andrew D.

Add more references

Citations of this work BETA

No citations found.

Add more citations

Added to PP index
2018-08-30

Total views
70 ( #29,479 of 41,542 )

Recent downloads (6 months)
51 ( #11,798 of 41,542 )

How can I increase my downloads?

Downloads since first upload
This graph includes both downloads from PhilArchive and clicks to external links.