@inproceedings{kuparinen-2023-murreviikko,
    title = "Murreviikko - A Dialectologically Annotated and Normalized Dataset of {F}innish Tweets",
    author = "Kuparinen, Olli",
    editor = {Scherrer, Yves  and
      Jauhiainen, Tommi  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Nakov, Preslav  and
      Tiedemann, J{\"o}rg  and
      Zampieri, Marcos},
    booktitle = "Tenth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2023)",
    month = may,
    year = "2023",
    address = "Dubrovnik, Croatia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2023.vardial-1.3/",
    doi = "10.18653/v1/2023.vardial-1.3",
    pages = "31--39",
    abstract = "This paper presents Murreviikko, a dataset of dialectal Finnish tweets which have been dialectologically annotated and manually normalized to a standard form. The dataset can be used as a test set for dialect identification and dialect-to-standard normalization, for instance. We evaluate the dataset on the normalization task, comparing an existing normalization model built on a spoken dialect corpus and three newly trained models with different architectures. We find that there are significant differences in normalization difficulty between the dialects, and that a character-level statistical machine translation model performs best on the Murreviikko tweet dataset."
}