DOI : 10.11992/tis.201811022网络出版地址: knski/kcms/detail/23.1538.TP.20190520.1347.006.html
基于相似性负采样的知识图谱嵌入
饶官军,古天龙,常亮,宾辰忠,秦赛歌,宣闻
(桂林电子科技大学 广西可信软件重点实验室,广西 桂林 541004)
摘 要:针对现有知识图谱嵌入模型通过从实体集中随机抽取一个实体来生成负例三元组,导致负例三元组质量较低,影响了实体与关系的特征学习能力。研究了影响负例三元组质量的相关因素,提出了基于实体相似性负采样的方法来生成高质量的负例三元组。在相似性负采样方法中,首先使用K-Means 聚类算法将所有实体划分为多个组,然后从正例三元组中头实体所在的簇中选择一个实体替换头实体,并以类似的方法替换尾实体。通过将相似性负采样方法与TransE 相结合得到TransE-SNS 。研究结果表明:TransE-SNS 在链路预测和三元组分类任务上取得了显著的进步。
关键词:知识图谱;表示学习;随机抽样;相似性负采样;K-Means 聚类;随机梯度下降;链接预测;三元组分类
社会知识
cba赛程表中图分类号:TP391 文献标志码:A 文章编号:1673−4785(2020)02−0218−09
社保频道
中文引用格式:饶官军, 古天龙, 常亮, 等. 基于相似性负采样的知识图谱嵌入[J]. 智能系统学报, 2020, 15(2): 218–226.
做什么业务员好英文引用格式:RAO Guanjun, GU Tianlong, CHANG Liang, et al. Knowledge graph embedding bad on similarity negative sampling[J]. CAAI transactions on intelligent systems, 2020, 15(2): 218–226.
Knowledge graph embedding bad on similarity negative sampling
RAO Guanjun ,GU Tianlong ,CHANG Liang ,BIN Chenzhong ,QIN Saige ,XUAN Wen
(Guangxi Key Laboratory of Trusted Software, Guilin University of
qq申诉查询Electronic Technology, Guilin 541004, China)
公牛开关Abstract : For the existing knowledge graph embedding model, the random extraction of an entity from the entity t results in the generation of lower-quality negative triples, and this affects the feature learning ability of the entity and the relationship. In this paper, we study the related factors affecting the quality of negative triples, and propo an entity similarity negative sampling method to generate high-quality negative triples. In the similarity negative sampling meth-od, all entities are first
divided into a number of groups using the K-means clustering algorithm. Then, corresponding to each positive triple, an entity is lected to replace the head entity from the cluster, whereby the head entity is located in the positive triple, and the tail entity is replaced in a similar approach. TransE-SNS is obtained by combining the similar-ity negative sampling method with TransE. Experimental results show that TransE-SNS has made significant progress in link prediction and triplet classification tasks.
Keywords : knowledge graph; reprentation learning; random sampling; similarity sampling; K-means clustering;stochastic gradient descent; link prediction; triple classification
长的英文单词知识图谱(knowledge graph)的概念是谷歌在2012年正式提出的,主要用于提升搜索引擎性能。随着大数据时代的到来,知识图谱规模得到了快速的增长,各种大规模知识图谱相继出现(如Freeba [1]、WordNet [2]、NULL [3]等)。当前知识收稿日期:2018−12−04. 网络出版日期:2019−05−21.
基金项目:国家自然科学基金资助项目(U1501252,61572146);
广西创新驱动重大专项项目(AA17202024);广西自然科学基金项目(2016GXNSFDA380006);广西高校中青年教师基础能力提升项目(2018KYD203);广西研究生教育创新计划项目(YCSW2018139).
通信作者:宾辰忠. E-mail :***************.第 15 卷第 2 期
智 能 系 统 学 报Vol.15 No.22020 年 3 月
用心躁也CAAI Transactions on Intelligent Systems Mar. 2020