@inproceedings{knowles-lo-2022-test,
    title = "Test Set Sampling Affects System Rankings: Expanded Human Evaluation of {WMT}20 {E}nglish-{I}nuktitut Systems",
    author = "Knowles, Rebecca  and
      Lo, Chi-kiu",
    editor = {Koehn, Philipp  and
      Barrault, Lo{\"i}c  and
      Bojar, Ond{\v{r}}ej  and
      Bougares, Fethi  and
      Chatterjee, Rajen  and
      Costa-juss{\`a}, Marta R.  and
      Federmann, Christian  and
      Fishel, Mark  and
      Fraser, Alexander  and
      Freitag, Markus  and
      Graham, Yvette  and
      Grundkiewicz, Roman  and
      Guzman, Paco  and
      Haddow, Barry  and
      Huck, Matthias  and
      Jimeno Yepes, Antonio  and
      Kocmi, Tom  and
      Martins, Andr{\'e}  and
      Morishita, Makoto  and
      Monz, Christof  and
      Nagata, Masaaki  and
      Nakazawa, Toshiaki  and
      Negri, Matteo  and
      N{\'e}v{\'e}ol, Aur{\'e}lie  and
      Neves, Mariana  and
      Popel, Martin  and
      Turchi, Marco  and
      Zampieri, Marcos},
    booktitle = "Proceedings of the Seventh Conference on Machine Translation (WMT)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.wmt-1.8/",
    pages = "140--153",
    abstract = "We present a collection of expanded human annotations of the WMT20 English-Inuktitut machine translation shared task, covering the Nunavut Hansard portion of the dataset. Additionally, we recompute News rankings to take into account the completed set of human annotations and certain irregularities in the annotation task construction. We show the effect of these changes on the downstream task of the evaluation of automatic metrics. Finally, we demonstrate that character-level metrics correlate well with human judgments for the task of automatically evaluating translation into this polysynthetic language."
}