基于Word Net的藏文常用名词概念的语义关系分析研究

发布时间：2018-02-02 00:48

本文关键词： 藏文常用名词名词概念语义关系 Word Net数据库　出处：《西北民族大学》2016年硕士论文　论文类型：学位论文

【摘要】：藏文信息处理的现状是未构建出供计算机使用的词汇语义网络系统,而词汇语义网络系统的构建是基于藏文词汇知识库,就国内所创建的CCD、How Net、CWN等词汇语义网,都是基于Word Net(即基于英文词汇知识库)的构建方法获得了成功,Word Net也已成为词汇知识库构建的国际标准。本文是基于Word Net词汇知识库的设计原理及方法,对藏文常用名词概念的理定,藏文常用名词的范围、分类以及藏文常用名词的语义分析等信息,进行分析研究。运用了词汇语义学、认知语义学、藏语语法、计算机技术等学科相契合,采用了以语义场理论为基础的语义分类法与基于对复杂特征集的属性描述法相结合的分析方法,获得并建立了《藏文常用词汇概念Word Net数据库》,探索藏文常用名词词汇的13种语义关系,达到了藏文名词语义分类目的,为面向藏文信息处理的现代藏语语义信息词典做好基础性理论研究。其创新点在于以Word Net概念为依据,对藏文常用名词进行语义分类体系的划分,并对藏文的常用名词进行概念语义框架的表示,进一步地对藏文的常用名词概念进行语义关系及语义成分的分析等。本文中第一章为引言,主要探讨了供机器阅读的(即信息处理应用的)语义类词典在日本、美国等先进国家也已有研究或成果,尤其是概述了Word Net(基于英文词汇知识库)的国内外研究现状,并概述了面向藏文信息处理的词性语义分析的发展现状。分别于第二章中讨论了语言学中的名词概念、词与词义特性、何谓名词概念进行了简要概述。第三章、第四章、第五章为本文的中心部分。第三章中讨论了藏文名词概念的范围、藏文常用名词的分类、藏文常用名词的语义分类体系等问题。第四章中是基于Word Net的藏文常用名词概念的设计原理及方法。第五章中探讨并归纳了对基于Word Net的藏文常用名词概念的13中语义关系的分析与研究。第六章主要描述了藏文常用名词概念Word Net数据库的创建,对藏文常用名词的选取、分类标记、分类标记集的拟定以及藏文常用名词概念Word Net数据库部分示例。
[Abstract]:The present situation of Tibetan information processing is that there is no lexical semantic network system for computer use, and the construction of lexical semantic network system is based on the knowledge base of Tibetan vocabulary, which is based on the CCD created in China. How NetCWN and other lexical semantic web are all based on Word Net-based (English vocabulary knowledge base) construction method has been successful. Word Net has also become the international standard for the construction of lexical knowledge base. This paper is based on the design principle and method of Word Net lexical knowledge base, and defines the concept of commonly used nouns in Tibetan. The scope, classification and semantic analysis of commonly used nouns in Tibetan language are analyzed and studied. Lexical semantics, cognitive semantics, Tibetan grammar, computer technology and other disciplines are used to match each other. In this paper, the semantic classification method based on semantic field theory and the attribute description method based on complex feature sets are adopted to obtain and establish the Word Net Database of Tibetan Common Vocabulary. In order to achieve the purpose of semantic classification of Tibetan nouns, this paper explores 13 kinds of semantic relations of commonly used nouns in Tibetan. This paper studies the basic theory of modern Tibetan semantic information dictionary oriented to Tibetan information processing. Its innovation lies in the division of semantic classification system of commonly used nouns in Tibetan language based on the concept of Word Net. And the commonly used nouns in Tibetan are represented by conceptual semantic framework, and the semantic relations and semantic components of commonly used nouns in Tibetan are further analyzed. The first chapter of this paper is the introduction. This paper mainly discusses the semantic dictionaries for machine reading (that is, information processing applications) in Japan, the United States and other advanced countries have also done research or achievements. In particular, the domestic and foreign research status of Word Net-based (English Vocabulary knowledge Base) is summarized. In the second chapter, we discuss the concept of nouns, the characteristics of words and meanings, and the concept of what is a noun. Chapter three is a brief summary of the development of the semantic analysis of parts of speech oriented to Tibetan information processing. Chapter three discusses the concept of nouns, the characteristics of words and meanings, and the concept of what is a noun in the second chapter. Chapter 4th, chapter 5th is the central part of this paper. Chapter three discusses the scope of the concept of Tibetan nouns and the classification of commonly used nouns in Tibetan. In chapter 4th, the design principle and method of the concept of commonly used nouns in Tibetan language based on Word Net are discussed and summarized. Chapter 5th discusses and summarizes the concept of commonly used nouns based on Word. The analysis and research of semantic relation in 13 common noun concepts of Tibetan by Net. Chapter 6th mainly describes the creation of Word Net database of commonly used noun concepts in Tibetan. The selection of commonly used nouns in Tibetan, the classification marks, the drawing up of classifying mark sets and the examples of Word Net database of commonly used nouns in Tibetan are given.
【学位授予单位】：西北民族大学
【学位级别】：硕士
【学位授予年份】：2016
【分类号】：H214

【相似文献】