@inproceedings{yang-etal-2024-optimising,
    title = "Optimising {LLM}-Driven Machine Translation with Context-Aware Sliding Windows",
    author = "Yang, Xinye  and
      Mu, Yida  and
      Bontcheva, Kalina  and
      Song, Xingyi",
    editor = "Haddow, Barry  and
      Kocmi, Tom  and
      Koehn, Philipp  and
      Monz, Christof",
    booktitle = "Proceedings of the Ninth Conference on Machine Translation",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.wmt-1.101/",
    doi = "10.18653/v1/2024.wmt-1.101",
    pages = "1004--1010",
    abstract = "This paper describes SheffieldGATE{'}s submission to WMT 2024 Chat Shared Translation Task. We participate in three language pairs: English-German, English-Dutch, and English-Portuguese (Brazil). In this work, we introduce a context-aware sliding window decoding method to track dependencies between chat messages. We fine-tune a large pre-trained language model based on the training data provided by the shared task Our experiments (i) compare the model performance between multilingual and bilingual fine-tuning and (ii) assess the impact of different window sizes. Our experimental results demonstrate that utilising contextual information yields superior performance in document-level translation compared to translating documents as isolated text segments, and that models fine-tuned with multilingual data perform better than those fine-tuned with bilingual data."
}