知识图谱多跳问答推理研究进展、挑战与展望

杜会芳, 王昊奋, 史英慧, 王萌

Progress, challenges and research trends of reasoning in multi-hop knowledge graph based question answering

Huifang DU, Haofen WANG, Yinghui SHI, Meng WANG

表3 基于强化学习的模型的结果

指标 方法 FB15k FB15k-237 NELL-995 Hits@1 MINERVA - 21.7% 66.3% RewardShaping - 32.7% 65.6% MAP DeepPath 57.2% - 79.6% DIVA 59.8% - 88.6% M-Walk - - 89.9%