{"url":"/dataset/wikisplit","name":"WikiSplit","full_name":null,"description_markdown":"Contains one million naturally occurring sentence rewrites, providing sixty times more distinct split examples and a ninety times larger vocabulary than the WebSplit corpus introduced by Narayan et al. (2017) as a benchmark for this task.\r\n\r\nSource: [Learning To Split and Rephrase From Wikipedia Edit History](/paper/learning-to-split-and-rephrase-from-wikipedia)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/wiki-split","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-to-split-and-rephrase-from-wikipedia","title":"Learning To Split and Rephrase From Wikipedia Edit History","first_author":"Jan A. Botha","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Simplification","url":"/task/text-simplification","datasets_with_task":"/datasets/task/text-simplification"},{"name":"Sentence Fusion","url":"/task/sentence-fusion","datasets_with_task":"/datasets/task/sentence-fusion"},{"name":"Split and Rephrase","url":"/task/split-and-rephrase","datasets_with_task":"/datasets/task/split-and-rephrase"}],"languages":[],"variants":["WikiSplit1.0","WikiSplit"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/wiki_split","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wiki_split","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/google-research-datasets/wiki-split","url":"https://github.com/google-research-datasets/wiki-split","frameworks":[]}],"num_papers_in_archive":21,"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."}