@inproceedings{raunak-etal-2023-evaluating,
    title = "Evaluating Metrics for Document-context Evaluation in Machine Translation",
    author = "Raunak, Vikas  and
      Kocmi, Tom  and
      Post, Matt",
    editor = "Koehn, Philipp  and
      Haddow, Barry  and
      Kocmi, Tom  and
      Monz, Christof",
    booktitle = "Proceedings of the Eighth Conference on Machine Translation",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.wmt-1.68/",
    doi = "10.18653/v1/2023.wmt-1.68",
    pages = "812--814",
    abstract = "We describe our submission of a new metric, SLIDE (Raunak et al., 2023), to the WMT 2023 metrics task. SLIDE is a reference-free quality-estimation metric that works by constructing a fixed sentence-length window over the documents in a test set, concatenating chunks and then sending them for scoring as a single unit by COMET (Rei et al, 2022). We find that SLIDE improves dramatically over its context-less counterpart on the two WMT22 evaluation campaigns (MQM and DA+SQM)."
}