@inproceedings{bouton-2024-towards,
    title = "Towards standardized inflected lexicons for the Finnic languages",
    author = "Bouton, Jules",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      Pirinen, Flammie  and
      Macias, Melany  and
      Crespo Avila, Mario},
    booktitle = "Proceedings of the 9th International Workshop on Computational Linguistics for Uralic Languages",
    month = nov,
    year = "2024",
    address = "Helsinki, Finland",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.iwclul-1.7/",
    pages = "59--66",
    abstract = "We introduce three richly annotated lexicons of nouns for Livonian, standard Finnish and Livvi Karelian. Our datasets are distributed in the machine-readable Paralex standard, which consists of linked CSV tables described in a JSON metadata file. We built on the morphological dictionary of Livonian, the VepKar database and the Omorfi software to provide inflected forms. All noun forms were transcribed with grapheme-to-phoneme conversion rules and the paradigms annotated for both overabundance and defectivity. The resulting datasets are usable for quantitative studies of morphological systems and for qualitative investigations. They are linked to the original resources and can be easily updated."
}