@inproceedings{scherrer-2023-character,
    title = "Character alignment methods for dialect-to-standard normalization",
    author = "Scherrer, Yves",
    editor = {Nicolai, Garrett  and
      Chodroff, Eleanor  and
      Mailhot, Frederic  and
      {\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
    booktitle = "Proceedings of the 20th SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.sigmorphon-1.12/",
    doi = "10.18653/v1/2023.sigmorphon-1.12",
    pages = "110--116",
    abstract = "This paper evaluates various character alignment methods on the task of sentence-level standardization of dialect transcriptions. We compare alignment methods from different scientific traditions (dialectometry, speech processing, machine translation) and apply them to Finnish, Norwegian and Swiss German dialect datasets. In the absence of gold alignments, we evaluate the methods on a set of characteristics that are deemed undesirable for the task. We find that trained alignment methods only show marginal benefits to simple Levenshtein distance. On this particular task, eflomal outperforms related methods such as GIZA++ or fast{\_}align by a large margin."
}