{"url":"/dataset/bug","name":"BUG","full_name":null,"description_markdown":"**BUG** is a large-scale gender bias dataset of 108K diverse real-world English sentences, sampled semiautomatically from large corpora using lexical syntactic pattern matching","description_withheld":null,"homepage":"http://www.github.com/SLAB-NLP/BUG","introduced_date":"2021-09-08","introduced_date_note":null,"introduced_by":{"paper":"/paper/collecting-a-large-scale-gender-bias-dataset","title":"Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation","first_author":"Shahar Levy","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Gender Bias Detection","url":"/task/gender-bias-detection","datasets_with_task":"/datasets/task/gender-bias-detection"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["BUG"],"data_loaders":[],"num_papers_in_archive":17,"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."}