@inproceedings{hamalainen-wiechetek-2020-morphological,
    title = "Morphological Disambiguation of {S}outh {S}{\'a}mi with {FST}s and Neural Networks",
    author = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      Wiechetek, Linda},
    editor = "Beermann, Dorothee  and
      Besacier, Laurent  and
      Sakti, Sakriani  and
      Soria, Claudia",
    booktitle = "Proceedings of the 1st Joint Workshop on Spoken Language Technologies for Under-resourced languages (SLTU) and Collaboration and Computing for Under-Resourced Languages (CCURL)",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources association",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2020.sltu-1.5/",
    pages = "36--40",
    language = "eng",
    ISBN = "979-10-95546-35-1",
    abstract = "We present a method for conducting morphological disambiguation for South S{\'a}mi, which is an endangered language. Our method uses an FST-based morphological analyzer to produce an ambiguous set of morphological readings for each word in a sentence. These readings are disambiguated with a Bi-RNN model trained on the related North S{\'a}mi UD Treebank and some synthetically generated South S{\'a}mi data. The disambiguation is done on the level of morphological tags ignoring word forms and lemmas; this makes it possible to use North S{\'a}mi training data for South S{\'a}mi without the need for a bilingual dictionary or aligned word embeddings. Our approach requires only minimal resources for South S{\'a}mi, which makes it usable and applicable in the contexts of any other endangered language as well."
}