首页> 外文会议>2018 International Conference on Intelligent Systems and Computer Vision >Improving the Arabic root extraction by using the quadratic splines
【24h】

Improving the Arabic root extraction by using the quadratic splines

机译:使用二次样条改进阿拉伯语根提取

获取原文
获取原文并翻译 | 示例

摘要

In this paper, we present an Arabic root extraction system. It provides the root of each word of a given sentence. It is an indispensable tool for several natural language processing applications such as search engines, text classification and information retrieval. The method of extraction used in this work runs in two steps. The first one consists in seeking of all the possible roots of each word analyzed out of context with the morphological analyzer Alkhalil Morpho Sys 2. Then, we develop in the second step a disambiguation approach based on continuous quadratic splines to choose among these roots the one that corresponds to the word context. We test this method on a representative corpus, and we obtained encouraging results with an accuracy of the order of 96%.
机译:在本文中,我们提出了阿拉伯语根提取系统。它提供给定句子的每个单词的词根。它是几种自然语言处理应用程序(例如搜索引擎,文本分类和信息检索)必不可少的工具。本工作中使用的提取方法分两个步骤。第一个步骤是使用形态分析仪Alkhalil Morpho Sys 2寻找在上下文之外分析的每个单词的所有可能词根。然后,我们在第二步中开发出一种基于连续二次样条的歧义消除方法,从这些词根中选择一个对应于上下文一词。我们在代表性语料库上测试了该方法,并获得了令人鼓舞的结果,其准确度约为96%。

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