Computer Science ›› 2024, Vol. 51 ›› Issue (9): 196-206.doi: 10.11896/jsjkx.231000123

• Artificial Intelligence • Previous Articles     Next Articles

Survey on Event Extraction Methods:Comparative Analysis of Deep Learning and Pre-training

WANG Jiabin, LUO Junren, ZHOU Yanzhong, WANG Chao, ZHANG Wanpeng   

  1. College of Intelligence Science and Technology,National University of Defense Technology,Changsha 410073,China
  • Received:2023-10-18 Revised:2024-03-15 Online:2024-09-15 Published:2024-09-10
  • About author:WANG Jiabin,born in 1995,postgra-duate.His main research interests in-clude event extraction and temporal knowledge graph forecasting.
    ZHANG Wanpeng,born in 1981,Ph.D,researcher.His main research interests include big data intelligence and intelligent evolution.

Abstract: Event extraction is born along with the development of information technology.As people's demand for extracting useful information from a wide variety of daily information is increasing,the research and development of event extraction has attracted more and more attention.This paper first introduces the development process of event extraction,clarifies the development context of event extraction,and then introduces two paradigms of event extractionand a comparative analysis of pipeline and fe-derated extraction paradigms is presented.Secondly,according to the level of event extraction,the development of event extraction in recent years is described from sentence level event extraction and text level event extraction.Then,the event extraction me-thods are compared and analyzed from three aspects:traditional event extraction methods,deep learning based event extraction methods,and Pre-training model-based event extraction methods.Finally,some typical application scenarios of event extraction are introduced,and the future development of event extraction topics is prospected according to the development status of event extraction.

Key words: Event extraction, Argument, Trigger word, Entity extraction, Temporal extraction, Pre-training

CLC Number: 

  • TP391
[1]DEJONG G.An overview of the FRUMP system[J].Strategies for Natural Language Processing,1982,113:149-176.
[2]SAGER N.Natural language information processing,reading[M].Addison-Wesley Publishing Company,Inc.,1981.
[3]GRISHMAN R,SUNDHEIM B M.Message understanding conference-6:A brief history[C]//Proceedings of the 16th Conference on Computational Linguistics-Volume 1.1996:466-471.
[4]DODDINGTON G R,MITCHELL A,PRZYBOCKI M A,et al.The automatic content extraction(ace) program-tasks,data,and evaluation[C]//Proc.4th Int.Conf.on Language Resources and Evaluation(LREC-2004).2004:837-840.
[5]AHN D.The stages of event extraction[C]//Proceedings of the Workshop on Annotating and Reasoning about Time and Events.2006:1-8.
[6]RUDNIK C,EHRHART T,FERRET O,et al.Searching news articles using an event knowledge graph leveraged by wikidata[C]//Companion Proceedings of the 2019 World Wide Web Conference.2019:1232-1239.
[7]EIN-DOR L,GERA A,TOLEDO-RONEN O,et al.Financialevent extraction using Wikipedia-based weak supervision[J].arXiv:1911.10783,2019.
[8]MA C M,LI X H,LI Z,et al.A review of event extraction[J].Computer Applications,2022,42(10):2975-2989.
[9]ZHU Y N,CAO Y,ZHONG J Y,et al.A review of event extrac-tion techniques[J].Computer Science,2022,49(12):264-273.
[10]LI Q,LI J,SHENG J,et al.A survey on deep learning event extraction:Approaches and applications[J].IEEE Transactions on Neural Networks and Learning Systems,2022,35(5):1-21.
[11]LINGUISTIC DATA CONSORTIUM.ACE(Automatic Con-tent Extraction) Chinese annotation guidelines for events [OL].[2023-10-11].http://www.ldc.upenn.edu/Projects/ACE,2005.
[12]CHEN Y,XU L,LIU K,et al.Event extraction via dynamicmulti-pooling convolutional neural networks[C]//Proceedings of the 53rd Annual Meeting of the Association for Compu-tational Linguistics and the 7th International Joint Conference on Natural Language Processing.2015:167-176.
[13]DU X,CARDIE C.Event extraction by answering(almost) natural questions[J].arXiv:2004.13625,2020.
[14]DEVLIN J,CHANG M W,LEE K,et al.Bert:Pre-training of deep bidirectional transformers for language understanding[J].arXiv:1810.04805,2018.
