Biomedical ontology alignment : an approach based on representation learning

Kolyvakis, Prodromos (École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland) ; Kalousis, Alexandros (Haute école de gestion de Genève, HES-SO // Haute Ecole Spécialisée de Suisse Occidentale) ; Smith, Barry (University at Buffalo, USA) ; Kiritsis, Dimitris (École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland)

Background: 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. Results: 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. Conclusions: Our proposed representation learning approach leverages terminological embeddings to capture semantic similarity. Our results provide evidence that the approach produces embeddings that are especially well tailored to the ontology matching task, demonstrating a novel pathway for the problem.


Keywords:
Article Type:
scientifique
Faculty:
Economie et Services
School:
HEG - Genève
Institute:
CRAG - Centre de Recherche Appliquée en Gestion
Subject(s):
Informatique
Date:
2018-08
Pagination:
20p.
Published in:
Journal of biomedical semantics
Numeration (vol. no.):
2018, vol. 9, no. 21, pp. 1-20
DOI:
ISSN:
2041-1480
Appears in Collection:



 Record created 2018-10-04, last modified 2018-12-07

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)