计算机科学 ›› 2016, Vol. 43 ›› Issue (3): 279-284.doi: 10.11896/j.issn.1002-137X.2016.03.052

• 人工智能 • 上一篇    下一篇

基于模式识别的文本知识点深度挖掘方法

温浩,温有奎,王民   

  1. 西安建筑科技大学信息与控制工程学院 西安710055,西安电子科技大学经济管理学院 西安710071,西安建筑科技大学信息与控制工程学院 西安710055
  • 出版日期:2018-12-01 发布日期:2018-12-01
  • 基金资助:
    本文受国家自然科学基金项目(70373946)资助

Approach to Text Knowledge Depth Mining Based on Pattern Recognition

WEN Hao, WEN You-kui and WANG Min   

  • Online:2018-12-01 Published:2018-12-01

摘要: 针对目前大数据知识获取存在的噪声大的问题,提出了文本知识点深度挖掘方法。首先构建了学术论文创造性特征的“问题,方法,结果”三元组本体模型;其次利用模式识别等技术对学术论文文摘进行统计分析、特征提取、机器学习、模式判定分析;最后对学术论文创造性核心知识的三元组进行深度挖掘。实验结果表明,该方法能大大过滤掉学术文献大数据检索的噪声,便于用户快速定位大型学术文献数据库论文的研究问题,采用的新方法和得到的结果能判断学术论文的阅读价值,并为大数据深度知识挖掘和关联发现研究提供基础。该类方法未见有公开的文献报道,属于一种探索性研究和实验。

关键词: 模式识别,文本挖掘,语义三元组,直接知识获取

Abstract: A new method of text mining was presented to make up for the disadvantages of big data knowledge acquisition.Firstly,we constructed triple ontology model about academic inventive features “problem,methods,results”.Se-condly,pattern recognition techniques were used for statistical analysis,feature extraction,machine learning and pattern determination analysis.Finally,depth mining of triples of the creative core academic knowledge was realized.The Expe-rimental results show that the new method can effectively reduce the retrieval noise of academic literature,which is convenient for users to quickly locate the research problem.The methods and results can determine the reading value of papers and provide a basis for depth knowledge mining of large data and related discovery.The method has not been reported in the literature,and it is a kind of exploratory research and experimentation.

Key words: Pattern recognition,Text mining,Semantic triples,Direct knowledge acquisition

[1] Li Guo-jie,Cheng Xue-qi.Research Status and Scientific Thinking of Big Data[J].Bulletin of the Chinese Academy of Sciences,2012,7(6):647-657(in Chinese) 李国杰,程学旗.数据研究:未来科技及经济社会发展的重大战略领域——大数据的研究现状与科学思考[J].中国科学院院刊,2012,7(6):647-657
[2] Ramesh B P,Sethi R J,Yu Hong.Figure-Associated Text Summarization and Evaluation[J].PLoS ONE,2015,10(2):e0115671
[3] Wen You-kui,Xu Gua-hua.Linking theory of Knowledge element[J].J ournal of the China Society for Scientific and Technical Information,2003,2(6):665-670(in Chinese) 温有奎,徐国华.知识元链接理论[J].情报学报,2003,2(6):665-670
[4] Brookes B C.The foundations of information science ( Part IV)[J].Journal of Information Science,1981,3(1):3-12
[5] Suo Chuan-jun.Study on Obsolescence and Innovation of Aca-demic Papers from Perspective of Knowledge Transfer[J].Library and Information Service,2014,8(5):5-12(in Chinese) 索传军.知识转移视角下的学术论文老化与创新研究[J].图书情报工作,2014,8(5):5-12
[6] Liu S,Liu F,Yu C,et al.An effective approach to document retrieval via utilizing worldnet and recognizing phrases[C]∥Proc of the 27th Annual Int ACM SIGIR Conference on Research and Development in Information Retrieval(SIGIR’04).New York:ACM,2004:266-272
[7] Wang Yuan-zhuo,Jia Yan-tao,Liu Da-wei,et al.Open WebKnowledge Aided Information Search and Data Mining[J].Journal of Computer Research and Development,2015,2(2):456-474(in Chinese) 王元卓,贾岩涛,刘大伟,等.基于开放网络知识的信息检索与数据挖掘[J].计算机研究与发展,2015,2(2):456-474
[8] Sebastiani F.Machine Learning in Automated Text Categorization[J].ACM Computing Surveys,2002,34(1):1-47
[9] Shehata S,Karray F,Kamel M.A Concept-Based Model for Enhancing Text Categorization[C]∥Proc.13th Int’l Conf.Know-ledge Discovery and Data Mining (KDD’07).2007: 629-637

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!