[15]YANG S,FENG D,QIAO L,et al.Exploring Pre-trained Language Models for Event Extraction and Generation[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.2019:5284-5294.
[16]LI Q,JI H,HUANG L.Joint event extraction via structured prediction with global features[C]//Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics.2013:73-82.
[17]COLLINS M.Discriminative training methods for hidden Markovmodels:Theory and experiments with perceptron algorithms[C]//Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing(EMNLP 2002).2002:1-8.
[18]NGUYEN T H,CHO K,GRISHMAN R.Joint event extraction via recurrent neural networks[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2016:300-309.
[19]WANG K,WANG M Y,LIU X,et al.Incorporating self-attention mechanism and CNN-BiGRU for event detection[J].Journal of Xi'an Electronic Science and Technology University,2022,49(5):181-188.
[20]JOULIN A,CISSE M,GRANGIER D,et al.Efficient Softmaxapproximation for GPUs[C]//International Conference on Machine Learning.PMLR,2017:1302-1310.
[21]REN Y G,YAN G,HE X Y.Generalised fine-grained event detection by fusing multi-scale CNN and CRF[J/OL].http://kns.cnki.net.libyc.nudt.edu.cn:80/kcms/detail/21.1106.tp.20230216.1653.003.html.
[22]VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[23]LAFFERTY J,MCCALLUM A,PEREIRA F C N.Conditional random fields:Probabilistic models for segmenting and labeling sequence data[C]//International Conference on Machine Lear-ning.Williamstown,2001:282-289.
[24]WANG Y Q,ZHOU Q S.A study on the application of Internet open source information extraction and intelligence analysis based on pre-trained language models-an example of conference activities such as “academic,lectures,and forums”[J/OL].http://kns.cnki.net.libyc.nudt.edu.cn:80/kcms/detail/11.1762.G3.20230905.1925.008.html.
[25]SHENG B.Research on event extraction model based on pre-training and GAT [D].Wuhan:South Central University of Economics and Law,2022.
[26]CHENG Y,MAO Y C,WAN X,et al.Dual-attention based Chinese event detection without trigger words[J].Computer Science,2023,50(1):276-284.
[27]LI J,HU R J,ZHANG K L,et al.A generic framework forevent extraction based on task transformation[J/OL].http://kns.cnki.net.libyc.nudt.edu.cn:80/kcms/detail/11.2127.TP.20230818.0954.004.html.
[28]ZHAO Y H,CHEN Y P,HUANG R Z,et al.Chinese event trigger word extraction based on spanning regression[J].Journal of Applied Science,2023,41(1):95-106.
[29]YANG H,ZHAO G,WANG X F.Event-triggered word extraction based on hybrid model[J].Computer Engineering and Science,2023,45(1):171-180.
[30]CHENG Q,FU Y,HUANG J,et al.Event detection based on the label attention mechanism[J].International Journal of Machine Learning and Cybernetics,2023:633-641.
[31]XU Z L,ZHU R S,YU D H,et al.Joint extraction of unexpected hotspot events for graph attention networks[J].Small Microcomputer Systems,2023,44(5):902-909.
[32]MIHALCEA R,TARAU P.Textrank:Bringing order into text[C]//Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing.2004:404-411.
[33]CHEN M,WU F,LI P F,et al.Chinese event theory meta-extraction based on reading comprehension framework[J].Journal of Chinese Information,2022,36(10):107-115.
[34]ZHU M,MAO Y C,CHENG Y,et al.An event extractionmethod based on dual attention mechanism[J].Journal of Software,2023,34(7):3226-3240.
[35]GAO B,HUANG F N,ZOU Q J,et al.A chapter-level event extraction method based on global semantic matching[J].Compu-ter Technology and Development,2023,33(7):154-159.
[36]LIU J W.Research on prediction model based on news event extraction [D].Shanghai:Shanghai University of Finance and Economics,2022.
[37]YAN J,CHEN L,YU Y,et al.EmergEventMine:End-to-EndChinese Emergency Event Extraction Using a Deep Adversarial Network[J].ISPRS International Journal of Geo-Information,2022,11(6):345.
[38]YANG H,CHEN Y,LIU K,et al.Multi-Turn and Multi-Granularity Reader for Document-Level Event Extraction[J].ACM Transactions on Asian and Low-Resource Language Information Processing,2022,22(2):1-16.
