{"url":"/dataset/wikipedia-generation","name":"Wikipedia Generation","full_name":"Wikipedia Generation","description_markdown":"**Wikipedia Generation** is a dataset for article generation from Wikipedia from references at the end of Wikipedia page and the top 10 search results for the Wikipedia topic.","description_withheld":null,"homepage":"https://github.com/tensorflow/tensor2tensor/tree/master/tensor2tensor/data_generators/wikisum","introduced_date":"2018-01-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/generating-wikipedia-by-summarizing-long","title":"Generating Wikipedia by Summarizing Long Sequences","first_author":"Peter J. Liu","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Document Summarization","url":"/task/document-summarization","datasets_with_task":"/datasets/task/document-summarization"},{"name":"Multi-Document Summarization","url":"/task/multi-document-summarization","datasets_with_task":"/datasets/task/multi-document-summarization"}],"languages":[],"variants":["Wikipedia Generation"],"data_loaders":[{"repo":"https://github.com/tensorflow/tensor2tensor","url":"https://github.com/tensorflow/tensor2tensor","frameworks":["tf"]}],"num_papers_in_archive":4,"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."}