A knowledge enhanced learning and semantic composition model for multi-claim fact checking

Shuai Wang, Penghui Wei, Qingchao Kong, Wenji Mao

Abstract: Highlights•Propose the first model to address the multi-claim fact checking problem.•KG-based module learns context-specific entity representations.•Graph-based module models inter-claim semantic interactions.•Experimental results on the benchmark KGs show the effectiveness of our model.