{"url":"/dataset/utcd","name":"UTCD","full_name":"Universal Text Classification Dataset","description_markdown":"UTCD is a compilation of 18 classification datasets spanning 3 categories of Sentiment, Intent/Dialogue, and Topic classification. UTCD focuses on the task of zero-shot text classification where the candidate labels are descriptive of the text being classified. UTCD consists of ~ 6M/800K train/test examples.","description_withheld":null,"homepage":"https://huggingface.co/datasets/claritylab/utcd","introduced_date":"2023-05-25","introduced_date_note":null,"introduced_by":{"paper":"/paper/label-agnostic-pre-training-for-zero-shot","title":"Label Agnostic Pre-training for Zero-shot Text Classification","first_author":"Christopher Clarke","url":null},"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["UTCD"],"data_loaders":[],"num_papers_in_archive":1,"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."}