@inproceedings{bauer-etal-2025-universal,
    title = "{U}niversal {D}ependencies for {S}indhi",
    author = "Bauer, John  and
      Shah, Sakiina  and
      Shaheer, Muhammad  and
      Talpur, Mir Afza Ahmed  and
      Sanjrani, Zubair  and
      Qureshi, Sarwat  and
      Pirzada, Shafi  and
      Manning, Christopher D.  and
      Rahman, Mutee U",
    editor = {Bomma, 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/mtsummit-25-ingestion/2025.udw-1.11/",
    pages = "105--118",
    ISBN = "979-8-89176-292-3",
    abstract = "Sindhi is an Indo-Aryan language spoken primarily in Pakistan and India by about 40 million people. Despite this extensive use, it is a low resource language for NLP tasks, with few datasets or pretrained embeddings available. In this work, we explore linguistic challenges for annotating Sindhi in the UD paradigm, such as language-specific analysis of adpositions and verb forms. We use this analysis to present a newly annotated dependency treebank for Universal Dependencies, along with pretrained embeddings and an annotation pipeline specifically for Sindhi annotation."
}