Concept recognition and the TREC genomics tasks

J. Gregory Caporaso, William A. Baumgartner, K. Bretonnel Cohen, Helen L. Johnson, Jesse Paquette, Lawrence Hunter

Research output: Contribution to journalConference article

Abstract

We applied concept recognition techniques to the Genomics track primary and secondary tasks. For the primary task, we developed a foundational information retrieval system which incorporated Entrez Gene entries and UMLS concepts for query expansion via phrasal and term boosting representations of synonyms. For the secondary task, we evaluated three conceptual features-mouse strain names, indexed MeSH terms, and normalized citations-in addition to two surface linguistic features-BOW and bigrams. Our final feature set yielded consistently high F-measures.

Original languageEnglish (US)
JournalNIST Special Publication
StatePublished - Dec 1 2005
Event14th Text REtrieval Conference, TREC 2005 - Gaithersburg, MD, United States
Duration: Nov 15 2005Nov 18 2005

    Fingerprint

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Gregory Caporaso, J., Baumgartner, W. A., Bretonnel Cohen, K., Johnson, H. L., Paquette, J., & Hunter, L. (2005). Concept recognition and the TREC genomics tasks. NIST Special Publication.