中文网页语义标注：由句子到RDF表示  

Semantic Annotation of Chinese Web Pages:From Sentences to RDF Representations

作　　者：荆涛[1] 左万利[1] 孙吉贵[1] 车海燕[1] 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012

出　　处：《计算机研究与发展》2008年第7期1221-1231,共11页Journal of Computer Research and Development

基　　金：国家自然科学基金重大项目(60496321);吉林省科技发展计划基金项目(20070533)

摘　　要：语义网远景的实现需要自动化的语义标注方法.提出了一种在领域本体指导下,针对中文网页的语义标注方法.运用统计学方法与自然语言处理技术,以文档中句子为处理对象,采取识别和组合两个阶段来完成句子向RDF表示的映射.它具有以下特点:以统计方法获得领域相关词汇,构造领域词汇标注列表作为外部领域知识,降低对通用语言本体的依赖;显式的属性类型标注方法识别出句子中表达关系的词汇,标注为属性类型,利于后续关系抽取;构造句子的句法依存关系树(森林),按照依存关系对词汇进行组合,形成RDF陈述.实验结果显示此方法较基于主谓宾语法关系的语义标注方法更为有效.The Semantic Web aims to leverage the World Wide Web to a Web of data,where machines are able to process annotations and relations between resources,and where implicit information can be derived from utilizing ontologies and shared vocabularies.To fulfill the vision of the Semantic Web,a method of automatic semantic annotation is needed.Proposed in this paper is a methodology for semantic annotation of Chinese Web pages,which is guided by domain ontology.The statistical method and the natural language processing technology are employed,and the mapping from sentences to RDF representations are realized through the identification phase and the grouping phase.The major technical contributions are：the domain lexicon constructed by the statistical method rather than the linguistic ontology is used as the external domain knowledge;the explicit property type tagging algorithm is used to recognize both instances and properties contained in sentences to facilitate relation extraction;after building dependency trees or dependency forests of sentences,the identified instances and properties can be grouped into RDF statements according to the dependency relationship among Chinese words.The experimental result shows that compared with the semantic annotation method based on the grammatical relationship of subject-verb-object,this method is significantly more effective.

关 键 词：自然语言处理 依存关系 类型标注 关系抽取 本体 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]