[1]黄河燕,刘啸.面向新领域的事件抽取研究综述[J].智能系统学报,2022,17(1):201-212.[doi:10.11992/tis.202109045]
　HUANG Heyan,LIU Xiao.A survey on event extraction in new domains[J].CAAI Transactions on Intelligent Systems,2022,17(1):201-212.[doi:10.11992/tis.202109045]
点击复制

面向新领域的事件抽取研究综述

《智能系统学报》[ISSN 1673-4785/CN 23-1538/TP] 卷: 17 期数: 2022年第1期 页码: 201-212 栏目: 人工智能院长论坛 出版日期: 2022-01-05
Title:
A survey on event extraction in new domains
作者:
黄河燕1,2,3, 刘啸1,2,3
1. 北京理工大学 计算机学院, 北京 100081;
2. 北京海量语言信息处理与云计算应用工程研究中心, 北京 100081;
3. 北京理工大学 东南信息技术研究院, 福建 莆田 351100
Author(s):
HUANG Heyan1,2,3, LIU Xiao1,2,3
1. School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China;
2. Beijing Engineering Research Center of High-Volume Language Information Processing and Cloud Computing Applications, Beijing 100081, China;
3. Southeast Academy of Information Technology, Beijing Institute of Technology, Putian 351100, China
关键词:
事件抽取; 新领域; 信息抽取; 事件模板推导; 联合抽取; 事件真实性检测; 自然语言处理; 知识库
Keywords:
event extraction; new domains; information extraction; event schema induction; collective extraction; event factuality prediction; natural language processing; knowledge base
分类号:
TP391.4
DOI:
10.11992/tis.202109045
摘要:
在当前互联网时代，大量新领域下的非结构文本数据中蕴含了海量信息。面向新领域的事件抽取方法研究能快速地构建领域知识库，用于支撑基于知识的下游应用。但现有事件抽取系统的领域限定性强，在新领域中从零构建会极度依赖事件体系和标注数据的质量及规模，需要大量人力和专家知识来定制模板和标注语料。而且数据集中常见在相同的上下文中出现多个相关联的事件实例，对事件抽取和真实性检测产生了极大阻碍。本文针对面向新领域的事件抽取这一新兴研究领域进行综述，从事件模板推导、多实例联合事件抽取、事件真实性检测三个研究方向介绍了相关工作的研究现状，并对目前存在的重点和难点问题进行了讨论，指出了下一步需要开展的研究工作。
Abstract:
In the current Internet era, numerous unstructured text data in new domains often contain high-volume information. Studies on event extraction in new domains can accelerate building of domain knowledge bases, supporting downstream knowledge-based applications. However, the existing event extraction methods have substantial limitations of the domain. Building event extraction systems from scratch in new domains will heavily depend on the quality and scale of event schemas and annotated data, requiring a lot of human efforts and expertise. Moreover, it is common in the datasets that multiple associated event instances often appear in the same context, heavily hindering event extraction and factuality prediction. This paper summarizes the emerging research field of event extraction in new domains and investigates current research status from three directions: event schema induction, collective event extraction, and event factuality prediction. In addition, this paper discusses the existing difficulties and challengings and indicates the potential research work to be carried out in the future.
参考文献/References:
[1] SRIHARI R, LI Wei. Information extraction supported question answering[C]//8th Text Retrieval Conference. Gaithersburg, USA: NIST, 1999: 500–511.
[2] BASILE P, CAPUTO A, SEMERARO G, et al. Time event extraction to boost an information retrieval system[M]//Information Filtering and Retrieval. Cham: Springer International Publishing, 2016: 1–12.
[3] LU Di, VOSS C, TAO Fangbo, et al. Cross-media event extraction and recommendation[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations. Stroudsburg, USA: ACL, 2016: 72–76.
[4] LIU Xiao, LUO Zhunchen, HUANG Heyan. Jointly multiple events extraction via attention-based graph information aggregation[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2018: 1247–1256.
[5] SHINYAMA Y, SEKINE S. Preemptive information extraction using unrestricted relation discovery[C]//Proceedings of the main conference on Human Language Technology Conference of the North American Chapter of the Association of Computational Linguistics. Stroudsburg, USA: ACL, 2006: 304–311.
[6] FILATOVA E, HATZIVASSILOGLOU V, MCKEOWN K. Automatic creation of domain templates[C]//Proceedings of the COLING/ACL on Main conference poster sessions. Stroudsburg, USA: ACL, 2006: 207–214.
