深度学习实体关系抽取研究综述
|
摘要
实体关系抽取作为信息抽取、自然语言理解、信息检索等领域的核心任务和重要环节,能够从文本中抽取实体对间的语义关系.近年来,深度学习在联合学习、远程监督等方面上的应用,使关系抽取任务取得了较为丰富的研究成果.目前,基于深度学习的实体关系抽取技术,在特征提取的深度和模型的精确度上已经逐渐超过了传统基于特征和核函数的方法.围绕有监督和远程监督两个领域,系统总结了近几年来中外学者基于深度学习的实体关系抽取研究进展,并对未来可能的研究方向进行了探讨和展望.
Entity relation extraction is a core task and an important part in the fields of information extraction, natural language understanding, and information retrieval. It can extract the semantic relationships between entity pairs from the texts. In recent years, the application of deep learning in the fields of joint learning, remote supervision has resulted in relatively abundant research results in relation extraction tasks. At present, entity relationship extraction technology based on deep learning has gradually exceeded the traditional methods which are based on features and kernel functions in terms of the depth of feature extraction and the accuracy. This paper focuses on the two fields of supervision and remote supervision. It systematically summarizes the research progress of Chinese and overseas scholars' deep relationship-based entity relationship extraction in recent years, and discusses and prospects future possible research directions as well.
Entity relation extraction is a core task and an important part in the fields of information extraction, natural language understanding, and information retrieval. It can extract the semantic relationships between entity pairs from the texts. In recent years, the application of deep learning in the fields of joint learning, remote supervision has resulted in relatively abundant research results in relation extraction tasks. At present, entity relationship extraction technology based on deep learning has gradually exceeded the traditional methods which are based on features and kernel functions in terms of the depth of feature extraction and the accuracy. This paper focuses on the two fields of supervision and remote supervision. It systematically summarizes the research progress of Chinese and overseas scholars' deep relationship-based entity relationship extraction in recent years, and discusses and prospects future possible research directions as well.
引文
[1]Golshan PN,Dashti HR,Azizi S.A study of recent contributions on information extraction.arXiv preprint arXiv:1803.05667,2018.
[2]Xu J,Zhang ZX,Wu ZX.Review on techniques of entity relation extraction.New Technology of Library and Information Service,2008,24(8):18-23(in Chinese with English abstract).
[3]Gan LX,Wan CX,Liu DX,Zhong Q,Jiang TJ.Chinese entity relationship extraction based on syntactic and semantic features.Journal of Computer Research and Development,2016,53(2):284-302(in Chinese with English abstract).
[4]Liu Q,Li Y,Duan H,Liu Y,Qin ZG.A survey of knowledge mapping construction techniques.Journal of Computer Research and Development,2016,53(3):582-600(in Chinese with English abstract).
[5]Ye H,Chao W,Luo Z,Li Z.Jointly extracting relations with class ties via effective deep ranking.arXiv:preprint arXiv:1612.07602,2016.
[6]Guo XY,He TT,Hu XH,Chen QJ.Chinese entity relationship extraction based on syntactic and semantic features.Journal of Chinese Information Processing,2014,28(6):183-189(in Chinese with English abstract).
[7]Kumar S.A survey of deep learning methods for relation extraction.arXiv:arXiv preprint arXiv:1705.03645,2017.
[8]Surdeanu M,Tibshirani J,Nallapati R,Manning CD.Multi-instance multi-label learning for relation extraction.In:Proc.of the Joint Conf.on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.2012.455-465.
[9]Zheng S,Hao Y,Lu D,Bao H,Xu J,Hao H,Xu B.Joint entity and relation extraction based on a hybrid neural network.Neurocomputing,2017,257:1-8.
[10]Lin Y,Shen S,Liu Z,Luan H,Sun M.Neural relation extraction with selective attention over instances.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.2124-2133.
[11]Xu Y,Mou LL,Li G,Chen YC,Peng H,Jin Z.Classifying relation via long short term memory networks along shortest dependency paths.Conf.on Empirical Methods in Natural Language Processing,2015,42(1):56-61.
[12]Miwa M,Bansal M.End-to-end relation extraction using LSTMs on sequences and tree structures.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.1105-1116.
[13]Katiyar A,Cardie C.Going out on a limb:Joint extraction of entity mentions and relations without dependency trees.In:Proc.of the Meeting of the Association for Computational Linguistics.2017.917-928.
[14]Mintz M,Bills S,Snow R,Jurafsky D.Distant supervision for relation extraction without labeled data.In:Proc.of the Joint Conf.of the Meeting of the ACL and the Int’l Joint Conf.on Natural Language Processing of the Afnlp.2009.1003-1011.
