知识图谱构建研究综述
(1.江西开放大学,江西 南昌 330046;2.江西飞行学院,江西 南昌 330088)
摘要
知识图谱作为结构化的语义知识库,在信息检索、智能问答和推荐系统等多个领域发挥着关键作用。文章综述了知识图谱构建的三个核心环节:信息抽取、知识融合和知识推理。信息抽取技术从基于规则的方法发展到机器学习模型,再到深度学习模型,目前正朝着减少误差传播和提高准确性的实体关系联合抽取模型方向演进。在知识融合部分,探讨了实体链接和知识合并策略,以及通过实体消歧和实体对齐解决实体识别问题。知识推理部分则分析了基于规则、表示学习和深度学习的推理方法,及其在新知识发现和错误信息纠正中的应用。最后,指出了构建过程中的挑战,并对未来研究方向提出了建议,旨在促进知识图谱研究和应用的发展。
关键词
知识图谱;信息抽取;知识融合;知识推理;深度学习
参考文献
- [1] WU W T,LI H S,WANG H X,et al. Probase: A Probabilistic Taxonomy for Text Understanding [C]//Proceedings of the 2012 ACMSIGMOD International Conference on Management of Data.Scottsdale:ACM,2012:481-492.
- [2] AUER S,BIZER C,KOBILAROV G,et al. DBpedia: A Nucleus for A Web of Open Data [C]//Proceedings of the 6th International The Semantic Web and 2nd Asian Conference on Asian Semantic Web Conference.Busan:ACM,2007:722-735.
- [3] GUPTA S,KENKRE S,TALUKDAR P. CaRe: Open Knowledge Graph Embeddings [C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Hong Kong:ACL,2019:378-388.
- [4] COLLINS M,SINGER Y. Unsupervised Models for Named Entity Classification [C]//Proceedings of the Joint SIGDAT Conference on Empirical Methods in Natural Language Processing and Very Large Corpora.Hong Kong:ACL,1999:100-110.
- [5] 程志刚.基于规则和条件随机场的中文命名实体识别方法研究 [D].武汉:华中师范大学,2015.
- [6] ISOZAKI H,KAZAWA H. Efficient Support Vector Classifiers for Named Entity Recognition [C]//Proceedings of the 19th International Conference on Computational Linguistics.Taipei:ACL,2002,1:1-7.
- [7] 郝乐川.基于条件随机场的音乐领域命名实体识别 [D].哈尔滨:哈尔滨工业大学,2012.
- [8] 徐建忠,朱俊,赵瑞,等.基于CRF算法的航天命名实体识别 [J].电子设计工程,2017,25(20):42-46.
- [9] 周晓辉.基于隐式马尔科夫模型的法律命名实体识别模型的设计与应用 [D].广州:华南理工大学,2018.
- [10] 李世超.基于Hadoop平台和隐马尔可夫模型的生物医学命名实体识别方法研究[D].咸阳:西北农林科技大学,2018.
- [11] 俞鸿魁,张华平,刘群,等.基于层叠隐马尔可夫模型的中文命名实体识别 [J].通信学报,2006,27(2):87-94.
- [12] LI L S,MAO T,HUANG D G,et al. Hybrid Models for Chinese Named Entity Recognition [C]//Proceedings of the Fifth SIGHAN Workshop on Chinese Language Processing.Sydney:ACL,2006,:72-78.
- [13] 周俊生,戴新宇,尹存燕,等.基于层叠条件随机场模型的中文机构名自动识别 [J].电子学报,2006(5):804-809.
- [14] 红霞.基于层叠条件随机场的中文机构名识别的研究 [D].大连:大连理工大学,2010.
- [15] 毛新年,董远,庞文博,等.一种基于条件随机场和最大熵的两阶段识别中文命名实体方法(英文) [C]//第七届中文信息处理国际会议.武汉:电子工业出版社,2007:445-459.
- [16] 陈霄.基于支持向量机的中文组织机构名识别 [D].上海:上海交通大学,2007.
- [17] 黄浩炜.SVM与基于转换的错误驱动学习方法相结合的生物实体识别 [D].长沙:国防科学技术大学,2008.
