@inproceedings{zhang-etal-2025-systran,
    title = "{SYSTRAN} @ {WMT} 2025 General Translation Task",
    author = "Zhang, Dakun  and
      Khater, Yara  and
      Rahli, Ramzi  and
      Rebollo, Anna  and
      Crego, Josep",
    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-1.35/",
    pages = "599--606",
    ISBN = "979-8-89176-341-8",
    abstract = "We present an English-to-Japanese translationsystem built upon the EuroLLM-9B (Martinset al., 2025) model. The training process involvestwo main stages: continue pretraining(CPT) and supervised fine-tuning (SFT). Afterboth stages, we further tuned the model using adevelopment set to optimize performance. Fortraining data, we employed both basic filteringtechniques and high-quality filtering strategiesto ensure data cleanness. Additionally, we classifyboth the training data and development datainto four different domains and we train andfine-tune with domain specific prompts duringsystem training. Finally, we applied MinimumBayes Risk (MBR) decoding and paragraph-levelreranking for post-processing to enhancetranslation quality."
}