Improving the utility of MeSH® terms using the TopicalMeSH representation.

Journal: Journal of biomedical informatics
Published Date: Mar 19, 2016

Abstract

OBJECTIVE: To evaluate whether vector representations encoding latent topic proportions that capture similarities to MeSH terms can improve performance on biomedical document retrieval and classification tasks, compared to using MeSH terms.

Authors

  • Zhiguo Yu
  • Elmer Bernstam
    School of Biomedical Informatics and Department of Internal Medicine, McGovern Medical School, The University of Texas Health Science Center at Houston, Houston, TX, USA.
  • Trevor Cohen
    University of Washington, Seattle, WA.
  • Byron C Wallace
    School of Information, University of Texas at Austin, Austin, Texas, USA.
  • Todd R Johnson
    School of Biomedical Informatics, The University of Texas Health Science Center at Houston, Houston, TX, USA. Electronic address: Todd.R.Johnson@uth.tmc.edu.

Keywords

External Resources

Popular Topics
Recent Journals