基于强度熵的中文关键词识别方法

摘要/Abstract

摘要：

文本的关键词识别是文本挖掘中的基本问题之一。在研究现有基于复杂网络的关键词识别方法的基础上

，从整个复杂网络拓扑结构特征的信息缺失角度来考察各节点的重要程度。提出强度熵测度来量化评估

各节点重要程度，用于解决中文关键词识别问题。实验结果表明，该评估方法简单有效，特别适用于带

权复杂网络的节点重要性评估。

关键词: 复杂网络, 关键词抽取, 语言网络, 强度熵

Abstract:

To identify keywords of the document is one of the fundamental issues for text mining.

Focusing on the study of the existing keyword identification approaches based on complex

networks, we exploit the importance of nodes from the aspect of information missing in the

whole complex network topology. We introduce a novel measurement, called strength entropy,

to quantitatively evaluate the importance of nodes and solve Chinese keyword identification

problem. Experimental results show that the evaluation method is simple and effective,

especially for weighted complex networks.

Key words: complex network, keyword extraction, language network, strength entropy

闫蓉,高光来. 基于强度熵的中文关键词识别方法[J]. 计算机工程与科学.

YAN Rong,GAO Guanglai. Chinese keywords identification based on strength entropy[J]. Computer Engineering & Science.

参考文献

［1］Gang P,Minett J W,Wang W SY.The networks of syllables and characters in Chinese［J］

.Journal of Quantitative Linguistics,2008,15(3):243255.

［2］Wei Luoxia, Li Yong, Kang Shiyong, et al. Organization structure and scalefree

property of Chinese phrase network［J］.Chinese Science Bulletin,2005,50(15):15751579.(in

Chinese)

［3］Liu Haitao, Hu Fengguo. What role does syntax play in a language network?

［J］.Europhysics Letters,2008,83(1):226234.

［4］Liu Zhiyuan, Sun Maosong. Chinese word cooccurrence network:Its small world

effect and scalefree property［J］.Journal of Chinese Information Processing,2007,21

(6):5258.(in Chinese)

［5］Zhu Mengxiao, Cai Zhi, Cai Qingsheng. Automatic keywords extraction of Chinese

document using small world structure［C］∥Proc of the International Conference on Natural

Language Processing and Knowledge Engineering Proceedings,2003:438443.

［6］Li J, Zhou J. Chinese character structure analysis based on complex networks

［J］.Physica A Statistical Mechanics & Its Applications,2007,380(7):629638.

［7］Liu Haitao.Language is a complex network［J］.Journal of Shanxi University

(Philosophy and Social Science Edition),2013,36(5):6669.(in Chinese)

［8］Liu Haitao.Linguistic complex networks:A new approach to language exploration

［J］.grkg/Humankybernetik,2011,52(4):151170.

［9］Watts D J, Strogatz S H. Collective dynamics of ‘smallworld’ networks

［J］.Nature,1998,393(6684):440442.

［10］Barabasi A L, Albert R. Emergence of scaling in random networks

［J］.Science,1999,286(5439):509512.

［11］Zhao Peng,Cai Qingsheng,Wang Qingyi,et al.An automatic keyword extraction of

Chinese document algorithm based on complex network features［J］.Pattern Recognition and

Artificial Intelligence,2007,20(6):827831.(in Chinese)

［12］Zhang Min, Geng Huantong,Wang Xufa.Automatic keyword extraction algorithm

research using BC method［J］.Journal of Chinese Computer Systems,2007,28(1):189192.(in

Chinese)

［13］Ren Keqiang, Zhao Guangfu, Zhang Guoping. Extracting keywords from web page

based on weighted natural language network［J］.Computer Engineering and

Applications,2008,44(8):155157.(in Chinese)

［14］Ma Li,Jiao Licheng,Bai Lin,et al.Research on a compound keywords detection method

based on small world model［J］.Journal of Chinese Information Processing,2009,23(3):121

128.(in Chinese)

［15］Liu J G,Ren Z M,Guo Q,et al.Node importance ranking of complex networks［J］.Acta

Physica Sinica,2013,62(17):178901.(in Chinese)

［16］Liu Ying,Tang Ming,Zhou Tao,et al,Corelike groups result in invalidation of

identifying superspreader by kshell decomposition［J］.Science Reports,2015(5):9602.

［17］Hou B, Yao Y, Liao D. Identifying allaround nodes for spreading dynamics in complex

networks［J］.Physica A Statistical Mechanics & Its Applications,2012,391(15):40124017.

［18］Opsahl T, Agneessens F, Skvoretz J. Node centrality in weighted networks:Generalizing

degree and shortest paths［J］.Social Networks,2010,32(3):245251.

［19］Hu Yihong. Analysis of complex transportation networks［D］.Shanghai:Fudan

University,2008.(in Chinese)

［20］Christopher D M, Schütze H. Foundations of statistical natural language processing［M

］.Cambridge:MIT Press,1999.

