CASPIAN JOURNAL

MANAGEMENT AND HIGH TECHNOLOGIES

CLASSIFICATION OF NOUNS OF THE TAJIK LANGUAGE FOR NATURAL LANGUAGE PROCESSING

Read Madibragimov Navruz Sh., Prutzkow Alexander V. CLASSIFICATION OF NOUNS OF THE TAJIK LANGUAGE FOR NATURAL LANGUAGE PROCESSING // Caspian journal : management and high technologies. — 2020. — №4. — pp. 39-52.

Madibragimov Navruz Sh. - Ryazan State Radio Engineering University named after V.F. Utkin (RSREU), navruzmadibragimov@gmail.com

Prutzkow Alexander V. - Ryazan State Radio Engineering University named after V.F. Utkin (RSREU), mail@prutzkow.com

Tajik computer linguistics remains in dire need of development because many works in this direction have been performed only at a theoretical level. We have implemented the use of a universal method for generating and determining word forms for the Tajik language. Also, we have described natural language processing its levels, consider the morphological level. The features of the Tajik language and the morphology system of the Tajik language are analyzed. Studies are also presented in the field of the Tajik language processing at a morphological level. Classification of the Tajik nouns by type of morphology is explained in detail. We have found 5 types of the Tajik nouns wordforming and 12 subtypes. These types and subtypes are characterized by peculiarity. The results of this study are the basis of software implementation of word form generation of Tajik language. The development of an Internet application for the generation of Tajik word forms is briefly outlined.

Key words: computer linguistics, natural language linguistics, Tajik language, morphology of the Tajik language, formbuilding model, generation and recognition of wordforms, Internet application