@inproceedings{walsh-etal-2025-estor,
    title = "e{ST{\'O}R}: Curating {I}rish Datasets for Machine Translation",
    author = "Walsh, Abigail  and
      Loinsigh, {\'O}rla N{\'i}  and
      Adkins, Jane  and
      O{'}Connell, Ornait  and
      Andrade, Mark  and
      Clifford, Teresa  and
      Gaspari, Federico  and
      Dunne, Jane  and
      Davis, Brian",
    editor = {Bouillon, Pierrette  and
      Gerlach, Johanna  and
      Girletti, Sabrina  and
      Volkart, Lise  and
      Rubino, Raphael  and
      Sennrich, Rico  and
      L{\"a}ubli, Samuel  and
      Volk, Martin  and
      Espl{\`a}-Gomis, Miquel  and
      Vandeghinste, Vincent  and
      Moniz, Helena  and
      Szoc, Sara},
    booktitle = "Proceedings of Machine Translation Summit XX: Volume 2",
    month = jun,
    year = "2025",
    address = "Geneva, Switzerland",
    publisher = "European Association for Machine Translation",
    url = "https://preview.aclanthology.org/nschneid-patch-1/2025.mtsummit-2.28/",
    pages = "115--116",
    ISBN = "978-2-9701897-1-8",
    abstract = "Minority languages such as Irish are massively under-resourced, particularly in terms of high-quality domain-relevant data, limiting the capabilities of machine translation (MT) engines, even those integrating large language models (LLMs). The eST{\'O}R project, described in this paper, focuses on the collection and curation of high-quality Irish text data for diverse domains."
}