[39]ZHANG M,FANG F,LI H,et al.MHGEE:Event Extraction via Multi-granularity Heterogeneous Graph[C]//International Conference on Computational Science.Cham:Springer International Publishing,2022:473-487.
[40]SUN H,ZHOU J,KONG L,et al.Seq2EG:a novel and effective event graph parsing approach for event extraction[J].Know-ledge and Information Systems,2023(10):65.
[41]RILOFF E.Automatically constructing a dictionary for information extraction tasks[C]//Proceedings of the AAAI Conference on Artificial Intelligence.1993.
[42]KIM J T,MOLDOVAN D I.Acquisition of semantic patterns for information extraction from corpora[C]//Proceedings of 9th IEEE Conference on Artificial Intelligence for Applications.IEEE,1993:171-176.
[43]KIM J T,MOLDOVAN D I.Acquisition of linguistic patterns for knowledge-based information extraction[J].IEEE Transactions on Knowledge and Data Engineering,1995(5):713-724.
[44]JIANG J F.Research on Information Extraction Pattern Acquisition of Free Text [D].Beijing:Graduate School of Chinese Academy of Sciences(Institute of Computing Technology),2004.
[45]CAO K,LI X,FAN M,et al.Improving event detection with active learning[C]//Proceedings of the International Conference Recent Advances in Natural Language Processing.2015:72-77.
[46]GOODMAN J.Classes for fast maximumentropy training[C]//IEEE International Conference on Acoustics,Speech,and Signal Processing.Proceedings.IEEE,2001:561-564.
[47]RABINER L R.A tutorial on hidden Markov models and selec-ted applications in speech recognition[J].Proceedings of the IEEE,1989,77(2):257-286.
[48]CORTES C,VAPNIK V.Support-vector networks[J].Machine Learning,1995,20:273-297.
[49]MCCALLUM A,FREITAG D,PEREIRA F C N.Maximum entropy Markov models for information extraction and segmentation[C]//International Conference on Machine Learning.2000:591-598.
[50]CHIEU H L,NG H T.A maximum entropy approach to information extraction from semi-structured and free text[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2002:786-791.
[51]BETHARD S,MARTIN J H.Identificationof event mentionsand their semantic class[C]//Proceedings of the 2006Confe-rence on Empirical Methods in Natural Language Processing.2006:146-154.
[52]LLORENS H,SAQUETE E,NAVARRO B.TimeML events recognition and classification:learning CRF models with semantic roles[C]//Proceedings of the 23rd International Conference on Computational Linguistics(Coling 2010).2010:725-733.
[53]PUSTEJOVSKY J,CASTANO J M,INGRIA R,et al.TimeML:Robust specification of event and temporal expressions in text[J].New Directions in Question Answering,2003,3:28-34.
[54]HONG Y,ZHANG J,MA B,et al.Using cross-entity inference to improve event extraction[C]//Proceedings of the 49th An-nual Meeting of the Association for Computational Linguistics:Human Language Technologies.2011:1127-1136.
[55]YANG B,MITCHELL T.Joint extraction of events and entities within a document context[J].arXiv:1609.03632,2016.
[56]ZHANG Z,XU W,CHEN Q.Joint Event Extraction Based on Skip-Window Convolutional Neural Networks[C]//Natural Language Understanding and Intelligent Applications:5th CCF Conference on Natural Language Processing and Chinese Computing(NLPCC).2016:324-334.
[57]SHA L,QIAN F,CHANG B,et al.Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018:5916-5923.
[58]FENG X,QIN B,LIU T.A language-independent neural net-work for event detection[J].Science China Information Sciences,2018,61:1-12.
[59]CUI S,YU B,LIU T,et al.Edge-enhanced graph convolution networks for event detection with syntactic relation [J].arXiv:2002.10757,2020.
[60]NGUYEN T,GRISHMAN R.Graph convolutional networkswith argument-aware pooling for event detection[C]//Procee-dings of the AAAI Conference on Artificial Intelligence.2018:5900-5907.
[61]LIU X,LUO Z,HUANG H.Jointly multiple events extraction via attention-based graph information aggregation[J].arXiv:1809.09078,2018.
[62]MA J,HUANG Y,LIU W P.A joint extraction recognitionmethod for domain events based on attention mechanism[J].Command Information Systems and Technology,2022,13(1):90-98.
