@inproceedings{soni-roberts-2020-evaluation,
    title = "Evaluation of Dataset Selection for Pre-Training and Fine-Tuning Transformer Language Models for Clinical Question Answering",
    author = "Soni, Sarvesh  and
      Roberts, Kirk",
    editor = "Calzolari, Nicoletta  and
      B{\'e}chet, Fr{\'e}d{\'e}ric  and
      Blache, Philippe  and
      Choukri, Khalid  and
      Cieri, Christopher  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Isahara, Hitoshi  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, H{\'e}l{\`e}ne  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Twelfth Language Resources and Evaluation Conference",
    month = may,
    year = "2020",
    address = "Marseille, France",
    publisher = "European Language Resources Association",
    url = "https://preview.aclanthology.org/ingest-emnlp/2020.lrec-1.679/",
    pages = "5532--5538",
    language = "eng",
    ISBN = "979-10-95546-34-4",
    abstract = "We evaluate the performance of various Transformer language models, when pre-trained and fine-tuned on different combinations of open-domain, biomedical, and clinical corpora on two clinical question answering (QA) datasets (CliCR and emrQA). We perform our evaluations on the task of machine reading comprehension, which involves training the model to answer a question given an unstructured context paragraph. We conduct a total of 48 experiments on different combinations of the large open-domain and domain-specific corpora. We found that an initial fine-tuning on an open-domain dataset, SQuAD, consistently improves the clinical QA performance across all the model variants."
}