@inproceedings{bernhard-etal-2025-pre,
    title = "Pre-annotation Matters: A Comparative Study on {POS} and Dependency Annotation for an {A}lsatian Dialect",
    author = {Bernhard, Delphine  and
      Beiner, Nathana{\"e}l  and
      Hoff, Barbara},
    editor = "Peng, Siyao  and
      Rehbein, Ines",
    booktitle = "Proceedings of the 19th Linguistic Annotation Workshop (LAW-XIX-2025)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.law-1.14/",
    doi = "10.18653/v1/2025.law-1.14",
    pages = "173--186",
    ISBN = "979-8-89176-262-6",
    abstract = "The annotation of corpora for lower-resource languages can benefit from automatic pre-annotation to increase the throughput of the annotation process in a a context where human resources are scarce. However, this can be hindered by the lack of available pre-annotation tools. In this work, we compare three pre-annotation methods in zero-shot or near-zero-shot contexts for part-of-speech (POS) and dependency annotation of an Alsatian Alemannic dialect. Our study shows that good levels of annotation quality can be achieved, with human annotators adapting their correction effort to the perceived quality of the pre-annotation. The pre-annotation tools also vary in efficiency depending on the task, with better global results for a system trained on closely related languages and dialects."
}