2019-6关系抽取综述_谢德鹏

2019-10-10  本文已影响0人  HsuanvaneCHINA

这篇综述文章是发表在知网上的一篇关于知识图谱技术中的关系抽取技术,记得看过一句话,如果要想了解一个新的领域,那么就看文献就要从综述下手,从而了解整个领域的全貌。这里就要根据个人兴趣攻其一点,在读研期间发上1-2篇C刊的论文就好,这段研究生经历也就圆满了。

进入正题。

题目:

关系抽取综述

作者:

谢鹏德,常青

关键词:

关系抽取; 有监督方法; 无监督方法; 半监督方法; 远程监督; 神经网络; 联合抽取;

摘要:

关系抽取任务作为信息抽取的基本组成之一,在很多领域具有十分重要的地位。关系抽取发展至今,总体可以分为基于规则的抽取方式基于统计方式的抽取;之后出现的众多方法大多是以统计为主,辅助以规则。后来引入了包括远程监督深度学习等模式并融合了注意力机制多标签多实例方法

引言:

正文:

1.产生发展:

以上提到的包含关系抽取研究的会议极大地推动了其发展,但是它们所发布的评测语料对于人工标注的依赖性较大。这类语料库耗费大量人力进行手工的模板和规则的编写及训练语料的标注,虽然质量有所保证,却无法提供大规模材料,并且领域适应性和后期扩充性很差。后来包括维基百科、

DBpedia和Freebase等大规模事实知识库出现后,为标注语料提供大量的语料支持,使得开放域关系抽取成为可能,并使其具有在跨领域性和规模性方面的先天优势。

2.研究现状:

3.评价指标:

这套关系抽取工作的最终效果评价体系是在ACE会议上提出,以准确率(precision)、召回率(recall)进行衡量,但是准确率和召回率在一定程度上过于偏重评测抽取的单方面效果,于是引入F值,综合衡量抽取的结果。
三者的计算公式为:


image.png

4.挑战与趋势:

