BioEGRE: a linguistic topology enhanced method for biomedical relation extraction based on BioELECTRA and graph pointer neural network.

Journal: BMC bioinformatics
Published Date:

Abstract

BACKGROUND: Automatic and accurate extraction of diverse biomedical relations from literature is a crucial component of bio-medical text mining. Currently, stacking various classification networks on pre-trained language models to perform fine-tuning is a common framework to end-to-end solve the biomedical relation extraction (BioRE) problem. However, the sequence-based pre-trained language models underutilize the graphical topology of language to some extent. In addition, sequence-oriented deep neural networks have limitations in processing graphical features.

Authors

  • Xiangwen Zheng
    Academy of Military Medical Sciences, Beijing, 100039, China.
  • Xuanze Wang
    Academy of Military Medical Sciences, Beijing, 100039, China.
  • Xiaowei Luo
    Academy of Military Medical Sciences, Beijing, 100039, China.
  • Fan Tong
    Academy of Military Medical Sciences, Beijing, 100039, China.
  • Dongsheng Zhao
    Information Center, Academy of Military Medical Sciences, Beijing, China. dszhao@bmi.ac.cn.