［21］Liu Y, Jin J,Zhang Y,et al.A new clustering algorithm based on data field in complex

networks［J］.Journal of Supercomputing,2014,67(3):723737.

［22］Somwrita S,Andy D.Community detection in graphs using singular value decomposition［J

］.Physical Review E Statistical Nonlinear & Soft Matter Physics,2011,83(2):801811.

附中文参考文献：

［2］韦洛霞,李勇,康世勇,等.汉语词组网的组织结构与无标度特性［J］.科学通报,2005,50(15):1575

1579.

［4］刘知远,孙茂松.汉语词同现网络的小世界效应和无标度特性［J］.中文信息学报,2007,21(6):52

58.

［7］刘海涛.语言是一种复杂网络［J］.山西大学学报(哲学社会科学版),2013,36(5):6669.

［11］赵鹏,蔡庆生,王清毅,等.一种基于复杂网络特征的中文文档关键词抽取算法［J］.模式识别与人

工智能,2007,20(6):827831.

［12］张敏,耿焕同,王煦法.一种利用BC方法的关键词自动提取算法研究［J］.小型微型计算机系

统,2007,28(1):189192.

［13］任克强,赵光甫,张国萍.基于带权语言网络的网页关键词抽取［J］.计算机工程与应用,2008,44

(8):155157.

［14］马力,焦李成,白琳,等.基于小世界模型的复合关键词提取方法研究［J］.中文信息学报,2009,23

(3):121128.

［15］刘建国，任卓明，郭强，等.复杂网络中节点重要性排序的研究进展［J］.物理学报,2013,62

(17):178901.

［19］胡一竑.基于复杂网络的交通网络复杂性研究［D］.上海:复旦大学,2008.

[1]	皇甫斐斐, 杨阳, 邓晓懿, . 基于节点影响力的理性节点标签传播算法[J]. 计算机工程与科学, 2022, 44(04): 713-722.
[2]	燕云鸿, 钱晓东. 区块链环境下电商消费者网络多子群混合增长模型构建及特性研究[J]. 计算机工程与科学, 2021, 43(12): 2157-2168.
[3]	张丽, 马静. 融合词语统计特征和语义信息的文本分类方法研究[J]. 计算机工程与科学, 2021, 43(07): 1308-1315.
[4]	张士进, 张胜, 田纪彪, 吴志强, 戴维凯. 基于深度编码器的复杂网络社区发现算法 #br# [J]. 计算机工程与科学, 2020, 42(09): 1640-1648.
[5]	潘曙灿, 许青林. 融合特征向量中心性与标签熵的标签传播算法[J]. 计算机工程与科学, 2020, 42(08): 1489-1499.
[6]	徐曼1,2,3，鲁富荣1,2,3，马国帅1,2,3，钱宇华1,2,3. 基于信息传播影响因素的边重要性度量方法[J]. 计算机工程与科学, 2020, 42(01): 55-63.
[7]	宁珊, 严馨, 周枫, 王红斌, 张金鹏. 融合LSTM和LDA差异的新闻文本关键词抽取方法[J]. 计算机工程与科学, 2020, 42(01): 153-160.
[8]	杨迪，刘琰，陈静，张伟丽. 基于模体的目标区域网络拓扑划分方法[J]. 计算机工程与科学, 2019, 41(03): 466-478.
[9]	李慧，杨青泉，王慧慧. 一种基于局部扩展优化的重叠社区发现算法[J]. 计算机工程与科学, 2018, 40(12): 2258-2264.
[10]	付丹龙1，朱淑华1，原智峰2，梁倬骞1,2，邓原2. 基于不同子网络级联机制的相依网络鲁棒性研究[J]. 计算机工程与科学, 2018, 40(03): 439-444.
[11]	吕铃，彭雅丽，曾欣怡,杨雨鑫，黄明和. 公共自行车复杂网络可达性指标潜力评价模型[J]. 计算机工程与科学, 2018, 40(01): 175-183.
[12]	董建亮，赵文涛，李方,黄心昊. 一种基于标签传播算法的关键链路探测方法[J]. 计算机工程与科学, 2017, 39(11): 2022-2027.
[13]	伍杰华1,2,沈静1,周蓓1. 改进朴素贝叶斯模型的复杂网络关系预测[J]. 计算机工程与科学, 2017, 39(10): 1825-1831.
[14]	聂祥林1,2,张玉梅1,2,吴晓军1,2,吴霞1. 基于节点依赖度和相似社团融合的社团结构发现算法[J]. 计算机工程与科学, 2017, 39(07): 1273-1280.
[15]	张其林1，董政呈2，赵永标1 . 一种具有核心-边缘结构的无标度网络演化模型[J]. 计算机工程与科学, 2017, 39(03): 500-504.