{
 "id": "McGill-NLP/medal",
 "owner": "McGill-NLP",
 "name": "medal",
 "downloads": 348,
 "likes": 31,
 "last_modified": "2023-06-13T12:39:11.000Z",
 "stated_licence": "unknown",
 "stated_from": "tag",
 "licence_name": null,
 "licence_link": null,
 "file_licence": null,
 "licence_files": [],
 "sources": [],
 "gated": false,
 "tasks": [
  "other"
 ],
 "citation": "@inproceedings{wen-etal-2020-medal,\n    title = \"{M}e{DAL}: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining\",\n    author = \"Wen, Zhi  and\n      Lu, Xing Han  and\n      Reddy, Siva\",\n    booktitle = \"Proceedings of the 3rd Clinical Natural Language Processing Workshop\",\n    month = nov,\n    year = \"2020\",\n    address = \"Online\",\n    publisher = \"Association for Computational Linguistics\",\n    url = \"https://www.aclweb.org/anthology/2020.clinicalnlp-1.15\",\n    pages = \"130--135\",\n    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.\",\n}",
 "signal": "unclear",
 "reason": "The checks could not identify a recognised licence ID in the dataset's metadata.",
 "revision": "1b7eb6a1b85ce9849238b5aaac70d1f97a9f04b5",
 "stated_evidence": "https://huggingface.co/datasets/McGill-NLP/medal/blob/1b7eb6a1b85ce9849238b5aaac70d1f97a9f04b5/README.md",
 "file_evidence": "https://huggingface.co/datasets/McGill-NLP/medal/tree/1b7eb6a1b85ce9849238b5aaac70d1f97a9f04b5",
 "card_nc": false
}