Please wait a minute...
Advanced Search
数据分析与知识发现  2020, Vol. 4 Issue (10): 1-13     https://doi.org/10.11925/infotech.2096-3467.2020.0383
  综述评介 本期目录 | 过刊浏览 | 高级检索 |
领域事件图谱构建方法综述*
王毅1,沈喆1,姚毅凡1,成颖1,2()
1南京大学信息管理学院 南京 210023
2山东师范大学文学院 济南 250014
Domain-Specific Event Graph Construction Methods:A Review
Wang Yi1,Shen Zhe1,Yao Yifan1,Cheng Ying1,2()
1School of Information Management, Nanjing University, Nanjing 210023, China
2School of Chinese Language and Literature, Shandong Normal University, Jinan 250014, China
全文: PDF (812 KB)   HTML ( 42
输出: BibTeX | EndNote (RIS)      
摘要 

【目的】 分析并评述领域事件知识图谱构建的相关研究,为后续研究提供理论基础和实践指导。【文献范围】 利用Web of Science核心数据库和Google Scholar以“Event Graph”、“Event extraction”和“Event relation”等主题词进行检索,经过手工筛选获得代表性文献61篇。【方法】 采用文献调研方法系统梳理领域事件图谱在定义、构建流程、识别方法等方面的工作。总结了基于规则、基于特征学习以及基于神经网络三种事件抽取的方法,对事件抽取与事件关系抽取中的特征选择、模型架构以及实验结果等进行分析和对比。【结果】 借鉴通用图谱构建的方法,提出包括事件触发词识别、事件要素识别、事件关系识别以及事件存储等在内的领域事件图谱构建流程模型。从描述结构、领域限制、事件形式、推理能力和时序关系等角度阐明构建标准应具备的元素。在构建实践中,事件本体的借鉴和复用是必要选项,事件抽取采用神经网络方法是目前最优的选择。【局限】 由于标准数据集的缺失,事件关系抽取对比中未能采用统一的数据集进行量化比较。【结论】 提出从知识提升、迁移学习以及认知模型等三个视角开展该主题后继研究的建议。

服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
王毅
沈喆
姚毅凡
成颖
关键词 领域事件图谱知识图谱事件抽取信息提取    
Abstract

[Objective] This paper reviews construction methods for domain-specific event graphs, aiming to facilitate future research.[Coverage] We searched “Event Graph”, “Event extraction” and “Event relation” with Web of Science and Google Scholar, then retrieved a total of 61 representative literature.[Methods] We summarized the definition, construction process and extraction methods with literature review. Then, we discussed the rule-based, feature learning based, and neural network-based extraction techniques. Finally, we analyzed their feature selection procedures, model architecture and experiment results.[Results] Refer to the general knowledge graph construction methods, we proposed a process model that include trigger argument and relation recognition. We briefly described on construction standard in structure, domain, event form, inference ability and temporal relations. In practice, we found that Ontology reuse is necessary, and neural network is the best choice.[Limitations] We did not use the same dataset to evaluate all methods.[Conclusions] We proposed knowledge-boosted methods, transfer learning and cognitive models for future studies.

Key wordsDomain-Specific Event Graph    Knowledge Graph    Event Extraction    Information Extraction
收稿日期: 2020-05-05      出版日期: 2020-07-17
ZTFLH:  G350  
基金资助:*本文系国家社会科学基金重大项目“中国近现代文学期刊全文数据库建设与研究(1872-1949)”的研究成果之一(17ZDA276)
通讯作者: 成颖     E-mail: Chengy@nju.edu.cn
引用本文:   
王毅,沈喆,姚毅凡,成颖. 领域事件图谱构建方法综述*[J]. 数据分析与知识发现, 2020, 4(10): 1-13.
Wang Yi,Shen Zhe,Yao Yifan,Cheng Ying. Domain-Specific Event Graph Construction Methods:A Review. Data Analysis and Knowledge Discovery, 2020, 4(10): 1-13.