[15]Yu XK,Chen L,Guo J,Cai YY,Wu Y,Wang JC.Relationship extraction method combining clause-level remote supervision and semi-supervised integration learning.Pattern Recognition and Artificial Intelligence,2017,30(1):54-63(in Chinese with English abstract).
[16]Yao L,Riedel S,Mccallum A.Unsupervised relation discovery with sense disambiguation.In:Proc.of the Annual Meeting of the Association for Computational Linguistics.2012.
[17]Qin L,Zhang Z,Zhao H,Hu Z,Xing EP.Adversarial connective-exploiting networks for implicit discourse relation classification.2017.1006-1017.https://arxiv.org/abs/1704.00217
[18]Zhang D,Wang D.Relation classification via recurrent neural network.arXiv preprint arXiv:1508.01006,2015.
[19]Hashimoto K,Miwa M,Tsuruoka Y,Chikayama T.Simple customization of recursive neural networks for semantic relation classification.In:Proc.of the 2013 Conf.on Empirical Methods in Natural Language Processing.2013.18-21.
[20]Zeng D,Liu K,Lai S,Zhou G,Zhao J.Relation classification via convolutional deep neural network.In:Proc.of the 25th Int’l Conf.on Computational Linguistics:Technical Papers(COLING 2014).2014.2335-2344.
[21]Santos CND,Xiang B,Zhou B.Classifying relations by ranking with convolutional neural networks.Computer Science,2015,86:132-137.
[22]Nguyen TH,Grishman R.Combining neural networks and log-linear models to improve relation extraction.arXiv preprint arXiv:1511.05926,2015.
[23]Miyato T,Dai AM,Goodfellow I.Adversarial training methods for semi-supervised text classification.arXiv preprint arXiv:1605.07725,2016.
[24]Wu Y,Bamman D,Russell S.Adversarial training for relation extraction.In:Proc.of the Conf.on Empirical Methods in Natural Language Processing.2017.1778-1783.
[25]He Z,Chen W,Li Z,Zhang M,Zhang W,Zhang M.SEE:Syntax-aware entity embedding for neural relation extraction.arXiv preprint arXiv:1801.03603,2018.
[26]Chikka VR,Karlapalem K.A hybrid deep learning approach for medical relation extraction.arXiv preprint arXiv:1806.11189,2018.
[27]Wen J,Sun X,Ren X,Su Q.Structure regularized neural network for entity relation classification for chinese literature text.arXiv preprint arXiv:1803.05662,2018.
[28]Adilova L,Giesselbach S,Rüping S.Making efficient use of a domain expert’s time in relation extraction.arXiv preprint arXiv:180704687,2018.
[29]Zhou GD,Su J,Zhang J,Zhang M.Exploring various knowledge in relation extraction.In:Proc.of the Conf.on Meeting of the Association for Computational Linguistics(ACL 2005).University of Michigan,2002.419-444.
[30]Huang X,You HL,Yu Y.A Survey of Research on Relationship Extraction Technology.New Technology of Library and Information Service,2013,29(11):30-39(in Chinese with English abstract).
[31]Liu JW,Liu Y,Luo XL.Semi-supervised Learning Method.Chinese Journal of Computers,2015,38(8):1592-1617(in Chinese with English abstract).
[32]Brin S.Extracting patterns and relations from the World Wide Web.In:Proc.of the Int’l Workshop on the World Wide Web and Databases.1998.172-183.
[33]Kumlien MCJ.Constructing viological knowledge bases by extraction information from text sources.In:Proc.of the 7th Int’l Conf.on Intelligent Systems for Molecular Biology.AAAI Press,1999.77-86.
[34]Hasegawa T,Sekine S,Grishman R.Discovering relations among named entities from large corpora.In:Proc.of the Meeting on Association for Computational Linguistics.2004.415.
[35]Jiao LC,Yang SY,Liu F,Wang SG,Feng ZX.Neural Network Seventy Years:Retrospect and Prospect.Chinese Journal of Computers,2016,39(8):1697-1716(in Chinese with English abstract).
[36]Zhou FY,Jin LP,Dong J.A survey of Convolutional Neural Networks.Chinese Journal of Computers,2017,40(6):1229-1251(in Chinese with English abstract).
[37]Zeng D,Liu K,Chen Y,Zhao J.Distant supervision for relation extraction via piecewise convolutional neural networks.In:Proc.of the Conf.on Empirical Methods in Natural Language Processing.2015.1753-1762.
[38]Ji GL,Liu K,He SZ,Zhao J.Distant supervision for relation extraction with sentence-level attention and entity descriptions.In:Proc.of the AAAI.2017.3060-3066.
