Linguistic and Statistical Analysis of the Terminology for Constructing the Thesaurus of a Specified Field

Abstract

The paper is devoted to the analysis of the body of terms and terminological sources for further automation of constructing the thesaurus of a subject area, which is regarded as poetics in our work. Preliminary systematization of terminology with a linguistic and statistical approach forms the body of semantically related concepts to automate extraction of semantic relationships between terms that define the structure of the thesaurus of the specified field.

Keywords

• тезаурус
• метрики семантической близости
• data mining
• компьютерная лингвистика