Path-based multi-hop reasoning over knowledge graph for answering questions via adversarial reinforcement learning

Hai Cui, Tao Peng, Ridong Han, Jiayu Han, Lu Liu

Abstract: Highlights•The agent takes an opportunistic way to explicitly pursue predictive accuracy.•The generator infers answer entities by following the correct reasoning chain.•The discriminator is capable of evaluating the plausibility of reasoning paths.•RL-based models enhance the interpretability of reasoning process.