[39]Ren X,Wu Z,He W,Qu M,Voss CR,Ji H,Abdelzaher TF,Han JW.CoType:Joint extraction of typed entities and relations with knowledge bases.2016.1015-1024.https://arxiv.org/abs/1610.08763
[40]Huang YY,Wang WY.Deep residual learning for weakly-supervised relation extraction.arXiv preprint arXiv:1707.08866,2017.
[41]Golshan PN,Dashti HAR,Azizi S,Safari L.A study of recent contributions on information extraction.arXiv preprint arXiv:1803.05667,2018.
[42]Wang LY.Entity relationship extraction based on deep convolutional neural network[MS.Thesis].Taiyuan:Taiyuan University of Technology,2017(in Chinese).
[43]Yang JF,Yu QB,Guan Y,Jiang ZP.A survey of research on electronic medical record named entity recognition and entity relationship extraction.Acta Automatica Sinica,2014,40(8):1537-1562(in Chinese with English abstract).
[44]Qin B,Liu AA,Liu T.Unguided Chinese open entity relationship extraction.Journal of Computer Research and Development,2015,52(5):1029-1035(in Chinese with English abstract).
[45]Chinchor N,Marsch E.MUC-7 information extraction task definition.In:Proc.of the 7th Message Understanding Conf.Appendices,1998.359-367.
[46]Socher R,Huval B,Manning CD,Ng AY.Semantic compositionality through recursive matrix-vector spaces.In:Proc.of the Joint Conf.on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.2012.1201-1211.
[47]Xu K,Feng Y,Huang S,Zhao D.Semantic relation classification via convolutional neural networks with simple negative sampling.Computer Science,2015,71:941-949.
[48]Vu NT,Adel H,Gupta P,Schütze H.Combining recurrent and convolutional neural networks for relation classification.arXiv preprint arXiv:1605.07333,2016.
[49]Wang L,Cao Z,Melo GD,Liu Z.Relation classification via multi-level attention CNNs.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.1298-1307.
[50]Li F,Zhang M,Fu G,Qian T,Ji D.A Bi-LSTM-RNN model for relation classification using low-cost sequence features.arXiv preprint arXiv:1608.07720,2016.
[51]Cai R,Zhang X,Wang H.Bidirectional recurrent convolutional neural network for relation classification.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.756-765.
[52]Zheng S,Xu J,Bao H,Qi Z,Zhang J,Hao H,Xu B.Joint learning of entity semantics and relation pattern for relation extraction.In:Proc.of the Joint European Conf.on Machine Learning and Knowledge Discovery in Databases.Cham:Springer-Verlag,2016.443-458.
[53]Li F,Zhang M,Fu G,Ji D.A neural joint model for extracting bacteria and their locations.In:Proc.of the Pacific-Asia Conf.on Knowledge Discovery and Data Mining.Cham:Springer-Verlag,2017.15-26.
[54]Katiyar A,Cardie C.Investigating LSTMs for joint extraction of opinion entities and relations.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.919-929.
[55]Zheng S,Wang F,Bao H,Hao Y,Zhou P,Xu B.Joint extraction of entities and relations based on a novel tagging scheme.2017.1227-1236.https://arxiv.org/abs/1706.05075
[56]Fei L,Zhang M,Fu G,Ji D.A neural joint model for entity and relation extraction from biomedical text.Bmc Bioinformatics.2017,18:198.
[57]He D,Zhang H,Hao W,Zhang R,Chen G,Jin D,Cheng K.Distant supervised relation extraction via long short term memory networks with sentence embedding.Intelligent Data Analysis,2017,21:1213-1231.
[58]Riedel S,Yao L,Mccallum A.Modeling relations and their mentions without labeled text.In:Proc.of the European Conf.on Machine Learning and Knowledge Discovery in Databases.2010.148-163.
[59]Liu Q,Zhai JW,Zhang ZC,Zhong S,Zhou Q,Zhang P,Xu J.An overview of deep reinforcement learning.Chinese Journal of Computers,2018,41(1):1-27(in Chinese with English abstract).
[60]Feng Y,Zhang H,Hao W,Chen G.Joint extraction of entities and relations using reinforcement learning and deep learning.In:Proc.of the Comput Intell Neurosci.2017.1-11.
[61]Qin P,Xu W,Wang WY.Robust distant supervision relation extraction via deep reinforcement learning.arXiv preprint arXiv:1805.09927,2018.
[62]Goodfellow IJ,Pouget-Abadie J,Mirza M,Xu B,Warde-Farley D,Ozair S,Courville A,Bengio Y.Generative adversarial networks.Advances in Neural Information Processing Systems,2014,3:2672-2680.
