基于多级关系路径语义组合的关系推理算法

doi:10.19678/j.issn.1000-3428.0054825

计算机工程 ›› 2020, Vol. 46 ›› Issue (5): 109-114. doi: 10.19678/j.issn.1000-3428.0054825

基于多级关系路径语义组合的关系推理算法

陈恒^1,2, 韩雨婷¹, 李冠宇¹, 王京徽¹

1. 大连海事大学信息科学技术学院, 辽宁大连 116026;
2. 大连外国语大学软件学院, 辽宁大连 116044

收稿日期:2019-05-06 修回日期:2019-06-26 发布日期:2019-07-12
作者简介:陈恒(1982-),男,副教授、博士研究生,主研方向为智能信息处理;韩雨婷,硕士研究生;李冠宇,教授、博士;王京徽,硕士研究生。
基金资助:
国家自然科学基金（61371090）；辽宁省自然科学基金重点项目（20170540232）；辽宁省重点研发计划指导项目（61801007）；大连外国语大学科研基金（2018CXTD04）。

Relational Reasoning Algorithm Based on Semantic Combination of Multi-hop Relational Path

CHEN Heng^1,2, HAN Yuting¹, LI Guanyu¹, WANG Jinghui¹

1. School of Information Science and Technology, Dalian Maritime University, Dalian, Liaoning 116026, China;
2. School of Software, Dalian University of Foreign Languages, Dalian, Liaoning 116044, China

Received:2019-05-06 Revised:2019-06-26 Published:2019-07-12

摘要/Abstract

摘要： 针对目前知识图谱中存在关系事实缺失且对隐含知识挖掘不足等问题，提出一种基于多级关系路径语义组合的关系推理算法。将知识图谱嵌入到低维向量空间中，利用强化学习进行路径发现，使得路径中实体和关系对应的向量作为循环神经网络的输入，经过迭代学习输出多级关系路径语义组合的结果向量，并将结果向量与目标关系向量进行相似度计算，从而进行关系推理。在FB15K-237和NELL-995数据集上的实验结果表明，该算法事实预测精度分别为0.314和0.417，均优于PRA、TransE与TransH模型。

关键词: 关系推理, 表示学习, 强化学习, 循环神经网络, 知识图谱, 语义组合

Abstract: To address the lack of relationship facts and insufficient mining of hidden knowledge in the current Knowledge Graph(KG),this paper proposes a relationship reasoning algorithm based on the semantic combination of multi-hop relational path.The algorithm embeds KG into a low-dimensional vector space and uses reinforcement learning for path discovery,so that the vectors corresponding to the entities and relationships in the path are used as the input of the Recurrent Neural Network(RNN).After iterative learning,the result vector of the semantic combination of multi-level relation path is output,and the similarity between the result vector and the target relation vector is calculated.Experimental results on the FB15K-237 and NELL-995 datasets show that the factual prediction results of the proposed algorithm are 0.314 and 0.417 respectively,which are better than the PRA,TransE,and TransH models.

Key words: relational reasoning, represent learning, reinforcement learning, Recurrent Neural Network(RNN), Knowledge Graph(KG), semantic combination

中图分类号:

TP18

陈恒, 韩雨婷, 李冠宇, 王京徽. 基于多级关系路径语义组合的关系推理算法[J]. 计算机工程, 2020, 46(5): 109-114.

CHEN Heng, HAN Yuting, LI Guanyu, WANG Jinghui. Relational Reasoning Algorithm Based on Semantic Combination of Multi-hop Relational Path[J]. Computer Engineering, 2020, 46(5): 109-114.

