{"url":"/dataset/medical-abstracts","name":"Medical Abstracts","full_name":"Medical Abstracts Text Classification Dataset","description_markdown":"The Medical Abstracts dataset contains 14,438 medical abstracts describing 5 different classes of patient conditions, with all of the dataset being annotated. The dataset is split into training and test sets.","description_withheld":null,"homepage":"https://github.com/sebischair/Medical-Abstracts-TC-Corpus","introduced_date":"2022-11-29","introduced_date_note":null,"introduced_by":{"paper":"/paper/evaluating-unsupervised-text-classification","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","first_author":"Tim Schopf","url":null},"license":{"name":"Creative Commons","url":"https://github.com/sebischair/Medical-Abstracts-TC-Corpus/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Classification","url":"/task/text-classification","datasets_with_task":"/datasets/task/text-classification"},{"name":"Unsupervised Text Classification","url":"/task/unsupervised-text-classification","datasets_with_task":"/datasets/task/unsupervised-text-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Medical Abstracts"],"data_loaders":[],"num_papers_in_archive":4,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/unsupervised-text-classification-on-medical","task":"Unsupervised Text Classification","dataset_variant":"Medical Abstracts","rows":2,"metrics":["F1-score"],"first_row_in_archive_order":{"model":"Lbl2TransformerVec","paper":"/paper/evaluating-unsupervised-text-classification","metrics":{"F1-score":"56.46"},"code_links":[{"title":"sebischair/lbl2vec","url":"https://github.com/sebischair/lbl2vec"},{"title":"sebischair/medical-abstracts-tc-corpus","url":"https://github.com/sebischair/medical-abstracts-tc-corpus"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/evaluating-unsupervised-text-classification","title":"Evaluating Unsupervised Text Classification: Zero-shot and Similarity-based Approaches","date":"2022-11-29","rows_on_this_dataset":2,"code_links":2,"syntology":null}],"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."}