Deep alignment: Unsupervised ontology matchingwith refined word vectors

Abstract

Ontologies compartmentalize types and relations in a target domain and provide the semantic backbone needed for a plethora of practical applications. Very often different ontologies are developed independently for the same domain. Such "parallel" ontologies raise the need for a process that will establish alignments between their entities in order to unify and extend the existing knowledge. In this work, we present a novel entity alignment method which we dub DeepAlignment. DeepAlignment refines pre-Trained word vectors aiming at deriving ontological entity descriptions which are tailored to the ontology matching task. The absence of explicit information relevant to the ontology matching task during the refinement process makes DeepAlignment completely unsupervised. We empirically evaluate our method using standard ontology matching benchmarks. We present significant performance improvements over the current state-of-The-Art, demonstrating the advantages that representation learning techniques bring to ontology matching.