链接本文:  
https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/10.11925/infotech.2096-3467.2020.0383      或      https://manu44.magtech.com.cn/Jwk_infotech_wk3/CN/Y2020/V4/I10/1
Fig.1  领域事件图谱构建流程
Fig.2  事件图谱层次关系
Fig.3  事件抽取例子
方法分类 方法 学习方式 事件触发词识别 事件要素识别
P R F1 P R F1
基于特征的方法 Li’s baseline[61] 联合学习 74.5% 59.1% 65.9% 74.1% 37.4% 49.7%
基于特征的方法 Liao’s cross-event[43] 管道模型 68.7% 68.9% 68.8% 50.9% 49.7% 50.3%
基于特征的方法 Hong’s cross-entity[42] 管道模型 72.9% 64.3% 68.3% 53.4% 52.9% 53.1%
基于神经网络的方法 CNN[46] 管道模型 72.5% 43.1% 66.3% 51.6% 36.6% 48.9%
基于神经网络的方法 DMCNN[46] 管道模型 74.6% 50.9% 69.1% 54.6% 48.7% 53.5%
基于神经网络的方法 JRNN[52] 联合模型 66.0% 73.0% 69.3% 61.4% 64.2% 62.8%
Table 1  事件抽取代表模型在ACE数据集的效果对比
方法 算法 关系类型 R P F1
KERNEL-method[55] Voted Perceptron Person-Affiliation 81.62% 90.05% 85.61%
KERNEL-method[55] SVM Person-Affiliation 82.73% 91.32% 86.80%
Joint Extraction[57] Hybrid Neural Network Live_In/Work_For 78.30% 83.20% 80.60%
Event Co-occurrence Network[60] Co-occurrence Network Casual/Follow Accompany/Taxonomic 85.20% 89.60% 87.30%
Event-Argument Relation Extraction[54] SVM Event-Argument - - 69.70%
Long-Distance[59] Linear+PTK Time-Event 64.00% 60.90% 62.30%
Temporal Relation Extraction[56] CNN Time-Event 68.10% 72.70% 70.30%
Temporal Relation Extraction[56] LSTM Time-Event 66.00% 69.80% 67.90%
Joint Reasoning[58] Joint Learning Temporal/Causal 74.40% 69.30% 71.80%
Table 2  事件关系抽取效果对比
[1] Erxleben F, Günther M, Krötzsch M, et al. Introducing Wikidata to the Linked Data Web[C]//Proceedings of the 13th International Semantic Web Conference. Springer, Cham, 2014: 50-65.
[2] Lehmann J, Isele R, Jakob M, et al. DBpedia-A Large-Scale, Multilingual Knowledge Base Extracted from Wikipedia[J]. Semantic Web, 2015,6(2):167-195.
doi: 10.3233/SW-140134
[3] Dong X, Gabrilovich E, Heitz G, et al. Knowledge Vault: A Web-Scale Approach to Probabilistic Knowledge Fusion[C]// Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2014: 601-610.
[4] Herrmannova D, Knoth P. An Analysis of the Microsoft Academic Graph[J]. D-Lib Magazine, 2016,22(9/10). DOI: 10.1045/september2016-herrmannova.
[5] Leetaru K, Schrodt P A. GDELT: Global Data on Events, Location, and Tone, 1979-2012[C]// Proceedings of the 2013 Annual Meeting of the International Studies Association. Citeseer, 2013,2(4):1-49.
[6] Berners-Lee T, Hendler J, Lassila O. The Semantic Web[J]. Scientific American, 2001,284(5):34-43.
[7] Ji S, Pan S, Cambria E, et al. A Survey on Knowledge Graphs: Representation, Acquisition and Applications[OL]. arXiv Preprint, arXiv:2002.00388.
[8] Bonatti P A, Decker S, Polleres A, et al. Knowledge Graphs: New Directions for Knowledge Representation on the Semantic Web(Dagstuhl Seminar 18371)[J]. Dagstuhl Reports, 2019,8(9):29-111.
[9] Yan J, Wang C, Cheng W, et al. A Retrospective of Knowledge Graphs[J]. Frontiers of Computer Science, 2018,12(1):55-74.
doi: 10.1007/s11704-016-5228-9
[10] Wu T, Qi G, Li C, et al. A Survey of Techniques for Constructing Chinese Knowledge Graphs and Their Applications[J]. Sustainability, 2018,10(9):3245.
doi: 10.3390/su10093245
[11] Paulheim H. Knowledge Graph Refinement: A Survey of Approaches and Evaluation Methods[J]. Semantic Web, 2017,8(3):489-508.
doi: 10.3233/SW-160218
[12] Ehrlinger L, Wöß W. Towards a Definition of Knowledge Graphs[C]//Joint Proceedings of the Posters and Demos Track of 12th International Conference on Semantic Systems and the 1st International Workshop on Semantic Change & Evolving Semantics. 2016.