- [18] 郭喜跃,周琴,陈前军.基于CRF与规则的工程领域命名实体识别方法 [J].软件导刊,2014,13(11):28-30.
- [19] 何炎祥,罗楚威,胡彬尧.基于CRF和规则相结合的地理命名实体识别方法 [J].计算机应用与软件,2015,32(1):179-185+202.
- [20] CHERRY C,GUO H Y. The Unreasonable Effectiveness of Word Representations for Twitter Named Entity Recognition [C]//Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.Denver:ACL,2015:735-745.
- [21] 陈琛,刘小云,方玉华.融合注意力机制的电子病历命名实体识别 [J].计算机技术与发展,2020,30(10):216-220.
- [22] 常君.基于注意力机制的命名实体识别研究 [D].太原:太原理工大学,2022.
- [23] 封红旗,孙杨,杨森,等.基于BERT的中文电子病历命名实体识别 [J].计算机工程与设计,2023,44(4):1220-1227.
- [24] 王为国.基于Bert的命名实体识别研究 [D].广州:广州大学,2021.
- [25] PENG N,DREDZE M. Improving Named Entity Recognition for Chinese Social Media With Word Segmentation Representation Learning [C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics.Berlin:ACL,2016,2:149-155.
- [26] 尹光花,陈鹏.基于双向LSTM模型的中文命名实体识别 [J].信息技术与信息化,2021(10):44-46.
- [27] DONG X S,QIAN L J,GUAN Y,et al. A Multi-Class Classification Method Based on Deep Learning for Named Entity Recognition in Electronic Medical Records [C]//2016 New York Scientific Data Summit.New York:IEEE,2016:1-10.
- [28] 李一斌,张欢欢.基于双向GRU-CRF的中文包装产品实体识别 [J].华东理工大学学报:自然科学版,2019,45(3):486-490.
- [29] 吴超,王汉军.基于GRU的电力调度领域命名实体识别方法 [J].计算机系统应用,2020,29(8):185-191.
- [30] ZHU Y,WANG G. CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition [C]//Proceedings of NAACL-HLT 2019.Minneapolis:ACL,2019:3384-3393.
- [31] 王子牛,姜猛,高建瓴,等.基于BERT的中文命名实体识别方法 [J].计算机科学,2019,46(S2):138-142.
- [32] 张志昌,周侗,张瑞芳,等.融合双向GRU与注意力机制的医疗实体关系识别 [J].计算机工程,2020,46(6):296-302.
- [33] 杨培,杨志豪,罗凌,等.基于注意机制的化学药物命名实体识别 [J].计算机研究与发展,2018,55(7):1548-1556.
- [34] 张浩.基于深度学习的生物医学实体关系抽取算法研究 [D].长春:吉林大学,2020.
- [35] ZHU Y,WANG G. CAN-NER: Convolutional Attention Network for Chinese Named Entity Recognition [C]//Proc of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Minneapolis:ACL,2019:3384-3393.
- [36] GUI T,MA R T,ZHANG Q,et al. CNN-based Chinese NER with Lexicon Rethinking [C]//Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence.Macao:IJCAI,2019:4982-4988.
- [37] 车万翔,刘挺,李生.实体关系自动抽取 [J].中文信息学报,2005,19(2):2-7.
- [38] CULOTTA A,MCCALLUM A,BETZ J. Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text [C]//Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics.New York:ACL,2006:296-303.
- [39] JIANG JING,ZHAI CHENGXIANG. A Systematic Exploration of the Feature Space for Relation Extraction [C]//Proceedings of NAACL HLT 2007.New York:ACL,2007:113-120.
- [40] SUN X,DONG L H. Feature-Based Approach to Chinese Term Relation Extraction [C]//2009 International Conference on Signal Processing Systems.Singapore Piscataway:IEEE,2009:410-414.
- [41] TRATZ S,HOVY E. Isi: Automatic Classification of Relations Between Nominals Using a Maximum Entropy Classifier [C]//Proceedings of the 5th International Workshop on Semantic Evaluation.Los Angeles:ACL,2010:222-225.
- [42] 郭喜跃,何婷婷,胡小华,等.基于句法语义特征的中文实体关系抽取 [J].中文信息学报,2014,28(6):183-189.
