一种新的基于Ontology的信息抽取方法

被引:17
作者
陈兰
左志宏
熊毅
孟令谦
机构
[1] 电子科技大学计算机科学与工程学院
关键词
Ontology; 语法分析; 标注; 规则; 信息抽取;
D O I
暂无
中图分类号
TP393 [计算机网络];
学科分类号
081201 ; 1201 ;
摘要
把语法分析和Ontology结合起来 ,先利用领域Ontology里的概念、关系、关键字自动生成标注规则(Rule) ,然后对文章、句子的语法结构进行分析 ,再利用语法分析的结果和先前生成的标注规则一起对文档进行信息标注与抽取 ,最后把信息抽取的结果以记录的形式输出
引用
收藏
页码:155 / 157+170 +170
页数:4
相关论文
共 8 条
  • [1] AnAnnotationFrameworkfortheSemanticWeb. StaabS,M¨adcheA,HandschuhS. ProceedingsoftheFirstInternationalWorkshoponmultiMediaAnnotation . 2001
  • [2] JAPE :AJavaAnnotationPatternsEngine. CunninghamH,MaynardD,TablanV. Research Memorandum CS 0010 . 2000
  • [3] Bootstrapping an Ontology-based Information Extraction System. Maedche A,Neumann G,Staab S. Studies in Fuzziness and SoftComputing. Intelligent Exploration of the Web[C]P S Szczepaniak, J Segovia, J Kacprzyk, et al . 2002
  • [4] A Corpus-based Probabilistic Grammar with Only Two Non-terminals. Sekine S,Grishman R. . 1995
  • [5] Architectural Elements of Language Engineering Robustness. Maynard D,Tablan V,Cunningham H. Journal of Natural Language Engineering-Special Issue on Robust Methods in Analysis of Natural Language Data, Forthcoming . 2002
  • [6] BuildingaLargeAnnotat edCorpusofEnglish"thePennTreeBank"intheDistributedPennTreeBankProjectCD ROM. MarcusM,SantoriniB,MarcinkiewiczM. .
  • [7] OntologyDrivenInforma tionExtractionandKnowledgeAcquisitionfromHeterogeneous,Dis tributedBiologicalDataSources. HonavarV,SilvescuA,ReinosoCastilloJ. Proceedings ofthe LJCAI 2001 Workshopon Knowledge Discovery from Hererogeneous,Distributed,Antonomous,Dynamic Dataand Knowledge Sources . 2001
  • [8] Ontology basedExtractionandStructuringofInformationfromDataRichUnstructuredDocuments. EmbleyW,CampbellM,LiddleW. ProceedingsofInternationalConferenceonInformationandKnowledgeManagement . 1998