@inproceedings{rello-gayo-2012-portuguese,
    title = "A {P}ortuguese-{S}panish Corpus Annotated for Subject Realization and Referentiality",
    author = "Rello, Luz  and
      Gayo, Iria",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Do{\u{g}}an, Mehmet U{\u{g}}ur  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Eighth International Conference on Language Resources and Evaluation ({LREC}`12)",
    month = may,
    year = "2012",
    address = "Istanbul, Turkey",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/L12-1252/",
    pages = "154--157",
    abstract = "This paper presents a comparable corpus of Portuguese and Spanish consisting of legal and health texts. We describe the annotation of zero subject, impersonal constructions and explicit subjects in the corpus. We annotated 12,492 examples using a scheme that distinguishes between different linguistic levels (phonology, syntax, semantics, etc.) and present a taxonomy of instances on which annotators disagree. The high level of inter-annotator agreement (83{\%}-95{\%}) and the performance of learning algorithms trained on the corpus show that our corpus is a reliable and useful resource."
}