@inproceedings{idahl-etal-2026-multisynt,
    title = "{M}ulti{S}ynt/{MT}: Trillion-Token Multi-Parallel Pretraining Data Translated Across 36 Languages",
    author = {Idahl, Maximilian  and
      Tiedemann, J{\"o}rg  and
      Pyysalo, Sampo  and
      Salinas, David  and
      Galica, Tomasz  and
      Qian, Shenbin  and
      Mateiu, Tudor Nicolae  and
      Li, Zihao  and
      Lokrantz, Anna  and
      Vitiugin, Fedor  and
      Martins, Andre  and
      Kanerva, Jenna  and
      Ginter, Filip  and
      Lindemann, Matthias  and
      Isbister, Tim  and
      Moell, Birger  and
      Lindh, Jonas  and
      Haji{\v{c}}, Jan  and
      Jitsev, Jenia  and
      Kutuzov, Andrey  and
      Oepen, Stephan  and
      Ram{\'i}rez-S{\'a}nchez, Gema},
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.2185/",
    pages = "49670--49694",
    ISBN = "979-8-89176-459-0"
}