@inproceedings{yang-2025-shud,
    title = "{S}h{UD}: the First Shanghainese {U}niversal {D}ependency Treebank",
    author = "Yang, Qizhen",
    editor = {Bouma, Gosse  and
      {\c{C}}{\"o}ltekin, {\c{C}}a{\u{g}}r{\i}},
    booktitle = "Proceedings of the Eighth Workshop on Universal Dependencies (UDW, SyntaxFest 2025)",
    month = aug,
    year = "2025",
    address = "Ljubljana, Slovenia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.udw-1.20/",
    pages = "186--193",
    ISBN = "979-8-89176-292-3",
    abstract = "This paper introduces ShUD, the first Universal Dependencies (UD) treebank for Shanghainese, a Wu Chinese variant spoken by approximately 14 million people but severely under-resourced in NLP. The treebank is built through a scalable annotation pipeline that exploits grammatical parallels between Shanghainese and Mandarin. Our pipeline also provides a practical strategy for bootstrapping resources for other Chinese dialects. We documented syntactic phenomena unique to Shanghainese within the UD framework and fine-tuned a dependency parser using our annotated treebank, contributing a foundation to both NLP tool development and cross-linguistic syntactic research."
}