Joint extraction of Chinese medical entities and relations based on RoBERTa and single-module global pointer.

Journal: BMC medical informatics and decision making
Published Date: Jul 31, 2024

Abstract

BACKGROUND: Most Chinese joint entity and relation extraction tasks in medicine involve numerous nested entities, overlapping relations, and other challenging extraction issues. In response to these problems, some traditional methods decompose the joint extraction task into multiple steps or multiple modules, resulting in local dependency in the meantime.

Authors

  • Dongmei Li
    Clinical and Translational Science Institute, University of Rochester School of Medicine and Dentistry, Rochester, New York.
  • Yu Yang
    Department of Obstetrics & Gynecology, the First Affiliated Hospital of Xi'an Jiaotong University, Xian, Shaanxi, China.
  • Jinman Cui
    School of Information Science and Technology, Beijing Forestry University, 100083, Beijing, China.
  • Xianghao Meng
    School of Electronic Countermeasures, National University of Defense Technology, Hefei 230000, China.
  • Jintao Qu
    School of Information Science and Technology, Beijing Forestry University, 100083, Beijing, China.
  • Zhuobin Jiang
    National Data Center of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, 100700, Beijing, China. bobjzb@163.com.
  • Yufeng Zhao
    Institute of Basic Research in Clinical Medicine/National Data Center of Traditional Chinese Medicine, China Academy of Chinese Medical Sciences, No.16 South Street,Dongzhimen,Dongcheng District, Beijing, 100700, China. snowmanzhao@163.com.

Keywords

External Resources

Popular Topics
Recent Journals