事件抽取综述

doi:10.11772/j.issn.1001-9081.2021081542

《计算机应用》唯一官方网站 ›› 2022, Vol. 42 ›› Issue (10): 2975-2989.DOI: 10.11772/j.issn.1001-9081.2021081542

• 人工智能 • 下一篇

事件抽取综述

马春明¹, 李秀红¹, 李哲², 王惠茹¹, 杨丹¹

^1.新疆大学信息科学与工程学院，乌鲁木齐 830046
^2.香港理工大学电子及资讯工程学系，香港 999077

收稿日期:2021-08-31 修回日期:2021-12-08 接受日期:2021-12-09 发布日期:2022-10-14 出版日期:2022-10-10
通讯作者: 李秀红
作者简介:第一联系人：马春明（1997—），男，四川绵阳人，硕士研究生，主要研究方向：自然语言处理、事件抽取
李秀红（1977—），女，山东威海人，副教授，博士，主要研究方向：自然语言处理、图像处理 xjulxh@xju.edu.cn
李哲（1992—），男，山东泰安人，博士研究生，主要研究方向：说话人识别、多模态语义分析
王惠茹（1996—），女，新疆伊犁人，硕士研究生，主要研究方向：自然语言处理、图像处理
杨丹（1996—），女，四川南充人，硕士研究生，主要研究方向：自然语言处理、图像处理。
基金资助:
国家语委科研重点项目(ZDI135-96)

Survey of event extraction

Chunming MA¹, Xiuhong LI¹, Zhe LI², Huiru WANG¹, Dan YANG¹

^1.College of Information Science and Engineering，Xinjiang University，Urumqi Xinjiang 830046，China
^2.Department of Electronic and Information Engineering，The Hong Kong Polytechnic University，Hong Kong 999077，China

Received:2021-08-31 Revised:2021-12-08 Accepted:2021-12-09 Online:2022-10-14 Published:2022-10-10
Contact: Xiuhong LI
About author:MA Chunming， born in 1997， M. S. candidate. His research interests include natural language processing， event extraction.
LI Xiuhong， born in 1977， Ph. D. ， associate professor. Her research interests include natural language processing， image processing.
LI Xiuhong， born in 1977， Ph. D. ， associate professor. Her research interests include natural language processing， image processing.
LI Zhe， born in 1992， Ph. D. candidate. His research interests include speaker recognition， multi-modal semantic analysis.
WANG Huiru， born in 1996， M. S. candidate. Her research interests include natural language processing， image processing.
YANG Dan， born in 1996， M. S. candidate. Her research interests include natural language processing， image processing.
Supported by:
Scientific Research Key Project of National Language Commission(ZDI135-96)

摘要/Abstract

摘要：

将用户感兴趣的事件从非结构化信息中提取出来，然后以结构化的方式展示给用户，这就是事件抽取。事件抽取在信息收集、信息检索、文档合成、信息问答等方面有着广泛应用。从全局出发，事件抽取算法可以分为基于模式匹配的算法、触发词法、基于本体的算法以及前沿联合模型方法这四类。在研究过程中根据相关需求可使用不同评价方法和数据集，而不同的事件表示方法也与事件抽取研究有一定联系；以任务类型区分，元事件抽取和主题事件抽取是事件抽取的两大基本任务。其中，元事件抽取有基于模式匹配、基于机器学习和基于神经网络这三种方式，而主题事件抽取有基于事件框架和基于本体两种方式。事件抽取研究在中英等单语言上均已取得了优秀成果，而跨语言事件抽取依然面临着许多问题。最后，总结了事件抽取的相关工作并提出未来研究方向，以期为后续研究提供参考。

关键词: 事件抽取, 事件表示, 元事件抽取, 主题事件抽取, 跨语言事件抽取

Abstract:

