Cross-type biomedical named entity recognition with deep multi-task learning.

Journal: Bioinformatics (Oxford, England)
Published Date: May 15, 2019

Abstract

MOTIVATION: State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases. Although recent studies explored using neural network models for BioNER to free experts from manual feature engineering, the performance remains limited by the available training data for each entity type.

Authors

  • Xuan Wang
    Baylor Scott & White Health, Dallas, TX, USA.
  • Yu Zhang
    College of Marine Electrical Engineering, Dalian Maritime University, Dalian, China.
  • Xiang Ren
    The Bradley Department of Electrical and Computer Engineering , Virginia Tech , Blacksburg , Virginia 24061 , United States.
  • Yuhao Zhang
    Biomedical Informatics Training Program, Stanford University, Stanford, CA, USA.
  • Marinka Zitnik
    Department of Computer Science, Stanford University.
  • Jingbo Shang
    Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA.
  • Curtis Langlotz
    School of Medicine, Stanford University, Palo Alto, CA, United States.
  • Jiawei Han
    Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, IL, USA Institute of Genomic Biology, University of Illinois at Urbana-Champaign, Urbana, IL, USA.

Keywords

External Resources

Popular Topics
Recent Journals