@inproceedings{tomita-etal-2025-automatic,
    title = "Automatic Evaluation of Linguistic Validity in {J}apanese {CCG} Treebanks",
    author = "Tomita, Asa  and
      Yanaka, Hitomi  and
      Bekki, Daisuke",
    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-1.9/",
    pages = "74--80",
    ISBN = "979-8-89176-291-6",
    abstract = "In natural language inference, the accuracy of systems based on compositional semantics depends on the quality of syntactic analysis, which in turn relies on linguistically valid training and evaluation data, typically provided by treebanks. However, conventional treebank evaluation metrics focus on data coverage and fail to assess the linguistic validity of syntactic structures. This paper proposes novel evaluation methods to enable automatic and multifaceted assessment of linguistic validity. We apply these methods to a Japanese treebank based on combinatory categorial grammar and report the evaluation results."
}