[13] Akerkar R, Sajja P. Knowledge-based Systems[M]. Jones & Bartlett Publishers, 2010.
[14] Deng J, Qiao F, Li H, et al. An Overview of Event Extraction from Twitter[C]//Proceedings of the 2015 International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery. IEEE, 2015: 251-256.
[15] Kejriwal M. Domain-Specific Knowledge Graph Construction[M]. Springer International Publishing, 2019.
[16] Lautenschlager J, Shellman S, Ward M. ICEWS Events and Aggregations[OL]. Advanced Technology Laboratories. http://data.nber.org/ens/feldstein/NBER_Sources/ENS%20Conference% 20Sources/2016/Predicting%20Conflict%20Via%20Machine%20Learning/ICEWS%20(Lockheed%20Martin)/Dictionaries/ICEWS%20Events%20and%20Aggregations.pdf.
[17] Sadeghian A, Rodriguez M, Wang D Z, et al. Temporal Reasoning over Event Knowledge Graphs[C]//Proceedings of the 2018 Workshop on Knowledge Base Construction, Reasoning and Mining. 2018.
[18] Li Z, Ding X, Liu T. Constructing Narrative Event Evolutionary Graph for Script Event Prediction[OL]. arXiv Preprint, arXiv:1805.05081.
[19] Rospocher M, van Erp M, Vossen P, et al. Building Event-Centric Knowledge Graphs from News[J]. Journal of Web Semantics, 2016,37/38:132-151.
doi: 10.1016/j.websem.2015.12.004
[20] Noy N F, McGuinness D L. Ontology Development 101: A Guide to Creating Your First Ontology[R]. Stanford Knowledge Systems Laboratory, 2001.
[21] Fabian M S, Gjergji K, Gerhard W. YAGO: A Core of Semantic Knowledge Unifying WordNet and Wikipedia[C]// Proceedings of the 16th International World Wide Web Conference. 2007: 697-706.
[22] van Hage W R, Malaisé V, Segers R, et al. Design and Use of the Simple Event Model (SEM)[J]. Journal of Web Semantics, 2011,9(2):128-136.
doi: 10.1016/j.websem.2011.03.003
[23] Fokkens A, van Erp M, Vossen P, et al. GAF: A Grounded Annotation Framework for Events[C]//Proceedings of the 1st Workshop on Events: Definition, Detection, Coreference, and Representation. 2013: 11-20.
[24] Bejan C A, Harabagiu S M. A Linguistic Resource for Discovering Event Structures and Resolving Event Coreference[C]// Proceedings of the 6th International Conference on Language Resources and Evaluation. 2008.
[25] Cybulska A, Vossen P. Using a Sledgehammer to Crack a Nut? Lexical Diversity and Event Coreference Resolution[C]// Proceedings of the 9th International Conference on Language Resources and Evaluation. 2014: 4545-4552.
[26] Baker C F, Fillmore C J, Lowe J B. The Berkeley FrameNet Project[C]// Joint Proceedings of the 36th Annual Meeting of the Association for Computational Linguistics and the 17th International Conference on Computational Linguistics. Association for Computational Linguistics, 1998: 86-90.
[27] Segers R, Vossen P T J M, Rospocher M, et al. ESO: A Frame Based Ontology for Events and Implied Situations[A]//Maplex[M]. Vrije Universiteit Amsterdam, 2015.
[28] Piskorski J, Tanev H, Atkinson M, et al. Online News Event Extraction for Global Crisis Surveillance[A]// Transactions on Computational Collective Intelligence V[M]. Springer, Berlin, Heidelberg, 2011: 182-212.
[29] The ACE 2005 (ACE05) Evaluation Plan Evaluation of the Detection and Recognition of ACE[R]. The ACE 2005 Evaluation Plan, 2005.
[30] Fellbaum C. WordNet: An Electronic Lexical Database and Some of Its Applications[M]. MIT Press, 1998.
