{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/wikihow-a-large-scale-text-summarization","title":"WikiHow: A Large Scale Text Summarization Dataset","arxiv_id":"1810.09305","date":"2018-10-18","proceeding":null,"authors":["Mahnaz Koupaee","William Yang Wang"],"abstract":"Sequence-to-sequence models have recently gained the state of the art\nperformance in summarization. However, not too many large-scale high-quality\ndatasets are available and almost all the available ones are mainly news\narticles with specific writing style. Moreover, abstractive human-style systems\ninvolving description of the content at a deeper level require data with higher\nlevels of abstraction. In this paper, we present WikiHow, a dataset of more\nthan 230,000 article and summary pairs extracted and constructed from an online\nknowledge base written by different human authors. The articles span a wide\nrange of topics and therefore represent high diversity styles. We evaluate the\nperformance of the existing methods on WikiHow to present its challenges and\nset some baselines to further improve it.","url_abs":"http://arxiv.org/abs/1810.09305v1","url_pdf":"http://arxiv.org/pdf/1810.09305v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/LubdaMax/Data-Science-1","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/ThierryBarros/reproduction-textrank","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/Wikidepia/indonesia_dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/anbunathan/WikiHow-Semantic","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/dengyang17/wikihowQA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/pvl/wikihow_pairs_dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/stancld/GeneratingHeadline_GANs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/stancld/GeneratingHeadlines_GANs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"wikihow-a-large-scale-text-summarization","repo_url":"https://github.com/wikidepia/indonesian_datasets","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"articles","task_name":"Articles"},{"task_slug":"diversity","task_name":"Diversity"},{"task_slug":"text-summarization","task_name":"Text Summarization"}],"methods":[],"datasets_introduced":[{"slug":"wikihow","name":"WikiHow","full_name":""}],"methods_introduced":[],"results":[{"leaderboard":"/sota/text-summarization-on-wikihow","task":"Text Summarization","dataset":"WikiHow","model":"Pointer-generator + coverage","rank_in_archive_order":3,"of":3,"metrics":{"ROUGE-1":"28.53","ROUGE-2":"9.23","ROUGE-L":"26.54"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1810.09305","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1810.09305"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/LubdaMax/Data-Science-1","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/anbunathan/WikiHow-Semantic","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ThierryBarros/reproduction-textrank","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Wikidepia/indonesia_dataset","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/dengyang17/wikihowQA","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/wikidepia/indonesian_datasets","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stancld/GeneratingHeadlines_GANs","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pvl/wikihow_pairs_dataset","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stancld/GeneratingHeadline_GANs","reach":{"status":"ok"}}],"summary":{"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":1,"samples":[{"code_sha256_prefix":"b79affd36fe04fd9","entry":"clean_title","repo":"pvl/wikihow_pairs_dataset","repo_kind":"listed","path":"extract.py","file_url":"https://github.com/pvl/wikihow_pairs_dataset/blob/HEAD/extract.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b79affd36fe04fd9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}