首页> 外文会议>International Conference on Enterprise Information Systems >Towards an Arabic Ontology Defining Morpho-lexical Patterns for Semantic Relation Extraction
【24h】

Towards an Arabic Ontology Defining Morpho-lexical Patterns for Semantic Relation Extraction

机译:朝着一个关于语义关系提取的Morpho-Lexical模式的阿拉伯本体论

获取原文

摘要

In this paper, we propose a method for defining morpho-lexical patterns used to detect semantic relation between Arabic nouns. This method is based on study corpus built from online encyclopedia. This corpus consists of a set of articles selected on the basis of a database containing pairs of terms linked by semantic relations. Defined patterns are then implemented using NooJ platform. The pattern evaluation result is very encouraging. We obtained 79% as F-Measure rate.
机译:在本文中,我们提出了一种定义了Morpho-Lexical模式的方法,用于检测阿拉伯语名词之间的语义关系。此方法基于从在线百科全书建造的研究语料库。该语料库包括一组基于包含由语义关系链接的术语对的数据库选择的一组文章。然后使用nooj平台实现定义的模式。模式评估结果非常令人鼓舞。我们获得了79%的F测量率。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号