@inproceedings{pagliai-etal-2026-spanish,
    title = "The {S}panish Learner and Heritage Speaker Dependency Treebank",
    author = "Pagliai, Valeria  and
      Rod{\'o}, Sergio Jos{\'e} Salazar  and
      Pulido, Emiliana  and
      Gutierrez-Quintero, Andres  and
      Liu, Zoey",
    editor = "Voigt, Rob  and
      Warstadt, Alex  and
      Feldman, Naomi  and
      Linzen, Tal",
    booktitle = "Proceedings of the Society for Computation in Linguistics 2026",
    month = jul,
    year = "2026",
    address = "San Diego, CA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.scil-main.12/",
    pages = "127--128",
    ISBN = "979-8-89176-412-5",
    abstract = "We present a manually curated L2-Heritage Speaker Spanish dataset (N = 49,247) following the Universal Dependencies framework, including lemmatizations, part-of-speech tags, syntactic dependencies, and instances of pro-drop and ungrammatical structures. In addition to this, for dependency parsing we examined different data partitioning strategies and data representations, as well as different training configurations using our data and the AnCora treebank. Overall, the results yield reasonable LAS scores and comparable performance between AnCora and our dataset."
}