基于模糊贝叶斯决策的核心概念抽取方法

计算机工程与科学 ›› 2022, Vol. 44 ›› Issue (09): 1686-1692.

基于模糊贝叶斯决策的核心概念抽取方法

钟寒1,2，徐艺嘉1,鹿浩1，孙旌睿1

（1.中国人民公安大学信息网络安全学院，北京 102623；2.安全防范与风险评估公安部重点实验室,北京 102623）

收稿日期:2021-10-29 修回日期:2022-03-16 接受日期:2022-09-25 出版日期:2022-09-25 发布日期:2022-09-25
基金资助:
国家社会科学基金(20AZD114)；公安部科技强警基础工作专项(2019GABJC01)；公安部软科学理论研究计划(2021LL39)；中央高校基本科研业务费项目(2021JKF107)

A core concept extracting method based on fuzzy Bayesian decision-making

ZHONG Han1,2,XU Yi-jia1,LU Hao1,SUN Jing-rui1

(1.College of Information and Network Safety,People’s Public Security University of China,Beijing 102623;
2.Key Laboratory of Safety Precautions and Risk Assessment,Ministry of Public Security,Beijing 102623,China)

Received:2021-10-29 Revised:2022-03-16 Accepted:2022-09-25 Online:2022-09-25 Published:2022-09-25

摘要/Abstract

摘要： 为了提高特定领域核心概念抽取的效率，提出一种基于模糊贝叶斯决策的核心概念抽取方法。在特定领域内随机抽取大量文本并进行分词获取候选概念；然后采用TF-IDF算法计算候选概念的各项特征值，采用概念隶属度归一化处理候选概念特征值；最终通过贝叶斯决策计算候选概念为核心概念的概率。在财经领域相关数据集上进行文本核心概念抽取的实验结果表明，所提方法的F1值相比TextRank、LDA主题模型、word2vec词聚类模型、RNN、LSTM等的F1值有所提高。综合实验结果表明，基于模糊贝叶斯决策的核心概念抽取方法在核心概念抽取方面表现较好。

关键词: 概念抽取；概念隶属度；贝叶斯决策 ,

Abstract: In order to improve the efficiency of concept extraction in the field, a core concept extraction method based on fuzzy Bayesian decision-making is proposed. Firstly, after randomly extracting a large amount of text and sorting the text vocabulary, candidate concepts are obtained. Secondly, the characteristic values of the candidate concepts are calculated by the traditional TF-IDF algorithm, and normalized by the conceptual membership. Finally, the probability that the candidate concepts are the core concepts is calculated by Bayesian decision-making. The extraction experiment of the core concept of financial text shows that the average accuracy of core concept extraction is much higher than that of the traditional TextRank, LDA, word2vec, RNN and LSTM. Comprehensive experimental results show that the core concept extraction method based on fuzzy Bayesian decision-making performs better in core concept extraction.

Key words: concept extraction, conceptual membership, Bayesian decision-making

钟寒, 徐艺嘉, 鹿浩, 孙旌睿. 基于模糊贝叶斯决策的核心概念抽取方法[J]. 计算机工程与科学, 2022, 44(09): 1686-1692.

ZHONG Han, XU Yi-jia, LU Hao, SUN Jing-rui. A core concept extracting method based on fuzzy Bayesian decision-making[J]. Computer Engineering & Science, 2022, 44(09): 1686-1692.

