{"url":"/dataset/ytd-18m","name":"YTD-18M","full_name":null,"description_markdown":"YTD-18M is a large-scale corpus of 18M video-based dialogues, constructed from web videos: crucial to the data collection pipeline is a pretrained language model that converts error-prone automatic transcripts to a cleaner dialogue format while maintaining meaning.\r\n\r\nSource: [CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos](https://arxiv.org/pdf/2303.09713v1.pdf)\r\n\r\nImage Source: [https://seungjuhan.me/champagne/](https://seungjuhan.me/champagne/)","description_withheld":null,"homepage":"https://seungjuhan.me/champagne","introduced_date":"2023-03-17","introduced_date_note":null,"introduced_by":{"paper":"/paper/champagne-learning-real-world-conversation","title":"CHAMPAGNE: Learning Real-world Conversation from Large-Scale Web Videos","first_author":"Seungju Han","url":null},"license":{"name":"Apache-2.0 license","url":"https://github.com/wade3han/champagne/blob/master/LICENSE"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["YTD-18M"],"data_loaders":[],"num_papers_in_archive":3,"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."}