计算机科学 ›› 2022, Vol. 49 ›› Issue (9): 215-220.doi: 10.11896/jsjkx.210700190

• 人工智能 • 上一篇    下一篇

基于自注意力模型的本体对齐方法

吴子仪, 李邵梅, 姜梦函, 张建朋   

  1. 国家数字交换系统工程技术研究中心 郑州 450002
  • 收稿日期:2021-07-19 修回日期:2022-02-28 出版日期:2022-09-15 发布日期:2022-09-09
  • 通讯作者: 李邵梅(13513127249@163.com)
  • 作者简介:(mushaboommm@163.com)
  • 基金资助:
    国家自然科学基金青年科学基金(62002384);郑州市协同创新重大专项(162/32410218)

Ontology Alignment Method Based on Self-attention

WU Zi-yi, LI Shao-mei, JIANG Meng-han, ZHANG Jian-peng   

  1. National Digital Switching System Engineering &Technological R & D Center,Zhengzhou 450002,China
  • Received:2021-07-19 Revised:2022-02-28 Online:2022-09-15 Published:2022-09-09
  • About author:WU Zi-yi,born in 1998,master.Her main research interests include know-ledge graph and NLP.
    LI Shao-mei,born in 1982,Ph.D,asso-ciate professor,master supervisor.Her main research interests include know-ledge graph and NLP.
  • Supported by:
    Young Scientists Fund of the National Natural Science Foundation of China(62002384) and Zhengzhou Collaborative Innovation Major Project(162/32410218).

摘要: 随着知识图谱在人工智能领域的发展,对不同源的知识图谱进行融合,以得到覆盖范围更广的知识图谱的需求日益增加。本体作为知识图谱的上层结构,对知识图谱的构建具有指导作用。为了解决知识图谱融合中本体对齐的问题,文中提出了基于自注意力模型融合多维相似度的方法,从而提高本体对齐的精度。首先,对来自两个本体的概念进行基于字符串的、基于语义的和基于结构信息的多维度相似性度量;然后,使用自注意力模型对上述多种相似度度量结果进行融合,进而判断是否相似并进行对齐。在公开数据集上进行实验,实验结果表明,相比现有的本体对齐方法,所提方法通过聚合多维度的相似性特征能够得到更优的对齐结果。

关键词: 知识图谱融合, 本体对齐, 相似度计算, 自注意力模型

Abstract: With the development of knowledge graph in the field of artificial intelligence,there is an increasing demand to integrate knowledge graph from different sources to obtain a big knowledge graph with wider coverage.Ontology is the superstructure that can guide the construction of knowledge graph.To solve the problem of ontology alignment in knowledge graph fusion,this paper proposes an ontology alignment method based on self-attention model to combine multidimensional similarities.Firstly,two concepts from two ontologies are multi-dimensional measured by string-based,semantic-based and structure-based similarities.Then,self-attention model is used to combine above similarity calculations to judge whether the two concepts are similar or not and align them.Experiments on public datasets show that,compared with existing ontology alignment methods,the proposed method can obtain better alignment results by aggregating multi-dimensional similarity features.

Key words: Knowledge graph fusion, Ontology alignment, Similarity calculation, Self-attention model

中图分类号: 

