{"url":"/dataset/czeng-2-0-parallel-corpus","name":"CzEng 2.0 Parallel Corpus","full_name":null,"description_markdown":"Czech-English parallel corpus CzEng 2.0 consisting of over 2 billion words (2 \"gigawords\") in each language. The corpus contains document-level information and is filtered with several techniques to lower the amount of noise.\r\n\r\nSource: [Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords](/paper/announcing-czeng-2-0-parallel-corpus-with)","description_withheld":null,"homepage":"https://ufal.mff.cuni.cz/czeng","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/announcing-czeng-2-0-parallel-corpus-with","title":"Announcing CzEng 2.0 Parallel Corpus with over 2 Gigawords","first_author":"Tom Kocmi","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["CzEng 2.0 Parallel Corpus"],"data_loaders":[],"num_papers_in_archive":1,"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."}