@inproceedings{jaswal-2025-takes,
    title = "It Takes Two: A Dual Stage Approach for Terminology-Aware Translation",
    author = "Jaswal, Akshat",
    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/author-page-yu-wang-polytechnic/2025.wmt-1.112/",
    doi = "10.18653/v1/2025.wmt-1.112",
    pages = "1344--1350",
    ISBN = "979-8-89176-341-8",
    abstract = "This paper introduces DuTerm, a novel two-stage architecture for terminology-constrained machine translation. Our system combines a terminology-aware NMT model, adapted via fine-tuning on large-scale synthetic data, with a prompt-based LLM for post-editing. The LLM stage refines NMT output and enforces terminology adherence. We evaluate DuTerm on English-to German, English-to-Spanish, and English-to-Russian for the WMT 2025 Terminology Shared Task. We demonstrate that flexible, context-driven terminology handling by the LLM consistently yields higher quality translations than strict constraint enforcement. Our results highlight a critical trade-off, revealing that an LLM{'}s intrinsic knowledge often provides a stronger basis for high-quality translation than rigid, externally imposed constraints."
}