{"url":"/dataset/umc005-english-urdu","name":"UMC005 English-Urdu","full_name":null,"description_markdown":"UMC005 English-Urdu is a parallel corpus of texts in English and Urdu language with sentence alignments. The corpus can be used for experiments with statistical machine translation.\r\n\r\nThe texts come from four different sources:\r\n\r\n- Quran\r\n- Bible\r\n- Penn Treebank (Wall Street Journal)\r\n- Emille corpus\r\n\r\nSource: [UMC005 English-Urdu](http://ufal.ms.mff.cuni.cz/umc/005-en-ur/)","description_withheld":null,"homepage":"http://ufal.ms.mff.cuni.cz/umc/005-en-ur/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[],"tasks":[],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Urdu","url":"/datasets/language/urdu"}],"variants":["UMC005 English-Urdu"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/community-datasets/um005","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/um005","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":"2026-09-25T09:33:49+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."}