@inproceedings{sierro-etal-2024-automatic,
    title = "Automatic Detection and Labelling of Personal Data in Case Reports from the {ECHR} in {S}panish: Evaluation of Two Different Annotation Approaches",
    author = "Sierro, Maria  and
      Altuna, Bego{\~n}a  and
      Gonzalez-Dios, Itziar",
    editor = {Volodina, Elena  and
      Alfter, David  and
      Dobnik, Simon  and
      Lindstr{\"o}m Tiedemann, Therese  and
      Mu{\~n}oz S{\'a}nchez, Ricardo  and
      Szawerna, Maria Irena  and
      Vu, Xuan-Son},
    booktitle = "Proceedings of the Workshop on Computational Approaches to Language Data Pseudonymization (CALD-pseudo 2024)",
    month = mar,
    year = "2024",
    address = "St. Julian{'}s, Malta",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.caldpseudo-1.3/",
    pages = "18--24",
    abstract = "In this paper we evaluate two annotation approaches for automatic detection and labelling of personal information in legal texts in relation to the ambiguity of the labels and the homogeneity of the annotations. For this purpose, we built a corpus of 44 case reports from the European Court of Human Rights in Spanish language and we annotated it following two different annotation approaches: automatic projection of the annotations of an existing English corpus, and manual annotation with our reinterpretation of their guidelines. Moreover, we employ Flair on a Named Entity Recognition task to compare its performance in the two annotation schemes."
}