The event that the user is interested in is extracted from the unstructured information， and then displayed to the user in a structured way， that is event extraction. Event extraction has a wide range of applications in information collection， information retrieval， document synthesis， and information questioning and answering. From the overall perspective， event extraction algorithms can be divided into four categories： pattern matching algorithms， trigger lexical methods， ontology-based algorithms， and cutting-edge joint model methods. In the research process， different evaluation methods and datasets can be used according to the related needs， and different event representation methods are also related to event extraction research. Distinguished by task type， meta-event extraction and subject event extraction are the two basic tasks of event extraction. Among them， meta-event extraction has three methods based on pattern matching， machine learning and neural network respectively， while there are two ways to extract subjective events： based on the event framework and based on ontology respectively. Event extraction research has achieved excellent results in single languages such as Chinese and English， but cross-language event extraction still faces many problems. Finally， the related works of event extraction were summarized and the future research directions were prospected in order to provide guidelines for subsequent research.

Key words: event extraction, event representation, meta-event extraction, subject event extraction, cross-language event extraction

中图分类号:

TP391.1

马春明, 李秀红, 李哲, 王惠茹, 杨丹. 事件抽取综述[J]. 计算机应用, 2022, 42(10): 2975-2989.

Chunming MA, Xiuhong LI, Zhe LI, Huiru WANG, Dan YANG. Survey of event extraction[J]. Journal of Computer Applications, 2022, 42(10): 2975-2989.

