Benchmarking Multilabel Topic Classification in the Kyrgyz Language
This provides a foundational resource for Kyrgyz NLP, addressing a gap for researchers and practitioners working with this underrepresented language.
The authors tackled the lack of modern NLP resources for the Kyrgyz language by creating a new public benchmark for multilabel topic classification, based on annotated news data from 24.KG, and reported baseline model scores including both classical statistical and neural approaches.
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.