@inproceedings{o-meachair-etal-2026-corpas,
    title = "Corpas N{\'a}isi{\'u}nta {N}a Gaeilge 2022-2029: A Project Overview",
    author = "{\'O} Meachair, M{\'i}che{\'a}l J.  and
      Bhreathnach, {\'U}na  and
      Scannell, Kevin  and
      Mechura, Michal  and
      {\'O} Raghallaigh, Brian  and
      {\'O} Cleirc{\'i}n, Gear{\'o}id",
    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-1.8/",
    doi = "10.63317/4ybzkgmrs3hd",
    pages = "63--65",
    abstract = "This paper reports the latest developments, planned works, and issues of the Corpas N{\'a}isi{\'u}nta na Gaeilge (henceforth: CNG, translation: the National Corpus of Irish) project, detailing the work that has been completed to date, current work, and planned future work. This report details the compilation of corpora, development of a project website and part-speech tagger, the challenges of expanding existing corpora, and the addition of historical and legal corpora. We also present the training and outreach activities of the project."
}