计算机工程与应用 ›› 2016, Vol. 52 ›› Issue (10): 128-134.

• 模式识别与人工智能 • 上一篇    下一篇

蒙古语语义信息词典SIKM的研发

海银花   

  1. 内蒙古大学 蒙古学学院,呼和浩特 010021
  • 出版日期:2016-05-15 发布日期:2016-05-16

Development of semantic information knowledge-base in Mongolian

HAI Yinhua   

  1. School of Mongolian Studies, Inner Mongolia University, Hohhot 010021, China
  • Online:2016-05-15 Published:2016-05-16

摘要: 蒙古语语义信息词典(SIKM)作为一部知识库已成为整个蒙古语语言资源的组成部分。自2009年至今,词典的研发取得了阶段性进展。SIKM现已收录5.7万多条记录,涵盖4个词典库。其中包含全部词语的1个“总库”,名词、形容词、动词等3个词类各建一个数据库。每个数据库文件都详细刻画了各词类词语及其语义属性的二维关系。目前已完成5.7万多条词语的语义分类和属性描述,该分类体系和词典的一些属性信息初步被应用到蒙古文信息处理相关基础研究和开发之中。介绍词典规模及结构,语义分类体系、属性字段描述以及研制过程中遇到的一些难点,词典的初步应用情况等内容。

关键词: 蒙古语, 语义信息词典, 蒙古文信息处理, 研发

Abstract: The Semantic Information Knowledge-base in Mongolian(SIKM) is an integral part of the overall Mongolian language resources as a knowledge base. The knowledge base has achieved initial results since 2009. In SIKM there are 57 000 entries, covering four databases, which contains all the words in a general base and other sub-bases of noun, adjective and verb. Each database file has a detailed description on words and its semantic attributes with a two-dimensional relationship. At present, the semantic classification and attribute descriptions on more than 57 000 wordsare completed, and some of the semantic classification and attribute knowledge of the dictionary has been initially applied to the basic research and development for Mongolian Information Processing. The paper will dissertate the scale and structure of the knowledge base, semantic classification, description of attribute, difficulty of the development of SIKM and its initial application in some researches.

Key words: Mongolian, Semantic Information Knowledge-base, Mongolian information processing, development