{"url":"/dataset/medal","name":"MeDAL","full_name":null,"description_markdown":"The  Medical Dataset for Abbreviation Disambiguation for Natural Language Understanding (**MeDAL**) is a large medical text dataset curated for abbreviation disambiguation, designed for natural language understanding pre-training in the medical domain. It was published at the ClinicalNLP workshop at EMNLP.\r\n\r\nSource: [https://github.com/McGill-NLP/medal](https://github.com/McGill-NLP/medal)\r\nImage Source: [https://github.com/McGill-NLP/medal](https://github.com/McGill-NLP/medal)","description_withheld":null,"homepage":"https://github.com/McGill-NLP/medal","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/medal-medical-abbreviation-disambiguation","title":"MeDAL: Medical Abbreviation Disambiguation Dataset for Natural Language Understanding Pretraining","first_author":"Zhi Wen","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Natural Language Understanding","url":"/task/natural-language-understanding","datasets_with_task":"/datasets/task/natural-language-understanding"},{"name":"Mortality Prediction","url":"/task/mortality-prediction","datasets_with_task":"/datasets/task/mortality-prediction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MeDAL"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/McGill-NLP/medal","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/medal","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/mcGill-NLP/medal","url":"https://github.com/mcGill-NLP/medal","frameworks":["pytorch"]}],"num_papers_in_archive":7,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":0,"samples_harvested":0,"samples_ran":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}