{"url":"/dataset/united-nations-parallel-corpus","name":"United Nations Parallel Corpus","full_name":null,"description_markdown":"The first parallel corpus composed from United Nations documents published by the original data creator. The parallel corpus presented consists of manually translated UN documents from the last 25 years (1990 to 2014) for the six official UN languages, Arabic, Chinese, English, French, Russian, and Spanish.\r\n\r\nSource: [The United Nations Parallel Corpus v1.0](https://www.aclweb.org/anthology/L16-1561)","description_withheld":null,"homepage":"https://conferences.unite.un.org/UNCORPUS/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-united-nations-parallel-corpus-v10","title":"The United Nations Parallel Corpus v1.0","first_author":"Micha{\\l} Ziemski","url":null},"license":{"name":"Custom","url":"https://conferences.unite.un.org/UNCORPUS/#disclaimer"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"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":"Spanish","url":"/datasets/language/spanish"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Arabic","url":"/datasets/language/arabic"}],"variants":["United Nations Parallel Corpus"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/Helsinki-NLP/un_pc","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/un_pc","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":18,"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."}