@inproceedings{nogolova-etal-2025-syntactic,
    title = "Syntactic units and their length distributions: A case study in {C}zech",
    author = "Nogolov{\'a}, Michaela  and
      Ko{\v{s}}{\v{c}}ov{\'a}, Michaela  and
      Macutek, Jan  and
      Cech, Radek",
    editor = "Chen, Xinying  and
      Wang, Yaqin",
    booktitle = "Proceedings of the Third Workshop on Quantitative Syntax (QUASY, SyntaxFest 2025)",
    month = aug,
    year = "2025",
    address = "Ljubljana, Slovenia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.quasy-1.14/",
    pages = "115--123",
    ISBN = "979-8-89176-293-0",
    abstract = "This study investigates the length distributions of syntactic units in Czech across multiple hierarchical levels: sentences, independent clauses, clauses, phrases, subphrases, and chunks. Using a diverse dataset {--} including Universal Dependency treebanks, presidential speeches, the Czech Bible, and random sample from corpora of modern Czech {--} the analysis examines whether lengths of these syntactic units follow consistent distributional patterns. Length is defined as the number of immediate subunits, and the distributions were modeled using the hyper-Poisson distribution. The results demonstrate that the hyper-Poisson model fits well distributions of length of all abovementioned syntactic units, pointing to a common principle underlying the organization of syntactic structure in Czech."
}