@inproceedings{salaun-etal-2024-europa,
    title = "{EUROPA}: A Legal Multilingual Keyphrase Generation Dataset",
    author = {Sala{\"u}n, Olivier  and
      Piedboeuf, Fr{\'e}d{\'e}ric  and
      Le Berre, Guillaume  and
      Alfonso-Hermelo, David  and
      Langlais, Philippe},
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.acl-long.687/",
    doi = "10.18653/v1/2024.acl-long.687",
    pages = "12718--12736",
    abstract = "Keyphrase generation has primarily been explored within the context of academic research articles, with a particular focus on scientific domains and the English language. In this work, we present EUROPA, a novel dataset for multilingual keyphrase generation in the legal domain. It is derived from legal judgments from the Court of Justice of the European Union (EU), and contains instances in all 24 EU official languages. We run multilingual models on our corpus and analyze the results, showing room for improvement on a domain-specific multilingual corpus such as the one we present."
}