  • TP391.1
[1]EUZENAT J,SHVAIKO P.Ontology Matching[M].Berlin:Springer-Verlag,2007:25-54.
[2]WANG S,KANG D Z,JIANG D Y.Survey of Ontology Mapping[J].Computer Science,2017,44(9):1-10.
[3]XU J,FANG A,HONG N.An Ontology Mapping MethodBased on Lexical Similarity Calculation[J].New Technology of Library and Information Service,2013,29(2):36-42.
[4]YAO X M,WANG F,LIN L F,et al.An Efficient Multi-policy Ontology Mapping Method[J].Chinese Science and Technology Papers,2013,8(7):642-647.
[5]YU J,XIONG Z H,OU Z H.Eliminating Redundant Ontology Relations Based on Hasse Diagram[J].Journal of the China Society for Scientific and Technical Information,2015,34(3):279-285.
[6]JIANG M,YU M G,WANG Z X.Multi-strategy AdaptiveLarge-scale Ontology Mapping Algorithm[J].Computer Engineering,2019,45(3):14-19.
[7]EUZENAT J,GUÉGAN P,VALTCHEVP.OLA in the OAEI2005 alignment contest[C]//Proceedings of the K-CAP 2005 Workshop on Integrating Ontologies.2005:61-71.
[8]NEZHADI A,SHADGAR B,OSAREH A.Ontology Alignment Using Machine LearningTechniques[J].International Journal of Computer Science & Information Technology,2011,12(3):139-150.
[9]ALBOUKAEY N,JOUKHADAR A.Ontology Matching as Regression Problem[J].Journal of Digital Information Management,2018,16(1):85-99.
[10]LEV B,SERGEY S.Applying of Machine Learning Techniques to Combine String-based,Language-based and Structure-based Similarity Measures for Ontology Matching[C]//Selected Papers of the XXI International Conference on Data Analytics and Management in Data Intensive Domains.2019:129-147.
[11]SENGODAN M,SAMUKUTTY A.Explicit Link DiscoveryScheme Optimized with Ontology Mapping using Improved Machine Learning Approach[J].Studies in Informatics and Control,2021,30(1):189-201.
[12]SABOU M,THIÉBLIN E,HAEMMERLÉ O,et al.Survey on complex ontology matching[J].Semantic Web,2020,11(4):32-62.
[13]WANG R J.Research on Ontology Mapping Methods[D].Changchun:Jilin University,2012.
[14]LOU W,WANG H,JU Y.An ontology fusion method based on binary similarity calculation[J].Journal of the China Society for Scientific and Technical Information,2019,38(6):622-631.
[15]SUN X.Research on Ontology Alignment Based on Word Embedding[D].Harbin:Harbin Institute of Technology,2020.
[16]CHEN E J,JIANG E B.Review of Studies on Text Similarity Measures[J].Data Analysis and Knowledge Discovery,2017,1(6):1-11.
[17]LIN H L,WANG Y Z,JIA Y T,et al.Network Big Data Oriented Knowledge Fusion Methods:A Survey[J].Chinese Journal of Computers,2017,40(1):1-27.
[18]KANG S Z,JI L X,ZHANG J P.Ontology Alignment Method Based on Word Embedding and Conceptual Context Information[J].Journal of Information Engineering University,2020,21(5):607-613.
[19]SAEDI C,BRANCOA,RODRIGUES J,et al.Wordnet embeddings[C]//Proceedings of the Third Workshop on Representation Learning for NLP.2018:122-131.
[20]JANG B,KIM I,KIM J W.Word2vec convolutional neural networks for classification of news articles and tweets[J].PloS One,2019,14(8):178-189.
[21]LE Q V,MIKOLOV T.Distributed Representations of Sen-tences and Documents[C]//International Conference on Machine Learning.2014:1188-1196.
[22]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Advances in Neural Information Processing Systems.2017:5998-6008.