图/表 20

参考文献 62

1	谭红叶. 中文事件抽取关键技术研究［D］. 哈尔滨：哈尔滨工业大学 2008：14-89.
	TAN H Y. Research on Chinese event extraction［D］. Harbin： Harbin Institute of Technology， 2008：14-89.
2	许红磊，陈锦秀，周昌乐，等. 自动识别事件类别的中文事件抽取技术研究［J］. 心智与计算， 2010， 4（1）：34-44.
	XU H L， CHEN J X， ZHOU C L， et al. Research on event type identification for Chinese event extraction［J］. Mind and Computation， 2010， 4（1）：34-44.
3	AHN D. The stages of event extraction［C］// Proceedings of the 2006 Workshop on Annotating and Reasoning about Time and Events. Stroudsburg， PA： Association for Computational Linguistics， 2006：1-8. 10.3115/1629235.1629236
4	NAUGHTON M， KUSHMERICK N， CARTHY J. Event extraction from heterogeneous news sources［C］// Proceedings of the 2006 AAAI Workshop on Event Extraction and Synthesis. Menlo Park， CA： AAAI Press， 2006：1-6.
5	CHEN Y B， XU L H， LIU K， et al. Event extraction via dynamic multi-pooling convolutional neural networks［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）. Stroudsburg， PA： Association for Computational Linguistics， 2015：167-176. 10.3115/v1/p15-1017
6	FENG X C， QIN B， LIU T. A language-independent neural network for event detection［J］. Science China Information Sciences， 2018， 61（9）： No.092106. 10.1007/s11432-017-9359-x
7	DU X Y， CARDIE C. Document-level event role filler extraction using multi-granularity contextualized encoding［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： Association for Computational Linguistics， 2020：8010-8020. 10.18653/v1/2020.acl-main.714
8	WANG Z Q， WANG X Z， HAN X， et al. CLEVE： contrastive pre-training for event extraction［C］// Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing （Volume 1： Long Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2021：6283-6297. 10.18653/v1/2021.acl-long.491
9	杨选选，张蕾. 基于语义角色和概念图的信息抽取模型［J］. 计算机应用， 2010， 30（2）：411-414. 10.3724/sp.j.1087.2010.00411
	YANG X X， ZHANG L. Information extraction based on semantic role and concept graph［J］. Journal of Computer Applications， 2010， 30（2）：411-414. 10.3724/sp.j.1087.2010.00411
10	LI C H， HU Y， ZHONG Z M. An event ontology construction approach to web crime mining［C］// Proceedings of the 7th International Conference on Fuzzy Systems and Knowledge Discovery. Piscataway： IEEE， 2010：2441-2445. 10.1109/fskd.2010.5569290
11	丁效，宋凡，秦兵，等. 音乐领域典型事件抽取方法研究［J］. 中文信息学报， 2011， 25（2）：15-20. 10.3969/j.issn.1003-0077.2011.02.003
	DING X， SONG F， QIN B， et al. Research on typical event extraction method in the field of music［J］. Journal of Chinese Information Processing， 2011， 25（2）：15-20. 10.3969/j.issn.1003-0077.2011.02.003
12	吉久明，陈锦辉，李楠，等. 中文事件抽取研究文献之算法效果分析［J］. 现代情报， 2015， 35（12）： 3-10. 10.3969/j.issn.1008-0821.2015.12.001
	JI J M， CHEN J H， LI N， et al. Effect analysis of Chinese event extraction method based on literatures［J］. Journal of Modern Information， 2015， 35（12）： 3-10. 10.3969/j.issn.1008-0821.2015.12.001
13	吴奇. 基于领域本体的Web实体事件抽取问题研究［D］. 济南：山东大学， 2014：1-6.
	WU Q. Research on domain ontology-based Web entity event extraction［D］. Jinan： Shandong University， 2014：1-6.
14	赵小明，朱洪波，陈黎，等. 基于多分类器的金融领域多元关系信息抽取算法［J］. 计算机工程与设计， 2011， 32（7）：2348-2351.
	ZHAO X M， ZHU H B， CHEN L， et al. Multi-relation extraction in finance based on multi-classifier［J］. Computer Engineering and Design， 2011， 32（7）：2348-2351.
15	HAN S Q， HAO X L， HUANG H L. An event-extraction approach for business analysis from online Chinese news［J］. Electronic Commerce Research and Applications， 2018， 28：244-260. 10.1016/j.elerap.2018.02.006
16	WANG A R， WANG J， LIN H F， et al. A multiple distributed representation method based on neural network for biomedical event extraction［J］. BMC Medical Informatics and Decision Making， 2017， 17（S3）： No.171. 10.1186/s12911-017-0563-9
17	KIM J. Supervenience and Mind： Selected Philosophical Essays［M］. New York： Cambridge University Press， 1993：336-357.
18	RADINSKY K， DAVIDOVICH S， MARKOVITCH S. Learning causality for news events prediction［C］// Proceedings of the 21st International Conference on World Wide Web. New York： ACM， 2012： 909-918. 10.1145/2187836.2187958
19	DING X， ZHANG Y， LIU T， et al. Using structured events to predict stock price movement： an empirical investigation［C］// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： Association for Computational Linguistics， 2014：1415-1425. 10.3115/v1/d14-1148
20	CHAMBERS N， JURAFSKY D. Unsupervised learning of narrative event chains［C］// Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics： Human Language Technologies. Stroudsburg， PA： Association for Computational Linguistics， 2008：789-797. 10.3115/1557690
21	WEBER N， BALASUBRAMANIAN N， CHAMBERS N. Event representations with tensor-based compositions［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2018：4946-4953. 10.1609/aaai.v32i1.11932
22	LI Z Y， DING X， LIU T. Constructing narrative event evolutionary graph for script event prediction［C］// Proceedings of the 27th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2018：4201-4207. 10.24963/ijcai.2018/584
