• 中国计算机学会会刊
  • 中国科技核心期刊
  • 中文核心期刊
论文

复杂自然语言的简化处理

展开
  • (云南大学软件学院,云南 昆明 )
杨应元(1985),男,云南昆明人,工程师,研究方向为人工智能、机器自学习和自然语言处理。

收稿日期: 2009-10-10

  修回日期: 2010-04-12

  网络出版日期: 2011-03-25

Concise Processing of Complex Natural Languages

Expand
  • (School of Software,Yunnan University,Kunming 650091,China)

Received date: 2009-10-10

  Revised date: 2010-04-12

  Online published: 2011-03-25

摘要

目前自然语言处理系统难以正确解释部分复杂句子,其中的知识关系只能由操作者简化后再输入,如何使复杂的句子直接被计算机理解呢?本文针对这一问题而提出了自动识别关键字词的新算法。与人的大脑类似,知识处理机也可以对简化后的不完整信息(甚至缺少大多数语言处理机所必需的链接谓词)进行准确理解,而且这种理解对复杂句子要比逐字逐句地理解更为精确和快速。

本文引用格式

杨应元 . 复杂自然语言的简化处理[J]. 计算机工程与科学, 2011 , 33(3) : 152 -158 . DOI: 10.3969/j.issn.1007130X.2011.

Abstract

It is hard for most knowledge extraction machines to correctly construct a complex sentence that can contain several clauses and connections. For this reason, many knowledge systems need to input complex sentences by human. In this paper, the way without human inputting by using concise processing has been presented and analyzed. In this way, the timeconsuming and misunderstanding by computer can be largely decreased and the accuracy can be enhanced. As the same as the brain in human being, the incomplete sentence can also be understood by machine in a way of extracting the key information in the sentence.

参考文献

[1]彭聃龄.普通心理学[M].第三版.北京:北京师范大学出版社,2004.
[2]Pecheux M. Analyse Automatique Du Discours Analyse Automatique Du Discours[J]. Journal Groupe de Recherche Interdisciplinaire en Développement de l’Est du Quebec,1969,8:142143.
[3]Valencia G R, Fernandez B J,Gomez T C. et al. An Approach for Acquiring Structured Knowledge from Text[J].Text Technology,2004,13(2):2754.
[4]Dhamija R,Perrig A. A User Study Using Images for Authentication[EB/OL].[20100312].http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.61.24&rep=rep1&type=pdf.
[5]Bouchaffra D,Meunier J G. A Thematic Knowledge Extraction in Text Using a Markovian Random Field Approach[J]. Oxford Journals,6(1):5771.
[6]Remaki L, Meunier J G, Hamidi S. Analyse Automatique du Discours: Note Sur le système 3AD75, Communication Interne, Université Stendhal,Grenoble[EB/OL].[20100312]. http://www.cavi.univparis3.fr/lexicometrica/jadt/jadt1998/remaki.htm.
[7]July L E. Information Extraction from World Wide Web 1999[EB/OL].[20100312]. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.41.4905&rep=rep1&type=pdf.
[8]Salton G. Automatic Text Processing: The Transformation. Analysis and Retrieval of Information[M] . AddisonWesley Series In Computer Science,1989.
[9]Musen M A. Modern Architectures for Intelligent Systems: Reusable Ontologies and ProblemSolving Methods[C]∥Proc of the 1998 AMIA Annual Symp,1998:4652.
[10]Craven M. Constructing Biological Knowledge Bases by Extracting Information from Text Sources[EB/OL].[20100312]. http://www.aaai.org/Papers/ISMB/1999/ISMB99010.pdf.
[11]ValenciaGarcía R,FernándezBreis J T. Pascual CantosGómez and Rodrigo MartínezBéjar[EB/OL].[20100312]. An Approach for Acquiring Structured Knowledge from Text. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.132.98&rep=rep1&type=pdf.
[12]常宝宝.自然语言处理的最大熵模型:[博士学位论文][D].北京:北京大学计算语言学研究所,2009.

文章导航

/