[31] Borsje J, Hogenboom F, Frasincar F. Semi-Automatic Financial Events Discovery Based on Lexico-Semantic Patterns[J]. International Journal of Web Engineering and Technology, 2010,6(2):115-140.
doi: 10.1504/IJWET.2010.038242
[32] Yakushiji A, Tateisi Y, Miyao Y, et al. Event Extraction from Biomedical Papers Using a Full Parser[J]. Pacific Symposium Biocomputing, 2001: 408-419. DOI: 10.1142/9789814447362_0040.
[33] Nishihara Y, Sato K, Sunayama W. Event Extraction and Visualization for Obtaining Personal Experiences from Blogs[C]// Proceedings of the 2009 Symposium on Human Interface. Springer, Berlin, Heidelberg, 2009: 315-324.
[34] Hung S H, Lin C H, Hong J S. Web Mining for Event-Based Commonsense Knowledge Using Lexico-Syntactic Pattern Matching and Semantic Role Labeling[J]. Expert Systems with Applications, 2010,37(1):341-347.
doi: 10.1016/j.eswa.2009.05.060
[35] Stevenson M, Greenwood M A. A Semantic Approach to IE Pattern Induction[C]// Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics. Association for Computational Linguistics, 2005: 379-386.
[36] Huang R, Riloff E. Bootstrapped Training of Event Extraction Classifiers[C]//Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics. Association for Computational Linguistics, 2012: 286-295.
[37] Bronstein O, Dagan I, Li Q, et al. Seed-Based Event Trigger Labeling: How Far can Event Descriptions Get Us?[C]// Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing. 2015: 372-376.
[38] Yangarber R, Grishman R, Tapanainen P, et al. Automatic Acquisition of Domain Knowledge for Information Extraction[C]//Proceedings of the 18th Conference on Computational Linguistics. Association for Computational Linguistics, 2000: 940-946.
[39] Grishman R, Westbrook D, Meyers A. 2005 NYU’s English ACE 2005 System Description[OL]. https://nlp.cs.nyu.edu/publication/papers/ACE05-NYUEnglishSysDescrDec10.pdf.
[40] Li Q. Joint Information Extraction[D]. New York: Rensselaer Polytechnic Institute, 2015.
[41] Patwardhan S, Riloff E. A Unified Model of Phrasal and Sentential Evidence for Information Extraction[C]//Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, 2009: 151-160.
[42] Hong Y, Zhang J, Ma B, 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. Association for Computational Linguistics, 2011: 1127-1136.
[43] Liao 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. Association for Computational Linguistics, 2010: 789-797.
[44] Ji H, Grishman R. Refining Event Extraction Through Cross-Document Inference[C]//Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics. 2008: 254-262.
[45] 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. 2016: 886-891.
[46] Chen Y, Xu L, 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. 2015: 167-176.
[47] Niklaus C, Cetto M, Freitas A, et al. A Survey on Open Information Extraction[C]//Proceedings of the 27th International Conference on Computational Linguistics. 2018: 3866-3878.
[48] Peng H, Li J, Gong Q, et al. Fine-grained Event Categorization with Heterogeneous Graph Convolutional Networks[OL]. arXiv Preprint, arXiv:1906.04580.
[49] Jagannatha A N, Yu H. Bidirectional RNN for Medical Event Detection in Electronic Health Records[C]//Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016: 473-482.
[50] Duan S, He R, Zhao W. Exploiting Document Level Information to Improve Event Detection via Recurrent Neural Networks[C]//Proceedings of the 8th International Joint Conference on Natural Language Processing. 2017: 352-361.
[51] Zhao Y, Jin X, Wang Y, et al. Document Embedding Enhanced Event Detection with Hierarchical and Supervised Attention[C]// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. 2018: 414-419.
[52] 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.
[53] Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of Deep Bidirectional Transformers for Language Understanding[OL]. arXiv Preprint, arXiv:1810.04805.
[54] Yoshikawa K, Riedel S, Hirao T, et al. Coreference Based Event-Argument Relation Extraction on Biomedical Text[J]. Journal of Biomedical Semantics, 2011, 2(S5): Article No. S6.
doi: 10.1186/2041-1480-2-S4-S1 pmid: 21995847
[55] Zelenko D, Aone C, Richardella A. Kernel Methods for Relation Extraction[J]. Journal of Machine Learning Research, 2003,3:1083-1106.
