Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (2): 337-342.DOI: 10.11772/j.issn.1001-9081.2020060843

Special Issue: 人工智能

• Artificial intelligence • Previous Articles     Next Articles

Knowledge reasoning method based on differentiable neural computer and Bayesian network

SUN Jianqiang, XU Shaohua   

  1. College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao Shandong 266590, China
  • Received:2020-06-18 Revised:2020-09-20 Online:2021-02-10 Published:2020-12-18
  • Supported by:
    This work is partially supported by the National Key Research and Development Program of China (2018YFC1406203).


孙建强, 许少华   

  1. 山东科技大学 计算机科学与工程学院, 山东 青岛 266590
  • 通讯作者: 孙建强
  • 作者简介:孙建强(1996-),男,山东德州人,硕士研究生,CCF会员,主要研究方向:人工智能、知识图谱;许少华(1962-),男,河北邢台人,教授,博士,主要研究方向:人工智能、大数据建模分析。
  • 基金资助:

Abstract: Aiming at the problem that Artificial Neural Network (ANN) has limited memory capability for knowledge reasoning oriented to Knowledge Graph (KG) and the KG cannot deal with uncertain knowledge, a reasoning method named DNC-BN was propsed based on Differentiable Neural Computer (DNC) and Bayesian Network. Firstly, using Long Short-Term Memory (LSTM) network as the controller, the output vector and the interface vector of network were obtained by processing the input vector and the read vector obtained from the memory at each moment. Then, the read and write heads were used to realize the interaction between the controller with the memory, the read weights were used to calculate the weighted average of data to obtain the read vector, and the write operation was performed by combining the erase vector and write vector with the write weights, so as to modify the memory matrix. Finally, based on the probabilistic inference mechanism, the BN was used to judge the inference relationship between the nodes, and the KG was completed. In the experiments, on the WN18RR dataset, DNC-BN has the Mean Rank of 2 615 and the Hits@10 of 0.528; on the FB15k-237 dataset, DNC-BN has the Mean Rank of 202, and the Hits@10 of 0.519. Experimental results show that the proposed method has good application effect on knowledge reasoning oriented to KG.

Key words: Knowledge Graph (KG), knowledge reasoning, differentiable neural computer, Bayesian network, long-term memory

摘要: 针对人工神经网络(ANN)对面向知识图谱(KG)的知识推理的记忆能力有限以及KG无法处理不确定知识的问题,提出一种可微神经计算机(DNC)和贝叶斯网络(BN)相结合的推理方法DNC-BN。首先,将长短时记忆 (LSTM) 网络作为控制器,在每个时刻对输入向量和从记忆体获取的读向量进行处理,得到网络输出向量和交互向量;其次,通过读写头实现控制器与记忆体的交互,使用读取权重计算数据的加权平均以得到读向量,并用写入权重结合擦除向量及写入向量进行写操作,对存储矩阵进行修改;最后,基于概率推理机制,使用BN对数据节点之间存在的推理关系进行判断,对KG进行补全。在数据集WN18RR上的推理中,DNC-BN的Mean Rank为2 615,Hits@10为0.528;在数据集FB15k-237上的推理中,DNC-BN的Mean Rank为202,Hits@10为0.519。实验结果表明,DNC-BN方法对面向KG的知识推理具有良好的应用效果。

关键词: 知识图谱, 知识推理, 可微神经计算机, 贝叶斯网络, 长期记忆

CLC Number: