ELECTRONIC PASHTO DICTIONARY: CREATING A MORPHOLOGY DATABASE

The article deals with the creation of an electronic dictionary based on the “Pushto-Russian Dictionary” by M. G. Aslanov, which is currently the most comprehensive Pashto dictionary. However, paper dictionaries inevitably become outdated, while electronic dictionaries have a number of indisputable advantages over traditional ones. The work on an electronic dictionary includes three stages: 1) compiling a vocabulary (or using an already completed one), 2) creating a morphology base, 3) working with syntax, which consists in creating a corpus of texts that will allow revealing non-free compatibility of words, starting with a word combination. The article focuses mainly on creation of a Pashto morphology database for an electronic dictionary, on nouns and adjectives, which has never been done before. According to grammatical variables, the paradigmatic classes of the indicated parts of speech are distinguished, as well as all possible forms of the word (morphemes) within the classes. Twenty-six paradigmatic classes are distinguished for nouns, and eight for adjectives. Some classes are divided into subclasses, each of which includes one word. This refers to the so-called exceptions to the rules. For each class, the most characteristic word is given as a model. Each morpheme (as well as each meaning of a word) appears as a separate dictionary unit, which allows the user to easily find the desired word, as well as to make a reverse translation. This article is intended for Afghans who speak Pashto, as well as Russian speakers who deal with Pashto. Of particular interest are the results of the study for those who compose or intend to compile electronic dictionaries, especially of rare languages.

1. Zubov A. V., Zubova I. I. Osnovy iskusstvennogo intellekta dlia lingvistov. [Basics of artificial intelligence for linguists]. Moskva: RGGU, 2013. 320s.

2. Baza dannykh po russkoi I angliiskoi leksike I morfologii [Database on Russian and English vocabulary and morphology]. Available at: http://www.solarix.ru/sql-dictionary-sdk.shtml (accessed 15 May 2018).

3. Selegej V. P. Komp’iuternaia leksikografiia [Computer lexicography]. Availableat: https://www.abbyy.com/ru-ru/science/tech-nologies/lexicography/ (accessed 15 May 2018).

4. Lingvisticheskii protsessor estestvennogo iazika [Natural Language Linguistic Processor]. Availableat: https://studfiles.net/preview/972381/page:5/ (accessed 16 May 2018).