[7] QIU Long, KAN M, CHUA T. Modeling context in scenario template creation[C]//Proceedings of the 3rd International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2008: 157–164.
[8] CHAMBERS N, JURAFSKY D. Template-based information extraction without the templates[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2011: 976–986.
[9] SUNDHEIM B M. Overview of the fourth message understanding evaluation and conference[C]//MUC4 ’92: Proceedings of the 4th conference on Message understanding. New York, USA: ACM, 1992: 3–21.
[10] CHAMBERS N. Event schema induction with a probabilistic entity-driven model[C]//Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2013: 1797–1807.
[11] CHEUNG J, POON H, VANDERWENDE L. Probabilistic frame induction[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2013: 837–846.
[12] NGUYEN K H, TANNIER X, FERRET O, et al. Generative event schema induction with entity disambiguation[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2015: 188–197.
[13] SHA Lei, LI Sujian, CHANG Baobao, et al. Joint learning templates and slots for event schema induction[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2016: 428–434.
[14] HUANG Lifu, CASSIDY T, FENG Xiaocheng, et al. Liberal event extraction and event schema induction[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2016: 258–268.
[15] AHN N. Inducing event types and roles in reverse: Using function to discover theme[C]//Proceedings of the Events and Stories in the News Workshop. Stroudsburg, USA: ACL, 2017: 66–76.
[16] YUAN Quan, REN Xiang, HE Wenqi, et al. Open-schema event profiling for massive news corpora[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York, USA: ACM, 2018: 587–596.
[17] MODI A, TITOV I. Inducing neural models of script knowledge[C]//Proceedings of the Eighteenth Conference on Computational Natural Language Learning. Stroudsburg, USA: ACL, 2014: 49–57.
[18] RUDINGER R, RASTOGI P, FERRARO F, et al. Script induction as language modeling[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2015: 1681–1686.
[19] PICHOTTA K, MOONEY R J. Using sentence-level LSTM language models for script inference[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2016: 279–289.
[20] LIU Xiao, HUANG Heyan, ZHANG Yue. Open domain event extraction using neural latent variable models[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2019: 2860–2871.
[21] WANG Rui, ZHOU Deyu, HE Yulan. Open event extraction from online text using a generative adversarial network[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2019: 282–291.
[22] SRIVASTAVA A, SUTTON C. Autoencoding variational inference for topic models[C]//Proceedings of the 5th International Conference on Learning Representations. La Jolla, USA: ICLR, 2017.
[23] GRISHMAN R, WESTBROOK D, MEYERS A. NYU’s English ACE 2005 system description[C]//Proceedings of the ACE 2005 Evaluation Workshop. Gaithersburg, USA: NIST, 2005: 1–7.
[24] SONG Zhiyi, 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. Stroudsburg, USA: ACL, 2015: 89–98.
[25] MCCLOSKY D, SURDEANU M, MANNING C. Event extraction as dependency parsing[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2011: 1626–1635.
[26] LIN Ying, JI Heng, HUANG Fei, et al. A joint neural model for information extraction with global features[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2020: 73–82.
[27] LIU Shulin, LIU Kang, HE Shizhu, et al. A Probabilistic Soft Logic based approach to exploiting latent and global information in event classification[C]//30th AAAI Conference on Artificial Intelligence. Menlo Park, CA: AAAI, 2016: 2993–2999.
[28] LIU Shulin, CHEN Yubo, LIU Kang, 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. Stroudsburg, USA: ACL, 2017: 1789–1798.
[29] YANG Bishan, 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, USA: ACL, 2016: 289–299.
[30] KEITH K, HANDLER A, PINKHAM M, et al. Identifying civilians killed by police with distantly supervised entity-event extraction[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2017: 1547–1557.
[31] LIAO Shasha, 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, USA: ACL, 2010: 789–797.
[32] JI Heng, GRISHMAN R. Refining event extraction through cross-document inference[C]//Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2008: 254–262.
[33] HONG Yu, ZHANG Jianfeng, MA Bin, et al. Using cross-entity inference to improve event extraction[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2011: 1127–1136.
[34] REICHART R, BARZILAY R. Multi-event extraction guided by global constraints[C]//Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2012: 70–79.
[35] LU Wei, ROTH D. Automatic event extraction with structured preference modeling[C]//Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2012: 835–844.
