@inproceedings{kuulmets-fishel-2023-translated,
    title = "Translated Benchmarks Can Be Misleading: the Case of {E}stonian Question Answering",
    author = "Kuulmets, Hele-Andra  and
      Fishel, Mark",
    editor = {Alum{\"a}e, Tanel  and
      Fishel, Mark},
    booktitle = "Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)",
    month = may,
    year = "2023",
    address = "T{\'o}rshavn, Faroe Islands",
    publisher = "University of Tartu Library",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.nodalida-1.71/",
    pages = "710--716",
    abstract = "Translated test datasets are a popular and cheaper alternative to native test datasets. However, one of the properties of translated data is the existence of cultural knowledge unfamiliar to the target language speakers. This can make translated test datasets differ significantly from native target datasets. As a result, we might inaccurately estimate the performance of the models in the target language. In this paper, we use both native and translated Estonian QA datasets to study this topic more closely. We discover that relying on the translated test dataset results in an overestimation of the model`s performance on native Estonian data."
}