{"url":"/dataset/chren","name":"ChrEn","full_name":"Cherokee-English Parallel Dataset","description_markdown":"Cherokee-English Parallel Dataset is a low-resource dataset of 14,151 pairs of sentences with around\r\n313K English tokens and 206K Cherokee tokens. The parallel corpus is accompanied by a monolingual Cherokee dataset of 5,120 sentences. Both datasets are mostly derived from Cherokee monolingual books.","description_withheld":null,"homepage":"https://github.com/ZhangShiyue/ChrEn","introduced_date":"2020-10-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/chren-cherokee-english-machine-translation","title":"ChrEn: Cherokee-English Machine Translation for Endangered Language Revitalization","first_author":"Shiyue Zhang","url":null},"license":null,"modalities":[{"name":"Parallel","url":"/datasets/modality/parallel"}],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Cherokee","url":"/datasets/language/cherokee"}],"variants":["ChrEn"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/shiyue/chr_en","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/chr_en","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/ZhangShiyue/ChrEn","url":"https://github.com/ZhangShiyue/ChrEn","frameworks":["pytorch"]}],"num_papers_in_archive":3,"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."}