23	GRANROTH-WILDING M， CLARK S. What happens next？ event prediction using a compositional neural network model［C］// Proceedings of the 30th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2016：2727-2733. 10.1609/aaai.v30i1.10344
24	LEE I T， GOLDWASSER D. FEEL： featured event embedding learning［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2018：4840-4847. 10.1609/aaai.v32i1.11936
25	TILK O， DEMBERG V， SAYEED A， et al. Event participant modelling with neural networks［C］// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： Association for Computational Linguistics， 2016：171-182. 10.18653/v1/d16-1017
26	HONG X D， SAYEED A， DEMBERG V. Learning distributed event representations with a multi-task approach［C］// Proceedings of the 7th Joint Conference on Lexical and Computational Semantics. Stroudsburg， PA： Association for Computational Linguistics， 2018： 11-21. 10.18653/v1/s18-2002
27	DING X， ZHANG Y， LIU T， et al. Deep learning for event-driven stock prediction［C］// Proceedings of the 24th International Joint Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2015：2327-2333.
28	DING X， LIAO K， LIU T， et al. Event representation learning enhanced with external commonsense knowledge［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg， PA： Association for Computational Linguistics， 2019： 4894-4903. 10.18653/v1/d19-1495
29	吴平博，陈群秀，马亮. 基于事件框架的事件相关文档的智能检索研究［J］. 中文信息学报， 2003， 17（6）：25-30， 59. 10.3969/j.issn.1003-0077.2003.06.004
	WU P B， CHEN Q X， MA L. Study on intelligent retrieval of event relevant documents based on event frame［J］. Journal of Chinese Information Processing， 2003， 17（6）： 25-30， 59. 10.3969/j.issn.1003-0077.2003.06.004
30	姜吉发. 一种跨语句汉语事件信息抽取方法［J］. 计算机工程， 2005， 31（2）：27-29， 66. 10.3969/j.issn.1000-3428.2005.02.011
	JIANG J F. A method to do Chinese event IE from a multiple sentences’ event narration［J］. Computer Engineering， 2005， 31（2）：27-29， 66. 10.3969/j.issn.1000-3428.2005.02.011
31	贾美英，杨炳儒，郑德权，等. 基于模式匹配的军事演习情报信息抽取［J］. 现代图书情报技术， 2009（9）：70-75. 10.3969/j.issn.1003-3513.2009.09.012
	JIA M Y， YANG B R， ZHENG D Q， et al. Sham battle information extraction based on pattern matching［J］. New Technology of Library and Information Service， 2009（9）： 70-75. 10.3969/j.issn.1003-3513.2009.09.012
32	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 （Volume 1： Long Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2013： 73-82.
33	ZHANG J C， QIN Y X， ZHANG Y， et al. Extracting entities and events as a single task using a transition-based neural model［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence. California： ijcai.org， 2019：5422-5428. 10.24963/ijcai.2019/753
34	LYBARGER K， OSTENDORF M， THOMPSON M， et al. Extracting COVID-19 diagnoses and symptoms from clinical text： a new annotated corpus and neural event extraction framework［J］. Journal of Biomedical Informatics， 2021， 117： No.103761. 10.1016/j.jbi.2021.103761
35	CHIEU H L， NG H T. A maximum entropy approach to information extraction from semi-structured and free text［C］// Proceedings of the 18th National Conference on Artificial Intelligence. Menlo Park， CA： AAAI Press， 2002： 786-791. 10.3115/1072228.1072253
36	LLORENS H， SAQUETE E， NAVARRO-COLORADO B. TimeML events recognition and classification： learning CRF models with semantic roles［C］// Proceedings of the 23rd International Conference on Computational Linguistics. ［S.l.］： COLING 2010 Organizing Committee， 2010：725-733. 10.1007/978-3-642-12550-8_19
37	赵妍妍，秦兵，车万翔，等. 中文事件抽取技术研究［J］. 中文信息学报， 2008， 22（1）：3-8. 10.3969/j.issn.1003-0077.2008.01.001
	ZHAO Y Y， QIN B， CHE W X， et al. Research on Chinese event extraction［J］. Journal of Chinese Information Processing 2008， 22（1）：3-8. 10.3969/j.issn.1003-0077.2008.01.001
38	LIU J， CHEN Y B， LIU K， et al. Event extraction as machine reading comprehension［C］// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： Association for Computational Linguistics， 2020： 1641-1651. 10.18653/v1/2020.emnlp-main.128
39	LI S， JI H， HAN J W. Document-level event argument extraction by conditional generation［C］// Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies. Stroudsburg， PA： Association for Computational Linguistics， 2021： 894-908. 10.18653/v1/2021.naacl-main.69
40	LIU S L， CHEN Y B， LIU K， et al. Exploiting argument information to improve event detection via supervised attention mechanisms［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2017：1789-1798. 10.18653/v1/p17-1164
41	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. Stroudsburg， PA： Association for Computational Linguistics， 2016：300-309. 10.18653/v1/n16-1034
42	YANG B S， MITCHELL T M. Joint extraction of events and entities within a document context［C］// Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics： Human Language Technologies. Stroudsburg， PA： Association for Computational Linguistics， 2016：289-299. 10.18653/v1/n16-1033
