{"url":"/dataset/wikibio","name":"WikiBio","full_name":"Wikipedia Biography Dataset","description_markdown":"This dataset gathers 728,321 biographies from English Wikipedia. It aims at evaluating text generation algorithms. For each article, we provide the first paragraph and the infobox (both tokenized).","description_withheld":null,"homepage":"https://rlebret.github.io/wikipedia-biography-dataset/","introduced_date":"2016-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/neural-text-generation-from-structured-data","title":"Neural Text Generation from Structured Data with Application to the Biography Domain","first_author":"Remi Lebret","url":null},"license":{"name":"CC BY-SA 3.0","url":"https://github.com/rlebret/wikipedia-biography-dataset/blob/master/LICENSE.txt"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Table-to-Text Generation","url":"/task/table-to-text-generation","datasets_with_task":"/datasets/task/table-to-text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiBio"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/michaelauli/wiki_bio","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wiki_bio","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/wiki_bio","frameworks":["tf","jax"]}],"num_papers_in_archive":84,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/table-to-text-generation-on-wikibio","task":"Table-to-Text Generation","dataset_variant":"WikiBio","rows":4,"metrics":["BLEU","ROUGE","PARENT"],"first_row_in_archive_order":{"model":"Field-gating Seq2seq + dual attention","paper":"/paper/table-to-text-generation-by-structure-aware","metrics":{"BLEU":"44.89","ROUGE":"41.21"},"code_links":[{"title":"tyliupku/wiki2bio","url":"https://github.com/tyliupku/wiki2bio"},{"title":"anjbapat/D2T","url":"https://github.com/anjbapat/D2T"},{"title":"Parth27/Data2Text","url":"https://github.com/Parth27/Data2Text"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/controlling-hallucinations-at-word-level-in","title":"Controlling Hallucinations at Word Level in Data-to-Text Generation","date":"2021-02-04","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/table-to-text-generation-by-structure-aware","title":"Table-to-text Generation by Structure-aware Seq2seq Learning","date":"2017-11-27","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/neural-text-generation-from-structured-data","title":"Neural Text Generation from Structured Data with Application to the Biography Domain","date":"2016-03-24","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"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."}