The Boundary And Function Identification Research Of The "Suo" Construction In Modern Chinese Based On Modern Chinese Corpus

On the purpose of information processing, this paper researches the autoidentification of the “suo” Construction in modern Chinese in which process on thebasis of studying large-scale text corpus. This paper is divided into three parts.Part1is the introduction, which firstly defines the objects and introduces thesignificance of study, then summarizes the current research of “suo” and “suo”Construction and introduces the research thinking and methods for this paper, at last,explains the source of the corpus that we use.Part2is the straight matter, which includes chapter1to chapter5.Chapter2is classified and selected corpus.This chapter preprocessessegmentation and speech tagging using MyTxtSeg Tag from http://www.cncorpus.organd classifies the corpus according to the nature of “suo”, and then selects theeffective corpus.Chapter3is the analysis of the boundary of the “suo” Construction in modernChinese. This chapter analysises the components before and after the character “suo”,and then concludes the words and the delated words before and after “suo”Construction, lay the foundation for chapter5of boundary identification..Chapter4is the analysis of the function of the “suo” Construction in modernChinese.This chapter gives a detailed description of the syntactic function of the“suo” Construction, and then summarizes the formal rules, lay the foundation for thenext chapter of function identification.Chapter5is the boundary and function identification of the “suo” Constructionin modern Chinese.This chapter explains the specific recognition step of the boundaryand function of the “suo” Construction, and prepares procedure to achieve thesefunctions.Part3(chapter6) is the epilogue, which summarizes the conclusions of thisstudy, then proposes the insufficient and problems that need to be solved, at last,makes a possibly outlook for future study.