You are here
Semantic Processing for Enhanced Access to Biomedical Knowledge
The Semantic Knowledge Representation (SKR) project at the National Library of Medicine (NLM) develops programs that extract usable semantic information from biomedical text by building on resources currently available at NLM. Two programs in particular, MetaMap and SemRep, are being applied to a variety of problems in biomedical informatics. Both programs depend on the biomedical domain knowledge available in the Unified Medical Language System (UMLS). In representing concepts and relationships extracted from text, the semantic predications produced by these programs support a variety of applications in biomedical information management, including automatic indexing of MEDLINE citations, concept-based query expansion, accurate identification of anatomical terminology and relationships in clinical records, and the mining of biomedical text for drug-disease relations and molecular biology information.