[63]Miyato T,Dai AM,Goodfellow I.Adversarial training methods for semi-supervised text classification.2016.https://arxiv.org/abs/1605.07725
[64]Qin P,Xu W,Wang WY.DSGAN:Generative adversarial training for distant supervision relation extraction.arXiv preprint arXiv:1805.09929,2018.
[65]Nickel M,Murphy K,Tresp V,Gabrilovich E.A review of relational machine learning for knowledge graphs.Proc.of the IEEE,2015,104:11-33.
[66]Grainger T,Aljadda K,Korayem M,Smith A.The semantic knowledge graph:A compact,auto-generated model for real-time traversal and ranking of any relationship within a domain.2016.420-429.https://arxiv.org/abs/1609.00464
[67]Sahu SK,Anand A,Oruganty K,Gattu M.Relation extraction from clinical texts using domain invariant convolutional neural network.In:Proc.of the 15th Workshop on Biomedical Natural Language Processing,2016.206-215.
[68]Gu J,Sun F,Qian L,Zhou G.Chemical-induced disease relation extraction via convolutional neural network.In:Proc.of the Database 2017.[doi:10.1093/database/bax024]
[69]Ramamoorthy S,Murugan S.An attentive sequence model for adverse drug event extraction from biomedical text.arXiv preprint arXiv:1801.00625,2018.
[70]Peng Y,Rios A,Kavuluru R,Lu Z.Chemical-protein relation extraction with ensembles of SVM,CNN,and RNN models.arXiv preprint arXiv:1802.01255,2018.
[71]Nguyen DQ,Verspoor K.Convolutional neural networks for chemical-disease relation extraction are improved with characterbased word embeddings.arXiv preprint arXiv:1805.10586,2018.
[72]Feng X,Guo J,Qin B,Liu T,Liu Y.Effective deep memory networks for distant supervised relation extraction.In:Proc.of the26th Int’l Joint Conf.on Artificial Intelligence.2017.4002-4008.
[73]Liu T,Wang K,Chang B,Sui Z.A soft-label method for noise-tolerant distantly supervised relation extraction.In:Proc.of the Conf.on Empirical Methods in Natural Language Processing.2017.1790-1795.
[74]Han X,Liu ZY,Sun M.Neural knowledge acquisition via mutual attention between knowledge graph and text.In:Proc.of the AAAI.2018.
[75]Feng J,Huang M,Zhao L,Yang Y,Zhu XY.Reinforcement learning for relation classification from noisy data.In:Proc.of the AAAI.2018.
[76]Jiang X,Wang Q,Li P,Wang B.Relation extraction with multi-instance multi-label convolutional neural networks.In:Proc.of the COLING.2016.1471-1480.
[77]Chang YC,Zhang YX,Wang H,Wan HY,Xiao CJ.Features oriented survey of state-of-the-art keyphrase extraction algorithms.Ruan Jian Xue Bao/Journal of Software,2018,29(7):2046-2070(in Chinese with English abstract).http://www.jos.org.cn/1000-9825/5538.htm[doi:10.13328/j.cnki.jos.005538]
[78]Peng N,Poon H,Quirk C,Toutanova K,Yih WT.Cross-sentence N-ary relation extraction with graph LSTMs.arXiv preprint arXiv:1708.03743,2017.
[79]Li MY,Yang J.Open chinese entity relationship extraction method based on dependency parsing.Computer Engineering,2016,42(6):201-207(in Chinese with English abstract).
[2]徐健,张智雄,吴振新.实体关系抽取的技术方法综述.现代图书情报技术,2008,24(8):18-23.
[3]甘丽新,万常选,刘德喜,钟青,江腾蛟.基于句法语义特征的中文实体关系抽取.计算机研究与发展,2016,53(2):284-302.
[4]刘峤,李杨,段宏,刘瑶,秦志光.知识图谱构建技术综述.计算机研究与发展,2016,53(3):582-600.
[6]郭喜跃,何婷婷,胡小华,陈前军.基于句法语义特征的中文实体关系抽取.中文信息学报,2014,28(6):183-189.
[15]余小康,陈岭,郭敬,蔡雅雅,吴勇,王敬昌.结合从句级远程监督与半监督集成学习的关系抽取方法.模式识别与人工智能,2017,30(1):54-63.
[30]黄勋,游宏梁,于洋.关系抽取技术研究综述.现代图书情报技术,2013,29(11):30-39.
[31]刘建伟,刘媛,罗雄麟.半监督学习方法.计算机学报,2015,38(8):1592-1617.
[35]焦李成,杨淑媛,刘芳,王士刚,冯志玺.神经网络七十年:回顾与展望.计算机学报,2016,39(8):1697-1716.
[36]周飞燕,金林鹏,董军.卷积神经网络研究综述.计算机学报,2017,40(6):1229-1251.
