{"url":"/dataset/howsumm","name":"HowSumm","full_name":null,"description_markdown":"HowSumm is a large-scale query-focused multi-document summarization dataset. It is focused on summarization of various sources to create HowTo guides. It is derived from wikiHow articles.\r\n\r\nHowSumm is partitioned into HowSumm-Step where target summary is relatively short (avg. 90 words) and HowSumm-Method where target summary is a concatenation of several steps an therefore longer (avg. 500 words). HowSumm-Method and HowSumm-Step contain 11,121 and 84348 instances, respectively.\r\n\r\nDescription from: [HowSumm](https://github.com/odelliab/HowSumm)\r\n\r\nImage source: [HowSumm](https://github.com/odelliab/HowSumm)","description_withheld":null,"homepage":"https://github.com/odelliab/HowSumm","introduced_date":"2021-10-07","introduced_date_note":null,"introduced_by":{"paper":"/paper/howsumm-a-multi-document-summarization","title":"HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles","first_author":"Odellia Boni","url":null},"license":{"name":"CC BY-NC-SA 3.0","url":"https://creativecommons.org/licenses/by-nc-sa/3.0/legalcode"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Document Summarization","url":"/task/document-summarization","datasets_with_task":"/datasets/task/document-summarization"}],"languages":[],"variants":["HowSumm","HowSumm-Step","HowSumm-Method"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/document-summarization-on-howsumm-step","task":"Document Summarization","dataset_variant":"HowSumm-Step","rows":11,"metrics":["ROUGE-1"],"first_row_in_archive_order":{"model":"LexRank (query: step title)","paper":"/paper/howsumm-a-multi-document-summarization","metrics":{"ROUGE-1":"39.6"},"code_links":[{"title":"odelliab/HowSumm","url":"https://github.com/odelliab/HowSumm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-summarization-on-howsumm-method","task":"Document Summarization","dataset_variant":"HowSumm-Method","rows":9,"metrics":["ROUGE-1"],"first_row_in_archive_order":{"model":"LexRank (query: method + article + steps titles)","paper":"/paper/howsumm-a-multi-document-summarization","metrics":{"ROUGE-1":"53.5"},"code_links":[{"title":"odelliab/HowSumm","url":"https://github.com/odelliab/HowSumm"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/howsumm-a-multi-document-summarization","title":"HowSumm: A Multi-Document Summarization Dataset Derived from WikiHow Articles","date":"2021-10-07","rows_on_this_dataset":20,"code_links":1,"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."}