Uzbek News Categorization using Word Embeddings and Convolutional Neural Networks

Ilyos Rabbimov, Sami Kobilov, Iosif Mporas

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The rapid growth of online news belonging to different categories is causing users to spend a lot of time and effort searching for relevant and important news. Text categorization has a great significance in information retrieval and natural language processing where unstructured text can be organized into predefined categories. In this paper we investigate Uzbek news categorization using a convolution neural network and four word embedding models. We obtain two new word embeddings for Uzbek and present them in the Uzbek news categorization task.
Original languageEnglish
Title of host publication2020 IEEE 14th International Conference on Application of Information and Communication Technologies (AICT) Proceedings
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages5
ISBN (Electronic)9781728173863
ISBN (Print)9781728173870
DOIs
Publication statusPublished - 9 Mar 2021
EventThe 14th IEEE International Conference on Application of Information and Communication Technologies - Tashkent, Uzbekistan
Duration: 7 Oct 20209 Oct 2020
http://www.aict.info/2020

Publication series

Name14th IEEE International Conference on Application of Information and Communication Technologies, AICT 2020 - Proceedings

Conference

ConferenceThe 14th IEEE International Conference on Application of Information and Communication Technologies
Abbreviated titleAICT 2020
Country/TerritoryUzbekistan
CityTashkent
Period7/10/209/10/20
Internet address

Keywords

  • CNN
  • Uzbek
  • multi-class classification
  • news categorization
  • word embeddings

Fingerprint

Dive into the research topics of 'Uzbek News Categorization using Word Embeddings and Convolutional Neural Networks'. Together they form a unique fingerprint.

Cite this