Ontologies in cross-language information retrieval

Abstract

We present an approach to using ontologies as interlingua in cross-language information retrieval in the medical domain. Our approach is based on using the Unified Medical Language System (UMLS) as the primary ontology. Documents and queries are annotated with multiple layers of linguistic information (part-of-speech tags, lemmas, phrase chunks). Based on this we identify medical terms and semantic relations between them and map them to their position in the ontology. The paper describes experiments in monolingual and cross-language document retrieval, performed on a corpus of medical abstracts. Results show that semantic information, specifically the combined use of concepts and relations, increases the precision in monolingual retrieval. In cross-language retrieval the semantic annotation outperforms machine translation of the queries, but the best results are achieved by combining a similarity thesaurus with the semantic codes.