- [43] 高俊平,张晖,赵旭剑,等.面向维基百科的领域知识演化关系抽取 [J].计算机学报,2016,39(10):2088-2101.
- [44] 甘丽新,万常选,刘德喜,等.基于句法语义特征的中文实体关系抽取 [J].计算机研究与发展,2016,53(2):284-302.
- [45] ZHANG M,ZHANG J,SU J. Exploring Syntactic Features for Relation Extraction using a Convolution Tree Kernel [C]//Proceedings of the Main Conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics.New York:ACL,288-295.
- [46] ZHOU G D,QIAN L H,FAN J X. Tree Kernel-Based Semantic Relation Extraction with Rich Syntactic and Semantic Information [J].Information Sciences,2010,180(8):1313-1325.
- [47] ZHANG X F,GAO Z Q,ZHU M. Kernel methods and its application in Relation Extraction [C]// 2011 International Conference on Computer Science and Service System (CSSS).Nanjing:IEEE,2011:1362-1365.
- [48] 刘克彬.基于核函数中文关系自动抽取系统的实现 [J].计算机研究与发展,2007,44(8):1406-1411.
- [49] 陈鹏.基于多核融合的中文领域实体关系抽取研究 [D].昆明:昆明理工大学,2014.
- [50] 郭剑毅,陈鹏,余正涛,等.基于多核融合的中文领域实体关系抽取 [J].中文信息学报,2016,30(1):24-29.
- [51] BRIN S. Extracting Patterns and Relations from the World Wide Web [J].Lecture Notes in Computer Science,1998,1590:172-183.
- [52] AGICHTEIN E,GRAVANO L. Snowball: Extracting Relations from Large Plain-Text Collections [C]//Proceedings of the Fifth ACM Conference on Digital libraries.New York:ACM Press,2000:85-94.
- [53] YU L,FENG L,LIU X L. A Bootstrapping Based Approach for Open Geo-entity Relation Extraction [J].Acta Geodaetica et Cartographica Sinica,2016,45(5):616-622.
- [54] HASEGAWA T,SEKINE S,GRISHMAN R. Discovering Relations among Named Entities from Large Corpora [C]//Proceedings of the 42nd Annual Meeting on Association for Computational Linguistics.Barcelona:ACL,2004:415-422.
- [55] DAVIDOV D,RAPPOPORT A,KOPPEL M. Fully Unsupervised Discovery of Concept-Specific Relationships by WebMining [C]//Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics.Proceedings of the 45th Annual Meeting of the Association of Computational Linguistics:ACL,2007:232-239.
- [56] GONZALEZ E,TURMO J. Unsupervised Relation Extraction by Massive Clustering [C]//2009 Ninth IEEE International Conference on Data Mining.Miami:IEEE,2009:782-787.
- [57] YAN Y L,OKAZAKI N,MATSUO Y,et al. Unsupervised Relation Extraction By Mining Wikipedia Texts Using Information from the Web [C]//Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP.Suntec:ACL,2009:1021-1029.
- [58] BOLLEGALA D T,MATSUO Y,ISHIZUKA M. Measuring the Similarity Between Implicit Semantic Relations from the Web [C]//Proceedings of the 18th International Conference on World Wide Web.Madrid:ACM,2009:651-660.
- [59] 王晶.无监督的中文实体关系抽取研究 [D].上海:华东师范大学,2012.
- [60] 孙勇亮.开放领域的中文实体无监督关系抽取 [D].上海:华东师范大学,2014.
- [61] 施琦.无监督中文实体关系抽取研究 [D].北京:中国地质大学(北京),2015.
- [62] ZENG D J,LIU K,LAI S W,et al. Relation Classification via Convolutional Deep Neural Network [C]//Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics.Dublin:DCU & ACL,2014:2335-2344.
- [63] NGUYEN T H,GRISHMAN R. Relation Extraction: Perspective from Convolutional Neural Networks [C]//Proceedings of the 1st Workshop on Vector Space Modeling for Natural Language Processing.Denver,2015:39-48.
