Extending a natural language parser with UMLS knowledge.

摘要: Over the past several years our research efforts have been directed toward identification of natural language processing methods and techniques for improving access to biomedical information stored in computerized form. To provide a testing ground some these ideas we undertaken development SPECIALIST, prototype system parsing accessing text. The includes linguistic knowledge. Linguistic knowledge involves rules facts about grammar language. Biomedical domain biomedicine. UMLS sources, Meta-1 Semantic Network, as well test collection, recently contributed SPECIALIST system.