基于递归神经网络的中文事件检测

doi:10.3969/j.issn.1671-1122.2018.05.009

信息网络安全 ›› 2018, Vol. 18 ›› Issue (5): 75-81.doi: 10.3969/j.issn.1671-1122.2018.05.009

基于递归神经网络的中文事件检测

马晨曦^1,², 陈兴蜀^2,³, 王文贤^2,³, 王海舟^2,³()

1.四川大学计算机学院网络与可信计算研究所,四川成都 610065
2.四川大学网络空间安全研究院,四川成都 610065
3.四川大学网络空间安全学院,四川成都 610065

收稿日期:2017-11-26 出版日期:2018-05-15 发布日期:2020-05-11
作者简介:
作者简介：马晨曦（1993—）,女,河北,硕士研究生,主要研究方向为舆情分析、网络安全;陈兴蜀（1968—）,女,四川,教授,博士,主要研究方向为云计算和大数据安全、舆情分析;王文贤（1978—）,男,福建,讲师,博士,主要研究方向为网络空间安全、舆情分析和挖掘;王海舟（1986—）,男,四川,讲师,博士,主要研究方向为网络空间安全、舆情分析和挖掘。
基金资助:
国家自然科学基金[61272447];四川省科技厅计划项目[16ZHSF0483]

Chinese Event Detection Based on Recurrent Neural Network

Chenxi MA^1,², Xingshu CHEN^2,³, Wenxian WANG^2,³, Haizhou WANG^2,³()

1. Network and Trusted Computing Institute, Computer College, Sichuan University, Chengdu Sichuan 610065, China
2.Cybersecurity Research Institute, Sichuan University, Chengdu Sichuan 610065, China
3.College of Cybersecurity, Sichuan University, Chengdu Sichuan 610065, China

Received:2017-11-26 Online:2018-05-15 Published:2020-05-11

摘要/Abstract

摘要：

随着互联网的迅猛发展,我国网民的规模迅速增长,互联网对人们的生活和社会影响力也日益加深,面对日益增长的海量互联网信息,快速定位到公众讨论的事件变得至关重要。事件抽取是信息抽取领域的一个重要研究方向,事件检测是事件抽取任务的第一步,在事件抽取任务中起到至关重要的作用。文章采用了基于递归神经网络的事件检测联合模型,实现了对事件触发词的识别和事件类别的分类。与传统的触发词检测方法相比,本文提出的联合模型避免了误差的传播,不依赖于触发词表的构造和扩展,有很好的移植性,而且不需要设计复杂的语言特征,依赖神经网络自动学习特征。文章选用CEC语料库作为训练语料和测试语料,实验结果表明该方法识别触发词和事件类别的准确率和召回率较高,F值为70.2%,优于传统方法。

关键词: 事件检测, 触发词, 事件抽取, 递归神经网络, 词向量

Abstract:

With the development of Internet, the size of the Internet users has grown rapidly. The Internet has become more and more important to people’s life and social influence. In the face of the growing mass of Internet information, it is vital to quickly locate the events of public discussion. Event extraction is an important research in the field of information extraction. Event detection is the first step in the event extraction task, which plays a crucial role in the event extraction task.We designed a joint model based on recurrent neural network, to realize the recognition of event trigger and the classification of event category. Compared with the traditional method, our joint model can avoid error propagation, it doesn’t depend on the table of the trigger word and has good portability, and doesn’t need to design complex linguistic features.We used CEC corpus as training corpus and test corpus. The experimental results show that accuracy rate of the trigger word and event category is high, and the F value is 70.2%, better than the traditional method.

Key words: event detection, trigger, event extraction, RNN, word embedding

中图分类号:

TP309

马晨曦, 陈兴蜀, 王文贤, 王海舟. 基于递归神经网络的中文事件检测[J]. 信息网络安全, 2018, 18(5): 75-81.

Chenxi MA, Xingshu CHEN, Wenxian WANG, Haizhou WANG. Chinese Event Detection Based on Recurrent Neural Network[J]. Netinfo Security, 2018, 18(5): 75-81.

