TOPIC CLASSIFICATION OF UZBEK TEXTS

Journal Title: International scientific journal Science and Innovation - Year 2024, Vol 3, Issue 9

Abstract

Topic classification of text is an important task in the field of natural language processing, where the main goal is to classify text data into predefined categories. In this study, we analyze the dataset creation and methods for evaluating multi-tag news series as part of topic-based topic classification. First, in the article, we present obtained corpus for the classification of texts in Uzbek language. This corpus was collected from 5 different news and press websites and contains 4 categories of news, press and legal texts. We also trained a rule-based machine learning model and a neural network model for subject classification in this newly created corpus experiment. Experiments show that models based on recurrent neural network and convolutional neural network outperform rule-based models.

Authors and Affiliations

Salaev U. , Matlatipov S. G.

Keywords

Related Articles

USE OF INNOVATIVE PEDAGOGICAL TECHNOLOGIES IN PASSING EPIC WORKS IN LITERATURE LESSONS

This article talks about the use of innovative pedagogical technologies in the passage of epic works in literature classes, the effective methods of making the student interested in fiction and the formation of reading s...

POINT ESTIMATION OF THE TRUE VALUE AND MEAN SQUARE DEVIATION OF THE MEASUREMENT

This article covers in detail the issues of ensuring metrological dimensions at the required level in the process of production and repair of mechanical engineering parts, information about the types of measurements, m...

IMPORTANCE OF ORGANIZING SMART AUDIENCES BASED ON INNOVATIVE CHANGES IN ENSURING THE QUALITY OF EDUCATION IN PROFESSIONAL EDUCATIONAL INSTITUTIONS

The article examines the content of the concepts on quality of education, factors influencing the quality of education, smart education, smart audience, innovative approach. The importance of ensuring the quality of educ...

THE IMPORTANCE OF FINANCIAL CONTROL IN JOINT-STOCK COMPANIES

The artіcle proposes a model for controllіng profіts іn joіnt-stock companіes, whіch іncludes two blocks: strategіc and operatіonal, between whіch a relatіonshіp іs establіshed and the departments that іmplement them. Th...

WATERPROOFNESS AND ADHESION OF BITUMINOUS MASTIC

This article deeply analyzes the results of water resistance and adhesion strength of the developed waterproof material. It is revealed that under low water pressure conditions, the results of determining the water resis...

Download PDF file
  • EP ID EP747994
  • DOI 10.5281/zenodo.13882462
  • Views 1
  • Downloads 0

How To Cite

Salaev U. , Matlatipov S. G. (2024). TOPIC CLASSIFICATION OF UZBEK TEXTS. International scientific journal Science and Innovation, 3(9), -. https://europub.co.uk/articles/-A-747994