Concept based document retrieval for genomics literature
conference paper
The 2006 TREC Genomics evaluation focuses on document, passage and aspect retrieval in the genomics domain. The Erasmus Medical Center, TNO and University of Twente collaborated on an approach combining concept tagging (named entity recognition) and information retrieval based on statistical language models. Experiments on the 2004 collection show that document retrieval based on concepts could not outperform the baseline based on words. However, experiments on the 2006 collection shows no significant difference between the two approaches. Further investigation has to show if and how these concept and word based language models can be effectively combined.
TNO Identifier
470068
Publisher
NIST
Source title
15th Text REtrieval Conference, TREC 2006, 14-17 November 2006, Gaithersburg, MD, USA
Place of publication
Gaithersburg,MD