Update: The master thesis has been assigned to Florian Winkler as of June 26, 2014.
Detecting biomedical concepts in text documents or queries is a useful tool for improving biomedical information retrieval or navigating biomedical document collections. Known successful techniques for biomedical concept detection rely on natural language processing and/or machine learning and incur a substantial processing overhead at the document indexing stage compared to keyword-only indexing.
The goal of this master thesis is to evaluate a novel efficient concept detection algorithm based on position-dependent keyword matching on a recent public biomedical data set. Concepts are taken from a biomedical thesaurus called Medical Subject Headings (MeSH). Results should be compared to the accuracy achieved by the well-known MetaMap concept detector.