@inproceedings{moreno-2021-repu,
    title = "The {REPU} {CS}' {S}panish{--}{Q}uechua Submission to the {A}mericas{NLP} 2021 Shared Task on Open Machine Translation",
    author = "Moreno, Oscar",
    editor = "Mager, Manuel  and
      Oncevay, Arturo  and
      Rios, Annette  and
      Ruiz, Ivan Vladimir Meza  and
      Palmer, Alexis  and
      Neubig, Graham  and
      Kann, Katharina",
    booktitle = "Proceedings of the First Workshop on Natural Language Processing for Indigenous Languages of the Americas",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.americasnlp-1.27/",
    doi = "10.18653/v1/2021.americasnlp-1.27",
    pages = "241--247",
    abstract = "We present the submission of REPUcs to the AmericasNLP machine translation shared task for the low resource language pair Spanish{--}Quechua. Our neural machine translation system ranked first in Track two (development set not used for training) and third in Track one (training includes development data). Our contribution is focused on: (i) the collection of new parallel data from different web sources (poems, lyrics, lexicons, handbooks), and (ii) using large Spanish{--}English data for pre-training and then fine-tuning the Spanish{--}Quechua system. This paper describes the new parallel corpora and our approach in detail."
}