{"url":"/dataset/wikimatrix","name":"WikiMatrix","full_name":null,"description_markdown":"**WikiMatrix** is a dataset of parallel sentences in the textual content of Wikipedia for all possible language pairs. The mined data consists of:\r\n\r\n- 85 different languages, 1620 language pairs\r\n- 134M parallel sentences, out of which 34M are aligned with English\r\n\r\nSource: [WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia](/paper/wikimatrix-mining-135m-parallel-sentences-in)","description_withheld":null,"homepage":"https://github.com/facebookresearch/LASER/tree/master/tasks/WikiMatrix","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/wikimatrix-mining-135m-parallel-sentences-in","title":"WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia","first_author":"Holger Schwenk","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Sentence Embeddings","url":"/task/sentence-embeddings","datasets_with_task":"/datasets/task/sentence-embeddings"},{"name":"Word Embeddings","url":"/task/word-embeddings","datasets_with_task":"/datasets/task/word-embeddings"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"German","url":"/datasets/language/german"},{"name":"Breton","url":"/datasets/language/breton"},{"name":"Aragonese","url":"/datasets/language/aragonese"},{"name":"Egyptian Arabic","url":"/datasets/language/egyptian-arabic"},{"name":"Assamese","url":"/datasets/language/assamese"},{"name":"South Azerbaijani","url":"/datasets/language/south-azerbaijani"},{"name":"Bavarian","url":"/datasets/language/bavarian"},{"name":"Bishnupriya","url":"/datasets/language/bishnupriya"},{"name":"Chechen","url":"/datasets/language/chechen"}],"variants":["WikiMatrix"],"data_loaders":[{"repo":"https://github.com/facebookresearch/LASER","url":"https://github.com/facebookresearch/LASER","frameworks":["pytorch"]}],"num_papers_in_archive":91,"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."}