UMLS to DBPedia link discovery through circular resolution

John Cuzzola, Ebrahim Bagheri, Jelena Jovanovic
2018 JAMIA Journal of the American Medical Informatics Association  
Objective: The goal of this work is to map UMLS concepts to DBpedia resources using widely accepted ontology relations including skos:exactMatch, skos:closeMatch, and rdfs:seeAlso, as a result of which a complete mapping from UMLS 1 to DBpedia 2 is made publicly available that includes 221,690 skos:exactMatch, 26,276 skos:closeMatch, and 6,784,322 rdfs:seeAlso mappings. Materials and Methods: We propose a method called circular resolution that utilizes a combination of semantic annotators to
more » ... UMLS concepts to DBpedia resources. A set of annotators annotate definitions of UMLS concepts returning DBpedia resources while another set performs annotation on DBpedia resource abstracts returning UMLS concepts. Our pipeline aligns these two sets of annotations to determine appropriate mappings from UMLS to DBpedia. Results: We evaluate our proposed method using structured data from the Wikidata knowledge base as the ground truth, which consists of 4,899 already existing UMLS to DBpedia mappings. Our results show an 83% recall with 77% precision-at-one (P@1) in mapping UMLS concepts to DBpedia resources on this testing set. Conclusion: The proposed circular resolution method is a simple yet effective technique for linking UMLS concepts to DBpedia resources. Experiments using Wikidata-based ground truth reveal a high mapping accuracy. In addition to the complete UMLS mapping downloadable in n-triple format, we provide an online browser and a RESTful service to explore the mappings.
doi:10.1093/jamia/ocy021 pmid:29648604 fatcat:6bbmeyap2fgrbh346ccei6c62u