{"url":"/dataset/jw300","name":"JW300","full_name":null,"description_markdown":"A parallel corpus of over 300 languages with around 100 thousand parallel sentences per language pair on average.\r\n\r\nSource: [JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages](/paper/jw300-a-wide-coverage-parallel-corpus-for-low)","description_withheld":null,"homepage":"http://opus.nlpl.eu/JW300.php","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/jw300-a-wide-coverage-parallel-corpus-for-low","title":"JW300: A Wide-Coverage Parallel Corpus for Low-Resource Languages","first_author":"{\\v{Z}}eljko Agi{\\'c}","url":null},"license":{"name":"CC BY-NC-SA 3.0","url":"https://creativecommons.org/licenses/by-nc-sa/3.0/"},"modalities":[],"tasks":[],"languages":[{"name":"Twi","url":"/datasets/language/twi"},{"name":"Udmurt","url":"/datasets/language/udmurt"}],"variants":["JW300"],"data_loaders":[],"num_papers_in_archive":25,"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."}