43	TANG Z， HAHN-POWELL G， SURDEANU M. Exploring interpretability in event extraction： multitask learning of a neural event classifier and an explanation decoder［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics： Student Research Workshop. Stroudsburg， PA： Association for Computational Linguistics， 2020：169-175. 10.18653/v1/2020.acl-srw.23
44	HUANG P X， ZHAO X， TAKANOBU R， et al. Joint event extraction with hierarchical policy network［C］// Proceedings of the 28th International Conference on Computational Linguistics. ［S.l.］： International Committee on Computational Linguistics， 2020：2653-2664. 10.18653/v1/2020.coling-main.239
45	LIU S L， CHEN Y B， HE S Z， et al. Leveraging FrameNet to improve automatic event detection［C］// Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2016：2134-2143. 10.18653/v1/p16-1201
46	CHEN Y B， LIU S L， ZHANG X， et al. Automatically labeled data generation for large scale event extraction［C］// Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics （Volume 1： Long Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2017：409-419. 10.18653/v1/p17-1038
47	ZENG Y， FENG Y S， MA R， et al. Scale up event extraction learning via automatic training data generation［C］// Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2018：6045-6052. 10.1609/aaai.v32i1.12030
48	LI Q， PENG H， LI J X， et al. Reinforcement learning-based dialogue guided event extraction to exploit argument relations［J］. IEEE/ACM Transactions on Audio， Speech， and Language Processing， 2022， 30：520-533. 10.1109/taslp.2021.3138670
49	DU X Y， CARDIE C. Event extraction by answering （almost） natural questions［C］// Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg， PA： Association for Computational Linguistics， 2020：671-683. 10.18653/v1/2020.emnlp-main.49
50	LEE C S， CHEN Y J， JIAN Z W. Ontology-based fuzzy event extraction agent for Chinese e-news summarization［J］. Expert Systems with Applications， 2003， 25（3）：431-447. 10.1016/s0957-4174(03)00062-9
51	MAO Q R， LI X， PENG H， et al. Event prediction based on evolutionary event ontology knowledge［J］. Future Generation Computer Systems， 2021， 115： 76-89. 10.1016/j.future.2020.07.041
52	CHEN Z， JI H. Language specific issue and feature exploration in Chinese event extraction［C］// Proceedings of Human Language Technologies： The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics， Companion Volume： Short Papers. Stroudsburg， PA： Association for Computational Linguistics， 2009：209-212. 10.3115/1620853.1620910
53	ZENG Y， YANG H H， FENG Y S， et al. A convolution BiLSTM neural network model for Chinese event extraction［C］// Proceedings of the 2016 International Conference on Computer Processing of Oriental Languages. Cham： Springer， 2016： 275-287. 10.1007/978-3-319-50496-4_23
54	LI P F， ZHOU G D， ZHU Q M， et al. Employing compositional semantics and discourse consistency in Chinese event extraction［C］// Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. Stroudsburg， PA： Association for Computational Linguistics， 2012： 1006-1016.
55	JI H， GRISHMAN R. Refining event extraction through unsupervised cross-document inference［C］// Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： Association for Computational Linguistics， 2008： 254-262.
56	LIAO S S， GRISHMAN R. Using document level cross-event inference to improve event extraction［C］// Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Stroudsburg， PA： Association for Computational Linguistics， 2010：789-797.
57	JI H. Cross-lingual predicate cluster acquisition to improve bilingual event extraction by inductive learning［C］// Proceedings of the 2009 Workshop on Unsupervised and Minimally Supervised Learning of Lexical Semantics. Stroudsburg， PA： Association for Computational Linguistics， 2009：27-35. 10.3115/1641968.1641972
58	ZHU Z， LI S S， ZHOU G D， et al. Bilingual event extraction： a case study on trigger type determination［C］// Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics （Volume 2： Short Papers）. Stroudsburg， PA： Association for Computational Linguistics， 2014：842-847. 10.3115/v1/p14-2136
59	HSI A， YANG Y M， CARBONELL J， et al. Leveraging multilingual training for limited resource event extraction［C］// Proceedings of the 26th International Conference on Computational Linguistics： Technical Papers. ［S.l.］： COLING 2016 Organizing Committee， 2016：1201-1210.
60	LIU J， CHEN Y B， LIU K， et al. Neural cross-lingual event detection with minimal parallel resources［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg， PA： Association for Computational Linguistics， 2019：738-748. 10.18653/v1/d19-1068
61	SUBBURATHINAM A， LU D， JI H， et al. Cross-lingual structure transfer for relation and event extraction［C］// Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg， PA： Association for Computational Linguistics， 2019：313-325. 10.18653/v1/d19-1030
62	AHMAD W U， PENG N Y， CHANG K W. GATE： graph attention transformer encoder for cross-lingual relation and event extraction［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto， CA： AAAI Press， 2021：12462-12470. 10.1609/aaai.v35i14.17478

