{"url":"/dataset/cowese","name":"CoWeSe","full_name":"Corpus Web Salud Espanol","description_markdown":"**CoWeSe** is a Spanish biomedical corpus consisting of 4.5GB (about 750M tokens) of clean plain text. CoWeSe is the result of a massive crawler on 3000 Spanish domains executed in 2020.","description_withheld":null,"homepage":"https://zenodo.org/record/4561971","introduced_date":"2021-09-16","introduced_date_note":null,"introduced_by":{"paper":"/paper/spanish-biomedical-crawled-corpus-a-large","title":"Spanish Biomedical Crawled Corpus: A Large, Diverse Dataset for Spanish Biomedical Language Models","first_author":"Casimiro Pio Carrino","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Behavioural cloning","url":"/task/behavioural-cloning","datasets_with_task":"/datasets/task/behavioural-cloning"}],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"}],"variants":["CoWeSe"],"data_loaders":[],"num_papers_in_archive":3,"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."}