@inproceedings{zmiycharov-etal-2024-eurlexsummarization,
    title = "{E}ur{L}ex{S}ummarization {--} A New Text Summarization Dataset on {EU} Legislation in 24 Languages with {GPT} Evaluation",
    author = "Zmiycharov, Valentin  and
      Tsonkov, Todor  and
      Koychev, Ivan",
    booktitle = "Proceedings of the Sixth International Conference on Computational Linguistics in Bulgaria (CLIB 2024)",
    month = sep,
    year = "2024",
    address = "Sofia, Bulgaria",
    publisher = "Department of Computational Linguistics, Institute for Bulgarian Language, Bulgarian Academy of Sciences",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.clib-1.22/",
    pages = "206--213",
    abstract = "Legal documents are notorious for their length and complexity, making it challenging to extract crucial information efficiently. In this paper, we introduce a new dataset for legal text summarization, covering 24 languages. We not only present and analyze the dataset but also conduct experiments using various extractive techniques. We provide a comparison between these techniques and summaries generated by the state-of-the-art GPT models. The abstractive GPT approach outperforms the extractive TextRank approach in 8 languages, but produces slightly lower results in the remaining 16 languages. This research aims to advance the field of legal document summarization by addressing the need for accessible and comprehensive information retrieval from lengthy legal texts."
}