- [64] XU K,FENG Y S,HUANG S F,et al. Semantic Relation Classification via Convolutional Neural Networks with Simple Negative Sampling [C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing.Lisbon:ACL,2015:536-540.
- [65] SOCHER R,PENNINGTON J,HUANG E H,et al. Semi-Supervised Recursive Auto Encoders for Predicting Sentiment Distributions [C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.Edinburgh:ACL,2011:151-161.
- [66] HASHIMOTO K, MIWA M,TSURUOKA Y,et al. Simple Customization of Recursive Neural Networks for Semantic Relation Classification [C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing.Seattle:ACL,2013:1372-1376.
- [67] EBRAHIMI J,DOU D. Chain Based RNN for Relation Classification [C]//Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies.Denver:ACL,2015:1244-1249.
- [68] SCHLICHTKRULL M,KIPF T N,BLOEM P,et al. Modeling Relational Data with Graph Convolutional Networks [C]//Proceedings of the European Semantic Web Conference.Heraklion:Springer,2018:593-607.
- [69] GUO Z J,ZHANG Y,LU W. Attention Guided Graph Convolutional Networks for Relation Extraction [C]//Proceedings of the 57th Annual Meeting of the ACL.Florence:ACL,2019:241-251.
- [70] SUN K,ZHANG R CG,MAO Y Y,et al. Relation Extraction with Convolutional Network over Learnable Syntax-Transport Graph [J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(5):8928-8935.
- [71] LI Z H,YANG Z H,SHEN C,et al. Integratingshortest Dependency Path and Sentence Sequence into a Deep Learning Framework for Relation Extraction in Clinical Text [J/OL].BMC Medical Informatics and Decision Making,2019,19(1):1-8[2024-09-10].https://doi.org/10.1186/s12911-019-0736-9.
- [72] 王婷伟.基于Attention与BiLSTM模型的多情感分类方法研究 [D].衡阳:南华大学,2020.
- [73] 徐瑞涓,高建瓴.基于BERT和注意力引导图卷积网络的关系抽取 [J].智能计算机与应用,2023,13(2):204-209.
- [74] 刘燕.基于BERT-BiGRU的中文专利文本自动分类 [J].郑州大学学报:理学版,2023,55(2):33-40.
- [75] MIWA M,BANSAL M. End-to-end Relation Extraction using LSTMs on Sequences and Tree Structures [J/OL]. arXiv:1601.00770 [cs.CL].[2024-08-26].https://doi.org/10.48550/arXiv.1601.00770.
- [76] ZHENG S C,WANG F,BAO H Y,et al. Joint Extraction of Entities and Relations Based on a Novel Tagging Scheme [J/OL].arXiv:1706.05075 [cs.CL].[2024-08-23].https://doi.org/10.48550/arXiv.1706.05075.
- [77] 张军莲,张一帆,汪鸣泉,等.基于图卷积神经网络的中文实体关系联合抽取 [J].计算机工程,2021,47(12):103-111.
- [78] 何怀前.基于深度学习的实体关系联合抽取方法研究与系统实现 [D].上海:东华大学,2023.
- [79] HAN X P,ZHAO J. Named Entity Disambiguation by Leveraging Wikipedia Semantic Knowledge [C]//Proceedings of the 18th ACM Conference on Information and Knowledge Management.Hong Kong:ACM,2009:215-224.
- [80] SHEN W,WANG J Y,LUO P,et al. Linden: Linking Named Entities with Knowledge Base Via Semantic Knowledge [C]//Proceedings of the 21st International Conference on World Wide Web.Lyon:ACM,2012:449-458.
- [81] ZHU G G,IGLESIAS C A. Exploiting Semantic Similarity for Named Entity Disambiguation in Knowledge Graphs [J].Expert Systems with Applications,2018,101:8-24.
- [82] AGARWAL P,STRÖTGEN J,DEL CORRO L,et al. diaNED: Time-Aware Named Entity Disambiguation for Diachronic Corpora [C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.Melbourne:ACL,2018:686-693.
- [83] 石水倩,金晶,沈耕宇,等.基于多元相似度融合的中文命名实体消歧方法 [J].数据分析与知识发现,2024,8(2):56-64.
