Multi-label 24.kg Kyrgyz news articles classification into 20 topics: data & baselines.
Both data and baselines will be released after the competition.
The dataset will be introduced at the AIST 2023 conference. Meanwhile, the arXiv preprint is out.
@misc{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},
primaryClass={cs.CL}
}