蒙古语受事和客事配价自动识别研究
发布时间:2018-03-14 16:55
本文选题:受事 切入点:客事 出处:《内蒙古大学》2014年硕士论文 论文类型:学位论文
【摘要】:本文从《面向信息处理的蒙古语语义搭配分析数据库》中使用的句子中选取受事句和客事句,进行句子分析。然后对受事句和客事句的语义搭配情况进行分析总结,抽取受事句和客事句的特征,归纳受事句和客事句的识别规则。 全文由引言,第一章,第二章,第三章,第四章五个部分组成。 引言,主要介绍了选题意义,研究概况,研究理论与方法,研究步骤,语言资料来源与标记集等。 第一章,介绍了句子的选择、统计和加工情况,及遇到的问题及解决方法。 第二章,根据受事句和客事句的词性分类、语义分类和动词语义分类三个方面,对受事句和客事句的语义搭配情况进行分析总结。 第三章,基于动词语义分类,根据名词与动词的语义搭配,归纳受事句和客事句的识别规则。 第四章,总结全文,展望未来工作。
[Abstract]:In this paper, from the sentences used in the Mongolian semantic collocation Analysis Database for Information processing, we select the client sentence and the guest sentence for sentence analysis, and then analyze and summarize the semantic collocation of the client sentence and the guest sentence. Extract the characteristics of the patient sentence and the guest sentence, and conclude the recognition rules of the client sentence and the guest sentence. The full text consists of five parts: introduction, chapter one, chapter two, chapter three, and chapter 4th. The introduction mainly introduces the significance of the topic, the general situation of the research, the research theory and method, the research steps, the source of language data and the set of markers. The first chapter introduces the choice of sentences, statistics and processing, problems encountered and solutions. The second chapter analyzes and summarizes the semantic collocation of the subject sentence and the object sentence according to the classification of part of speech, semantic classification and verb semantic classification. In chapter 3, based on the semantic classification of verbs and the semantic collocation of nouns and verbs, the recognition rules of the subject sentence and the object sentence are summarized. Chapter 4th, summing up the full text, looking forward to future work.
【学位授予单位】:内蒙古大学
【学位级别】:硕士
【学位授予年份】:2014
【分类号】:H212
【参考文献】
相关期刊论文 前5条
1 范晓;动词的配价与句子的生成[J];汉语学习;1996年01期
2 赵军,黄昌宁;基于转换的汉语基本名词短语识别模型[J];中文信息学报;1999年02期
3 德·萨日娜;关于蒙古语语义分析的思考[J];内蒙古社会科学(汉文版);2004年03期
4 王斯日古楞;;蒙古语单词词性自动识别研究[J];内蒙古师范大学学报(自然科学汉文版);2007年03期
5 周强,孙茂松,黄昌宁;汉语最长名词短语的自动识别[J];软件学报;2000年02期
,本文编号:1612107
本文链接:https://www.wllwen.com/wenyilunwen/hanyulw/1612107.html