@inproceedings{shvedova-2026-general,
    title = "General Regionally Annotated Corpus of {U}krainian: Recent Developments and Future Plans",
    author = "Shvedova, Maria",
    editor = "Ba{\'n}ski, Piotr  and
      Knight, Dawn  and
      Kupietz, Marc  and
      Witt, Andreas  and
      Wr{\'o}blewska, Alina",
    booktitle = "Proceedings of the 12th Workshop on Challenges in the Management of Large Corpora",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "ELRA Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2026.cmlc-1.9/",
    doi = "10.63317/2qtbabb3qtjw",
    pages = "66--70",
    abstract = "The General Regionally Annotated Corpus of Ukrainian (GRAC) effectively serves as a national corpus. GRAC v.19 (2025) contains 2 billion tokens from over 800,000 texts (1816{--}2025). The corpus has multi-level annotations: rich metadata including regional tags, morphological annotation based on the VESUM dictionary, and partial semantic annotation. GRAC is the source of several derivative projects, including UD{\_}Ukrainian{\_}ParlaMint, ParaRook parallel corpora, Rada{\_}Trees, and others."
}