[23]LIN T,GOYAL P,GIRSHICK R,et al.Dollar Piotr.Focal Loss for Dense Object Detection[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2017,42(2):178-185.
[24]DAVID J,GUILLET F,BRIAND H.Association Rule Ontology Matching Approach[J].In:International Journal on Semantic Web and information systems,2007,3(2):27-49.
[25]ECKERT K,MEILICKE C,STUCKENSCHMIDT H.Impro-ving ontology matching using meta-level learning[C]//Euro-pean Semantic Web Conference.Berlin:Springer,2009:158-172.
[1] 王毅, 李政浩, 陈星.
基于用户场景的Android 应用服务推荐方法
Recommendation of Android Application Services via User Scenarios
计算机科学, 2022, 49(6A): 267-271. https://doi.org/10.11896/jsjkx.210700123
[2] 王省, 康昭.
基于光滑表示的半监督分类算法
Smooth Representation-based Semi-supervised Classification
计算机科学, 2021, 48(3): 124-129. https://doi.org/10.11896/jsjkx.200700078
[3] 陈迎仁, 郭莹楠, 郭享, 倪一涛, 陈星.
基于特征相似度计算的网页包装器自适应
Web Page Wrapper Adaptation Based on Feature Similarity Calculation
计算机科学, 2021, 48(11A): 218-224. https://doi.org/10.11896/jsjkx.210100230
[4] 束云峰, 王中卿.
基于专利结构的中文专利摘要研究
Research on Chinese Patent Summarization Based on Patented Structure
计算机科学, 2020, 47(6A): 45-48. https://doi.org/10.11896/JsJkx.190500028
[5] 钟雅,郭渊博,刘春辉,李涛.
内部威胁检测中用户属性画像方法与应用
User Attributes Profiling Method and Application in Insider Threat Detection
计算机科学, 2020, 47(3): 292-297. https://doi.org/10.11896/jsjkx.190200379
[6] 许飞翔,叶霞,李琳琳,曹军博,王馨.
基于SA-BP算法的本体概念语义相似度综合计算
Comprehensive Calculation of Semantic Similarity of Ontology Concept Based on SA-BP Algorithm
计算机科学, 2020, 47(1): 199-204. https://doi.org/10.11896/jsjkx.181202351
[7] 吴祎凡, 崔艳鹏, 胡建伟.
基于层次聚类的警报处理方法
Alert Processing Method Based on Hierarchical Clustering
计算机科学, 2019, 46(4): 203-209. https://doi.org/10.11896/j.issn.1002-137X.2019.04.032
[8] 卢献华, 王洪俊.
基于大数据计算框架的分布式新闻聚类系统设计
Design of Distributed News Clustering System Based on Big Data Computing Framework
计算机科学, 2019, 46(11A): 220-223.
[9] 程宏兵, 王珂, 李兵, 钱漫匀.
一种高效的社交网络朋友推荐方案
Efficient Friend Recommendation Scheme for Social Networks
计算机科学, 2018, 45(6A): 433-436.
[10] 廖彬,张陶,于炯,国冰磊,刘炎.
基于Spark的MapReduce相似度计算效率优化
Efficiency Optimization Method for MapReduce Similarity Computing Based on Spark
计算机科学, 2017, 44(8): 46-53. https://doi.org/10.11896/j.issn.1002-137X.2017.08.009
[11] 傅城州,汤庸,贺超波,王津凌,袁成哲.
基于标签相似度计算的学术圈构建方法
Construction Method of Academic Circle Based on Label Similarity Computation
计算机科学, 2016, 43(9): 52-56. https://doi.org/10.11896/j.issn.1002-137X.2016.09.009
[12] 余珊珊,苏锦钿,易法令.
基于范畴论的本体描述方法
Descriptions for Ontologies Based on Category Theory
计算机科学, 2016, 43(5): 42-46. https://doi.org/10.11896/j.issn.1002-137X.2016.05.007
[13] 李景玉,张仰森,陈若愚.
面向用户查询意图的句子相似度分层计算
User Query Intention Oriented Hierarchical Sentence Similarity Computation
计算机科学, 2015, 42(1): 227-231. https://doi.org/10.11896/j.issn.1002-137X.2015.01.050
[14] 秦丽,李兵.
一种基于云模型的不确定性数据的建模与分类方法
Novel Method of Uncertain Data Modeling and Classification Based on Cloud Model
计算机科学, 2014, 41(8): 233-240. https://doi.org/10.11896/j.issn.1002-137X.2014.08.050
[15] 贾长云,梁海军.
基于B-ISVM算法的物联网云存储数据伪装不良信息检测
Things Networking Cloud Storage Data Bad Information Detection Based on Boundary-incremental SVM Algorithm
计算机科学, 2013, 40(2): 95-97.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!