@inproceedings{guzman-landa-etal-2025-p,
    title = "{\ensuremath{\pi}}-{YALLI} : un nouveau corpus pour des mod{\`e}les de langue nahuatl / Yankuik nawatlahtolkorpus pampa tlahtolmachiotl",
    author = "Guzm{\'a}n-Landa, Juan-Jos{\'e}  and
      Torres-Moreno, Juan-Manuel  and
      Lorena Avenda{\~n}o Garrido, Martha  and
      Figueroa-Saavedra, Miguel  and
      Quintana-Torres, Ligia  and
      Ranger, Graham  and
      Gonz{\'a}lez-Gallardo, Carlos-Emiliano  and
      Linhares-Pontes, Elvys  and
      Vel{\'a}zquez-Morales, Patricia  and
      Moreno-Jim{\'e}nez, Luis-Gil",
    editor = "Bechet, Fr{\'e}d{\'e}ric  and
      Chifu, Adrian-Gabriel  and
      Pinel-sauvagnat, Karen  and
      Favre, Benoit  and
      Maes, Eliot  and
      Nurbakova, Diana",
    booktitle = "Actes des 32{\`e}me Conf{\'e}rence sur le Traitement Automatique des Langues Naturelles (TALN), volume 1 : articles scientifiques originaux",
    month = "6",
    year = "2025",
    address = "Marseille, France",
    publisher = "ATALA {\textbackslash}{\textbackslash}{\&} ARIA",
    url = "https://preview.aclanthology.org/corrections-2025-10/2025.jeptalnrecital-taln.49/",
    pages = "802--816",
    abstract = "{\ensuremath{\pi}}-YALLI : a new corpus for Nahuatl Language Models The Nahuatl is a language with few computational resources, despite the fact that it is a living language spoken by around two million people. We built {\ensuremath{\pi}}-YALLI, a corpus that enables research and development of dynamic and static Language Models (LM). We measured the perplexity of {\ensuremath{\pi}}-YALLI, evaluating state-of-the-art LM performance on a manually annotated semantic similarity corpus relative to annotator agreement. The results show the difficulty of working with this {\ensuremath{\pi}}-language, but at the same time open up interesting perspectives for the study of other NLP tasks on Nahuatl."
}