Generating Biomedical Hypothesis With Spatiotemporal Transformers.

Journal: IEEE journal of biomedical and health informatics
Published Date:

Abstract

Generating biomedical hypotheses is a difficult task as it requires uncovering the implicit associations between massive scientific terms from a large body of published literature. A recent line of Hypothesis Generation (HG) approaches - temporal graph-based approaches - have shown great success in modeling temporal evolution of term-pair relationships. However, these approaches model the temporal evolution of each term or term-pair with Recurrent Neural Network (RNN) independently, which neglects the rich covariation among all terms or term-pairs while ignoring direct dependencies between any two timesteps in a temporal sequence. To address this problem, we propose a Spatiotemporal Transformer-based Hypothesis Generation (STHG) method to interleave spatial covariation and temporal progression in a unified framework for constructing direct connections between any two term-pairs while modeling the temporal relevance between any two timesteps. Experiments on three biomedical relationship datasets show that STHG outperforms the state-of-the-art methods.

Authors

  • Huiwei Zhou
    School of Computer Science and Technology, Dalian University of Technology, Dalian, Liaoning, China.
  • Lanlan Wang
  • Weihong Yao
    School of Computer Science and Technology, Dalian University of Technology, Dalian 116024, Liaoning, China. Electronic address: weihongy@dlut.edu.cn.
  • Wenchu Li
  • Hao Zhou
    State Key Laboratory of Environment Health (Incubation), Key Laboratory of Environment and Health, Ministry of Education, Key Laboratory of Environment and Health (Wuhan), Ministry of Environmental Protection, School of Public Health, Tongji Medical College, Huazhong University of Science and Technology, #13 Hangkong Road, Wuhan, Hubei 430030, China.
  • Hongyun Zeng