| 基于领域本体和语块分析的信息抽取的研究与实现 |
| |
| 引用本文： | 丁晟春,刘逶迤,熊霞,梅健.基于领域本体和语块分析的信息抽取的研究与实现[J].情报学报,2010,29(1). |
| |
| 作者姓名： | 丁晟春 刘逶迤 熊霞 梅健 |
| |
| 作者单位： | 南京理工大学经济管理学院信息管理系,南京,210094 |
| |
| 基金项目： | 本文相关研究得到南京理工大学发展基金，总装备部技术基础项目 |
| |
| 摘 要： | 为了提高信息抽取过程中的语义深层次的理解和准确率,本文提出了一种基于领域本体和语块分析的语义信息抽取方法,在详细说明其信息抽取模型的基础上,重点针对命名实体识别、词性组合模板、基于本体的三元组和二元组规则等关键问题进行了深入的分析和研究,提出了相应的解决方法,并进行了相关试验性研究.结果表明:采用本文所述的系统结构及其技术构建文本信息抽取系统是可行的,其能在深层次语义理解的基础上进一步提高信息抽取的准确率.
|
| 关 键 词： | 领域本体 语块分析 信息抽取 |
Research and Implementation of Information Extraction Based on Domain Ontology and Chunk Parsing |
| |
| Ding Shengchun,Liu Weiyi,Xiong Xia , Mei Jian.Research and Implementation of Information Extraction Based on Domain Ontology and Chunk Parsing[J].Journal of the China Society for Scientific andTechnical Information,2010,29(1). |
| |
| Authors: | Ding Shengchun Liu Weiyi Xiong Xia Mei Jian |
| |
| Institution: | Nanjing University of Science and Technology/a>;Nanjing 210094 |
| |
| Abstract: | In order to improve deep-rooted semantic understanding and precision in information extraction process,this paper proposes a semantic information extraction method based on domain ontology and Chunk Parsing.The Chinese named entity recognition,the template of part-of-speech's combination,the triple and 2-tuple rules based on ontology as well as the solutions are mainly Experimental Studied.The experimental results show that constructing a text information extraction system based on the technology schemes de... |
| |
| Keywords: | information extraction domain ontology chunk parsing |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
