融合实体类型信息的本体-实例联合学习方法

doi:10.19678/j.issn.1000-3428.0062113

计算机工程 ›› 2022, Vol. 48 ›› Issue (7): 82-88. doi: 10.19678/j.issn.1000-3428.0062113

融合实体类型信息的本体-实例联合学习方法

游乐圻, 裴忠民, 罗章凯

航天工程大学复杂电子系统仿真重点实验室, 北京 101416

收稿日期:2021-07-19 修回日期:2021-09-07 出版日期:2022-07-15 发布日期:2021-09-10
作者简介:游乐圻(1997—),男,硕士研究生,主研方向为人工智能、系统科学;裴忠民(通信作者),副研究员、博士;罗章凯,助理研究员、博士。
基金资助:
国防科技重点实验室基础研究项目（DXZT-JC-ZZ-2018-007）。

Ontology-Instances Joint Learning Method Fusing Entity Type Information

YOU Leqi, PEI Zhongmin, LUO Zhangkai

Key Laboratory of Complex Electronic System Simulation, Space Engineering University, Beijing 101416, China

Received:2021-07-19 Revised:2021-09-07 Online:2022-07-15 Published:2021-09-10

摘要/Abstract

摘要： 对表示知识图谱的本体图和实例图进行联合学习能够提高嵌入学习效率，但不能区别表示实体在不同场景下的不同意义。在嵌入时考虑三元组中实体的关系类型特征，提出一种融合实体类型信息的本体-实例联合学习方法JOIE-TKRL-CT，达到在联合学习中表示多义实体、提高知识图谱嵌入学习效率的目的。在视图内部关系表示上，利用实体分层类型模型融入实体类型信息，在两个独立的嵌入空间中分别表征学习；在视图间关系表示上，将表征在两个独立空间的本体和实例通过非线性映射的方法跨视图链接。基于YAGO26K-906和DB111K-174数据集的实验结果表明，JOIE-TKRL-CT能够准确捕获知识图谱的实体类型信息，提高联合学习模型性能，与TransE、HolE、DisMult等基线模型相比，其在实例三元组补全和实体分类任务上均获得最优性能，具有较好的知识学习效果。

关键词: 联合学习, 实体多义性, 跨视图转换, 分层类型模型, 三元组补全, 实体分类

Abstract: The joint learning of the ontology graph and the instance graph that represent the knowledge graph can effectively improve the efficiency of embedded learning, but it cannot represent the ambiguity of entities in different scenarios.In this regard, this paper integrates the relationship type characteristics of the entities in the triples when embedding, and proposes an ontology-instances joint learning mothed, JOIE-TKRL-CT, that fuses entity type information to achieve the goals of representing polysemous entities in joint learning and improving the efficiency of knowledge map embedded learning.This method expresses the relationship within the view, integrates the entity type information based on the entity hierarchical type model, and characterizes learning in two independent embedding spaces.Meanwhile, it expresses the relationship between the views, passes the ontology and instance represented in the two independent spaces, and uses non-linear mapping methods for cross-view linking.Multi-group comparison experiments are performed on the YAGO26K-906 and DB111K-174 data sets, and the results show that JOIE-TKRL-CT can accurately capture the hierarchical type information of the knowledge graph and improve the performance of the joint learning model.Compared with baseline models such as TransE, HolE, and DisMult, this model achieves the best performance in instance triple complement and entity classification tasks, and has a better knowledge learning effect.

Key words: joint learning, entity polysemy, cross-view transformation, hierarchical type model, triple completion, entity classification

中图分类号:

TP18

游乐圻, 裴忠民, 罗章凯. 融合实体类型信息的本体-实例联合学习方法[J]. 计算机工程, 2022, 48(7): 82-88.

YOU Leqi, PEI Zhongmin, LUO Zhangkai. Ontology-Instances Joint Learning Method Fusing Entity Type Information[J]. Computer Engineering, 2022, 48(7): 82-88.

