{"url":"/dataset/wikicatsum","name":"WikiCatSum","full_name":null,"description_markdown":"**WikiCatSum** is a domain specific Multi-Document Summarisation (MDS) dataset. It assumes the summarisation task of generating Wikipedia lead sections for Wikipedia entities of a certain domain (e.g. Companies) from the set of documents cited in Wikipedia articles or returned by Google (using article titles as queries). The dataset includes three domains: Companies, Films, and Animals.\n\nSource: [https://datashare.ed.ac.uk/handle/10283/3368](https://datashare.ed.ac.uk/handle/10283/3368)","description_withheld":null,"homepage":"https://datashare.ed.ac.uk/handle/10283/3368","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/generating-summaries-with-topic-templates-and","title":"Generating Summaries with Topic Templates and Structured Convolutional Decoders","first_author":"Laura Perez-Beltrachini","url":null},"license":null,"modalities":[],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"}],"languages":[],"variants":["WikiCatSum"],"data_loaders":[],"num_papers_in_archive":7,"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."}