参考文献［22］

［1］	Rani M, Dhar A K,Vyas O P.Semi-automatic terminology ontology learning based on topic modeling［J］.Engineering Applications of Artificial Intelligence,2017,63:108-125.
［2］	Shi L,Setchi R.Ontology-based personalized retrieval in support of reminiscence［J］.Knowledge-Based Systems,2013,45(3):47-61.
［3］	Wimalasuriya D C,Dou D J.Ontology-based information extraction:An introduction and a survey of current approaches［J］.Journal of Information Science,2009,36(3):306-323.
［4］	Zhu Ze-de.Research on key technology in mining web bilingual corpora［D］.Hefei:University of Science and Technology of China,2014.(in Chinese)
［5］	Wei You, Liu Mao-fu,Hu Hui-jun.Biomedical event extraction based on deep contextual word representation and self-attention［J］.Computer Engineering & Science,2020,42(9):1670-1679.(in Chinese)
［6］	Li Gai,Li Lei,Zhang Jia-qiang.Social collaborative ranking recommendation algorithm by exploiting both explicit and implicit feedback［J］.Journal of Computer Applications,2021,41(12):1-9.(in Chinese)
［7］	Wang R, Liu W,McDonald C.Featureless domain-specific term extraction with minimal labelled data［C］∥Proc of the Australasian Language Technology Association Workshop,2016:103-112.
［8］	Zhao Hong, Wang Fang. A deep learning model and self-training algorithm for theoretical terms extraction［J］.Journal of the China Society for Scientific and Technical Information,2018,37(9):923-938.(in Chinese)
［9］	Yuan Y,Gao J,Zhang Y.Supervised learning for robust term extraction［C］∥Proc of the International Conference on Asian Language Processing,2017:302-305.
［10］	Ding Ze-yuan,Yang Zhi-hao,Luo Ling, et al.Chinese biomedical entity relation extraction system based on deep learning［J］.Journal of Chinese Information Processing,2021,35(5):70-76.(in Chinese)
［11］	Lopes L, Fernandes P,Vieira R.Estimating term domain relevance through term frequency,disjoint corpora frequency-tf-dcf［J］.Knowledge-based Systems,2016,97:237-249.
［12］	Mykowiecka A,Marciniak M,Rychlik P.Recognition of irrelevant phrases in automatically extracted lists of domain terms［J］.International Journal of Theoretical and Applied Issues in Specialized Communication,2018,24(1):66-90.
［13］	Xia Tian. Extracting keywords with modified TextRank model［J］.Data Analysis and Knowledge Discovery,2017,1(2):28-34.(in Chinese)
［14］	Fang Jun-wei,Cui Hao-ran,He Guo-xiu,et al.Keyword extraction of academic text with TextRank model based on prior knowledge［J］.Information Science,2019,37(3):75-80.(in Chinese)
［15］	Yan Qiang,Zhang Xiao-yan,Zhou Si-min.Extracting keywords based on sememe similarity［J］.Data Analysis and Knowledge Discovery,2021,5(4):80-89.(in Chinese)
［16］	Wang Ning-ning,Chen Jian-hui.Concepts extraction of depression drug based on domain correlation measure［J］.Computer Engineering and Applications,2016,52（19）：140-145.(in Chinese)
［17］	Zhang Meng-su,Liu Chun-tian,Li Xi-jin, et al.Design of fuzzy comprehensive evaluation system for performance appraisal based on K-means clustering algorithm［J］.Journal of Jilin University(Engineering and Technology Edition),2021,51(5):1851-1856.(in Chinese)
［18］	Quan T T,Hui S C,Cao T H.A fuzzy fca-based approach for citation-based document retrieval ［C］∥Proc of IEEE Conference on Cybernetics and Intelligent Systems,2004:578-583.
［19］	Bates M J.Toward an integrated model of information seeking and searching［J］.New Review of Information Behavior Research,2002,3:1-15.
［20］	Guo Zhi-peng, Zhao Yu, Zheng Ya-bin, et al. THUCTC:An efficient Chinese text classifier［EB/OL］.［2016-01-25］.http://thuctc.thunlp.org.(in Chinese)
［21］	Luo Chang-yin,Chen Xue-bin,Ma Chun-di, et al.Improved federated average algorithm based on tomographic analysis［J］.Computer Science,2021,48(8):32-40.(in Chinese)
［22］	Zhao Zhan-fang,Liu Peng-peng,Li Xue-shan.Keywords extraction algorithm of railway literature based on improved TextRank［J］.Journal of Beijing Jiaotong University,2021,45(2):80-86.(in Chinese)
［23］	Meng D F, Liu N, Li M X,et al.An improved dynamic collaborative filtering algorithm based on LDA［J］.IEEE Access,2021,9:122568-122577.
［24］	Kim S,Park H,Lee J. Word2vec-based latent semantic analysis(W2V-LSA) for topic modeling:A study on blockchain technology trend analysis［J］.Expert Systems with Applications,2020,152:113401.
［25］	Du J, Vong C M, Chen C L P.Novel efficient RNN and LSTM-like architectures:Recurrent and gated broad learning systems and their applications for text classification［J］.IEEE Transactions on Cybernetics,2021,51(3):1586-1597.
［26］	Jiang H P,Jiao R, Wang Z Q,et al.Construction and analysis of emotion computing model based on LSTM［J］.Complex,2021,2021:Article ID 8897105.
	附中文参考文献：
［4］	朱泽德.网络双语语料挖掘关键技术研究［D］.合肥：中国科学技术大学，2014.
［5］	魏优,刘茂福,胡慧君.基于深层语境词表示与自注意力的生物医学事件抽取［J］.计算机工程与科学,2020,42(9):1670-1679.
［6］	李改,李磊,张佳强.融合显/隐式反馈的社会化协同排序推荐算法［J］.计算机应用，2021,41(12)：1-9.
［8］	赵洪,王芳.理论术语抽取的深度学习模型及自训练算法研究［J］.情报学报,2018,37(9):923-938.
［10］	丁泽源,杨志豪,罗凌,等.基于深度学习的中文生物医学实体关系抽取系统［J］.中文信息学报,2021,35(5):70-76.
［13］	夏天.词向量聚类加权TextRank的关键词抽取［J］.数据分析与知识发现,2017,1(2):28-34.
［14］	方俊伟,崔浩冉,贺国秀,等.基于先验知识TextRank的学术文本关键词抽取［J］.情报科学,2019,37(3):75-80.
［15］	闫强,张笑妍,周思敏.基于义原相似度的关键词抽取方法［J］.数据分析与知识发现,2021,5(4):80-89.
［16］	王宁宁,陈建辉.基于领域相关性度量的抑郁症药物概念抽取［J］.计算机工程与应用,2016,52(19):140-145.
［17］	张萌谡,刘春天,李希今,等.基于K-means聚类算法的绩效考核模糊综合评价系统设计［J］.吉林大学学报(工学版),2021,51(5):1851-1856.
［20］	郭志芃，赵宇，郑亚斌，等.THVCTC:一个高效的中文文本分类工具［EB/OL］.［2016-01-25］.http://thuctc.thunlp.org.
［21］	罗长银,陈学斌,马春地,等.基于层析分析改进的联邦平均算法［J］.计算机科学,2021,48(8):32-40.
［22］	赵占芳,刘鹏鹏,李雪山.基于改进TextRank的铁路文献关键词抽取算法［J］.北京交通大学学报,2021,45(2):80-86.