http://www.ecice06.com/CN/Y2022/V48/I7/82

图/表 10

20220808084335

20220808084338

20220808084343

20220808084346

20220808084350

20220808084354

20220808084357

20220808084401

20220808084405

20220808084409

参考文献

[1] ADAMS T.Google and the future of search:amit singhal and the knowledge graph[EB/OL].[2021-04-10].https://www.mendeley.com/catalogue/a2ceb8b0-2e58-31cb-ae6a-09f3e89a8b88/.
[2] HE H, BALAKRISHNAN A, ERIC M, et al.Learning symmetric collaborative dialogue agents with dynamic knowledge graph embeddings[EB/OL].[2021-04-10].https://arxiv.org/abs/1704.07130.
[3] BORDES A, WESTON J, USUNIER N.Open question answering with weakly supervised embedding models[M]//CALDERS T, ESPOSITO F, HÜLLERMEIER E, et al.Machine learning and knowledge discovery in databases.Berlin, Germany:Springer, 2014:165-180.
[4] 陶天一, 王清钦, 付聿炜, 等.基于知识图谱的金融新闻个性化推荐算法[J].计算机工程, 2021, 47(6):98-103, 114. TAO T Y, WANG Q Q, FU Y W, et al.Personalized recommendation algorithm for financial news based on knowledge graph[J].Computer Engineering, 2021, 47(6):98-103, 114.(in Chinese)
[5] 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.
[6] LUONG T, SOCHER R, MANNING C D.Better word representations with recursive neural networks for morphology[2021-04-10].https://www.researchgate.net/publication/270878536_Better_Word_Representations_with_Recursive_Neural_Networks_for_Morphology.
[7] REISINGER J, MOONEY R.Multi-prototype vector-space models of word meaning[C]//Proceedings of 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics.[S.l.]:Association for Computational Linguistics, 2010:109-117.
[8] SPEER R, CHIN J, HAVASI C.ConceptNet 5.5:an open multilingual graph of general knowledge[EB/OL].[2021-04-10].https://arxiv.org/pdf/1612.03975.pdf.
[9] HAO J H, CHEN M H, YU W C, et al.Universal representation learning of knowledge bases by jointly embedding instances and ontological concepts[EB/OL].[2021-04-10].https://arxiv.org/abs/2103.08115.
[10] BORDES A, USUNIER N, GARCIA-DURAN A, et al.Translating embeddings for modeling multi-relational data[M]//GLEN D T, SUZANNA B, ZOUBIN G.Advances in neural information processing systems.Berlin, Germany:Springer, 2013:2787-2795.
[11] WANG Z, ZHANG J W, FENG J L, et al.Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the 28th AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press, 2014:1112-1119.
[12] LIN Y K, LIU Z Y, SUN M S, et al.Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the 29th AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press, 2015:2181-2187.
[13] JI G, HE S, XU L, 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 (Volume 1:Long Papers).[S.l.]:Association for Computational Linguistics, 2015:687-696.
[14] JI G, LIU K, HE S, et al.Knowledge graph completion with adaptive sparse transfer matrix[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press, 2016:1-10.
[15] HE S Z, LIU K, JI G L, et al.Learning to represent knowledge graphs with Gaussian embedding[C]//Proceedings of the 24th ACM International on Conference on Information and Knowledge Management.New York, USA:ACM Press, 2015:623-632.
[16] YANG B S, YIH W T, HE X D, et al.Embedding entities and relations for learning and inference in knowledge bases[EB/OL].[2021-04-10].https://arxiv.org/abs/1412.6575.
[17] TROUILLON T, NICKEL M.Complex and holographic embeddings of knowledge graphs:a comparison[EB/OL].[2021-04-10].https://arxiv.org/abs/1707.01475.
[18] CHEN M H, TIAN Y T, CHEN X L, et al.On2Vec:embedding-based relation prediction for ontology population[EB/OL].[2021-04-10].https://arxiv.org/abs/1809.02382.
[19] LÜ X, HOU L, LI J Z, et al.Differentiating concepts and instances for knowledge graph embedding[EB/OL].[2021-04-10].https://arxiv.org/abs/1811.04588.
[20] KROMPA D, BAIER S, TRESP V.Type-constrained representation learning in knowledge graphs[C]//Proceedings of SWC'15.Berlin, Gerany:Springer, 2015:640-655.
[21] SHU G, QUAN W, WANG B, et al.Semantically Smooth knowledge graph embedding[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1:Long Papers).[S.l.]:Association for Computational Linguistics, 2015:1-10.
[22] FORSYTH D.Representation learning[J].Computer, 2015, 48(4):6.
[23] 张晓明, 孙维雅, 王会勇.基于知识表示学习的知识可信度评估[J].计算机工程, 2021, 47(7):44-54. ZHANG X M, SUN W Y, WANG H Y.Evaluation of knowledge credibility based on knowledge representation learning[J].Computer Engineering, 2021, 47(7):44-54.(in Chinese)
[24] BORDES A, WESTON J, COLLOBERT R, et al.Learning structured embeddings of knowledge bases[C]//Proceedings of the 25th AAAI Conference on Artificial Intelligence.[S.l.]:AAAI Press, 2011:301-306.

选择文件类型/文献管理软件名称

选择包含的内容

融合实体类型信息的本体-实例联合学习方法

Ontology-Instances Joint Learning Method Fusing Entity Type Information

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	詹飞, 朱艳辉, 梁文桐, 张旭, 欧阳康, 孔令巍, 黄雅淋. 基于多任务学习的短文本实体链接方法[J]. 计算机工程, 2022, 48(3): 315-320.
[2]	董亚超, 刘宏哲, 徐成. 基于显著性多尺度特征协作融合的行人重识别方法[J]. 计算机工程, 2021, 47(6): 234-244,252.
[3]	陶洋, 鲍灵浪, 胡昊. 结合表示学习与嵌入子空间学习的降维方法[J]. 计算机工程, 2021, 47(6): 83-87,97.
[4]	徐龙壮, 彭力, 朱凤增. 多任务金字塔重叠匹配的行人重识别方法[J]. 计算机工程, 2021, 47(1): 239-245,254.
[5]	李薇,肖仰华,汪卫. 基于中文知识图谱的人物实体识别[J]. 计算机工程, 2017, 43(3): 225-231,240.

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

融合实体类型信息的本体-实例联合学习方法

Ontology-Instances Joint Learning Method Fusing Entity Type Information

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献

相关文章 5

编辑推荐

Metrics

本文评价