{"url":"/dataset/hummingbird","name":"Hummingbird","full_name":null,"description_markdown":"**Hummingbird** is a dataset to examine stylistic lexical cues from human perception and BERT used to characterize their discrepancy. In HUMMINGBIRD crowd-workers relabeled benchmarking datasets for style classification tasks.","description_withheld":null,"homepage":"https://github.com/sweetpeach/hummingbird","introduced_date":"2021-09-06","introduced_date_note":null,"introduced_by":{"paper":"/paper/does-bert-learn-as-humans-perceive","title":"Does BERT Learn as Humans Perceive? Understanding Linguistic Styles through Lexica","first_author":"Shirley Anugrah Hayati","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Hummingbird"],"data_loaders":[],"num_papers_in_archive":5,"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."}