基于可微神经计算机和贝叶斯网络的知识推理方法

doi:10.11772/j.issn.1001-9081.2020060843

计算机应用 ›› 2021, Vol. 41 ›› Issue (2): 337-342.DOI: 10.11772/j.issn.1001-9081.2020060843

所属专题：人工智能

基于可微神经计算机和贝叶斯网络的知识推理方法

孙建强, 许少华

山东科技大学计算机科学与工程学院, 山东青岛 266590

收稿日期:2020-06-18 修回日期:2020-09-20 出版日期:2021-02-10 发布日期:2020-12-18
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:
国家重点研发计划项目（2018YFC1406203）。

Knowledge reasoning method based on differentiable neural computer and Bayesian network

SUN Jianqiang, XU Shaohua

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).

摘要/Abstract

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

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

中图分类号:

TP391

孙建强, 许少华. 基于可微神经计算机和贝叶斯网络的知识推理方法[J]. 计算机应用, 2021, 41(2): 337-342.

SUN Jianqiang, XU Shaohua. Knowledge reasoning method based on differentiable neural computer and Bayesian network[J]. Journal of Computer Applications, 2021, 41(2): 337-342.

参考文献

[1] GOERTZEL B. Artificial general intelligence:concept,state of the art, and future prospects[J]. Journal of Artificial General Intelligence,2014,5(1):1-48.
[2] HURWITZ J S,KAUFMAN M,BOWLES A. Cognitive Computing and Big Data Analytics[M]. Indianapolis:Wiley,2015:6-12.
[3] PAN Y H. Heading toward artificial intelligence 2.0[J]. Engineering,2016,2(4):409-413.
[4] 徐增林, 盛泳潘, 贺丽荣, 等. 知识图谱技术综述[J]. 电子科技大学学报,2016,45(4):589-606.(XU Z L,SHENG Y P,HE L R,et al. Review on knowledge graph techniques[J]. Journal of University of Electronic Science and Technology of China,2016,45(4):589-606.)
[5] HECKERMAN D,GEIGER D,CHICKERING D M. Learning Bayesian networks:the combination of knowledge and statistical data[J]. Machine Learning,1995,20(3):197-243.
[6] 张仲伟, 曹雷, 陈希亮, 等. 基于神经网络的知识推理研究综述[J]. 计算机工程与应用,2019,55(12):8-19,36.(ZHANG Z W,CAO L,CHEN X L,et al. Survey of knowledge reasoning based on neural network[J]. Computer Engineering and Applications,2019,55(12):8-19,36.)
[7] SOCHER R,CHEN D,MANNING C D,et al. Reasoning with neural tensor networks for knowledge base completion[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc.,2013:926-934.
[8] SHI B,WENINGER T. ProjE:embedding projection for knowledge graph completion[C]//Proceedings of the 31st AAAI Conference on Artificial Intelligence. Pal,Alto,CA:AAAI Press,2017:1236-1242.
[9] SHEN Y,HUANG P S,CHANG M W,et al. Modeling large-scale structured relationships with shared memory for knowledge base completion[C]//Proceedings of the 2nd Workshop on Representation Learning for NLP. Stroudsburg,PA:Association for Computational Linguistics,2017:57-68.
[10] GRAVES A,WAYNE G,DANIHELKA I. Neural turing machines[EB/OL].[2019-08-17]. https://arxiv.org/pdf/1410.5401.pdf.
[11] GRAVES A, WAYNE G, REYNOLDS M, et al. Hybrid computing using a neural network with dynamic external memory[J]. Nature,2016,538(7626):471-476.
[12] SINGHAL A. Introducing the Knowledge Graph:things, not strings[EB/OL].[2019-06-12]. https://www.blog.google/products/search/introducing-knowledge-graph-things-not/.
[13] 王子涵, 邵明光, 刘国军, 等. 基于实体相似度信息的知识图谱补全算法[J]. 计算机应用,2018,38(11):3089-3093. (WANG Z H,SHAO M G,LIU G J,et al. Knowledge graph completion algorithm based on similarity between entities[J]. Journal of Computer Applications,2018,38(11):3089-3093.)
[14] CHEN X,JIA S,XIANG Y. A review:knowledge reasoning over knowledge graph[J]. Expert Systems with Applications,2020, 141:No. 112948.
[15] CHAN A,MA L,JUEFEI-XU F,et al. Metamorphic relation based adversarial attacks on differentiable neural computer[EB/OL].[2019-12-28]. https://arxiv.org/pdf/1809.02444.pdf.
[16] PEARL J. Probabilistic Reasoning in Intelligent Systems:Networks of Plausible Inference[M]. San Francisco:Morgan Kaufmann Publishers Inc.,1988:12-39.
[17] 翟社平, 郭琳, 高山, 等. 一种采用贝叶斯推理的知识图谱补全方法[J]. 小型微型计算机系统,2018,39(5):995-999.(ZHAI S P, GUO L, GAO S, et al. Method for knowledge graph completion based on Bayesian reasoning[J]. Journal of Chinese Computer Systems,2018,39(5):995-999.)
[18] HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780.
[19] MING Y,PELUSI D,FANG C N,et al. EEG data analysis with stacked differentiable neural computers[J]. Neural Computing and Applications,2020,32(12):7611-7621.
[20] DETTMERS T, MINERVINI P, STENETORP P, et al. Convolutional 2D knowledge graph embeddings[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto, CA:AAAI Press,2018:1811-1818.
[21] TOUTANOVA K,CHEN D. Observed versus latent features for knowledge base and text inference[C]//Proceedings of the 3rd Workshop on Continuous Vector Space Models and their Compositionality. Stroudsburg, PA:Association for Computational Linguistics,2015:57-66.
[22] BORDES A, USUNIER N, GARCIA-DURÁN A, et al. Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems. Red Hook, NY:Curran Associates Inc.,2013:2787-2795.
[23] YANG B,YIH W T,HE X,et al. Embedding entities and relations for learning and inference in knowledge bases[EB/OL].[2020-02-14]. https://arxiv.org/pdf/1412.6575.pdf.

