@inproceedings{rowe-etal-2025-edinhelsow,
    title = "{E}din{H}els{OW} {WMT} 2025 {C}reole{MT} System Description: Improving Lusophone Creole Translation through Data Augmentation, Model Merging and {LLM} Post-editing",
    author = "Rowe, Jacqueline  and
      De Gibert, Ona  and
      Klimaszewski, Mateusz  and
      Haley, Coleman  and
      Birch, Alexandra  and
      Scherrer, Yves",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Tenth Conference on Machine Translation",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.wmt-1.91/",
    pages = "1166--1182",
    ISBN = "979-8-89176-341-8",
    abstract = "In this work, we present our submissions to the unconstrained track of the System subtask of the WMT 2025 Creole Language Translation Shared Task. Of the 52 Creole languages included in the task, we focus on translation between English and seven Lusophone Creoles. Our approach leverages known strategies for low-resource machine translation, including back-translation and distillation of data, fine-tuning pre-trained multilingual models, and post-editing with large language models and lexicons. We also demonstrate that adding high-quality parallel Portuguese data in training, initialising Creole embeddings with Portuguese embedding weights, and strategically merging best checkpoints of different fine-tuned models all produce considerable gains in performance in certain translation directions. Our best models outperform the baselines on the Task test set for eight out of fourteen translation directions. When evaluated on a more diverse test set, they surpass the baselines in all but one direction."
}