图/表 4

参考文献 21

[1]	CNCERT. 第40次中国互联网络发展状况统计报告[EB/OL]. ,2017-10-1.
[2]	GUL K S Q, YIN Jize, PAN Limin, et al. Research on the Algorithm of Named Entity Recognition Based onDeep Neural Network[J]. Netinfo Security, 2017(10):29-35.
	GUL K S Q, 尹继泽, 潘丽敏,等. 基于深度神经网络的命名实体识别方法研究[J]. 信息网络安全, 2017(10):29-35.
[3]	XUAN Xiaoxing, LIAO Tao, GAO Beibei.Automatic Extraction of Chinese Event Trigger Word[J]. Computer & Digital Engineering, 2015(3):457-461.
	轩小星, 廖涛, 高贝贝. 中文事件触发词的自动抽取研究[J]. 计算机与数字工程, 2015(3):457-461.
[4]	AONE C, RAMOS-SANTACRUZ M.REES: A Large-Scale Relation and Event Extraction System[C]// Association for Computational Linguistics. Proceedings ofthe 6th Applied Natural Language Processing Conference, April 29 - May 4, 2000, Seattle, Washington. Stroudsburg, PA, USA. New York: Association for Computational Linguistics, 2000:76-83.
[5]	HUNG S H, LIN C H, HONG J S.Web Mining for Event-based Commonsense Knowledge using Lexicon-Syntactic Pattern Matching and Semantic Role Labeling[J]. Expert Systems with Applications, 2010, 37(1):341-347.
[6]	COHEN K B, VERSPOOR K, JOHNSON H L, et al.High-Precision Biological Event Extraction with a Concept Recognizer[C]//Association for Computational Linguistics. Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing, June 19, 2008, Columbus, Ohio. Stroudsburg, PA, USA. New York: Association for Computational Linguistics, 2008:50-58.
[7]	YANGARBER R.Scenario Customization for Information Extraction[D].New York:New York University, 2001.
[8]	JIANG Jifa.A Method to Do Chinese Event IE from A MultipleSentences' Event Narration[J]. Computer Engineering, 2005, 31(2):27-29.
	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.
[9]	HAI L C, NG H T.A Maximum Entropy Approach to Information Extraction from Semi-Structured and Free Text[C]// American Association for Artificial Intelligence. Proceedings of the Eighteenth National Conference on Artificial Intelligence, July 28-August 1, 2002, Edmonton, Alberta, Canada. Menlo Park, California: the AAAI Press, 2002:786-791.
[10]	CHEN Z, JI H.Language Specific Issue and Feature Exploration in Chinese Event Extraction[C]// Association for Computational Linguistics. Proceedings of Human Language Technologies: the 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, June 1-3, 2009, Boulder, Colorado. Stroudsburg, PA, USA. New York: Association for Computational Linguistics, 2009:209-212.
[11]	LLORENS H, SAQUETE E, NAVARRO-COLORADO B.TimeML Events Recognition and Classification: Learning CRF Models with Semantic Roles[C]// Association for Computational Linguistics. Proceedings of the 23rd International Conference on Computational Linguistics.August 23-27, 2010, Beijing, China. Stroudsburg, PA, USA: Association for Computational Linguistics, 2010:725-733.
[12]	LI Q, JI H, HUANG L.Joint Event Extraction via Structured Prediction with Global Features[C]// Association for Computational Linguistics. Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics,August 4-9, 2013, Sofia, Bulgaria. Stroudsburg, PA, USA. New York: Association for Computational Linguistics, 2013:73-82.
[13]	CHEN Y, XU L, LIU K, et al.Event Extraction via Dynamic Multi-Pooling Convolutional Neural Networks[C]// Association for Computational Linguistics. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguisticsand the 7th International Joint Conference on Natural Language Processing, July 26-31, 2015, Beijing, China. Stroudsburg, PA, USA: Association for Computational Linguistics, 2015:167-176.
[14]	NGUYEN T H, CHO K, GRISHMAN R.Joint Event Extraction via Recurrent Neural Networks[C]// Association for Computational Linguistics. Proceedings of NAACL-HLT, June 12-17, 2016,San Diego, California. Stroudsburg, PA, USA. New York: Association for Computational Linguistics, 2016:300-309.
[15]	ZENG Y, YANG H, FENG Y, et al.A Convolution BiLSTM Neural Network Model for Chinese Event Extraction[C]// CCF. Proceedings of NLPCC-ICCPOL,December 2-6, 2016, Kunming, China. Cham: Springer, 2016:275-287.
[16]	MIKOLOV T, SUTSKEVER I, CHEN K, et al.Distributed Representations of Words and Phrases and their Compositionality[C]//The Neural Information Processing Systems (NIPS) Foundation. Proceedings of NIPS,December 5-10, 2013,Harrahs and Harveys, Lake Tahoe. USA: NIPS, 2013: 3111-3119.
[17]	DUAN Dagao, XIE Yongheng, GAI Xinxin, et al.A Rumor Detection Model Based on Neural Network[J]. Netinfo Security, 2017(9):134-137.
	段大高, 谢永恒, 盖新新,等. 基于神经网络的微博虚假消息识别模型[J]. 信息网络安全, 2017(9):134-137.
[18]	ZHAO Yanyan, QIN Bing, CHE Wanxiang, et al.Research on Chinese Event Extraction[J]. Journal of Chinese Information Processing, 2008, 22(1):3-8.
	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.
[19]	CUI Pengfei, QIU Yue, SUN Rui.Research on Image Recognition Technology for the NetworkContent Security[J]. Netinfo Security, 2015(9):154-157.
	崔鹏飞, 裘玥, 孙瑞. 面向网络内容安全的图像识别技术研究[J]. 信息网络安全, 2015(9):154-157.
[20]	HOCHREITER S, SCHMIDHUBER J.Long Short-Term Memory[J]. Neural Computation, 1997, 9(8):1735.
[21]	CHO K, MERRIENBOER B V, GULCEHRE C, et al.Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation[C]// Association for Computational Linguistics. Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing,October 25-29, 2014, Doha, Qatar. Stroudsburg, PA, USA. New York: Association for Computational Linguistics, 2014:1724-1734.