参考文献

[1]刘绍毓.实体关系抽取关键技术研究[D].郑州:解放军信息工程大学, 2015. (Liu Shaoyu. Research on key technologies for entityrelation extraction [D].Zhengzhou: PLA Information EngineeringUniversity, 2015.)
[2]张素香.信息抽取中关键技术的研究[D].北京:北京邮电大学,2007. (Zhang Suxiang. Researchon key technologiesof the informstionextraction [D]. Beijing: Beijing University of Posts andTelecommunications, 2007.)
[3]Doddington G R, Mitchell A, Przybocki M A,et al.Theautomatic content extraction (ACE)program-tasks, data, and evaluation [C]//ProcofLREC. 2004.
[4]Hendrickx I, Kim S N, Kozareva Z,et al.Semeval-2010 task 8:Multi-way classification of semantic relation between pairs of nominal[C]// ProcofKorkshop on Semantic Evaluations: Recent Achievementsand Future Directions. 2009: 94-99.
[5]Kambhatla N. Combining lexical, syntactic, and semantic features with maximum entropy models for extracting relations [C]// ProcofACLonInteractivePoster andDemonstrationSessions.Stroudsburg, PA:Association for Computational Linguistics, 2004: 22-26.
[6]Giuliano C, Lavelli A, Pighin D,et al.FBK-IRST:kernel methods for semantic relation extraction [C]// Procof the 4th InternationalWorkshop on Semantic Evaluations.Stroudsburg, PA:Association for Computational Linguistics, 2007: 141-144.
[7]Tratz S, Hovy E. Isi:automatic classification of relations between nominals using a maximum entropy classifier [C]// Procof the 5thInternational Workshop on Semantic Evaluation.Stroudsburg, PA:Association forComputational Linguistics, 2010: 222-225.
[8]Culotta A, Mccallum A, Betz J.Integrating probabilistic extraction models and data mining to discover relations and patterns in text [C]//ProcofMain Conference on Human Language Technology Conferenceof the North American Chapter of the Association of ComputationalLinguistics.Stroudsburg, PA:Associationfor ComputationalLinguistics, 2006: 296-303.
[9]Zelenko D, Aone C, Richardella A. Kernel methods for relation extraction [J]. Journal of Machine Learning Research, 2003, 3(3):1083-1106.
[10]Zhao Shubin, Grishman R.Extracting relations with integrated information using kernel methods [C]// Procof the 43rdAnnualMeeting onAssociation forComputationalLinguistics.Stroudsburg, PA:Association for ComputationalLinguistics, 2005: 419-426.
[11]Culotta A, Sorensen J. Dependency tree kernels for relation extraction [C]// Procof the 42nd Annual Meeting on Association forComputational Linguistics.Stroudsburg, PA:Association for Computational Linguistics, 2004: 423.
[12]Bunescu R C, Mooney R J. A shortest pathdependency kernel for relation extraction [C]// ProcofConferenceonHumanLanguageTechnology andEmpiricalMethods inNaturalLanguageProcessing.Stroudsburg, PA:Association for Computational Linguistics, 2005:724-731.
[13]Zhang Min, Zhang Jie, Su Jian.Exploring syntactic features for relation extraction using a convolution tree kernel [C]// ProcofMainConference on Human Language Technology Conference of the NorthAmerican Chapter of the Association of Computational Linguistics.Stroudsburg, PA:Association for Computational Linguistics, 2006:288-295.
[14]庄成龙,钱龙华,周国栋.基于树核函数的实体语义关系抽取方法研究[J].中文信息学报, 2009, 23(1): 3-9. (Zhuang Chenglong, QianLonghua, Zhou Guodong. Research ontree kernel based entity semanticrelation extraction [J]. Journal of Chinese Information Processing, 2009,23(1): 3-9. )
[15]Brin S. Extracting patterns and relations from the World Wide Web [J]. Lecture Notes in ComputerScience, 1998, 1590: 172-183.
[16]Agichtein E, Gravano L. Snowball:extracting relations from large plain-text collections [C]//Proc ofACM Conference on DigitalLibraries.New York:ACMPress, 2000: 85-94.
[17]陈锦秀,姬东鸿.基于图的半监督关系抽取[J].软件学报, 2008 (11): 2843-2852. (Chen Jinxiu, Ji Donghong. Graph-basedsemi-supervised relation extraction [J]. Journal of Software,2008(11):2843-2852. )
[18]Hasegawa T, Sekine S, Grishman R. Discovering relations among named entities from large corpora[C]// Procof the 42nd AnnualMeeting on Association for ComputationalStroudsburg, PA:Linguistics.Association for Computational Linguistics, 2004: 415-422.
[19]Shinyama Y, Sekine S. Preemptive information extraction using unrestricted relation discovery [C]// ProcofMainConference onHuman Language Technology Conference of the North AmericanChapter of the Association of Computational Linguistics.Stroudsburg,PA:Association for Computational Linguistics, 2006:304-311.
[20]Hassan H, Hassan A, Emam O, Unsupervised informationextraction approach using graph mutual reinforcement [C]//ProcofConference onEmpirical Methods in Natural Language Processing.2006: 501-508.