源	words				files
源	1P	DUAL	ADJ	NORM	1P	DUAL	ADJ	NORM
合计	303 833	297 185	216 545	259 889	666	650	535	599
NW	60 658	57 807	33 459	48 399	128	124	81	106
BN	59 239	58 144	52 444	55 967	239	234	217	226
BC	46 612	46 110	33 874	40 415	68	67	52	60
WL	45 210	43 648	35 529	37 897	127	122	114	119
UN	45 161	44 473	26 371	37 366	58	57	37	49
CTS	47 003	47 003	34 868	39 845	46	46	34	39

源	words				files
源	1P	DUAL	ADJ	NORM	1P	DUAL	ADJ	NORM
合计	303 833	297 185	216 545	259 889	666	650	535	599
NW	60 658	57 807	33 459	48 399	128	124	81	106
BN	59 239	58 144	52 444	55 967	239	234	217	226
BC	46 612	46 110	33 874	40 415	68	67	52	60
WL	45 210	43 648	35 529	37 897	127	122	114	119
UN	45 161	44 473	26 371	37 366	58	57	37	49
CTS	47 003	47 003	34 868	39 845	46	46	34	39

源	中文						阿拉伯文
	chars			files			words			files
	1P	DUAL	ADJ	1P	DUAL	ADJ	1P	DUAL	ADJ	1P	DUAL	ADJ
合计	334 121	325 834	307 991	687	671	633	112 233	103 504	100 114	433	409	403
NW	127 319	124 175	121 797	248	242	238	61 287	56 158	53 026	239	226	221
BN	134 963	133 696	120 513	332	328	298	29 259	27 165	26 907	134	128	127
WL	71 839	68 063	65 681	107	101	97	21 687	20 181	20 181	60	55	55

源	中文						阿拉伯文
	chars			files			words			files
	1P	DUAL	ADJ	1P	DUAL	ADJ	1P	DUAL	ADJ	1P	DUAL	ADJ
合计	334 121	325 834	307 991	687	671	633	112 233	103 504	100 114	433	409	403
NW	127 319	124 175	121 797	248	242	238	61 287	56 158	53 026	239	226	221
BN	134 963	133 696	120 513	332	328	298	29 259	27 165	26 907	134	128	127
WL	71 839	68 063	65 681	107	101	97	21 687	20 181	20 181	60	55	55

方法	类别	R	P	F
文献［2］方法	训练	43.06	58.29	49.53
文献［2］方法	测试	38.91	52.36	44.64
文献［37］方法	训练	57.14	64.22	60.48
文献［37］方法	测试	54.86	69.29	61.24

事件抽取综述

Survey of event extraction

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 20

参考文献 62

相关文章 4

编辑推荐

Metrics

方法	语料库类别	训练次数	正面测试语料库		负面测试语料库		准确率/%
方法	语料库类别	训练次数	所有分类文档	正确分类文档	所有分类文档	正确分类文档	准确率/%
基于支持向量机	中奖欺诈	57	58	46	58	42	74.1
	网络色情	36	36	32	36	27	81.9
	非法交易	49	48	41	48	36	80.2
基于事件本体和支持向量机	中奖欺诈	57	58	52	58	45	83.6
	网络色情	36	36	34	36	28	86.1
	非法交易	49	48	43	48	39	85.4

