{"url":"/dataset/wikisection","name":"WikiSection","full_name":null,"description_markdown":"A publicly available dataset with 242k labeled sections in English and German from two distinct domains: diseases and cities.\r\n\r\nSource: [SECTOR: A Neural Model for Coherent Topic Segmentation and Classification](/paper/sector-a-neural-model-for-coherent-topic)","description_withheld":null,"homepage":"https://github.com/sebastianarnold/WikiSection","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/sector-a-neural-model-for-coherent-topic","title":"SECTOR: A Neural Model for Coherent Topic Segmentation and Classification","first_author":"Sebastian Arnold","url":null},"license":null,"modalities":[],"tasks":[{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"German","url":"/datasets/language/german"}],"variants":["WikiSection"],"data_loaders":[{"repo":"https://github.com/sebastianarnold/WikiSection","url":"https://github.com/sebastianarnold/WikiSection","frameworks":[]}],"num_papers_in_archive":17,"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."}