SCIENTIFIC AND PRACTICAL PROBLEMS OF AUTOMATION OF THE KAZAKH ORTHOGRAPHY THROUGH THE METHOD OF MODELING

Nazira Amirzhanova, D. Sadyk

2024

Full text Open access: Hybrid Metadata (CSL-JSON)
DOI 10.55491/2411-6076-2024-2-172-181
Data confidence 70 medium
How this score is calculated

It is built from checkable properties of the record itself: whether the article has a DOI, how many independent sources confirmed its data, whether the required fields are filled in, and how recent the latest confirmation is. Disagreement between sources and a missing identifier lower it. A value of 80 or above means the record was published without further checking; 60 to 79 means it is published at reduced confidence, with a manual check advisable. A record verified by an editor by hand is never pushed below 90 by a recalculation. This scores our data about the article, not the article itself.

Abstract

The rapid development of digital technologies, including the emergence of the Internet, led to a radical change in the communicative landscape of the 20th century. The possibility of constant access to the Internet, as well as the use of applications for the exchange of instant messages online gave an impetus to the formation of a new digital language, the development of a new language environment. Currently, the Kazakh language entered the digital space and the life force of the Kazakh language was formed in the virtual space. In this regard, an inventory of knowledge related to the Kazakh language was carried out and the development of Kazakh language resources in the virtual space was put on the agenda. Automation of orthography is the process of using computer programs and tools to check the spelling of words in a text. This allows one to automatically correct spelling errors and reduce the time spent on text editing. Innovative functions require the development of a formal language model. And for formal modeling of orthography, first of all, it is necessary to conduct an inventory of knowledge related to orthography, to identify difficulties in spelling. Currently, scientists of the Institute of Linguistics named after A. Baitursynuly are conducting research within the framework of the program-targeted financing project “Automatic recognition of Kazakh text: development of linguistic modules and IT solutions”. As a part of the research, linguistic resources are differentiated and analyzed, allowing to automatically correct errors in word spelling. The article analyzes in detail the automation of knowledge related to orthography, scientific and practical problems of its automatic representation, modeling of knowledge related to Kazakh orthography, definition of model concepts, common types of modeling, types of modeling used in automation. Also, for the automation of Kazakh orthography, types of modeling using phonetic-phonological and orthographic distinctive signs are proposed, the stages of automation of Kazakh orthography are described.