事件类别	类别	P	R	F
8类事件类别	测试	81.65	73.62	77.43
8类事件类别	训练	84.34	75.79	79.84
33类事件子类别	测试	74.24	65.34	69.51
33类事件子类别	训练	76.35	64.26	69.79

模型	ACE2005												TAC2005
	事件触发识别			事件触发分类			事件参数识别			参数角色分类			事件触发识别			事件触发分类
	P	R	F	P	R	F	P	R	F	P	R	F	P	R	F	P	R	F
MEM^［35］	73.1	65.4	69.0	70.1	63.3	66.5	75.0	20.3	31.9	71.0	19.3	30.3	69.7	46.8	56.0	65.4	44.5	53.0
DMCNN^［5］	79.6	67.2	72.9	74.3	62.9	68.1	69.1	51.8	59.2	62.8	45.0	52.4	77.4	48.7	59.8	71.3	45.8	55.8
HPNet^［44］	81.3	77.2	79.2	80.1	75.7	77.8	70.2	53.8	60.9	64.6	50.7	56.8	78.2	55.6	65.0	70.9	54.8	61.8

方法	P	R	F
文献［41］方法	71.8	66.4	69.0
文献［5］方法	75.6	63.6	69.1
文献［40］方法	75.3	64.4	69.4
ANN^［45］	79.5	60.7	68.8
ANN+FrameNet^［45］	77.6	65.2	70.7

方法	触发识别			触发标签			参数识别			参数标签
方法	P	R	F	P	R	F	P	R	F	P	R	F
基于词语	68.1	52.7	59.4	65.7	50.9	57.4	56.1	38.2	45.4	53.1	36.2	43.1
基于字符	82.4	50.6	62.7	78.8	48.3	59.9	64.4	36.4	46.5	60.6	34.3	43.8

事件抽取任务	分类	特点
事件表示	离散的事件表示	事件表示为由事件元素构成的元组；面临稀疏性的问题
事件表示	稠密的事件表示	以预训练的词向量为基础；根据事件结构对事件元素的词向量进行语义组合；为事件计算低维、稠密的向量表示
元事件抽取	基于模式匹配的元事件抽取	在特定领域内产生更好的结果；系统的可移植性不好；需要建模，既费时又费力
	基于机器学习的元事件抽取	分类简短，大部分是完整的句子；由于是事件表述语句，因此语句中包含的信息量很大
	基于神经网络的元事件抽取	一种有监督多元分类任务；抽取方法包括2个步骤：特征选择和分类模型
主题事件抽取	基于事件框架的主题事件抽取	通过定义结构化、层次化的事件框架来指导主题事件的抽取；利用框架来概括事件信息
主题事件抽取	基于本体的主题事件抽取	根据本体所描述的概念、关系、层次结构、实例等来抽取待抽取文本中所包含的侧面事件及相关实体信息
跨语言事件抽取	中文事件抽取	中文语言词语间没有显式间隔，而分词会带明显的错误和误差；存在触发词分词不一致、数据稀疏问题
	英文事件抽取	核心和主流方法是基于统计和机器学习的方法
	跨语言事件抽取	在多种语言上进行训练，并利用依赖于语言的特征和不依赖于语言的特征来提高性能

[1]	赵旭剑, 王崇伟, 王俊力. 融合社会影响力和时间分布的微博关键事件抽取方法[J]. 《计算机应用》唯一官方网站, 2022, 42(9): 2667-2673.
[2]	王元龙, 刘晓敏, 张虎. 基于事件表示的机器阅读理解模型[J]. 《计算机应用》唯一官方网站, 2022, 42(7): 1979-1984.
[3]	武国亮, 徐继宁. 基于命名实体识别任务反馈增强的中文突发事件抽取方法[J]. 计算机应用, 2021, 41(7): 1891-1896.
[4]	许荣华吴刚李培峰朱巧明. 基于指代消解的中文事件融合方法[J]. 计算机应用, 2009, 29(08): 2264-2267.