[42]王林玉.基于深度卷积神经网络的实体关系抽取[硕士学位论文].太原:太原理工大学,2017.
[43]杨锦锋,于秋滨,关毅,蒋志鹏.电子病历命名实体识别和实体关系抽取研究综述.自动化学报,2014,40(8):1537-1562.
[44]秦兵,刘安安,刘挺.无指导的中文开放式实体关系抽取.计算机研究与发展,2015,52(5):1029-1035.
[59]刘全,翟建伟,章宗长,钟珊,周倩,章鹏,徐进.深度强化学习综述.计算机学报,2018,41(1):1-27.
[77]常耀成,张宇翔,王红,万怀宇,肖春景.特征驱动的关键词提取算法综述.软件学报,2018,29(7):2046-2070.http://www.jos.org.cn/1000-9825/5538.htm[doi:10.13328/j.cnki.jos.005538]
[79]李明耀,杨静.基于依存分析的开放式中文实体关系抽取方法.计算机工程,2016,42(6):201-207.
[2]Xu J,Zhang ZX,Wu ZX.Review on techniques of entity relation extraction.New Technology of Library and Information Service,2008,24(8):18-23(in Chinese with English abstract).
[3]Gan LX,Wan CX,Liu DX,Zhong Q,Jiang TJ.Chinese entity relationship extraction based on syntactic and semantic features.Journal of Computer Research and Development,2016,53(2):284-302(in Chinese with English abstract).
[4]Liu Q,Li Y,Duan H,Liu Y,Qin ZG.A survey of knowledge mapping construction techniques.Journal of Computer Research and Development,2016,53(3):582-600(in Chinese with English abstract).
[5]Ye H,Chao W,Luo Z,Li Z.Jointly extracting relations with class ties via effective deep ranking.arXiv:preprint arXiv:1612.07602,2016.
[6]Guo XY,He TT,Hu XH,Chen QJ.Chinese entity relationship extraction based on syntactic and semantic features.Journal of Chinese Information Processing,2014,28(6):183-189(in Chinese with English abstract).
[7]Kumar S.A survey of deep learning methods for relation extraction.arXiv:arXiv preprint arXiv:1705.03645,2017.
[8]Surdeanu M,Tibshirani J,Nallapati R,Manning CD.Multi-instance multi-label learning for relation extraction.In:Proc.of the Joint Conf.on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.2012.455-465.
[9]Zheng S,Hao Y,Lu D,Bao H,Xu J,Hao H,Xu B.Joint entity and relation extraction based on a hybrid neural network.Neurocomputing,2017,257:1-8.
[10]Lin Y,Shen S,Liu Z,Luan H,Sun M.Neural relation extraction with selective attention over instances.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.2124-2133.
[11]Xu Y,Mou LL,Li G,Chen YC,Peng H,Jin Z.Classifying relation via long short term memory networks along shortest dependency paths.Conf.on Empirical Methods in Natural Language Processing,2015,42(1):56-61.
[12]Miwa M,Bansal M.End-to-end relation extraction using LSTMs on sequences and tree structures.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.1105-1116.
[13]Katiyar A,Cardie C.Going out on a limb:Joint extraction of entity mentions and relations without dependency trees.In:Proc.of the Meeting of the Association for Computational Linguistics.2017.917-928.
[14]Mintz M,Bills S,Snow R,Jurafsky D.Distant supervision for relation extraction without labeled data.In:Proc.of the Joint Conf.of the Meeting of the ACL and the Int’l Joint Conf.on Natural Language Processing of the Afnlp.2009.1003-1011.
[15]Yu XK,Chen L,Guo J,Cai YY,Wu Y,Wang JC.Relationship extraction method combining clause-level remote supervision and semi-supervised integration learning.Pattern Recognition and Artificial Intelligence,2017,30(1):54-63(in Chinese with English abstract).
[16]Yao L,Riedel S,Mccallum A.Unsupervised relation discovery with sense disambiguation.In:Proc.of the Annual Meeting of the Association for Computational Linguistics.2012.
[17]Qin L,Zhang Z,Zhao H,Hu Z,Xing EP.Adversarial connective-exploiting networks for implicit discourse relation classification.2017.1006-1017.https://arxiv.org/abs/1704.00217
[18]Zhang D,Wang D.Relation classification via recurrent neural network.arXiv preprint arXiv:1508.01006,2015.
[19]Hashimoto K,Miwa M,Tsuruoka Y,Chikayama T.Simple customization of recursive neural networks for semantic relation classification.In:Proc.of the 2013 Conf.on Empirical Methods in Natural Language Processing.2013.18-21.