[36] 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, USA: ACL, 2016: 300–309.
[37] SHA Lei, QIAN Feng, CHANG Baobao, et al. Jointly extracting event triggers and arguments by dependency-bridge RNN and tensor-based argument interaction[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Menlo Park, CA: AAAI, 2018: 5916–5923.
[38] LIU Jian, CHEN Yubo, LIU Kang, et al. Event detection via gated multilingual attention mechanism[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. Menlo Park, CA: AAAI, 2018: 4865–4872.
[39] CHEN Yubo, XU Liheng, LIU Kang, 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. Stroudsburg, USA: ACL, 2015: 167–176.
[40] FENG Xiaocheng, HUANG Lifu, TANG Duyu, et al. A language-independent neural network for event detection[C]//Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2016: 66–71.
[41] NGUYEN T H, GRISHMAN R. Modeling skip-grams for event detection with convolutional neural networks[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2016: 886–891.
[42] WADDEN D, WENNBERG U, LUAN Yi, et al. Entity, relation, and event extraction with contextualized span representations[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2019: 5783–5788.
[43] LIN Ying, JI Heng, HUANG Fei, et al. A joint neural model for information extraction with global features[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2020: 7999–8009.
[44] LIU Jian, CHEN Yubo, LIU Kang, et al. Event extraction as machine reading comprehension[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2020: 1641–1651.
[45] DU Xinya, CARDIE C. Event extraction by answering (almost) natural questions[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2020: 671–683.
[46] LI Fayuan, PENG Weihua, CHEN Yuguang, et al. Event extraction as multi-turn question answering[C]//Findings of the Association for Computational Linguistics: EMNLP 2020. Stroudsburg, USA: ACL, 2020: 829–838.
[47] PAOLINI G, ATHIWARATKUN B, KRONE J, et al. Structured prediction as translation between augmented natural languages[EB/OL]. (2021-01-28) [2021-12-10].https://www.researchgate.net/publication/348487215_Structured_Prediction_as_Translation_between_Augmented_Natural_Languages.
[48] LI Sha, JI Heng, HAN Jiawei. 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, USA: ACL, 2021: 894–908.
[49] LU Yaojie, LIN Hongyu, XU Jin, et al. Text2Event: controllable sequence-to-structure generation for end-to-end 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. Stroudsburg, USA: ACL, 2021: 2795–2806.
[50] DEVLIN J, CHANG M, LEE K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2019: 4171–4186.
[51] CHEN Pinzhen, BOGOYCHEV N, HEAFIELD K, et al. Parallel sentence mining by constrained decoding[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2020: 1672–1678.
[52] XU Benfeng, ZHANG Licheng, MAO Zhendong, et al. Curriculum learning for natural language understanding[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2020: 6095–6104.
[53] HUANG Lifu, JI Heng, CHO K, et al. Zero-shot transfer learning for event extraction[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2018: 2160–2170.
[54] WANG Chuan, XUE Nianwen, PRADHAN S. A transition-based algorithm for AMR parsing[C]//Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2015: 366–375.
[55] DENG Shumin, ZHANG Ningyu, KANG Jiaojian, et al. Meta-learning with dynamic-memory-based prototypical network for few-shot event detection[C]//Proceedings of the 13th International Conference on Web Search and Data Mining. New York, USA: ACM, 2020: 151–159.
[56] DENG Shumin, ZHANG Ningyu, LI Luoqiu, et al. OntoED: low-resource event detection with ontology embedding[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Stroudsburg, USA: ACL, 2021: 2828–2839.
[57] CONG Xin, CUI Shiyao, YU Bowen, et al. Few-shot event detection with prototypical amortized conditional random field[C]//Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Stroudsburg, USA: ACL, 2021: 28–40.
[58] NAIRN R, CONDORAVDI C, KARTTUNEN L. Computing relative polarity for textual inference[C]//Proceedings of the 5th International Workshop on Inference in Computational Semantics. Stroudsburg, USA: ACL, 2006: 1–10.
[59] SAURI R. A factuality profiler for eventualities in text[D]. Waltham, USA: Brandeis University, 2008.
[60] LOTAN A, STERN A, DAGAN I. Truthteller: Annotating predicate truth[C]//Proceedings of the 2013 Conference of the North American Chapter of the Association of Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2013: 752–757.