[56] Dligach D, Miller T, Lin C, et al. Neural Temporal Relation Extraction[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. 2017: 746-751.
[57] Zhou P, Zheng S, Xu J, et al. Joint Extraction of Multiple Relations and Entities by Using a Hybrid Neural Network[A]// Chinese Computational Linguistics and Natural Language Processing Based on Naturally Annotated Big Data[M]. Springer, Cham, 2017: 135-146.
[58] Ning Q, Feng Z, Wu H, et al. Joint Reasoning for Temporal and Causal Relations[OL]. arXiv Preprint, arXiv: 1906.04941.
[59] Moschitti A, Patwardhan S, Welty C. Long-Distance Time-Event Relation Extraction[C]// Proceedings of the 6th International Joint Conference on Natural Language Processing. 2013: 1330-1338.
[60] Liao T, Sun P, Liu Z. Event Relations Extraction Based on Event Co-occurrence Network[C]//Proceedings of the 8th International Symposium on Computational Intelligence and Design (ISCID). IEEE, 2015: 610-613.
[61] 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.
[1] 周阳,李学俊,王冬磊,陈方,彭莉娟. 炸药配方设计知识图谱的构建与可视分析方法研究*[J]. 数据分析与知识发现, 2021, 5(9): 42-53.
[2] 陈星月, 倪丽萍, 倪志伟. 基于ELECTRA模型与词性特征的金融事件抽取方法研究*[J]. 数据分析与知识发现, 2021, 5(7): 36-47.
[3] 喻雪寒, 何琳, 徐健. 基于RoBERTa-CRF的古文历史事件抽取方法研究*[J]. 数据分析与知识发现, 2021, 5(7): 26-35.
[4] 沈科杰, 黄焕婷, 化柏林. 基于公开履历数据的人物知识图谱构建*[J]. 数据分析与知识发现, 2021, 5(7): 81-90.
[5] 阮小芸,廖健斌,李祥,杨阳,李岱峰. 基于人才知识图谱推理的强化学习可解释推荐研究*[J]. 数据分析与知识发现, 2021, 5(6): 36-50.
[6] 李贺,刘嘉宇,李世钰,吴迪,金帅岐. 基于疾病知识图谱的自动问答系统优化研究*[J]. 数据分析与知识发现, 2021, 5(5): 115-126.
[7] 代冰,胡正银. 基于文献的知识发现新近研究综述 *[J]. 数据分析与知识发现, 2021, 5(4): 1-12.
[8] 余传明, 张贞港, 孔令格. 面向链接预测的知识图谱表示模型对比研究*[J]. 数据分析与知识发现, 2021, 5(11): 29-44.
[9] 陈仕吉, 邱均平, 余波. 基于Overlay图谱的图情领域大数据主题分析*[J]. 数据分析与知识发现, 2021, 5(10): 51-59.
[10] 邵琦,牟冬梅,王萍,靳春妍. 基于语义的突发公共卫生事件网络舆情主题发现研究*[J]. 数据分析与知识发现, 2020, 4(9): 68-80.
[11] 梁野,李小元,许航,胡伊然. CLOpin:一种面向舆情分析与预警领域的跨语言知识图谱架构*[J]. 数据分析与知识发现, 2020, 4(6): 1-14.
[12] 吕华揆,洪亮,马费成. 金融股权知识图谱构建与应用*[J]. 数据分析与知识发现, 2020, 4(5): 27-37.
[13] 孙鑫瑞,孟雨,王文乐. 基于知识图谱与目标检测的微博交通事件识别*[J]. 数据分析与知识发现, 2020, 4(12): 136-147.
[14] 朱超宇, 刘雷. 基于知识图谱的医学决策支持应用综述*[J]. 数据分析与知识发现, 2020, 4(12): 26-32.
[15] 胡正银,刘蕾蕾,代冰,覃筱楚. 基于领域知识图谱的生命医学学科知识发现探析*[J]. 数据分析与知识发现, 2020, 4(11): 1-14.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 2015 《数据分析与知识发现》编辑部
地址:北京市海淀区中关村北四环西路33号 邮编:100190
电话/传真:(010)82626611-6626,82624938
E-mail:jishu@mail.las.ac.cn