Benchmarking Multilabel Topic Classification in the Kyrgyz Language

Anton Alekseev, Sergey I. Nikolenko, Gulnara Kabaeva
8/30/2023
cs.CL

No official code found. Best implementation: alexeyev/kyrgyz-multi-label-topic-classification (2 stars, last commit 2025-02-23).

Abstract

Kyrgyz is a very underrepresented language in terms of modern natural language processing resources. In this work, we present a new public benchmark for topic classification in Kyrgyz, introducing a dataset based on collected and annotated data from the news site 24.KG and presenting several baseline models for news classification in the multilabel setting. We train and evaluate both classical statistical and neural models, reporting the scores, discussing the results, and proposing directions for future work.

View on arXivView PDF

Code Implementations(1)

alexeyev/kyrgyz-multi-label-topic-classificationCommunity100%

Multi-label 24.kg Kyrgyz news articles classification into 20 topics: data & baselines

20PythonAug 24, 20231 years ago
kyrgyzmulti-label-classificationnews-classificationtopic-classificationturkic-languages

Similar Papers

MasakhaNEWS: News Topic Classification for African languages

85% match1 repo262023

Text classification dataset and analysis for Uzbek language

84% match1 repo22023

Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati

84% match2023

ltzGLUE: Luxembourgish General Language Understanding Evaluation

84% match2026

SIB-200: A Simple, Inclusive, and Big Evaluation Dataset for Topic Classification in 200+ Languages and Dialects

82% match1 repo282023

Revisiting Topic-Guided Language Models

82% match2023

Cite this paper

@article{alekseev2023benchmarking,
  title  = {Benchmarking Multilabel Topic Classification in the Kyrgyz Language},
  author = {Anton Alekseev and Sergey I. Nikolenko and Gulnara Kabaeva},
  year   = {2023},
  eprint = {2308.15952},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.15952v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.15952.svg)](https://codeofpaper.com/paper/2308.15952)

Discussion