{"url":"/dataset/wikipii","name":"WikiPII","full_name":null,"description_markdown":"WikiPII, an automatically labeled dataset composed of Wikipedia biography pages, annotated for personal information extraction.","description_withheld":null,"homepage":"https://github.com/ratmcu/wikipiifed","introduced_date":"2021-05-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/a-privacy-preserving-approach-to-extraction","title":"A Privacy-Preserving Approach to Extraction of Personal Information through Automatic Annotation and Federated Learning","first_author":"Rajitha Hathurusinghe","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiPII"],"data_loaders":[],"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."}