@inproceedings{chaplynskyi-2023-introducing,
    title = "Introducing {U}ber{T}ext 2.0: A Corpus of {M}odern {U}krainian at Scale",
    author = "Chaplynskyi, Dmytro",
    editor = "Romanyshyn, Mariana",
    booktitle = "Proceedings of the Second Ukrainian Natural Language Processing Workshop (UNLP)",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.unlp-1.1",
    doi = "10.18653/v1/2023.unlp-1.1",
    pages = "1--10",
    abstract = "This paper addresses the need for massive corpora for a low-resource language and presents the publicly available UberText 2.0 corpus for the Ukrainian language and discusses the methodology of its construction. While the collection and maintenance of such a corpus is more of a data extraction and data engineering task, the corpus itself provides a solid foundation for natural language processing tasks. It can enable the creation of contemporary language models and word embeddings, resulting in a better performance of numerous downstream tasks for the Ukrainian language. In addition, the paper and software developed can be used as a guidance and model solution for other low-resource languages. The resulting corpus is available for download on the project page. It has 3.274 billion tokens, consists of 8.59 million texts and takes up 32 gigabytes of space.",
}