@inproceedings{keita-etal-2026-nsl,
    title = "{NSL}-{MT}: Linguistically Informed Negative Samples for Efficient Machine Translation in {A}frican Low-Resource Languages",
    author = "Keita, Mamadou K.  and
      Homan, Christopher M  and
      Le, Huy",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.465/",
    pages = "9545--9560",
    ISBN = "979-8-89176-395-1",
    abstract = "We introduce negative space learning machine translation (NSL-MT), a training method for underresourced languages, that augments limited parallel data with synthetically generated violations of the target language{'}s grammar and explicitly penalizes the model when it assigns high probability to these linguistically invalid outputs. NSL-MT delivers improvements across all baselines we tested, including 3-12{\%} BLEU gains for well-performing models and 56-89{\%} gains for models lacking decent initial support. Furthermore, NSL-MT provides a 5x data efficiency multiplier: training with 1,000 examples matches or exceeds normal training with 5,000 examples. NSL-MT thus provides a data-efficient alternative training method for settings where parallel data is limited."
}