[20]Zeng D,Liu K,Lai S,Zhou G,Zhao J.Relation classification via convolutional deep neural network.In:Proc.of the 25th Int’l Conf.on Computational Linguistics:Technical Papers(COLING 2014).2014.2335-2344.
[21]Santos CND,Xiang B,Zhou B.Classifying relations by ranking with convolutional neural networks.Computer Science,2015,86:132-137.
[22]Nguyen TH,Grishman R.Combining neural networks and log-linear models to improve relation extraction.arXiv preprint arXiv:1511.05926,2015.
[23]Miyato T,Dai AM,Goodfellow I.Adversarial training methods for semi-supervised text classification.arXiv preprint arXiv:1605.07725,2016.
[24]Wu Y,Bamman D,Russell S.Adversarial training for relation extraction.In:Proc.of the Conf.on Empirical Methods in Natural Language Processing.2017.1778-1783.
[25]He Z,Chen W,Li Z,Zhang M,Zhang W,Zhang M.SEE:Syntax-aware entity embedding for neural relation extraction.arXiv preprint arXiv:1801.03603,2018.
[26]Chikka VR,Karlapalem K.A hybrid deep learning approach for medical relation extraction.arXiv preprint arXiv:1806.11189,2018.
[27]Wen J,Sun X,Ren X,Su Q.Structure regularized neural network for entity relation classification for chinese literature text.arXiv preprint arXiv:1803.05662,2018.
[28]Adilova L,Giesselbach S,Rüping S.Making efficient use of a domain expert’s time in relation extraction.arXiv preprint arXiv:180704687,2018.
[29]Zhou GD,Su J,Zhang J,Zhang M.Exploring various knowledge in relation extraction.In:Proc.of the Conf.on Meeting of the Association for Computational Linguistics(ACL 2005).University of Michigan,2002.419-444.
[30]Huang X,You HL,Yu Y.A Survey of Research on Relationship Extraction Technology.New Technology of Library and Information Service,2013,29(11):30-39(in Chinese with English abstract).
[31]Liu JW,Liu Y,Luo XL.Semi-supervised Learning Method.Chinese Journal of Computers,2015,38(8):1592-1617(in Chinese with English abstract).
[32]Brin S.Extracting patterns and relations from the World Wide Web.In:Proc.of the Int’l Workshop on the World Wide Web and Databases.1998.172-183.
[33]Kumlien MCJ.Constructing viological knowledge bases by extraction information from text sources.In:Proc.of the 7th Int’l Conf.on Intelligent Systems for Molecular Biology.AAAI Press,1999.77-86.
[34]Hasegawa T,Sekine S,Grishman R.Discovering relations among named entities from large corpora.In:Proc.of the Meeting on Association for Computational Linguistics.2004.415.
[35]Jiao LC,Yang SY,Liu F,Wang SG,Feng ZX.Neural Network Seventy Years:Retrospect and Prospect.Chinese Journal of Computers,2016,39(8):1697-1716(in Chinese with English abstract).
[36]Zhou FY,Jin LP,Dong J.A survey of Convolutional Neural Networks.Chinese Journal of Computers,2017,40(6):1229-1251(in Chinese with English abstract).
[37]Zeng D,Liu K,Chen Y,Zhao J.Distant supervision for relation extraction via piecewise convolutional neural networks.In:Proc.of the Conf.on Empirical Methods in Natural Language Processing.2015.1753-1762.
[38]Ji GL,Liu K,He SZ,Zhao J.Distant supervision for relation extraction with sentence-level attention and entity descriptions.In:Proc.of the AAAI.2017.3060-3066.
[39]Ren X,Wu Z,He W,Qu M,Voss CR,Ji H,Abdelzaher TF,Han JW.CoType:Joint extraction of typed entities and relations with knowledge bases.2016.1015-1024.https://arxiv.org/abs/1610.08763
[40]Huang YY,Wang WY.Deep residual learning for weakly-supervised relation extraction.arXiv preprint arXiv:1707.08866,2017.
[41]Golshan PN,Dashti HAR,Azizi S,Safari L.A study of recent contributions on information extraction.arXiv preprint arXiv:1803.05667,2018.
[42]Wang LY.Entity relationship extraction based on deep convolutional neural network[MS.Thesis].Taiyuan:Taiyuan University of Technology,2017(in Chinese).
[43]Yang JF,Yu QB,Guan Y,Jiang ZP.A survey of research on electronic medical record named entity recognition and entity relationship extraction.Acta Automatica Sinica,2014,40(8):1537-1562(in Chinese with English abstract).
[44]Qin B,Liu AA,Liu T.Unguided Chinese open entity relationship extraction.Journal of Computer Research and Development,2015,52(5):1029-1035(in Chinese with English abstract).
