{"url":"/dataset/multiun","name":"MultiUN","full_name":"Multilingual Corpus from United Nation Documents","description_markdown":"The MultiUN parallel corpus is extracted from the United Nations Website , and then cleaned and converted to XML at Language Technology Lab in DFKI GmbH (LT-DFKI), Germany. The documents were published by UN from 2000 to 2009.\r\n\r\nSource: [MultiUN](http://www.euromatrixplus.net/multi-un/)","description_withheld":null,"homepage":"http://www.euromatrixplus.net/multi-un/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[],"variants":["MultiUN","un_multi"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Helsinki-NLP/multiun","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/opus/multiun","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/un_multi","frameworks":["tf","pytorch","jax"]}],"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."}