{"url":"/dataset/menyo-20k","name":"MENYO-20k","full_name":null,"description_markdown":"MENYO-20k is the first multi-domain parallel corpus with a special focus on clean orthography for Yorùbá--English with standardized train-test splits for benchmarking.","description_withheld":null,"homepage":"https://github.com/uds-lsv/menyo-20k_MT","introduced_date":"2021-03-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/menyo-20k-a-multi-domain-english-yoruba","title":"The Effect of Domain and Diacritics in Yorùbá-English Neural Machine Translation","first_author":"David I. Adelani","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://github.com/uds-lsv/menyo-20k_MT/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Parallel","url":"/datasets/modality/parallel"}],"tasks":[{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Yoruba","url":"/datasets/language/yoruba"}],"variants":["MENYO-20k"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/UdS-LSV/menyo20k_mt","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/menyo20k_mt","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."}