[63]SHEN C,TAO J,LI P,et al.Joint Event Extraction Based on CNN-BiGRU and Attention Mechanism[C]//Asia Conference on Algorithms,Computing and Machine Learning(CACML).2022:492-497.
[64]TIAN S C.Research on Chinese Event Extraction Based onQ&A [D].Suzhou:Soochow University,2022.
[65]ZHANG H,ZHANG G J.A chapter-level event extractionmethod based on multi-granularity entity heterogeneous graph[J].Computer Science,2023,50(5):255-261.
[66]HU J,HE W,ZENG Z F.Global graph neural network docu-ment-level Chinese financial event extraction based on RoBERTa[J].Journal of Chinese Information,2023,37(2):107-118.
[67]ZHANG H K,SONG H,XU B,et al.End-to-end Chinese chapter event extraction based on BERT[J].Journal of Chinese Information,2022,36(10):97-106.
[68]LIU L P,ZHOU X,CHENG J J,et al.An event extractionmethod based on conversational machine reading comprehension model[J].Computer Science,2023,50(2):275-284.
[69]HE L,ZHAO X,ZHAO L,et al.An Event Extraction Approach Based on a Multi-Round Q&A Framework[J].Applied Sciences,2023,13(10):6308.
[70]XI Q,REN Y,KOU L,et al.EABERT:An Event AnnotationEnhanced BERT Framework for Event Extraction[J/OL].https://doi.org/10.1007/s11036-023-02203-w.
[71]DING L,CHEN X J,WEI J,et al.MABERT:Mask-Attention-Based BERT for Chinese Event Extraction[J].ACM Transactions on Asian and Low-Resource Language Information Processing,2023,22(7):1-21.
[72]SONG Z,BIES A,STRASSEL S,et al.From light to rich ere:annotation of entities,relations,and events[C]//Proceedings of the the 3rd Workshop on EVENTS:Definition,Detection,Coreference,and Representation.2015:89-98.
[73]PENG H,WANG X,YAO F,et al.OmniEvent:A comprehensive,fair,and easy-to-use toolkit for event understanding[J].arXiv:2309.14258,2023.
[74]HUANG K H,HSU I,PAREKH T,et al.A Reevaluation ofEvent Extraction:Past,Present,and Future Challenges[J].ar-Xiv:2311.09562,2023.
[75]TANEV H,PISKORSKI J,ATKINSON M.Real-Time NewsEvent Extraction for Global Crisis Monitoring[C]//Natural Language and Information Systems.2008:207-218.
[76]ADAM N R,SHAFIQ B,STAFFIN R.Spatial computing and social media in thecontext of disaster management[J].IEEE Intelligent Systems,2012,27(6):90-96.
[77]VANEGAS J A,MATOS S,GONZÁLEZ F,et al.An Overview of Biomolecular Event Extraction from Scientific Documents[J].Computational and Mathematical Methods in Medicine,2015,2015:1-19.
[78]SOUZA COSTA T,GOTTSCHALK S,DEMIDOVA E.Event-QA:A dataset for event-centric question answering over know-ledge graphs[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management.2020:3157-3164.
[79]PAOLINI G,ATHIWARATKUN B,KRONE J,et al.Struc-tured prediction as translation between augmented natural languages[J].arXiv:2101.05779,2021.
[80]CHAI H,DU Y.A framework of situation awareness based on event extraction and correlation for military decision support[C]//2012 IEEE International Conference on Mechatronics and Automation.IEEE,2012:192-196.
[81]GAO H B.Military event extraction for encyclopaedic data [D].Dalian:Dalian University of Technology,2021.
[82]LEETARU K,SCHRODT P A.GDELT:Global data on events,location,and tone,1979-2012[C]//ISA Annual Convention.Citeseer,2013:1-49.
[83]WARD M D,BEGER A,CUTLER J,et al.Comparing GDELT and ICEWS event data[J].Analysis,2013,21(1):267-297.
[84]RALEIGH C,LINKE,HEGRE H,et al.Introducing ACLED:An armed conflict location and event dataset[J].Journal of Peace Research,2010,47(5):651-660.
[85]LAFREE G.The global terrorism database(GTD) accomplishments and challenges[J].Perspectives on Terrorism,2010,4(1):24-46.
[86]AZAR E E.The conflict and peace data bank(COPDAB) project[J].Journal of Conflict Resolution,1980,24(1):143-152.
