{"url":"/dataset/ccmatrix","name":"CCMatrix","full_name":null,"description_markdown":"CCMatrix uses ten snapshots of a curated common crawl corpus (Wenzek et al., 2019) totalling 32.7 billion unique sentences. \r\n\r\nSource: [CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB](/paper/ccmatrix-mining-billions-of-high-quality)","description_withheld":null,"homepage":"https://github.com/facebookresearch/LASER/tree/master/tasks/CCMatrix","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/ccmatrix-mining-billions-of-high-quality","title":"CCMatrix: Mining Billions of High-Quality Parallel Sentences on the WEB","first_author":"Holger Schwenk","url":null},"license":{"name":"Unknown","url":null},"modalities":[],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Unsupervised Machine Translation","url":"/task/unsupervised-machine-translation","datasets_with_task":"/datasets/task/unsupervised-machine-translation"}],"languages":[],"variants":["CCMatrix"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/xezpeleta/ccmatrix","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/yhavinga/ccmatrix","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/facebookresearch/LASER","url":"https://github.com/facebookresearch/LASER","frameworks":["pytorch"]}],"num_papers_in_archive":42,"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":"2026-09-25T09:33:49+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."}