An attention-based BiLSTM-CRF approach to document-level chemical named entity recognition.

Journal: Bioinformatics (Oxford, England)
Published Date: Apr 15, 2018

Abstract

MOTIVATION: In biomedical research, chemical is an important class of entities, and chemical named entity recognition (NER) is an important task in the field of biomedical information extraction. However, most popular chemical NER methods are based on traditional machine learning and their performances are heavily dependent on the feature engineering. Moreover, these methods are sentence-level ones which have the tagging inconsistency problem.

Authors

  • Ling Luo
    Department of Epidemiology and Medical Statistics School of Public Health, Guangdong Medical University, Dongguan, Guangdong, China.
  • Zhihao Yang
    College of Computer Science and Technology, Dalian University of Technology, Dalian 116024, China.
  • Pei Yang
    Department of Bone and Joint Surgery, The Second Affiliated Hospital of Xi'an Jiaotong University, Xi'an, China.
  • Yin Zhang
    Department of Radiation Oncology, Rutgers-Cancer Institute of New Jersey, Rutgers-Robert Wood Johnson Medical School, New Brunswick, NJ, United States.
  • Lei Wang
    Department of Nursing, Beijing Hospital, National Center of Gerontology, Institute of Geriatric Medicine, Chinese Academy of Medical Sciences, Beijing, China.
  • Hongfei Lin
  • Jian Wang
    Veterinary Diagnostic Center, Shanghai Animal Disease Control Center, Shanghai, China.

Keywords

External Resources

Popular Topics
Recent Journals