@inproceedings{velasco-etal-2024-samsung,
    title = "{S}amsung {R}{\&}{D} Institute {P}hilippines @ {WMT} 2024 Low-resource Languages of {S}pain Shared Task",
    author = "Velasco, Dan John  and
      Rufino, Manuel Antonio  and
      Cruz, Jan Christian Blaise",
    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-1.86/",
    doi = "10.18653/v1/2024.wmt-1.86",
    pages = "892--900",
    abstract = "This paper details the submission of Samsung R{\&}D Institute Philippines (SRPH) Language Intelligence Team (LIT) to the WMT 2024 Low-resource Languages of Spain shared task. We trained translation models for Spanish to Aragonese, Spanish to Aranese/Occitan, and Spanish to Asturian using a standard sequence-to-sequence Transformer architecture, augmenting it with a noisy-channel reranking strategy to select better outputs during decoding. For Spanish to Asturian translation, our method reaches comparable BLEU scores to a strong commercial baseline translation system using only constrained data, backtranslations, noisy channel reranking, and a shared vocabulary spanning all four languages."
}