@inproceedings{partanen-etal-2019-dialect,
    title = "Dialect Text Normalization to Normative Standard {F}innish",
    author = {Partanen, Niko  and
      H{\"a}m{\"a}l{\"a}inen, Mika  and
      Alnajjar, Khalid},
    editor = "Xu, Wei  and
      Ritter, Alan  and
      Baldwin, Tim  and
      Rahimi, Afshin",
    booktitle = "Proceedings of the 5th Workshop on Noisy User-generated Text (W-NUT 2019)",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/D19-5519/",
    doi = "10.18653/v1/D19-5519",
    pages = "141--146",
    abstract = "We compare different LSTMs and transformer models in terms of their effectiveness in normalizing dialectal Finnish into the normative standard Finnish. As dialect is the common way of communication for people online in Finnish, such a normalization is a necessary step to improve the accuracy of the existing Finnish NLP tools that are tailored for normative Finnish text. We work on a corpus consisting of dialectal data of 23 distinct Finnish dialects. The best functioning BRNN approach lowers the initial word error rate of the corpus from 52.89 to 5.73."
}