tomasmcz/edupo_v0.5

Model Card for Model ID

Generating Czech poetry in an educative and multimedia environment

Model Details

Model Description

This is the model card of the EduPo poetry generation model.

• Developed by: EduPo project
• Funded by: the EduPo grant (TQ01000153 Generating Czech poetry in an educative and multimedia environment), which is co-financed from the state budget by the Technology agency of the Czech Republic under the SIGMA DC3 Programme.
• Language(s) (NLP): Czech
• License: https://www.llama.com/llama3_1/license/
• Finetuned from model [optional]: Llama 3.1 8B

Model Sources

• Repository: https://github.com/ufal/edupo
• Paper: https://aclanthology.org/2025.nlp4dh-1.45/

Bias, Risks, and Limitations

The model was fine-tuned on the Corpus of Czech Verse and may reflect biases contained in that corpus, as well as biases contained in the original Llama training data.

Training Details

Training Data

Corpus of Czech Verse

Evaluation

See Evaluation of Generated Poetry

Citation

BibTeX:

@inproceedings{rosa-etal-2025-edupo,
    title = "{E}du{P}o: Progress and Challenges of Automated Analysis and Generation of {C}zech Poetry",
    author = "Rosa, Rudolf  and
      Mare{\v{c}}ek, David  and
      Musil, Tom{\'a}{\v{s}}  and
      Chudoba, Michal  and
      Landspersk{\'y}, Jakub",
    editor = {H{\"a}m{\"a}l{\"a}inen, Mika  and
      {\"O}hman, Emily  and
      Bizzoni, Yuri  and
      Miyagawa, So  and
      Alnajjar, Khalid},
    booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
    month = may,
    year = "2025",
    address = "Albuquerque, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.nlp4dh-1.45/",
    doi = "10.18653/v1/2025.nlp4dh-1.45",
    pages = "524--542",
    ISBN = "979-8-89176-234-3",
    abstract = "This paper explores automated analysis and generation of Czech poetry. We review existing tools, datasets, and methodologies while considering the unique characteristics of the Czech language and its poetic tradition. Our approach builds upon available resources wherever possible, yet requires the development of additional components to address existing gaps. We present and evaluate preliminary experiments, highlighting key challenges and potential directions for future research."
}