[45]Chinchor N,Marsch E.MUC-7 information extraction task definition.In:Proc.of the 7th Message Understanding Conf.Appendices,1998.359-367.
[46]Socher R,Huval B,Manning CD,Ng AY.Semantic compositionality through recursive matrix-vector spaces.In:Proc.of the Joint Conf.on Empirical Methods in Natural Language Processing and Computational Natural Language Learning.2012.1201-1211.
[47]Xu K,Feng Y,Huang S,Zhao D.Semantic relation classification via convolutional neural networks with simple negative sampling.Computer Science,2015,71:941-949.
[48]Vu NT,Adel H,Gupta P,Schütze H.Combining recurrent and convolutional neural networks for relation classification.arXiv preprint arXiv:1605.07333,2016.
[49]Wang L,Cao Z,Melo GD,Liu Z.Relation classification via multi-level attention CNNs.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.1298-1307.
[50]Li F,Zhang M,Fu G,Qian T,Ji D.A Bi-LSTM-RNN model for relation classification using low-cost sequence features.arXiv preprint arXiv:1608.07720,2016.
[51]Cai R,Zhang X,Wang H.Bidirectional recurrent convolutional neural network for relation classification.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.756-765.
[52]Zheng S,Xu J,Bao H,Qi Z,Zhang J,Hao H,Xu B.Joint learning of entity semantics and relation pattern for relation extraction.In:Proc.of the Joint European Conf.on Machine Learning and Knowledge Discovery in Databases.Cham:Springer-Verlag,2016.443-458.
[53]Li F,Zhang M,Fu G,Ji D.A neural joint model for extracting bacteria and their locations.In:Proc.of the Pacific-Asia Conf.on Knowledge Discovery and Data Mining.Cham:Springer-Verlag,2017.15-26.
[54]Katiyar A,Cardie C.Investigating LSTMs for joint extraction of opinion entities and relations.In:Proc.of the Meeting of the Association for Computational Linguistics.2016.919-929.
[55]Zheng S,Wang F,Bao H,Hao Y,Zhou P,Xu B.Joint extraction of entities and relations based on a novel tagging scheme.2017.1227-1236.https://arxiv.org/abs/1706.05075
[56]Fei L,Zhang M,Fu G,Ji D.A neural joint model for entity and relation extraction from biomedical text.Bmc Bioinformatics.2017,18:198.
[57]He D,Zhang H,Hao W,Zhang R,Chen G,Jin D,Cheng K.Distant supervised relation extraction via long short term memory networks with sentence embedding.Intelligent Data Analysis,2017,21:1213-1231.
[58]Riedel S,Yao L,Mccallum A.Modeling relations and their mentions without labeled text.In:Proc.of the European Conf.on Machine Learning and Knowledge Discovery in Databases.2010.148-163.
[59]Liu Q,Zhai JW,Zhang ZC,Zhong S,Zhou Q,Zhang P,Xu J.An overview of deep reinforcement learning.Chinese Journal of Computers,2018,41(1):1-27(in Chinese with English abstract).
[60]Feng Y,Zhang H,Hao W,Chen G.Joint extraction of entities and relations using reinforcement learning and deep learning.In:Proc.of the Comput Intell Neurosci.2017.1-11.
[61]Qin P,Xu W,Wang WY.Robust distant supervision relation extraction via deep reinforcement learning.arXiv preprint arXiv:1805.09927,2018.
[62]Goodfellow IJ,Pouget-Abadie J,Mirza M,Xu B,Warde-Farley D,Ozair S,Courville A,Bengio Y.Generative adversarial networks.Advances in Neural Information Processing Systems,2014,3:2672-2680.
[63]Miyato T,Dai AM,Goodfellow I.Adversarial training methods for semi-supervised text classification.2016.https://arxiv.org/abs/1605.07725
[64]Qin P,Xu W,Wang WY.DSGAN:Generative adversarial training for distant supervision relation extraction.arXiv preprint arXiv:1805.09929,2018.
[65]Nickel M,Murphy K,Tresp V,Gabrilovich E.A review of relational machine learning for knowledge graphs.Proc.of the IEEE,2015,104:11-33.
[66]Grainger T,Aljadda K,Korayem M,Smith A.The semantic knowledge graph:A compact,auto-generated model for real-time traversal and ranking of any relationship within a domain.2016.420-429.https://arxiv.org/abs/1609.00464
[67]Sahu SK,Anand A,Oruganty K,Gattu M.Relation extraction from clinical texts using domain invariant convolutional neural network.In:Proc.of the 15th Workshop on Biomedical Natural Language Processing,2016.206-215.
