An effective method of large scale ontology matching

Abstract

BackgroundWe are currently facing a proliferation of heterogeneous biomedical data sources accessible through various knowledge-based applications. These data are annotated by increasingly extensive and widely disseminated knowledge organisation systems ranging from simple terminologies and structured vocabularies to formal ontologies. In order to solve the interoperability issue, which arises due to the heterogeneity of these ontologies, an alignment task is usually performed. However, while significant effort has been made to provide tools that automatically align small ontologies containing hundreds or thousands of entities, little attention has been paid to the matching of large sized ontologies in the life sciences domain.ResultsWe have designed and implemented ServOMap, an effective method for large scale ontology matching. It is a fast and efficient high precision system able to perform matching of input ontologies containing hundreds of thousands of entities. The system, which was included in the 2012 and 2013 editions of the Ontology Alignment Evaluation Initiative campaign, performed very well. It was ranked among the top systems for the large ontologies matching.ConclusionsWe proposed an approach for large scale ontology matching relying on Information Retrieval (IR) techniques and the combination of lexical and machine learning contextual similarity computing for the generation of candidate mappings. It is particularly adapted to the life sciences domain as many of the ontologies in this domain benefit from synonym terms taken from the Unified Medical Language System and that can be used by our IR strategy. The ServOMap system we implemented is able to deal with hundreds of thousands entities with an efficient computation time.

RiMOM-IM: A Novel Iterative Framework for Instance Matching

“…Most traditional methods use all the words except stop words in the vocabulary as the keys for indexing. For example, Diallo and Ba [10] used the words in the direct virtual document of an entity as the keys for indexing, where the direct virtual document of an entity is constituted by the combination of its uniform resources identifier, the URI, the local name, the labels in different languages extracted by a function and the set of annotations associated with it. Li et al [11] built the inverted indexes for name vectors and virtual documents of an entity respectively.…”

OntoADR a semantic resource describing adverse drug reactions to support searching, coding, and information retrieval

“…Using other sources or improving existing ones: Diallo et al [31], Fung et al [32] or Bodenreider et al [33] developed methods to improve mappings already available in UMLS.…”

Definition of an Ontology Matching Algorithm for Context Integration in Smart Cities

“…RiMOM2013 [ 61 ] is an evolution of RiMOM (Risk Minimization based Ontology Mapping) [ 62 ] that integrates different matching strategies which are automatically selected and combined in order to achieve the combination that better fits each matching problem. ServOMap [ 19 , 63 , 64 ], as first step, dynamically generates a description of each entity in the ontologies, which is used to compute the lexical similarity among the entities as another entry of the vector of terms that represents each entity. Next, a context-based similarity value is calculated by computing the similarity of the surrounding concepts for each entity.…”