Hierarchical Global Pointer Network: An Implicit Relation Inference Method for Gene-Disease Knowledge Discovery

The investigation of new associations between genes and diseases is a crucial knowledge extraction task for drug discovery. In this paper, we present novel approach to gene-disease discovery in the 8th China Health Information Processing Conference (CHIP 2022) [31] Open Shared Task AGAC Track ( http://www.cips-chip.org.cn/2022/eval1 ). Selective annotation latent topic are two major challenges task. To address these challenges, propose Hierarchical Global Pointer Network with propagation module extract implicit relations that inferred based on explicit relations. We also first one design unified end-to-end model which can achieve three tasks simultaneously alleviate problem selective annotation. experiment results show method proposed F1-scores 52%, 31% 30% respectively.