@inproceedings{haltiuk-smywinski-pohl-2025-path,
    title = "On the Path to Make {U}krainian a High-Resource Language",
    author = "Haltiuk, Mykola  and
      Smywi{\'n}ski-Pohl, Aleksander",
    editor = "Romanyshyn, Mariana",
    booktitle = "Proceedings of the Fourth Ukrainian Natural Language Processing Workshop (UNLP 2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria (online)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.unlp-1.14/",
    pages = "120--130",
    ISBN = "979-8-89176-269-5",
    abstract = "Recent advances in multilingual language modeling have highlighted the importance of high-quality, large-scale datasets in enabling robust performance across languages. However, many low- and mid-resource languages, including Ukrainian, remain significantly underrepresented in existing pretraining corpora. We present Kobza, a large-scale Ukrainian text corpus containing nearly 60 billion tokens, aimed at improving the quality and scale of Ukrainian data available for training multilingual language models. We constructed Kobza from diverse, high-quality sources and applied rigorous deduplication to maximize data utility. Using this dataset, we pre-trained Modern-LiBERTa, the first Ukrainian transformer encoder capable of handling long contexts (up to 8192 tokens). Modern-LiBERTa achieves competitive results on various standard Ukrainian NLP benchmarks, particularly benefiting tasks that require broader contextual understanding or background knowledge. Our goal is to support future efforts to develop robust Ukrainian language models and to encourage greater inclusion of Ukrainian data in multilingual NLP research."
}