CosG: A Graph-Based Contrastive Learning Method for Fact Verification

CosG: A Graph-Based Contrastive Learning Method for Fact Verification

Fact verification aims to verify the authenticity of a given claim based on the retrieved evidence from Wikipedia articles. Existing works mainly focus on enhancing the semantic representation of evidence, e.g., introducing the graph structure to model the evidence relation. However, previous method...

Full description

Bibliographic Details
Main Authors: Chonghao Chen, Jianming Zheng, Honghui Chen
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Sensors
Subjects:
contrastive learning
fact verification
entity graph
graph neural network
Online Access:https://www.mdpi.com/1424-8220/21/10/3471

Internet

https://www.mdpi.com/1424-8220/21/10/3471

Similar Items