Iterative Reasoning over Knowledge Graph

Liang Xu, Junjie Yao

Abstract: The concept reasoning is an essential task in text data management and understanding. Recent methods usually capture shallow semantic features and cannot extend to multi-hop reasoning. Knowledge graphs have rich text information and connections. We use a knowledge graph to encode complex semantic relation between evidence and question. The nodes represent valuable information as clue entities and candidate answers in evidence and question, and the edges represent the reasoning rules between nodes.

External IDs:dblp:conf/dasfaa/XuY21