@article{mikulova-etal-2026-prague,
    title = "{P}rague Dependency Treebank - Consolidated 2.0: Enriching a Complex Annotation Scheme",
    author = "Mikulov{\'a}, Marie  and
      M{\'i}rovsk{\'y}, Ji{\v{r}}{\'i}  and
      Straka, Milan  and
      Synkov{\'a}, Pavl{\'i}na  and
      {\v{S}}t{\v{e}}p{\'a}nek, Jan  and
      {\v{S}}t{\v{e}}p{\'a}nkov{\'a}, Barbora  and
      Haji{\v{c}}, Jan",
    editor = "Piperidis, Stelios  and
      Bel, N{\'u}ria  and
      van den Heuvel, Henk  and
      Ide, Nancy  and
      Krek, Simon  and
      Toral, Antonio",
    journal = "International Conference on Language Resources and Evaluation",
    volume = "main",
    month = may,
    year = "2026",
    address = "Palma de Mallorca, Spain",
    publisher = "ELRA Language Resource Association",
    url = "https://preview.aclanthology.org/ingest-lrec/2026.lrec-main.908/",
    pages = "11593--11605",
    abstract = "The Prague Dependency Treebank framework is unique in its attempt to systematically include and link different layers of language, including a meaning representation with several types of inter-sentential phenomena, especially coreference and discourse relation. We present its second consolidated version (PDT-C 2.0), which concludes almost 30-years long project of sustained development of the resource to a uniformly and coherently annotated, genre-diversified, almost 4 million token language resource of Czech language, with accompanying fully compatible lexicons. In addition to continuous linguistic research, the richly linguistically annotated corpus is also widely used in international comparisons of the development of traditional and novel NLP tools as well as in conversions into other formalisms. The corpus and the trained parsers are available under the CC BY-NC-SA licence."
}