《蒙古语口语语料库》的标注及检索系统

发布时间：2018-12-20 13:22

【摘要】：基于现代活语言资料而建立的《口语语料库》是活语言的保存方式之一。它真实地反映当今语言使用情况的同时,也成为进行口语研究的保障。建立《蒙古语口语语料库》是研究语音、语音的变异、语法变化、句子结构等语言现象的时候提供重要资料。现在蒙古语的口语研究比书面语晚了一步,很多问题都还没有进行研究。随着社会的发展,语料库语言学已经成为语言研究的主流,所以为了进行口语研究,建立口语语料库是急需的、迫切的。本论文主要阐述了《蒙古语口语语料库》的标注及检索系统的相关内容,并归纳出标注及检索系统时遇到的问题,也提出了对其解决的方法。本论文由绪论、第一章、第二章、第三章等四部分组成。绪论部分简要说明了选题意义,典型的语料库简介,研究方法等内容。第一章,主要介绍了建立《蒙古语口语语料库》的目的、意义和方法等《蒙古语口语语料库》的基本概况。第二章,主要介绍了《蒙古语口语语料库》的加工方法和标注方法,提出了遇到的问题和解决方法。第三章,主要介绍了《蒙古语口语语料库》的检索系统。
[Abstract]:The spoken corpus, which is based on modern living language data, is one of the ways to preserve living language. It truly reflects the current situation of language use, but also becomes the guarantee of oral research. The establishment of spoken Mongolian Corpus is an important data for the study of phonological, phonetic variation, grammatical changes, sentence structure and other linguistic phenomena. The study of spoken Mongolian is one step later than written, and many questions have not yet been studied. With the development of society, corpus linguistics has become the mainstream of language research. This paper mainly expounds the related contents of the tagging and retrieval system of the spoken Mongolian Corpus, summarizes the problems encountered in the annotation and retrieval system, and puts forward some solutions to the problems. This thesis consists of four parts: introduction, chapter one, chapter two and chapter three. The introduction briefly explains the significance of the topic, the introduction of the typical corpus, the research methods and so on. In the first chapter, the purpose, significance and methods of establishing spoken Mongolian corpus are introduced. In the second chapter, the processing and labeling methods of spoken Mongolian Corpus are introduced, and the problems and solutions are put forward. Chapter three introduces the retrieval system of spoken Mongolian Corpus.
【学位授予单位】：内蒙古大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：H212

【参考文献】