Reasoning on Knowledge Graphs with Debate Dynamics

2 Jan 2020Marcel HildebrandtJorge Andres Quintero SernaYunpu MaMartin RingsquandlMitchell JoblinVolker Tresp

We propose a novel method for automatic reasoning on knowledge graphs based on debate dynamics. The main idea is to frame the task of triple classification as a debate game between two reinforcement learning agents which extract arguments -- paths in the knowledge graph -- with the goal to promote the fact being true (thesis) or the fact being false (antithesis), respectively... (read more)

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.