{"url":"/dataset/brwac","name":"BRWAC","full_name":null,"description_markdown":"Composed by 2.7 billion tokens, and has been annotated with tagging and parsing information. \r\n\r\nSource: [The brWaC Corpus: A New Open Resource for Brazilian Portuguese](/paper/the-brwac-corpus-a-new-open-resource-for)","description_withheld":null,"homepage":"https://www.inf.ufrgs.br/pln/wiki/index.php?title=BrWaC","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-brwac-corpus-a-new-open-resource-for","title":"The brWaC Corpus: A New Open Resource for Brazilian Portuguese","first_author":"Jorge A. Wagner Filho","url":null},"license":null,"modalities":[],"tasks":[{"name":"Word Sense Induction","url":"/task/word-sense-induction","datasets_with_task":"/datasets/task/word-sense-induction"}],"languages":[],"variants":["BRWAC"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/bfunicheli/brwac","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/UFRGS/brwac","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/dominguesm/brwac","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/brwac","frameworks":["tf","pytorch","jax"]}],"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."}