[68]Gu J,Sun F,Qian L,Zhou G.Chemical-induced disease relation extraction via convolutional neural network.In:Proc.of the Database 2017.[doi:10.1093/database/bax024]
[69]Ramamoorthy S,Murugan S.An attentive sequence model for adverse drug event extraction from biomedical text.arXiv preprint arXiv:1801.00625,2018.
[70]Peng Y,Rios A,Kavuluru R,Lu Z.Chemical-protein relation extraction with ensembles of SVM,CNN,and RNN models.arXiv preprint arXiv:1802.01255,2018.
[71]Nguyen DQ,Verspoor K.Convolutional neural networks for chemical-disease relation extraction are improved with characterbased word embeddings.arXiv preprint arXiv:1805.10586,2018.
[72]Feng X,Guo J,Qin B,Liu T,Liu Y.Effective deep memory networks for distant supervised relation extraction.In:Proc.of the26th Int’l Joint Conf.on Artificial Intelligence.2017.4002-4008.
[73]Liu T,Wang K,Chang B,Sui Z.A soft-label method for noise-tolerant distantly supervised relation extraction.In:Proc.of the Conf.on Empirical Methods in Natural Language Processing.2017.1790-1795.
[74]Han X,Liu ZY,Sun M.Neural knowledge acquisition via mutual attention between knowledge graph and text.In:Proc.of the AAAI.2018.
[75]Feng J,Huang M,Zhao L,Yang Y,Zhu XY.Reinforcement learning for relation classification from noisy data.In:Proc.of the AAAI.2018.
[76]Jiang X,Wang Q,Li P,Wang B.Relation extraction with multi-instance multi-label convolutional neural networks.In:Proc.of the COLING.2016.1471-1480.
[77]Chang YC,Zhang YX,Wang H,Wan HY,Xiao CJ.Features oriented survey of state-of-the-art keyphrase extraction algorithms.Ruan Jian Xue Bao/Journal of Software,2018,29(7):2046-2070(in Chinese with English abstract).http://www.jos.org.cn/1000-9825/5538.htm[doi:10.13328/j.cnki.jos.005538]
[78]Peng N,Poon H,Quirk C,Toutanova K,Yih WT.Cross-sentence N-ary relation extraction with graph LSTMs.arXiv preprint arXiv:1708.03743,2017.
[79]Li MY,Yang J.Open chinese entity relationship extraction method based on dependency parsing.Computer Engineering,2016,42(6):201-207(in Chinese with English abstract).
[2]徐健,张智雄,吴振新.实体关系抽取的技术方法综述.现代图书情报技术,2008,24(8):18-23.
[3]甘丽新,万常选,刘德喜,钟青,江腾蛟.基于句法语义特征的中文实体关系抽取.计算机研究与发展,2016,53(2):284-302.
[4]刘峤,李杨,段宏,刘瑶,秦志光.知识图谱构建技术综述.计算机研究与发展,2016,53(3):582-600.
[6]郭喜跃,何婷婷,胡小华,陈前军.基于句法语义特征的中文实体关系抽取.中文信息学报,2014,28(6):183-189.
[15]余小康,陈岭,郭敬,蔡雅雅,吴勇,王敬昌.结合从句级远程监督与半监督集成学习的关系抽取方法.模式识别与人工智能,2017,30(1):54-63.
[30]黄勋,游宏梁,于洋.关系抽取技术研究综述.现代图书情报技术,2013,29(11):30-39.
[31]刘建伟,刘媛,罗雄麟.半监督学习方法.计算机学报,2015,38(8):1592-1617.
[35]焦李成,杨淑媛,刘芳,王士刚,冯志玺.神经网络七十年:回顾与展望.计算机学报,2016,39(8):1697-1716.
[36]周飞燕,金林鹏,董军.卷积神经网络研究综述.计算机学报,2017,40(6):1229-1251.
[42]王林玉.基于深度卷积神经网络的实体关系抽取[硕士学位论文].太原:太原理工大学,2017.
[43]杨锦锋,于秋滨,关毅,蒋志鹏.电子病历命名实体识别和实体关系抽取研究综述.自动化学报,2014,40(8):1537-1562.
[44]秦兵,刘安安,刘挺.无指导的中文开放式实体关系抽取.计算机研究与发展,2015,52(5):1029-1035.
[59]刘全,翟建伟,章宗长,钟珊,周倩,章鹏,徐进.深度强化学习综述.计算机学报,2018,41(1):1-27.
[77]常耀成,张宇翔,王红,万怀宇,肖春景.特征驱动的关键词提取算法综述.软件学报,2018,29(7):2046-2070.http://www.jos.org.cn/1000-9825/5538.htm[doi:10.13328/j.cnki.jos.005538]
[79]李明耀,杨静.基于依存分析的开放式中文实体关系抽取方法.计算机工程,2016,42(6):201-207.