http://www.ecice06.com/CN/Y2020/V46/I5/109

图/表 9

20200513201421

20200513201431

20200513201435

20200513201439

20200513201442

20200513201447

20200513201451

20200513201456

20200513201500

参考文献

[1] BOLLACKER K,EVANS C,PARITOSH P,et al.Freebase:a collaboratively created graph database for structuring human knowledge[C]//Proceedings of 2008 ACM SIGMOD International Conference on Management of Data.New York,USA:ACM Press,2008:1247-1250.
[2] MILLER G A.WordNet:a lexical database for English[J].Communications of the ACM,1995,38(11):39-41.
[3] BIZER C,LEHMANN J,KOBILAROV G,et al.DBpedia:a crystallization point for the Web of data[J].Web Semantics:Science,Services and Agents on the World Wide Web,2009,7(3):154-165.
[4] MAHDISOLTANI F,BIEGA J,SUCHANEK F M.Yago3:a knowledge base from multilingual wikipedias[EB/OL].[2019-04-10].http://dblp.uni-trier.de/db/conf/cidr/cidr2015.
[5] CARLSON A,BETTERIDGE J,KISIEL B,et al.Toward an architecture for never-ending language learning[C]//Proceedings of the 24th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2010:1306-1313.
[6] XU Zenglin,SHENG Yongpan,HE Lirong,et al.Review on knowledge graph techniques[J].Journal of University of Electronic Science and Technology of China,2016,45(4):589-606.(in Chinese)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.
[7] QI Guilin,GAO Heng,WU Tianxing.Overview of knowledge mapping technology[J].Technology Intelligence Engineering,2017,3(1):4-25.(in Chinese)漆桂林,高桓,吴天星.知识图谱研究进展[J].情报工程,2017,3(1):4-25.
[8] DONG X,GABRILOVICH E,HEITZ G,et al.Knowledge vault:a Web-scale approach to probabilistic knowledge fusion[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York,USA:ACM Press,2014:601-610.
[9] NI L,COHEN W W.Relational retrieval using a combination of path-constrained random walks[J].Machine Learning,2010,81(1):53-67.
[10] BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of International Conference on Neural Information Processing Systems.[S.1.]:Curran Associates Inc.,2013:2787-2795.
[11] XIONG W,HOANG T,WANG W Y.DeepPath:a reinforcement learning method for knowledge graph reasoning[C]//Proceedings of 2017 IEEE Conference on Empirical Methods Natural Language Processing.Washington D.C.,USA:IEEE Press,2017:211-214.
[12] NEELAKANTAN A,ROTH B,MCCALLUM A.Compositional vector space models for knowledge base completion[EB/OL].[2019-04-10].http://www.oalib.com/paper/4073388.
[13] DAS R,NEELAKANTAN A,BELANGER D,et al.Chains of reasoning over entities,relations,and text using recurrent neural networks[EB/OL].[2019-04-10].https://blog.csdn.net/damuge2/article/details/88069381.
[14] WANG Zhen,ZHANG Jianwen,FENG Jianlin,et al.Knowledge graph and text jointly embedding[C]//Proceedings of Conference on Empirical Methods in Natural Language Processing.Doha,Qatar:[s.n.],2014:1591-1601.
[15] JI Guoliang,HE Shizhu,XU Liheng,et al.Knowledge graph embedding via dynamic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing.Berlin,Germany:Springer,2015:687-696.
[16] LIU Zhiyuan,SUN Maosong,LIN Yankai,et al.Knowledge representation learning:a review[J].Journal of Computer Research and Development,2016,53(2):247-261.(in Chinese)刘知远,孙茂松,林衍凯,等.知识表示学习研究进展[J].计算机研究与发展,2016,53(2):247-261.
[17] WU Yunbing,YANG Fan,LAI Guohua,et al.Research progress of knowledge graph learning and reasoning[J].Journal of Chinese Computer Systems,2016,37(9):2007-2013.(in Chinese)吴运兵,杨帆,赖国华,等.知识图谱学习和推理研究进展[J].小型微型计算机系统,2016,37(9):2007-2013.
[18] NICKEL M,TRESP V,KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//Proceedings of the 28th International Conference on Machine Learning.Washington D.C.,USA:IEEE Press,2011:809-816.
[19] NICKEL M,TRESP V.Tensor factorization for multi-relational learning[C]//Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases.Berlin,Germany:Springer,2013:617-621.
[20] SMOLENSKY P.Tensor product variable binding and the representation of symbolic structures in connectionist systems[J].Artificial Intelligence,1990,46(1):159-216.
[21] WANG Zhen,ZHANG Jianwen,FENG Jianlin,et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2014:1112-1119.
[22] LIN Yankai,LIU Zhiyuan.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2015:2181-2187.
[23] MNIH V,KAVUKCUOGLU K,SILVER D,et al.Playing atari with deep reinforcement learning[EB/OL].[2019-04-10].https://arXivpreprintarXiv:1312.5602.
[24] WILLIAMS R J.Simple statistical gradient-following algorithms for connectionist reinforcement learning[J].Machine Learning,1992,8(3/4):229-256.
[25] TOUTANOVA K,CHEN D,PANTEL P,et al.Representing text for joint embedding of text and knowledge bases[C]//Proceedings of IEEE EMNLP'15.Washington D.C.,USA:IEEE Press,2015:21-28.
[26] CARLSON A,BETTERIDGE J,KISIEL B,et al.Toward an architecture for never-ending language learning[C]//Proceedings of the 24th AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press,2010:354-369.

