基于BiLSTM-CRF的社会突发事件研判方法  

Social Emergency Event Judgement Based on BiLSTM-CRF

作　　者：胡慧君[1] 王聪 代建华 刘茂福[1] HU Huijun;WANG Cong;DAI Jianhua;LIU Maofu(School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan,Hubei 430065,China;Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing,Hunan Normal University,Changsha,Hunan 410081,China)

机构地区：[1]武汉科技大学计算机科学与技术学院,湖北武汉430065 [2]湖南师范大学智能计算与语言信息处理湖南省重点实验室,湖南长沙410081

出　　处：《中文信息学报》2022年第3期154-161,共8页Journal of Chinese Information Processing

基　　金：国家社会科学基金重大研究计划(11&ZD189)。

摘　　要：社会突发事件的分类和等级研判作为应急处置中的一环,其重要性不言而喻。然而,目前研究多数采用人工或规则的方法识别证据进行研判,由于社会突发事件构成的复杂性和语言描述的灵活性,这对于研判证据识别有很大局限性。该文参考“事件抽取”思想,将事件类型和研判证据作为事件中元素,以BiLSTM-CRF方法进行细粒度的识别,并将二者结合,分类结果作为等级研判的输入,识别出研判证据。最终将识别结果结合注意力机制进行等级研判,通过对研判证据的精准识别来增强等级研判的准确性。实验表明,相比人工或规则识别研判证据,该文提出的方法有着更好的鲁棒性,社会突发事件研判时也达到了较好的效果。In recent years,classification and rating of social emergency event have attracted more and more attentions.Most of the current studies adopt the rule-based methods to identify the evidences for event judgement.Inspired by the idea of event extraction,this paper proposes the event judgement method via BiLSTM(Bi-directional LongShort-Term Memory)and CRF(Conditional Random Fields)based on event classification and evidence extraction.The social emergency event classification is performed,and then the event evidences are extracted based on event type.In the end,the rating of social emergency event is determined by the attention mechanism with event type and evidences.Experimental results show that the proposed method is more robust than rule-based ones,and effective in the social emergency event judgment.

关 键 词：突发事件分类 研判证据识别 等级研判 BiLSTM-CRF 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]