@inproceedings{wen-etal-2020-medal,
    title = "{M}e{DAL}: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining",
    author = "Wen, Zhi  and
      Lu, Xing Han  and
      Reddy, Siva",
    editor = "Rumshisky, Anna  and
      Roberts, Kirk  and
      Bethard, Steven  and
      Naumann, Tristan",
    booktitle = "Proceedings of the 3rd Clinical Natural Language Processing Workshop",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.clinicalnlp-1.15/",
    doi = "10.18653/v1/2020.clinicalnlp-1.15",
    pages = "130--135",
    abstract = "One of the biggest challenges that prohibit the use of many current NLP methods in clinical settings is the availability of public datasets. In this work, we present MeDAL, a large medical text dataset curated for abbreviation disambiguation, designed for natural language understanding pre-training in the medical domain. We pre-trained several models of common architectures on this dataset and empirically showed that such pre-training leads to improved performance and convergence speed when fine-tuning on downstream medical tasks."
}