选择文件类型/文献管理软件名称

选择包含的内容

基于多级关系路径语义组合的关系推理算法

Relational Reasoning Algorithm Based on Semantic Combination of Multi-hop Relational Path

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	马坤, 安敬民, 李冠宇. 动态聚合实体和关系上下文的知识图谱补全[J]. 计算机工程, 2023, 49(8): 77-84, 95.
[2]	张冠莹, 伊鹏, 李丹, 朱棣, 毛明. 面向大规模网络的服务功能链部署方法[J]. 计算机工程, 2023, 49(8): 122-129.
[3]	梅晶, 戴龙宝, 童钊, 邓昕, 王嘉珂. 资源约束下基于Lyapunov优化的自适应卸载算法[J]. 计算机工程, 2023, 49(7): 34-46.
[4]	蔡丽娇, 秦进, 陈双. 远离旧区域和避免回路的强化探索方法[J]. 计算机工程, 2023, 49(7): 118-124.
[5]	李强, 仪晋辉, 杜婷婷, 王胜春. 移动边缘计算中基于A3C的依赖任务卸载与资源分配[J]. 计算机工程, 2023, 49(6): 42-52.
[6]	代祖华, 刘园园, 狄世龙. 语义增强的图神经网络方面级文本情感分析[J]. 计算机工程, 2023, 49(6): 71-80.
[7]	金志军, 王浩, 方宝富. 稀疏场景下基于理性好奇心的多智能体强化学习[J]. 计算机工程, 2023, 49(5): 302-309.
[8]	唐彦, 卢镘旭. 基于知识图谱与深度涟漪网络的推荐系统[J]. 计算机工程, 2023, 49(5): 63-72,80.
[9]	叶琪, 张一乾, 阮彤, 杜渂. 基于语义和结构置信度的知识图谱质量校验方法[J]. 计算机工程, 2023, 49(5): 48-55.
[10]	陈昱瑾, 王晶, 武志昊, 赵耀帅, 林友芳. 基于图卷积网络融合群组关系的社会化推荐方法[J]. 计算机工程, 2023, 49(5): 112-121.
[11]	沈学利, 韩倩雯. 基于注意力机制的场感知点击率预测模型[J]. 计算机工程, 2023, 49(3): 80-86,94.
[12]	邹长龙, 安敬民, 李冠宇. 基于邻域聚合与CNN的知识图谱实体类型补全[J]. 计算机工程, 2023, 49(3): 134-141.
[13]	马月坤, 张可心, 高唱. 体现辨证论治差异的不孕症知识图谱构建方法研究[J]. 计算机工程, 2023, 49(3): 280-287,295.
[14]	翟社平, 张宇航, 柏晓夏. 融合实体邻域信息的知识图谱嵌入负采样方法[J]. 计算机工程, 2023, 49(3): 95-104.
[15]	张晓晖, 马慧芳, 王文涛, 高子皓. 基于跨会话知识图谱的图注意力网络推荐方法[J]. 计算机工程, 2023, 49(2): 136-142,149.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

基于多级关系路径语义组合的关系推理算法

Relational Reasoning Algorithm Based on Semantic Combination of Multi-hop Relational Path

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献

相关文章 15

编辑推荐

Metrics

本文评价