{"url":"/dataset/wikiweb2m","name":"WikiWeb2M","full_name":"Wikipedia Webpage 2M","description_markdown":"**Wikipedia Webpage 2M (WikiWeb2M)** is a multimodal open source dataset consisting of over 2 million English Wikipedia articles. It is created by rescraping the ∼2M English articles in WIT. Each webpage sample includes the page URL and title, section titles, text, and indices, images and their captions.\r\n\r\nSource: [WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset](https://arxiv.org/pdf/2305.05432v1.pdf)\r\n\r\nImage Source: [WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset](https://arxiv.org/pdf/2305.05432v1.pdf)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/wit/blob/main/wikiweb2m.md","introduced_date":"2023-05-09","introduced_date_note":null,"introduced_by":{"paper":"/paper/wikiweb2m-a-page-level-multimodal-wikipedia","title":"WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset","first_author":"Andrea Burns","url":null},"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"},{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Image Captioning","url":"/task/image-captioning","datasets_with_task":"/datasets/task/image-captioning"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiWeb2M"],"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."}