@inproceedings{cols-2024-spanish,
    title = "{S}panish Corpus and Provenance with Computer-Aided Translation for the {WMT}24 {OLDI} Shared Task",
    author = "Cols, Jose",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Ninth Conference on Machine Translation",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.wmt-1.50/",
    doi = "10.18653/v1/2024.wmt-1.50",
    pages = "624--635",
    abstract = "This paper presents the Seed-CAT submission to the WMT24 Open Language Data Initiative shared task. We detail our data collection method, which involves a computer-aided translation tool developed explicitly for translating Seed corpora. We release a professionally translated Spanish corpus and a provenance dataset documenting the translation process. The quality of the data was validated on the FLORES+ benchmark with English-Spanish neural machine translation models, achieving an average chrF++ score of 34.9."
}