HHGN: A Hierarchical Reasoning-based Heterogeneous Graph Neural Network for fact verification

作者：

Highlights：

• A heterogeneous graph-based evidence representation method is proposed.

• A hierarchical reasoning-based node features aggregation strategy is designed.

• Experimental results demonstrate the superiority of our proposal on both multiple and single evidence scenarios.

摘要

•A heterogeneous graph-based evidence representation method is proposed.•A hierarchical reasoning-based node features aggregation strategy is designed.•Experimental results demonstrate the superiority of our proposal on both multiple and single evidence scenarios.

论文关键词：Fact verification,Graph neural network,Hierarchical reasoning,Heterogeneous graph

论文评审过程：Received 21 February 2021, Revised 20 April 2021, Accepted 3 June 2021, Available online 25 June 2021, Version of Record 25 June 2021.

论文官网地址：https://doi.org/10.1016/j.ipm.2021.102659