信息处理用“一X”词的自动识别与消歧研究

发布时间：2018-04-22 01:05

本文选题：“一X”词 + 自动识别　；参考：《上海师范大学》2012年硕士论文

【摘要】：本文以信息处理为目标，以“一X”词为研究对象，在考察大规模语料的基础上，研究“一X”词的自动识别与识别过程中可能遇到的歧义消解问题。全文共分为三个部分：第一部分是绪论，确定研究对象，阐述选题的目的和意义，综述“一X”词的研究现状，介绍本文的研究思路与拟采用的理论方法，最后交代语料来源。第二部分是正文，包括第一章至第五章。第一章是“一X”词的用法考察。本章依据“一X”词的词性对其进行分类，逐一考察它们的用法，分析其句法分布与制约因素，并进行词频统计。然后，对各种句法环境做总结，为下文提取算法规则服务。第二章是非句法结构“一X”的考察与歧解。本章首先考察非句法结构“一X”的左右边界特征，，以及“一X”作为语素组的情况，然后在此基础上研究非句法结构“一X”的歧义消解策略。第三章是短语结构“一X”的考察与歧解。本章首先考察短语结构“一X”的用法特征，并进行频度统计，再对比分析同形“一X”作为短语和词的异同。然后在此基础上探讨短语结构“一X”的歧义消解策略。第四章是词表与规则库构建。本章在前三章的基础上，建立“一X”词自动识别时所需的词表，总结提取相应的规则，并对规则表述进行形式化。第五章是算法设计与实现。本章在第四章的基础上，进行算法设计，并编写程序代码，进行编程测试，然后报告测试结果。第三部分是结语（即第六章）。本章总结全文研究成果和研究意义，分析存在的不足和尚需解决的问题，并展望后续研究努力的方向。
[Abstract]:This paper aims at information processing and takes "one X" as the research object. On the basis of investigating large-scale corpus, this paper studies the ambiguity resolution in the process of automatic recognition and recognition of "one X". The full text is divided into three parts:
The first part is the introduction, to determine the object of research, to explain the purpose and significance of the topic, to summarize the research status of "one X", and to introduce the research ideas and theoretical methods to be adopted in this paper, and finally to explain the source of the corpus.
The second part is the text, including the first to the fifth chapter.
The first chapter is the study of the usage of "one X". This chapter classifies it according to the word character of "one X", examines their usage one by one, analyzes its syntactic distribution and restrictive factors, and carries out the word frequency statistics. Then, we sum up various syntactic environments, and serve the following laws and regulations.
The second chapter is the investigation and disambiguation of the non syntactic structure "one X". This chapter first examines the left and right boundary features of the non syntactic structure "one X", and the situation of "one X" as a morpheme group, and then studies the ambiguity resolution strategy of the non syntactic structure "one X".
The third chapter is the investigation and disambiguation of the phrase structure "one X". This chapter first examines the usage characteristics of the phrase structure "one X", carries out the frequency statistics, and compares and analyzes the similarities and differences of the same form "one X" as the phrase and the word. On this basis, the ambiguity resolution strategy of the phrase structure "one X" is discussed.
The fourth chapter is the construction of the vocabulary and the rule base. On the basis of the first three chapters, this chapter sets up the word list for the automatic recognition of the word "one X", summarizes the corresponding rules, and formalisms of the rules.
The fifth chapter is the algorithm design and implementation. This chapter is based on the fourth chapter, carries on the algorithm design, writes the program code, carries on the programming test, and then reports the test result.
The third part is the conclusion (the sixth chapter). This chapter summarizes the research results and significance of the full text, analyzes the shortcomings of the existence and the problems that need to be solved, and looks forward to the direction of the follow-up research.

【学位授予单位】：上海师范大学
【学位级别】：硕士
【学位授予年份】：2012
【分类号】：H146

【参考文献】