全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

一种基于复杂网络特征的中文文档关键词抽取算法*

, PP. 827-831

Keywords: 复杂网络,语言网络,抽取

Full-Text   Cite this paper   Add to My Lib

Abstract:

关键词抽取是自然语言理解领域中的重要技术之一.本文研究汉语语言所组成的自然语言网络中的复杂网络特性,并根据语言网络中的“小世界”特性和近两年复杂网络研究中部分新的理论成果,提出基于复杂网络特征的中文文档关键词抽取算法.该算法根据文档语言网络中单词结点的复杂网络特征值进行关键词抽取.实验结果表明,本文算法抽取关键词所获得的平均准确率要高于TFIDF关键词抽取算法所获得的平均准确率.

References

[1]  FerreriCancho R, Sole R V. The Small World of Human Language // Proc of the Royal Society of London, Series B: Biological Sciences, 2001, 268(1482): 22612265
[2]  Watts D J. Small Worlds. Princeton, USA: Princeton University Press, 1999
[3]  Matsuo Y, Ohsawa Y, Ishizuka M. A Document as a Small World // Terano T, Nishida T, Namatame A, et al. eds. Lecture Notes in Computer Science. London, UK: SpringerVerlag, 2253: 444448
[4]  Zhu Mengxiao, Cai Zhi, Cai Qingsheng. Automatic Keywords Extraction of Chinese Document Using Small World Structure // Proc of the International Conference on Natural Language Processing and Knowledge Engineering. Beijing, China, 2003: 438443
[5]  Wei Luoxia, Li Yong, Li Wei, et al. Three Degrees of Separation of Chinese Networks and Small World Effect. Chinese Science Bulletin, 2004, 49(24): 26152616 (in Chinese) (韦络霞,李 勇,李 伟,等.汉字网络的3度分隔与小世界效应. 科学通报,2004, 49(24): 26152616)
[6]  Turney P D. Learning to Extract Keyphrases from Text. Technical Report, ERB1057, Ottawa, Canada: National Research Council Canada. Institute for Information Technology, 1999
[7]  Witten I H, Paynter G W, Frank E, et al. KEA: Practical Automatic Keyphrase Extraction // Proc of the 4th ACM Conference on Digital Libraries. Berkeley, USA, 1999: 254255
[8]  Lee D L, Chuang H, Seamons K. Document Ranking and the VectorSpace Model. IEEE Software, 1997, 14(2): 6775
[9]  Yao Xin. Studies on Complex Networks and Its Clustering Degree. Ph.D Dissertation. Beijing, China: Tsinghua University. Department of Automation, 2005 (in Chinese) (姚 欣.复杂网络及其聚集度研究.博士学位论文.北京:清华大学.自动化系,2005)

Full-Text

Contact Us

service@oalib.com

QQ:3279437679

WhatsApp +8615387084133