基于可微神经计算机和贝叶斯网络的知识推理方法

Knowledge reasoning method based on differentiable neural computer and Bayesian network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	余敦辉, 万鹏, 王社. 基于企业知识图谱构建的实体关联查询系统[J]. 计算机应用, 2021, 41(9): 2510-2516.
[2]	陈恒恒, 倪志伟, 朱旭辉, 金媛媛, 陈千. 基于聚类分析的差分隐私高维数据发布方法[J]. 计算机应用, 2021, 41(9): 2578-2585.
[3]	刘雅璇, 钟勇. 基于头实体注意力的实体关系联合抽取方法[J]. 计算机应用, 2021, 41(9): 2517-2522.
[4]	田玲, 张谨川, 张晋豪, 周望涛, 周雪. 知识图谱综述——表示、构建、推理与知识超图理论[J]. 计算机应用, 2021, 41(8): 2161-2186.
[5]	刘欢, 李晓戈, 胡立坤, 胡飞雄, 王鹏华. 基于知识图谱驱动的图神经网络推荐模型[J]. 计算机应用, 2021, 41(7): 1865-1870.
[6]	余敦辉, 张蕗怡, 张笑笑, 毛亮. 基于知识图谱和重启随机游走的跨平台用户推荐方法[J]. 计算机应用, 2021, 41(7): 1871-1877.
[7]	秦丽, 郝志刚, 李国亮. 国家食品安全标准图谱的构建及关联性分析[J]. 计算机应用, 2021, 41(4): 1005-1011.
[8]	董永峰, 刘超, 王利琴, 李英双. 融合多跳关系路径信息的关系推理方法[J]. 计算机应用, 2021, 41(10): 2799-2805.
[9]	武小平, 张强, 赵芳, 焦琳. 基于BERT的心血管医疗指南实体关系抽取方法[J]. 计算机应用, 2021, 41(1): 145-149.
[10]	马冬雪, 宋设, 谢振平, 刘渊. 领域本体驱动的招投标网页解析方法[J]. 计算机应用, 2020, 40(6): 1574-1579.
[11]	陈曦, 梅广, 张金金, 许维胜. 融合知识图谱和协同过滤的学生成绩预测方法[J]. 计算机应用, 2020, 40(2): 595-601.
[12]	张钊, 吉建民, 陈小平. 用于知识表示学习的对抗式负样本生成[J]. 计算机应用, 2019, 39(9): 2489-2493.
[13]	张榜, 朱金鑫, 徐正蓺, 刘盼, 魏建明. 基于贝叶斯网络的楼层定位算法[J]. 计算机应用, 2019, 39(8): 2468-2474.
[14]	杨洁, 李松斌, 邓浩江. 基于贝叶斯网络的压缩语音信息隐藏检测[J]. 计算机应用, 2018, 38(7): 1967-1973.
[15]	鲁强, 刘兴昱. 基于迁移学习的知识图谱问答语义匹配模型[J]. 计算机应用, 2018, 38(7): 1846-1852.