作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2011, Vol. 37 ›› Issue (21): 49-51. doi: 10.3969/j.issn.1000-3428.2011.21.017

• 软件技术与数据库 • 上一篇    下一篇

面向中文短信的信息抽取方法

吴中彪,刘椿年   

  1. (北京工业大学计算机学院,北京 100124)
  • 收稿日期:2011-05-17 出版日期:2011-11-05 发布日期:2011-11-05
  • 作者简介:吴中彪(1985-),男,硕士研究生,主研方向:信息抽取;刘椿年,教授、博士生导师
  • 基金资助:
    国家自然科学基金资助项目(60496322)

Information Extraction Method for Chinese Text Messages

WU Zhong-biao, LIU Chun-nian   

  1. (College of Computer Science and Technology, Beijing University of Technology, Beijing 100124, China)
  • Received:2011-05-17 Online:2011-11-05 Published:2011-11-05

摘要: 在手机3D动画自动生成系统中,研究面向中文短信的信息抽取方法。设计一种基于上下文无关文法的模板定义方式,以及对应的模板知识库与模板解析器。在模板解析器处理数据的过程中,通过最左规约算法保证中文短信的信息抽取效率。实验结果表明,该方法在扩展抽取内容范围的同时,能提高信息抽取的准确性。

关键词: 手机3D动画自动生成系统, 模板知识库, 模板解析器, 信息抽取

Abstract: In the application domain of mobile phone 3D animation automatic generation system, resesrches the information extraction method for Chinese text messages. It proposes a method to do the information extraction on Chinese text messages. A domain template definition method based on the limited context-free grammar is defined. After that designs and implements a template base with the corresponding template parser. The template parser uses the left-first deduction algorithm to ensure the efficiency. Experimental results show that this method can expand the extracted range and improve the accuracy of information extraction.

Key words: mobile phone 3D animation automatic generation system, template knowledge base, template resolver, information extraction

中图分类号: