Large Language Models for Summarizing Czech Historical Documents and Beyond

Václav Tran, Jakub Šmíd, Jakub Šmíd, Jiří Martínek, Jiří Martínek, Ladislav Lenc, Ladislav Lenc, Pavel Král, Pavel Král

2025

Abstract

Text summarization is the task of shortening a larger body of text into a concise version while retaining its essential meaning and key information. While summarization has been significantly explored in English and other high-resource languages, Czech text summarization, particularly for historical documents, remains underexplored due to linguistic complexities and a scarcity of annotated datasets. Large language models such as Mistral and mT5 have demonstrated excellent results on many natural language processing tasks and languages. Therefore, we employ these models for Czech summarization, resulting in two key contributions: (1) achieving new state-of-the-art results on the modern Czech summarization dataset SumeCzech using these advanced models, and (2) introducing a novel dataset called Posel od ˇCerchova for summarization of historical Czech documents with baseline results. Together, these contributions provide a great potential for advancing Czech text summarization and open new avenues for research in Czech historical text processing.

Paper Citation

in Harvard Style

Tran V., Šmíd J., Martínek J., Lenc L. and Král P. (2025). Large Language Models for Summarizing Czech Historical Documents and Beyond. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 798-804. DOI: 10.5220/0013374100003890

in Bibtex Style

@conference{icaart25,
author={Václav Tran and Jakub Šmíd and Jiří Martínek and Ladislav Lenc and Pavel Král},
title={Large Language Models for Summarizing Czech Historical Documents and Beyond},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={798-804},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013374100003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Large Language Models for Summarizing Czech Historical Documents and Beyond
SN - 978-989-758-737-5
AU - Tran V.
AU - Šmíd J.
AU - Martínek J.
AU - Lenc L.
AU - Král P.
PY - 2025
SP - 798
EP - 804
DO - 10.5220/0013374100003890
PB - SciTePress