[1]	赵振宇, 杨天豪, 蒋汶乘, 张书政. 基于机器学习的多压多温多参标准单元延迟快速计算方法[J]. 计算机工程与科学, 2023, 45(08): 1331-1338.
[2]	熊国杰, 张津铭, 贺光辉. 一种面向Chiplet互连的高效传输协议设计与实现[J]. 计算机工程与科学, 2023, 45(08): 1339-1346.
[3]	孙彩霞, 隋兵才, 邓全, 郑重, 倪晓强, 王永文. 应用级兼容RISC-V的混合指令集处理器[J]. 计算机工程与科学, 2023, 45(08): 1347-1353.
[4]	马思远, 焦佳辉, 任晟岐, 宋伟. 基于注意力机制的城市多元空气质量数据缺失值填充[J]. 计算机工程与科学, 2023, 45(08): 1354-1364.
[5]	史明川, 龙巧洲, 邹鸿基, 李暾. 基于Surrogate模型的断言覆盖技术研究[J]. 计算机工程与科学, 2023, 45(08): 1365-1375.
[6]	高文才, 陈小文. 一种基于混合加固的容软错误NoC路由器[J]. 计算机工程与科学, 2023, 45(08): 1376-1382.
[7]	王星苏, 熊文, 张瑞. 海量地铁乘客轨迹相似性连接方法：以深圳地铁为例[J]. 计算机工程与科学, 2023, 45(08): 1383-1392.
[8]	夏戈明, 虞朝栋, 陈健. 边缘计算中的信任问题：挑战与评论[J]. 计算机工程与科学, 2023, 45(08): 1393-1404.
[9]	尹春勇, 冯梦雪. 基于注意力机制的半监督日志异常检测方法[J]. 计算机工程与科学, 2023, 45(08): 1405-1415.
[10]	余子丞, 凌捷. 基于Transformer和多特征融合的DGA域名检测方法[J]. 计算机工程与科学, 2023, 45(08): 1416-1423.
[11]	侯占伟, 李鑫, 王辉, 申自浩, 刘琨, 刘沛骞. 面向路网的空间众包隐私保护任务分配算法[J]. 计算机工程与科学, 2023, 45(08): 1424-1432.
[12]	印杰, 黄肖宇, 刘家银, 牛博威, 谢文伟, . 基于预训练语言模型的安卓恶意软件检测方法[J]. 计算机工程与科学, 2023, 45(08): 1433-1442.
[13]	谷文俊, 张晟恺, 邱晓梦, 李亚康, 宋伟. 基于双模态的小角散射图像结构表征技术研究[J]. 计算机工程与科学, 2023, 45(08): 1443-1452.
[14]	唐剑, 车文刚, 高盛祥. 融入注意力机制的多尺度卷积图像去雾方法[J]. 计算机工程与科学, 2023, 45(08): 1453-1462.
[15]	吴栋梁, 刘知贵, . 基于轻量化YOLOX的电子元器件缺陷检测方法研究[J]. 计算机工程与科学, 2023, 45(08): 1463-1471.