@inproceedings{ginn-palmer-2023-robust,
    title = "Robust Generalization Strategies for Morpheme Glossing in an Endangered Language Documentation Context",
    author = "Ginn, Michael  and
      Palmer, Alexis",
    editor = "Hupkes, Dieuwke  and
      Dankers, Verna  and
      Batsuren, Khuyagbaatar  and
      Sinha, Koustuv  and
      Kazemnejad, Amirhossein  and
      Christodoulopoulos, Christos  and
      Cotterell, Ryan  and
      Bruni, Elia",
    booktitle = "Proceedings of the 1st GenBench Workshop on (Benchmarking) Generalisation in NLP",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2023.genbench-1.7/",
    doi = "10.18653/v1/2023.genbench-1.7",
    pages = "89--98",
    abstract = "Generalization is of particular importance in resource-constrained settings, where the available training data may represent only a small fraction of the distribution of possible texts. We investigate the ability of morpheme labeling models to generalize by evaluating their performance on unseen genres of text, and we experiment with strategies for closing the gap between performance on in-distribution and out-of-distribution data. Specifically, we use weight decay optimization, output denoising, and iterative pseudo-labeling, and achieve a 2{\%} improvement on a test set containing texts from unseen genres. All experiments are performed using texts written in the Mayan language Uspanteko."
}