@inproceedings{pugh-tyers-2024-experiments,
    title = "Experiments in Multi-Variant Natural Language Processing for {N}ahuatl",
    author = "Pugh, Robert  and
      Tyers, Francis",
    editor = {Scherrer, Yves  and
      Jauhiainen, Tommi  and
      Ljube{\v{s}}i{\'c}, Nikola  and
      Zampieri, Marcos  and
      Nakov, Preslav  and
      Tiedemann, J{\"o}rg},
    booktitle = "Proceedings of the Eleventh Workshop on NLP for Similar Languages, Varieties, and Dialects (VarDial 2024)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.vardial-1.12/",
    doi = "10.18653/v1/2024.vardial-1.12",
    pages = "140--151",
    abstract = "Linguistic variation is a complicating factor for digital language technologies. This is particularly true for languages that lack an official {\textquotedblleft}standard{\textquotedblright} variety, including many regional and minoritized languages. In this paper, we describe a set of experiments focused on multivariant natural language processing for the Nahuatl, an indigenous Mexican language with a high level of linguistic variation and no single recognized standard variant. Using small (10k tokens), recently-published annotated datasets for two Nahuatl variants, we compare the performance of single-variant, cross-variant, and joint training, and explore how different models perform on a third Nahuatl variant, unseen in training. These results and the subsequent discussion contribute to efforts of developing low-resource NLP that is robust to diatopic variation. We share all code used to process the data and run the experiments."
}