@inproceedings{krsnik-dobrovoljc-2025-stark,
    title = "{STARK}: A Toolkit for Dependency (Sub)Tree Extraction and Analysis",
    author = "Krsnik, Luka  and
      Dobrovoljc, Kaja",
    editor = {Jablotschkin, Sarah  and
      K{\"u}bler, Sandra  and
      Zinsmeister, Heike},
    booktitle = "Proceedings of the 23rd International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2025)",
    month = aug,
    year = "2025",
    address = "Ljubljana, Slovenia",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.tlt-1.5/",
    pages = "44--51",
    ISBN = "979-8-89176-291-6",
    abstract = "We present STARK, a lightweight and flexible Python toolkit for extracting and analyzing syntactic (sub)trees from dependency-parsed corpora. By systematically slicing each sentence into interpretable syntactic units based on configurable parameters, STARK enables bottom-up, data-driven exploration of syntactic patterns at multiple levels of abstraction{---}from fully lexicalized constructions to general structural templates. It supports any CoNLL-U-formatted corpus and is available as a command-line tool, Python library, and interactive online demo, ensuring seamless integration into both exploratory and large-scale corpus workflows. We illustrate its functionality through case studies in noun phrase analysis, multiword expression identification, and syntactic variation across corpora, demonstrating its utility for a wide range of corpus-driven syntactic investigations."
}