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。
Abstract
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
{{custom_keyword}} /
Key words
emergency event classification /
evidence extraction /
emergency event judgement /
BiLSTM-CRF
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Ivica Petrovi＇c, Srete Nikolovski, et al. Determining impact of lightning strike location on failures in transmission network elements using fuzzy decision making[J]. IEEE Systems Journal, 2020, 14(2):2665-2675.
[2] Sedova, Nelly A, et al. Analysis of emergency level at sea using fuzzy logic approaches[C]//Proceedings of the International Conference of Artificial Intelligence, Medical Engineering, Education, 2017: 314-322.
[3] Kaichang Sun, Wenjun Ma, Quan Li.Decision-making of IAHP-intuitionistic fuzzy set-based emergency rescue scheme[J]. Water Resources and Hydropower Engineering, 2018, 49(6):135-140.
[4] Lingxia Hou, Kunying Li. Classification of emergency supplies on fuzzy clustering[J]. Logistics engineering and management, 2013, (3):74-75.
[5] Jiangnan Qiu, Yanzhang Wang, Leilei Dong, et al. A model for predicting emergency event based on Bayesian networks[J]. Journal of Systems Management, 2011,20(1):98-103.
[6] Zhe Fu, Hao Zhang, Qiang Chen. Application of Naive Bayes classifier in stampede risk early-warning of large-scale activities[C]//Proceedings of the International Conference on Industrial Informatics, Computing Technology, Intelligent Technology, Industrial Information Integration. IEEE, 2016: 174-180.
[7] 商丽媛, 谭清美. 基于支持向量机的突发事件分级研究[J]. 管理工程学报, 2014. 028(001):119-123.
[8] 徐绪堪, 王京. 基于随机森林的突发事件分级模型研究[J]. 中国安全生产科学技术, 2018, 014(002):77-81.
[9] Xiaofeng Mu, Aiping Xu. A character-level BiLSTM-CRF model with multi-representations for Chinese event detection[J]. IEEE Access, 2019, 7: 146524-146532.
[10] Luheng He, Lee Kenton, Omer Levy, et al. Jointly predicting predicates and arguments in neural semantic role labeling[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 364-369.
[11] 李素建, 王厚峰, 俞士汶,等.关键词自动标引的最大熵模型应用研究[J]. 计算机学报, 2004, 27(9):1192-1197.
[12] 韩永峰, 郭志刚, 陈翰,等,基于领域特征词的突发事件层次分类方法[J]. 信息工程大学学报, 2012, 3(5):593-600.
[13] 沈兰奔,武志昊,纪宇泽,等. 结合注意力机制与双向LSTM的中文事件检测方法[J]. 中文信息学报, 2019, 33(9): 79-87.
[14] 贾泓昊, 罗智勇. 基于序列标注的引语识别初探[J]. 中文信息学报, 2019, 33(2): 1-7.
[15] 应文豪, 李素建, 穗志方. 一种话题敏感的抽取式多文档摘要方法[J]. 中文信息学报, 2017, 31(6): 155-161.
[16] 杨健, 黄瑞章, 丁志远,等. 基于边界识别与组合的裁判文书证据抽取方法研究[J]. 中文信息学报, 2020, 34(3): 80-87.
[17] Shuhui Gao, Xiao Jia. Application of convolutional neural network in forensic evidence examination and prospect of hair evidence identification[J]. Science technology and engineering, 2019, 19(23):1-9.
[18] Yang S, Feng D, Qiao L, et al. Exploring Pre-trained Language Models for Event Extraction and Generation[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 5284-5294.
[19] Sims M, Park J H, Bamman D. Literary Event Detection[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 3623-3634.
[20] Luo Y, Wang X, Liu X, et al. A Rule-Based Event Handling Model[C]//Proceedings of the IEEE Asia-pacific Services Computing Conference, IEEE, 2008: 869-875.
[21] Deliang Jiang. Research on extraction of emergency event information based on rules matching[J]. Computer Engineering and Design, 2010, 31(14):3294-3297.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家社会科学基金重大研究计划(11&ZD189)
{{custom_fund}}
PDF(2371 KB)