[21]Gonzalez E, Turmo J. Unsupervised relation extraction by massive clustering [C]//Proc of the9th IEEE International Conference on DataMining.Piscataway, NJ: IEEE Press,2009: 782-787.
[22]Rozenfeld B, Feldman R. High-performanceunsupervised relation extraction from large corpora [C]//Proc of the6th InternationalConference on Data Mining.Piscataway, NJ: IEEE Press,2006:1032-1037.
[23]Etzioni O, Cafarella M,Downey D,et al.Unsupervised named-entity extraction from theWeb:anexperimental study [J]. Artificialintelligence, 2005, 165(1): 91-134.
[24]Banko M, Cafarella M J, Soderland S,et al.Open information extraction from theWeb [C]//Procof the 20thInternationalJointConference on ArtificalIntelligence.San Francisco, CA:MorganKaufmann Publishers Inc2007: 2670-2676.
[25]Mintz M, Bills S, Snow R,et al.Distant supervision for relation extraction without labeled data [C]// Procofthe 47thJoint ConferenceofAnnual Meetingof the ACL and the 4th International JointConference on Natural Language Processing of the AFNLP.Stroudsburg, PA:Association for Computational Linguistics, 2009:1003-1011.
[26]Surdeanu M, Tibshirani J, Nallapati R,et al.Multi-instance multi-label learning for relation extraction [C]// ProcofJointConference onEmpiricalMethods inNaturalLAnguageProcessing andComputationalNaturalLanguageLearning.Stroudsburg, PA:Association forComputational Linguistics, 2012: 455-465.
[27]Hendrickx I, Kim S N, Kozareva Z,et al.Semeval-2010 task 8: multi-way classification of semantic relations between pairs ofnominals [C]// ProcofWorkshop on Semantic Evaluations: RecentAchievements and Future Directions.Stroudsburg, PA:Association forComputational Linguistics,2009: 94-99.
[28]Socher R, Huval B, Manning CD,et al.Semantic compositionality through recursive matrix-vector spaces [C]// ProcofJoint Conferenceon Empirical Methods in Natural LanguageProcessing andComputational Natural Language Learning.Stroudsburg, PA:Association for Computational Linguistics, 2012: 1201-1211.
[29]Hashimoto K, Stenetorp P, Miwa M,et al.Task-oriented learning of word embeddings for semantic relation classification [C]// Procof the19th Conference on Computational Natural Language Learning. 2015:268-278.
[30]Zeng Daojian, LiuKang, Lai Siwei,et al.Relation classification via convolutional deep neural network [C]// Procofthe 25th InternationalConference on Computational Linguistics. 2014: 2335-2344.
[31]NguyenT H, Grishman R. Relation extraction:perspective from convolutional neural networks [C]// Procof the 1st Workshop on VectorSpace Modeling for Natural Language Processing. 2015: 39-48.
[32]Lin Yankai, Shen Shiqi, Liu Zhiyuan,et al.Neural relation extraction with selective attention over instances [C]//Procof the 54thAnnualMeeting of the Association for Computational Linguistics.2016:2124-2133.
[33]Zhou Peng, Shi Wei, Tian Jun,et al.Attention-based bidirectional long short-term memory networks for relation classification [C]// Procof the54th Annual Meeting of the Association for Computational Linguistics.2016: 207-212.
[34]万静,李浩铭,严欢春,等.基于循环卷积神经网络的关系抽取方法研究[J/OL].计算机应用研究: 1-6[2019-02-22]. http://kns. cnki.net/kcms/detail/51.1196. TP. 20181225. 1615. 003. html.(Wan Jing, LiHaoming, Yan Huanchun,et al.Relation extraction based on recurrentconvolutional neural network [J/OL]. Application Research ofComputers: 1-6(2018-12-26)[2019-02-19]. http://kns. cnki.net/kcms/detail/51. 1196. TP. 20181225. 1615. 003. html. )
[35]Cai Rui, Zhang Xiaodong, Wang Houfeng. Bidirectional recurrent convolutional neural network for relation classification [C]// Procof the54th Annual Meeting of the Association for Computational Linguistics.2016: 756-765.
[36]Lin Yanka, Liu Zhiyuan, Sun Maosong. Neural relation extraction with multi-lingual attention [C]// Procof the 55th Annual Meeting of theAssociation for Computational Linguistics. 2017: 34-43.
[37]Zheng Suncong, Hao Yuexing, Lu Dongyuan,et al.Joint entity and relation extraction based on a hybrid neural network [J].Neurocomputing, 2017, 257(9): 59-66.
[38]Miwa M, Bansal M.End-to-end relation extraction using LSTMs on sequences and tree structures [C]//Procof the 54th Annual Meeting ofthe Association for Computational Linguistics. 2016: 1105-1116.
[39]Li Qi, Ji Heng. Incremental joint extraction of entity mentionsand relations [C]// Procof the 52nd Annual Meeting of the Association forComputational Linguistic. 2014: 402-412.
[40]Zheng Suncong, Wang Feng, Bao Hongyun,et al.Joint extraction of entities and relations based on a noveltagging scheme [C]// Procof the55th Annual Meeting of the Association for Computational Linguistics.2017: 1227-1236.

上一篇 下一篇

猜你喜欢

热点阅读