Types of adjectives and pronouns of the Tajik language and their use to generate word-forms

Navruz Madibragimov, Alexander Prutzkow

Abstract


Despite the informatization of all spheres of people's life, the computational linguistics of the Tajik language suffers from a lack of development. The reason is the lack of research done on this topic. Within the project of formalizing the inflection of natural languages for automatic processing of texts in the Tajik language, a classification of adjectives and pronouns of this language according to the types of morphogenesis is proposed. The classification is based on a universal morphogenesis model, which assumes that inflection can be represented as a chain of transformations of finite length. For 694 adjectives of the Tajik language, 5 types and 2 subtypes of morphogenesis are distinguished. For 32 words related to the pronouns of the Tajik language, 5 types of form formation have been identified. One type of shaping includes words, the receipt of forms of which is described by the same chains of transformations. For the selected types and subtypes, the distinctive features are described, the types of conversions used in the chains are indicated. The classification carried out continues the research begun by the classification of nouns in the Tajik language. The classification was used to fill in the linguistic knowledge base of an Internet application that is available to other researchers and people studying this language in different parts of the world. Using this knowledge base, an Internet application generates the forms of words in the Tajik language. The classification of the remaining parts of speech of the Tajik language continues.


Full Text:

PDF (Russian)

References


Dovudov G.M. Komp'yuternyy morfologicheskiy analiz tadzhikskikh slovoform [Computer morphological analysis of Tajik word forms]. Dushanbe, 2018. 161 p.

Arzumanov S.D., Sanginov, A. Tadzhikskiy yazyk [Tajik language]. Dushanbe: Maorif, 1988. 416 p.

Ivanov V.B., Semyonova E.V., Khushkadamova Kh.O. Textbook of the Tajik language for countries: in 2 parts, Part 1 / Moscow State University named after M.V. Lomonosov, Institute of Asian and African countries. - M.: Klyuch-S, 2009. – 232 с. – ISBN 978-5-93136-078-2.

Madibragimov N.Sh., Prutskov A.V. Klassifikatsiya sushchestvitel'nykh tadzhikskogo yazyka dlya avtomaticheskoy obrabotki tekstov [Classification of nouns of the Tajik language for natural language processing] // Caspian journal: management and high technologies. – 2020. – № 4. – С. 39–52.

Madibragimov N.Sh. Avtomatizatsiya morfologicheskogo analiza v promyshlennykh sistemakh obrabotki tekstov [Automation of morphological analysis in industrial text processing systems] Sovremennyye tekhnologii v nauke i obrazovanii - STNO-2020 [Modern technologies in science and education - STNO-2020]. Ryazan, 2020. pp. 34-38.

Madibragimov N. Komp'yuternyye modeli formoobrazovaniya slov i ikh primeneniye dlya opisaniya morfologii tadzhikskogo yazyka [Computer models of morphogenesis of words, and their application for description of tajik language morphology] Sovremennyye tekhnologii v nauke i obrazovanii - STNO-2018 [Modern technologies in science and education - STNO-2018]. Ryazan, 2018. pp. 65-68.

Prutskov A.V. Modeli, metody i programmy avtomaticheskoy obrabotki form slov v yestestvenno-yazykovykh interfeysakh [Models, methods and programs for automatic processing of word forms in natural language interfaces]. Ryazan, 2015. 279 p.


Refbacks

  • There are currently no refbacks.


Abava  Absolutech Convergent 2020

ISSN: 2307-8162