基于递归神经网络的中文事件检测

Chinese Event Detection Based on Recurrent Neural Network

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 4

参考文献 21

相关文章 15

编辑推荐

Metrics

本文评价

[1]	赵志岩, 纪小默. 智能化网络安全威胁感知融合模型研究[J]. 信息网络安全, 2020, 20(4): 87-93.
[2]	刘敏, 陈曙晖. 基于关联融合的VoLTE流量分析研究[J]. 信息网络安全, 2020, 20(4): 81-86.
[3]	边玲玉, 张琳琳, 赵楷, 石飞. 基于LightGBM的以太坊恶意账户检测方法[J]. 信息网络安全, 2020, 20(4): 73-80.
[4]	杜义峰, 郭渊博. 一种基于信任值的雾计算动态访问控制方法[J]. 信息网络安全, 2020, 20(4): 65-72.
[5]	傅智宙, 王利明, 唐鼎, 张曙光. 基于同态加密的HBase二级密文索引方法研究[J]. 信息网络安全, 2020, 20(4): 55-64.
[6]	王蓉, 马春光, 武朋. 基于联邦学习和卷积神经网络的入侵检测方法[J]. 信息网络安全, 2020, 20(4): 47-54.
[7]	董晓丽, 商帅, 陈杰. 分组密码9轮Rijndael-192的不可能差分攻击[J]. 信息网络安全, 2020, 20(4): 40-46.
[8]	郭春, 陈长青, 申国伟, 蒋朝惠. 一种基于可视化的勒索软件分类方法[J]. 信息网络安全, 2020, 20(4): 31-39.
[9]	陈璐, 孙亚杰, 张立强, 陈云. 物联网环境下基于DICE的设备度量方案[J]. 信息网络安全, 2020, 20(4): 21-30.
[10]	江金芳, 韩光洁. 无线传感器网络中信任管理机制研究综述[J]. 信息网络安全, 2020, 20(4): 12-20.
[11]	刘建伟, 韩祎然, 刘斌, 余北缘. 5G网络切片安全模型研究[J]. 信息网络安全, 2020, 20(4): 1-11.
[12]	刘鹏, 何倩, 刘汪洋, 程序. 支持撤销属性和外包解密的CP-ABE方案[J]. 信息网络安全, 2020, 20(3): 90-97.
[13]	宋宇波, 樊明, 杨俊杰, 胡爱群. 一种基于拓扑分析的网络攻击流量分流和阻断方法[J]. 信息网络安全, 2020, 20(3): 9-17.
[14]	王腾飞, 蔡满春, 芦天亮, 岳婷. 基于iTrace_v6的IPv6网络攻击溯源研究[J]. 信息网络安全, 2020, 20(3): 83-89.
[15]	张艺, 刘红燕, 咸鹤群, 田呈亮. 基于授权记录的云存储加密数据去重方法[J]. 信息网络安全, 2020, 20(3): 75-82.