[87]SUNDBERG R,MELANDER E.Introducing the UCDP geo-referenced event dataset[J].Journal of Peace Research,2013,50(4):523-532.
[88]ZHOU S,WANG X,YANG Z.Monitoring and early warning of newcyber-telecom crime platform based on BERT migration learning[J].China Communications,2020,17(3):140-148.
[89]WANG Z J,WANG S,LI X Q,et al.A review of event causalityextraction based on deep learning[J].Computer Applications,2021,41(5):1247.
[90]LAI V D.Event Extraction:A Survey[J].arXiv:2210.03419,2022.
[91]YANG H,CHEN Y,LIU K,et al.DCFEE:A document-levelChinese financial event extraction system based on automatically labeled training data[C]//Proceedings of ACL 2018,System Demonstrations.2018:50-55.
[92]FERGUSON J,LOCKARD C,WELD D S,et al.Semi-supervised event extraction with paraphrase clusters[J].arXiv:1808.08622,2018.
[1] YAN Jingtao, LI Yang, WANG Suge, PAN Bangze. Overlap Event Extraction Method with Language Granularity Fusion Based on Joint Learning [J]. Computer Science, 2024, 51(7): 287-295.
[2] GUI Haitao, WANG Zhongqing. Personalized Dialogue Response Generation Combined with Conversation State Information [J]. Computer Science, 2024, 51(6A): 230800055-7.
[3] DING Yi, WANG Zhongqing. Study on Pre-training Tasks for Multi-document Summarization [J]. Computer Science, 2024, 51(6A): 230300160-8.
[4] SHI Jiyun, ZHANG Chi, WANG Yuqiao, LUO Zhaojing, ZHANG Meihui. Generation of Structured Medical Reports Based on Knowledge Assistance [J]. Computer Science, 2024, 51(6): 317-324.
[5] CHEN Wenzhong, CHEN Hongmei, ZHOU Lihua, FANG Yuan. Time-aware Pre-training Method for Sequence Recommendation [J]. Computer Science, 2024, 51(5): 45-53.
[6] ZHANG Zhiyuan, ZHANG Weiyan, SONG Yuqiu, RUAN Tong. Multilingual Event Detection Based on Cross-level and Multi-view Features Fusion [J]. Computer Science, 2024, 51(5): 208-215.
[7] ZHANG Mingdao, ZHOU Xin, WU Xiaohong, QING Linbo, HE Xiaohai. Unified Fake News Detection Based on Semantic Expansion and HDGCN [J]. Computer Science, 2024, 51(4): 299-306.
[8] LIU Tao, JIANG Guoquan, LIU Shanshan, LIU Liu, HUAN Zhigang. Survey of Event Extraction in Low-resource Scenarios [J]. Computer Science, 2024, 51(2): 217-237.
[9] WU Jiawei, FANG Quan, HU Jun, QIAN Shengsheng. Pre-training of Heterogeneous Graph Neural Networks for Multi-label Document Classification [J]. Computer Science, 2024, 51(1): 143-149.
[10] TANG Jia, GUO Yan, YE Mingwei, WU Guixing. Multimodal Pre-training Method for Multi-view Contrastive Learning and Semantic Enhancement [J]. Computer Science, 2024, 51(1): 168-174.
[11] ZHAI Lizhi, LI Ruixiang, YANG Jiabei, RAO Yuan, ZHANG Qitan, ZHOU Yun. Overview About Composite Semantic-based Event Graph Construction [J]. Computer Science, 2023, 50(9): 242-259.
[12] YI Liu, GENG Xinyu, BAI Jing. Hierarchical Multi-label Text Classification Algorithm Based on Parallel Convolutional Network Information Fusion [J]. Computer Science, 2023, 50(9): 278-286.
[13] CAI Haoran, YANG Jian, YANG Lin, LIU Cong. Low-resource Thai Speech Synthesis Based on Alternate Training and Pre-training [J]. Computer Science, 2023, 50(6A): 220800127-5.
[14] WEI Tao, LI Zhihua, WANG Changjie, CHENG Shunhang. Cybersecurity Threat Intelligence Mining Algorithm for Open Source Heterogeneous Data [J]. Computer Science, 2023, 50(6): 330-337.
[15] ZHANG Hu, ZHANG Guangjun. Document-level Event Extraction Based on Multi-granularity Entity Heterogeneous Graph [J]. Computer Science, 2023, 50(5): 255-261.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!