@inproceedings{pikuliak-simko-2022-average,
    title = "Average Is Not Enough: Caveats of Multilingual Evaluation",
    author = "Pikuliak, Mat{\'u}{\v{s}}  and
      Simko, Marian",
    editor = {Ataman, Duygu  and
      Gonen, Hila  and
      Ruder, Sebastian  and
      Firat, Orhan  and
      G{\"u}l Sahin, G{\"o}zde  and
      Mirzakhalov, Jamshidbek},
    booktitle = "Proceedings of the 2nd Workshop on Multi-lingual Representation Learning (MRL)",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates (Hybrid)",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2022.mrl-1.13/",
    doi = "10.18653/v1/2022.mrl-1.13",
    pages = "125--133",
    abstract = "This position paper discusses the problem of multilingual evaluation. Using simple statistics, such as average language performance, might inject linguistic biases in favor of dominant language families into evaluation methodology. We argue that a qualitative analysis informed by comparative linguistics is needed for multilingual results to detect this kind of bias. We show in our case study that results in published works can indeed be linguistically biased and we demonstrate that visualization based on URIEL typological database can detect it."
}