@inproceedings{zhu-etal-2025-fine,
    title = "Fine-tuning {NMT} Models and {LLM}s for Specialised {EN}-{ES} Translation Using Aligned Corpora, Glossaries, and Synthetic Data: {MULTITAN} at {WMT}25 Terminology Shared Task",
    author = "Zhu, Lichao  and
      Zimina-Poirot, Maria  and
      Patin, Stephane  and
      Valdez, Cristian",
    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-1.108/",
    pages = "1284--1291",
    ISBN = "979-8-89176-341-8",
    abstract = "This paper describes our participation in the WMT25 Terminology Shared Task, specifically Track 1 (Spanish to English) focused on translation within the Information Technology (IT) domain. The shared task challenges participants to improve machine translation systems by effectively incorporating terminology constraints to ensure accurate and consistent translation of specialised technical terms. We experimented with several approaches to tackle terminology and lexical constraints with both NMT systems and LLMs with a small amount of training data and a glossary. Experimental results demonstrate that systems behave differently with and without glossary. The NMT system seems rather limited in adapting to special lexicon and resizing embeddings, which is the opposite of the case with LLMs preferring structured instructions. Through this participation, our objective is to improve terminology accuracy and overall translation quality, highlight the potential of specialised terminology-aware translation models for technical domains, and explore possibilities of fine-tuning of LLMs and NMT models with domain and lexical constraints."
}