- [84] 马瑛超,张晓滨.基于主题关系的中文短文本图模型实体消歧 [J].计算机工程与科学,2023,45(1):154-162.
- [85] LI J Z,WANG Z C,ZHANG X,et al. Large Scale Instance Matching Via Multiple Indexes and Candidate Selection [J].Knowledge-Based Systems,2013,50(9):112-120.
- [86] JIN Y,W JI,Y SHI,et al, Meta-path Guided Graph Attention Network for Explainable Herb 5-5Recommendation [J].Health Information Science and Systems,Springer,2023.11(1):5-5.
- [87] 李凤英,黎家鹏.联合三元组嵌入的实体对齐 [J].计算机工程与应用,2023,59(24):70-77.
- [88] 郭浩,李欣奕,唐九阳,等.自适应特征融合的多模态实体对齐研究 [J].自动化学报,2024,50(4):758-770.
- [89] SUCHANEK F M,ABITEBOUL S,SENELLART P. PARIS: Probabilistic Alignment of Relations, Instances, and Schema [J].Proceedings of the VLDB Endowment,2011,5(3):157-168.
- [90] 杨元锋.面向问答的知识图谱推理技术和合并技术研究 [D].哈尔滨:哈尔滨工业大学,2020.
- [91] 周利琴.面向智慧健康的多源异构知识融合研究 [D]. 武汉:武汉大学,2022.
- [92] SCHOENMACKERS S,DAVIS J,ETZIONI O,et al. Learning First Order Horn Clauses from Web Text [C]//Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing.Cambridge:ACL,2010:1088-1098.
- [93] 杨洁.基于本体的柑橘病虫害知识建模及推理研究 [D].武汉:华中师范大学,2014.
- [94] NICKEL M,TRESP V,KRIEGEL H P. A Three-Way Model for Collective Learning on Multi-Relational Data [C]//The 28th International Conference on Machine Learning The International Conference on Machine Learning. Bellevue:Omnipress,2011:809-816.
- [95] 陈德华,殷苏娜,乐嘉锦,等.一种面向临床领域时序知识图谱的链接预测模型 [J].计算机研究与发展,2017,54(12):2687-2697.
- [96] ZHANG S,TAY Y,YAO L N,et al. Quaternion Knowledge Graph Embeddings [C]//Thirty-third Conference on Neural Information Processing Systems.Vancouver:Curran Associates Inc,2019:2735-2745.
- [97] NGUYEN D Q,VU T,NGUYEN T D,et al. A Capsule Network-based Embedding Model for Knowledge Graph Completion and Search Personalization [J/OL].arXiv:1808.04122 [cs.CL].[2024-08-10].https://doi.org/10.48550/arXiv.1808.04122.
- [98] WANG H,LI S Y,PAN R,et al. Incorporating Graph Attention Mechanism into Knowledge Graph Reasoning Based on Deep Reinforcement Learning [C]//2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP).Hong Kong:ACL,2019:2623-2631.
- [99] VASHISHTH S,SANYAL S,NITIN V,et al. InteractE: Improving Convolution-Based Knowledge Graph Embeddings by Increasing Feature Interactions [C]//Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence.New York:AAAI Press,2020,34(3):3009-3016.
- [100] WANG Y Z,WANG H Z,HE J W,et al. TAGAT: Type-Aware Graph Attention Networks for Reasoning Over Knowledge Graphs [J/OL].Knowledge-Based Systems,2021,233:107500[2024-08-05].https://doi.org/10.1016/j.knosys.2021.107500.
- [101] KEZHI L,KUO Y,HAILONG S,et al. SympGAN: A Systematic Knowledge Integration System for Symptom-Gene Associations Network [J/OL].Knowledge-Based Systems,2023,276:110752[2024-08-03].https://doi.org/10.1016/j.knosys.2023.110752.
基金项目
江西省教育厅科技项目(GJJ215702);江西飞行学院校级系列科学研究项目(2024YB01)
作者简介
杨延云(1995.04—),女,汉族,河北张家口人,助教,硕士研究生,研究方向:自然语言处理、数据挖掘、软件开发;胡军(1996.09—),男,汉族,江西抚州人,助教,硕士研究生,研究方向:数据挖掘。