Skip to main content
Article
MeSH qualifiers, publication types and relation occurrence frequency are also useful for a better sentence-level extraction of biomedical relations
Journal of Biomedical Informatics (2018)
  • Houcemeddine Turki
  • Mohamed Ali Hadj Taieb, University of Sfax
  • Mohamed Ben Aouicha, University of Sfax
Abstract
This letter explains how MeSH qualifiers can be used to enhance the precision and recall of sentence-level biomedical relation extraction from scientific publications. After, it proposes that encyclopedic review allows a better sentence-level extraction of biomedical relations than any other type of scientific publications. Finally, it shows how the occurrence frequency of the statement of biomedical relations within the scientific literature can be useful to improve the efficacy of biomedical relation extraction.
Keywords
  • MeSH qualifiers,
  • Encyclopedic review,
  • Biomedical relation extraction,
  • Occurrence frequency
Publication Date
Spring May 29, 2018
DOI
10.1016/j.jbi.2018.05.011
Citation Information
Houcemeddine Turki, Mohamed Ali Hadj Taieb and Mohamed Ben Aouicha. "MeSH qualifiers, publication types and relation occurrence frequency are also useful for a better sentence-level extraction of biomedical relations" Journal of Biomedical Informatics Vol. 83 (2018) p. 217 - 218 ISSN: 1532-0464
Available at: http://works.bepress.com/houcemeddine_turki/33/