@inproceedings{marecek-etal-2025-evaluation,
    title = "Evaluation of Generated Poetry",
    author = "Mare{\v{c}}ek, David  and
      Hodkov{\'a}, Kate{\v{r}}ina Motal{\'i}k  and
      Musil, Tom{\'a}{\v{s}}  and
      Rosa, Rudolf",
    editor = "Akter, Mousumi  and
      Chowdhury, Tahiya  and
      Eger, Steffen  and
      Leiter, Christoph  and
      Opitz, Juri  and
      {\c{C}}ano, Erion",
    booktitle = "Proceedings of the 5th Workshop on Evaluation and Comparison of NLP Systems",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.eval4nlp-1.9/",
    pages = "109--118",
    ISBN = "979-8-89176-305-0",
    abstract = "We propose a range of automated metrics for evaluation of generated poetry.The metrics measure various aspects of poetry: rhyming, metre, syntax, semantics, and amount of unknown words.In a case study, we implement the metrics for Czech language, apply them to poetry generated by several automated systems as well as human-written, and correlate them with human judgment.We find that most of the proposed metrics correlate well with corresponding human evaluation, but semantically oriented metrics are much better predictors of the overall impression than metrics evaluating formal properties."
}