Linguistics Literature Title Terminology Extraction Study

Taken the literature titles in linguistics terms as the research object, This article ,under the segmentation notes corpus, on the base of understanding and explanation of terminology correlation theory and statistical analysis title words, uses the computer program to extract, screen and supplement linguistics terms in the literature titles and attempts to establish in this foundation the linguistics terms collection, analyze the structure and the logical relations of discipline terms system, providing reference for keyword table's renew and optimization. The full text divides four chapters:Chapter I: IntroductionThis chapter has first explained the importance of title research to language research and information search, then proposes that through the extraction of implied terms in titles; reach the achievement of the optimization of search language. Afterwards, the author introduces the survey of title research as well as the study theory methods in this paper.Chapter II: Design and Establishment of The Title CorpusThis chapter summarizes the goal of establishment title corpus, the selection principle of language material, the type and structure of language material, the automatic segmentation of the language materials database and the situation of manual intervention. On the base of that, the word frequency analysis of language material has carried out, as the foundation of the next step terminology extraction research.Chapter III: The Extraction of The Linguistics TermsFirstly, this chapter analyzes the part of speech of the language material and determines the key words of the terms of extraction. After that, the terminology extraction method and step are introduced, and the extraction work divides into four steps: machine extraction, initially selection, selection and supplement. Afterwards, the paper makes the explanation of the different length terms extraction fixed with the sample words. Finally, the author take the obtained 2,208 terms as the linguistics terms collection, being the quite complete source material for further study.Chapter IV: Words Left/Conclusion/OthersThe linguistics terms structure system is decrypted. The part of speech and the structure type of single-word terms, the interior combination relations of phrase terms as well as the terms polymerization relations and the logical level relations are introduced. Finally, this research application value is noted.Epilogue:The part has an overall look of the research, and points out deficiency exiting in the research, simultaneously proposed further study plan.