@inproceedings{gerlach-etal-2022-producing,
    title = "Producing {S}tandard {G}erman Subtitles for {S}wiss {G}erman {TV} Content",
    author = "Gerlach, Johanna  and
      Mutal, Jonathan  and
      Bouillon, Pierrette",
    editor = "Ebling, Sarah  and
      Prud{'}hommeaux, Emily  and
      Vaidyanathan, Preethi",
    booktitle = "Ninth Workshop on Speech and Language Processing for Assistive Technologies (SLPAT-2022)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.slpat-1.5/",
    doi = "10.18653/v1/2022.slpat-1.5",
    pages = "37--43",
    abstract = "In this study we compare two approaches (neural machine translation and edit-based) and the use of synthetic data for the task of translating normalised Swiss German ASR output into correct written Standard German for subtitles, with a special focus on syntactic differences. Results suggest that NMT is better suited to this task and that relatively simple rule-based generation of training data could be a valuable approach for cases where little training data is available and transformations are simple."
}