@inproceedings{reijnaers-pouw-2024-gtnc,
    title = "{GTNC}: A Many-To-One Dataset of {G}oogle Translations from {N}ews{C}rawl",
    author = "Reijnaers, Damiaan  and
      Pouw, Charlotte",
    editor = "Hahn, Michael  and
      Sorokin, Alexey  and
      Kumar, Ritesh  and
      Shcherbakov, Andreas  and
      Otmakhova, Yulia  and
      Yang, Jinrui  and
      Serikov, Oleg  and
      Rani, Priya  and
      Ponti, Edoardo M.  and
      Murado{\u{g}}lu, Saliha  and
      Gao, Rena  and
      Cotterell, Ryan  and
      Vylomova, Ekaterina",
    booktitle = "Proceedings of the 6th Workshop on Research in Computational Linguistic Typology and Multilingual NLP",
    month = mar,
    year = "2024",
    address = "St. Julian's, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.sigtyp-1.8/",
    pages = "58--65",
    abstract = "This paper lays the groundwork for initiating research into Source Language Identification; the task of identifying the original language of a machine-translated text. We contribute a dataset of translations from a typologically diverse spectrum of languages into English and use it to set initial baselines for this novel task."
}