[61] DIAB M T, LEVIN L, MITAMURA T, et al. Committed belief annotation and tagging[C]//Proceedings of the Third Linguistic Annotation Workshop on - ACL-IJCNLP ’09. Suntec, Singapore. Stroudsburg, USA: ACL, 2009: 68–73.
[62] PRABHAKARAN V, RAMBOW O, DIAB M. Automatic committed belief tagging[C]//Proceedings of the 23rd International Conference on Computational Linguistics. Stroudsburg, USA: ACL, 2010: 1014–1022.
[63] DE MARNEFFE M C, MANNING C D, POTTS C. Did it happen? the pragmatic complexity of veridicality assessment[J]. Computational linguistics, 2012, 38(2): 301–333.
[64] LEE K, ARTZI Y, CHOI Y, et al. Event detection and factuality assessment with non-expert supervision[C]//Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Lisbon, Portugal. Stroudsburg, USA: ACL, 2015: 1643–1648.
[65] SAURI R, PUSTEJOVSKY J. Are you sure that this happened? Assessing the factuality degree of events in text[J]. Computational linguistics, 2012, 38(2): 261–299.
[66] QIAN Zhong, LI Peifeng, ZHU Qiaoming. A two-step approach for event factuality identification[C]//2015 International Conference on Asian Language Processing. New York, USA: IEEE, 2015: 103–106.
[67] STANOVSKY G, ECKLE-KOHLER J, PUZIKOV Y, et al. Integrating deep linguistic features in factuality prediction over unified datasets[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2017: 352–357.
[68] QIAN Zhong, LI Peifeng, ZHU Qiaoming, et al. Document-level event factuality identification via adversarial neural network[C]//Proceedings of the 2019 Conference of the North. Stroudsburg, USA: ACL, 2019: 2799–2809.
[69] RUDINGER R, WHITE A S, VAN DURME B. Neural models of factuality[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Stroudsburg, USA: ACL, 2018: 731–744.
[70] POURAN BEN VEYSEH A, NGUYEN T H, DOU Dejing. Graph based neural networks for event factuality prediction using syntactic and semantic structures[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg, USA: ACL, 2019: 4393–4399.
[71] SAURí R, PUSTEJOVSKY J. FactBank: a corpus annotated with event factuality[J]. Language resources and evaluation, 2009, 43(3): 227–268.
[72] MINARD A, SPERANZA M, URIZAR R, et al. Meantime, the newsreader multilingual event and time corpus[C]//Proceedings of the 10th International Conference on Language Resources and Evaluation. Paris, France: LREC, 2016: 4417–4422.
[73] PUSTEJOVSKY J, HANKS P, SAURI R, et al. The timebank corpus[J]. Corpus linguistics, 2003, 2003: 647–656.
[74] WHITE A S, RUDINGER R, RAWLINS K, et al. Lexicosyntactic inference in neural models[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Stroudsburg, USA: ACL, 2018: 4717–4724.
[75] UZZAMAN N, LLORENS H, DERCZYNSKI L, et al. Semeval-2013 task 1: Tempeval-3: Evaluating time expressions, events, and temporal relations[C]//Proceedings of the 7th International Workshop on Semantic Evaluation. Stroudsburg, USA: ACL, 2013: 1–9.
[76] MARNEFFE M, DOZAT T, SILVEIRA N, et al. Universal Stanford dependencies: A cross-linguistic typology[C]//Proceedings of the 9th International Conference on Language Resources and Evaluation. Paris, France: LREC, 2014: 4585–4592.

备注/Memo

收稿日期:2021-09-27。
基金项目:国家自然科学基金项目（U19B2020）.
作者简介:黄河燕，教授，博士，中国中文信息学会副理事长，北京理工大学人工智能学院院长，北京海量语言信息处理与云计算工程研究中心主任，主要研究方向为自然语言处理、信息抽取、机器翻译、社交网络、信息检索、智能处理系统。曾获国家科技进步一等奖、中国科学院科技进步一等奖和北京市科学技术一等奖等奖励。发表学术论文50余篇;刘啸，博士研究生，主要研究方向为信息抽取、事件抽取、事件模板推导、自然语言处理。
通讯作者:黄河燕. E-mail：hhy63@bit.edu.cn

更新日期/Last Update: 1900-01-01
Copyright © 《 智能系统学报》 编辑部
地址：（150001）黑龙江省哈尔滨市南岗区南通大街145-1号楼 电话：0451- 82534001、82518134　邮箱：tis@vip.sina.com