期刊文献+

基于最大频繁等价类的Web信息自动抽取

Automatic Web Information Extraction Based on Maximal and Frenquent Equivalence Classes
下载PDF
导出
摘要 在定义模板的基础上,提出了页面创建模型。该模型描述了如何使用模板将来自于后台数据库的值编码生成页面。基于这个模型,设计了一个基于最大频繁等价类的抽取算法EBMFEC,通过分析给定的数据导向型页面的终端符号的出现情况,找出最大频繁等价类,并推导出用于生成页面的未知模板。然后使用推导出的模板,从输入页面中提取出相关信息。在大量实际HTML页面上的实验证明,EBMFEC在大部分情况下都可以从给定页面中推导出模板,并正确抽取出数据信息。 A novel approach based on MFEC (Maximal and Frenquent Equivalence Classes)is proposed to solve the problem of automatically extracting data from data-intensive Web pages. A template is defined and a model of page creation is proposed to describe how values are encoded into pages using the defined template. We present an algorithm, EBMFEC that takes,as input, a set of template-generated pages, analyzes the page-tokens of given pages to discover MFEC, deduces the unknown template used to generate the pages and extracts, as output, the values encoded in the pages. Experiments on a large number of HTML pages indicate that our algorithm correctly extracts data in most cases and the results are also provided.
出处 《计算机科学》 CSCD 北大核心 2006年第12期169-173,202,共6页 Computer Science
基金 国家自然科学基金(50474033) 福建省自然科学基金(A0310008) 福建省重点科技项目(2003H043)。
关键词 等价类 信息抽取 模式 模板 Equivalence classes, Information extraction,Schema,Template
  • 相关文献

参考文献10

  • 1Haas L M,Kossmann D, Wimmers E L,et al. Optimizing queries across diverse data sources. In: Proc of the 23th VLDB Conf.Athens, 1997. 276-285 被引量:1
  • 2Levy A,Rajaraman A,Ordille J J. Querying heterogeneous information sources using source descriptions. In: Proc. of the 22th VLDB Conf. Bombay,1996. 251-262 被引量:1
  • 3Kushmerik N. Wrapper induction: Efficiency and expressiveness.Journal of Artificial intelligence,2000,118(1-2): 15-68 被引量:1
  • 4Soderland S, Learning information extraction rules for semi- structured and free text. Journal of Machine learning, 1999, 34(1-3):233-272 被引量:1
  • 5Embley D W,Campbell D M. A conceptual-modeling approach to extracting data from the web. In:Proc. of the 17th Intl. Conf on Conceptual Modeling. Singapore,1998. 78-91 被引量:1
  • 6Chang C, Lui S. IEPAD: Information extraction based on pattern discovery. In:Proc of 10th WWW Conf. Hong Kong, 2001. 681-688 被引量:1
  • 7Crescenzi V, Mecca G, Merialdo P. ROADRUNNER: Towards automatic data extraction from large web sites. In: Proc of the 27th VLDB Conf. Roma,2001. 109-118 被引量:1
  • 8Crescenzl V, Mecca G. Automatic Information Extraetlon from Large Websites. Journal of the ACM, 2004,51 (5): 731-779 被引量:1
  • 9Sarawagi S. Automation in InformationExtraction and Data Integration (tutorial). VLDB, 2002 被引量:1
  • 10Myllymaki J. Effective Web data extraction with standard XML technologies. In:Proc of 10th WWW Conf. Hong Kong, 2001.689-696 被引量:1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部