Joint entity–relation knowledge embedding via cost-sensitive learning

Sheng-kang YU; Xue-yi ZHAO; Xi LI; Zhong-fei ZHANG

doi:10.1631/FITEE.1601255

Your Location：

Home >

Browse articles >

Joint entity–relation knowledge embedding via cost-sensitive learning

Regular Papers | Updated：2022-05-19

- Joint entity–relation knowledge embedding via cost-sensitive learning
- 基于代价敏感学习的实体–关系联合知识嵌入
- Frontiers of Information Technology & Electronic Engineering Vol. 18, Issue 11, Pages: 1867-1873(2017)
- Affiliations：
  
  College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou 310027, China
  College of Computer Science and Technology, Zhejiang University, Hangzhou 310027, China
- Author bio：
  
  [ "Sheng-kang YU, E-mail: shengkangyu@zju.edu.cn" ]
  [ "Xue-yi ZHAO, E-mail: xueyizhao@zju.edu.cn" ]
  [ "Xi LI, E-mail: xilizju@zju.edu.cn" ]
  Zhong-fei ZHANG, E-mail: zhongfei@zju.edu.cn
- Funds：
- DOI：10.1631/FITEE.1601255
  CLC： TP393
- Received：13 May 2016，
  
  Revised：2017-11-22，
  
  Published：2017-11
- Accepted：
Scan QR Code
Sheng-kang YU, Xue-yi ZHAO, Xi LI, et al. Joint entity–relation knowledge embedding via cost-sensitive learning[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(11): 1867-1873.
DOI：

Sheng-kang YU, Xue-yi ZHAO, Xi LI, et al. Joint entity–relation knowledge embedding via cost-sensitive learning[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(11): 1867-1873. DOI： 10.1631/FITEE.1601255.

摘要

我们将实体嵌入问题看作同时完成两个不同但相关的嵌入任务（实体嵌入和关系嵌入）的联合优化问题，并在联合嵌入框架下求解该问题。在该嵌入框架下，我们设计了联合评分函数，用以对实体和关系间的相关性实例进行量化评价，并将评分函数融入最大间隔学习方法中，使用知识库中的上下文信息学习实体与关系的嵌入向量。通过求解联合优化问题，我们的设计有效地表达了嵌入空间的固有拓扑结构。实验结果证实了我们的嵌入框架在表达不同关系的语义相关性和进行知识推理中的关系预测时的有效性。

Abstract

As a joint-optimization problem which simultaneously fulfills two different but correlated embedding tasks (i.e.

entity embedding and relation embedding)

knowledge embedding problem is solved in a joint embedding scheme. In this embedding scheme

we design a joint compatibility scoring function to quantitatively evaluate the relational facts with respect to entities and relations

and further incorporate the scoring function into the maxmargin structure learning process that explicitly learns the embedding vectors of entities and relations using the context information of the knowledge base. By optimizing the joint problem

our design is capable of effectively capturing the intrinsic topological structures in the learned embedding spaces. Experimental results demonstrate the effectiveness of our embedding scheme in characterizing the semantic correlations among different relation units

and in relation prediction for knowledge inference.

关键词

Keywords

references

K. Bollacker , , , C. Evans , , , P. Paritosh , , , 等 . . Freebase: a collaboratively created graph database for structuring human knowledge . . Proc. Int. Conf. on ACM SIGMOD Management of Data , , 2008 . . p.1247 - - 1250 . . DOI: 10.1145/1376616.1376746 http://doi.org/10.1145/1376616.1376746 . .

A. Bordes , , , J. Weston , , , R. Collobert , , , 等 . . Learning structured embeddings of knowledge bases . . Proc. Comput. Sci. , , 2011 . . 108 345 - - 354 . . DOI: 10.1016/j.procs.2017.05.045 http://doi.org/10.1016/j.procs.2017.05.045 . .

A. Bordes , , , N. Usunier , , , A. Garcia-Duran , , , 等 . . Translating embeddings for modeling multi-relational data . . NIPS , , 2013 . . p.2787 - - 2795 . . . .

A. Bordes , , , X. Glorot , , , J. Weston , , , 等 . . A semantic matching energy function for learning with multirelational data . . Mach. Learn. , , 2014 . . 94 ( ( 2 ): ): 233 - - 259 . . DOI: 10.1007/s10994-013-5363-6 http://doi.org/10.1007/s10994-013-5363-6 . .

K.W. Chang , , , W.T. Yih , , , C. Meek . . Multi-relational latent semantic analysis . . Proc. Conf. on Empirical Methods in Natural Language Processing , , 2013 . . p.1602 - - 1612 . . . .

J. Duchi , , , E. Hazan , , , Y. Singer . . Adaptive subgradient methods for online learning and stochastic optimization . . J. Mach. Learn. Res. , , 2011 . . 12 2121 - - 2159 . . . .

A. Elisseeff , , , J. Weston . . A kernel method for multilabelled classification . . NIPS , , 2001 . . p.681 - - 687 . . . .

A. Garc a-Dur n , , , A. Bordes , , , N. Usunier . . Composing Relationships with Translations . . Technical Report No. hal-01167811, CNRS-Heudiasyc, Compiègne , , 2015 . . .

L. Getoor , , , L. Mihalkova . . Learning statistical models from relational data . . Proc. Int. Conf. on ACM SIGMOD Management of Data , , 2011 . . p.1195 - - 1198 . . DOI: 10.1145/1989323.1989451 http://doi.org/10.1145/1989323.1989451 . .

R. Hoffmann , , , C. Zhang , , , X. Ling , , , 等 . . Knowledgebased weak supervision for information extraction of overlapping relations . . Proc. 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies , , 2011 . . p.541 - - 550 . . . .

R. Jenatton , , , N.L. Roux , , , A. Bordes , , , 等 . . A latent factor model for highly multi-relational data . . NIPS , , 2012 . . p.3167 - - 3175 . . . .

Y.K. Lin , , , Z.Y. Liu , , , H.B. Luan , , , 等 . . Modeling relation paths for representation learning of knowledge bases . . arXiv: 1506.00379 , , 2015 . . http://arxiv.org/abs/1506.00379 . .

L.V.D. Maaten , , , G. Hinton . . Visualizing data using t-SNE . . J. Mach. Learn. Res. , , 2008 . . 9 2579 - - 2605 . . . .

G.A. Miller . . WordNet: a lexical database for English . . Commun. ACM , , 1995 . . 38 ( ( 11 ): ): 39 - - 41 . . DOI: 10.1145/219717.219748 http://doi.org/10.1145/219717.219748 . .

M. Nickel , , , V. Tresp , , , H.P. Kriegel . . A three-way model for collective learning on multi-relational data . . Proc. 28th Int. Conf. on Machine Learning , , 2011 . . p.809 - - 816 . . . .

A. Singhal . . Introducing the Knowledge Graph: Things, not Strings. Google , , 2012 . . https://21stcenturylibrary.com/2012/05/21/introducinggoogles-knowledge-graph-things-not-strings https://21stcenturylibrary.com/2012/05/21/introducinggoogles-knowledge-graph-things-not-strings [Accessed on May 21, 2012] . .

R. Socher , , , D. Chen , , , C.D. Manning , , , 等 . . Reasoning with neural tensor networks for knowledge base completion . . NIPS , , 2013 . . p.926 - - 934 . . . .

Z. Wang , , , J.W. Zhang , , , J.L. Feng , , , 等 . . Knowledge graph embedding by translating on hyperplanes . . Proc. 28th Conf. on Artificial Intelligence , , 2014 . . p.1112 - - 1119 . . . .

R. Waters . . Google to unveil search results overhaul . . Financial Times, May , , 2012 . . .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

No data

Related Author

No data

Related Institution

No data

Chat

Address：Zhejiang University Press, 148 Tianmushan Road, Hangzhou, China Postal code：310028
Tel：+86-571-88273162 Email：fitee@zju.edu.cn
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