@inproceedings{seto-etal-2025-assessing,
    title = "Assessing the Role of Data Quality in Training Bilingual Language Models",
    author = "Seto, Skyler  and
      Ter Hoeve, Maartje  and
      de Seyssel, Maureen  and
      Grangier, David",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/lei-li-partial-disambiguation/2025.findings-emnlp.1236/",
    pages = "22694--22720",
    ISBN = "979-8-89176-335-7"
}