@inproceedings{cruz-2023-samsung,
    title = "{S}amsung {R}{\&}{D} Institute {P}hilippines at {WMT} 2023",
    author = "Cruz, Jan Christian Blaise",
    editor = "Koehn, Philipp  and
      Haddow, Barry  and
      Kocmi, Tom  and
      Monz, Christof",
    booktitle = "Proceedings of the Eighth Conference on Machine Translation",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.wmt-1.6/",
    doi = "10.18653/v1/2023.wmt-1.6",
    pages = "103--109",
    abstract = "In this paper, we describe the constrained submission systems of Samsung R{\&}D Institute Philippines to the WMT 2023 General Translation Task for two directions: en-{\ensuremath{>}}he and he-{\ensuremath{>}}en. Our systems comprise of Transformer-based sequence-to-sequence models that are trained with a mix of best practices: comprehensive data preprocessing pipelines, synthetic backtranslated data, and the use of noisy channel reranking during online decoding. Our models perform comparably to, and sometimes outperform, strong baseline unconstrained systems such as mBART50 M2M and NLLB 200 MoE despite having significantly fewer parameters on two public benchmarks: FLORES-200 and NTREX-128."
}