@inproceedings{vilares-gomez-rodriguez-2019-head,
    title = "{HEAD}-{QA}: A Healthcare Dataset for Complex Reasoning",
    author = "Vilares, David  and
      G{\'o}mez-Rodr{\'i}guez, Carlos",
    editor = "Korhonen, Anna  and
      Traum, David  and
      M{\`a}rquez, Llu{\'i}s",
    booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
    month = jul,
    year = "2019",
    address = "Florence, Italy",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/P19-1092/",
    doi = "10.18653/v1/P19-1092",
    pages = "960--966",
    abstract = "We present HEAD-QA, a multi-choice question answering testbed to encourage research on complex reasoning. The questions come from exams to access a specialized position in the Spanish healthcare system, and are challenging even for highly specialized humans. We then consider monolingual (Spanish) and cross-lingual (to English) experiments with information retrieval and neural techniques. We show that: (i) HEAD-QA challenges current methods, and (ii) the results lag well behind human performance, demonstrating its usefulness as a benchmark for future work."
}