@inproceedings{lupicki-etal-2025-jhus,
    title = "{JHU}{'}s Submission to the {A}mericas{NLP} 2025 Shared Task on the Creation of Educational Materials for Indigenous Languages",
    author = "Lupicki, Tom  and
      Shankar, Lavanya  and
      Chaparala, Kaavya  and
      Yarowsky, David",
    editor = "Mager, Manuel  and
      Ebrahimi, Abteen  and
      Pugh, Robert  and
      Rijhwani, Shruti  and
      Von Der Wense, Katharina  and
      Chiruzzo, Luis  and
      Coto-Solano, Rolando  and
      Oncevay, Arturo",
    booktitle = "Proceedings of the Fifth Workshop on NLP for Indigenous Languages of the Americas (AmericasNLP)",
    month = may,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.americasnlp-1.12/",
    doi = "10.18653/v1/2025.americasnlp-1.12",
    pages = "105--111",
    ISBN = "979-8-89176-236-7",
    abstract = "This paper presents JHU{'}s submission to the AmericasNLP shared task on the creation of educational materials for Indigenous languages. The task involves transforming a base sentence given one or more tags that correspond to grammatical features, such as negation or tense. The task also spans four languages: Bribri, Maya, Guaran{\'i}, and Nahuatl. We experiment with augmenting prompts to large language models with different information, chain of thought prompting, ensembling large language models by majority voting, and training a pointer-generator network. Our System 1, an ensemble of large language models, achieves the best performance on Maya and Guaran{\'i}, building upon the previous successes in leveraging large language models for this task and highlighting the effectiveness of ensembling large language models."
}