{"url":"/dataset/meetingbank","name":"MeetingBank","full_name":null,"description_markdown":"MeetingBank, a benchmark dataset created from the city councils of 6 major U.S. cities to supplement existing datasets. \r\n\r\nIt contains **1,366** meetings with over 3,579 hours of video, as well as transcripts, PDF documents of meeting minutes, agenda, and other metadata. On average, a council meeting is 2.6 hours long and its transcript contains over **28k tokens**, making it a valuable testbed for meeting summarizers and for extracting structure from meeting videos. The datasets contains **6,892** segment-level summarization instances for training and evaluating of performance.","description_withheld":null,"homepage":"https://meetingbank.github.io","introduced_date":"2023-05-27","introduced_date_note":null,"introduced_by":{"paper":"/paper/meetingbank-a-benchmark-dataset-for-meeting","title":"MeetingBank: A Benchmark Dataset for Meeting Summarization","first_author":"Yebowen Hu","url":null},"license":{"name":"Attribution-NonCommercial-NoDerivatives 4.0 International","url":"https://creativecommons.org/"},"modalities":[{"name":"Videos","url":"/datasets/modality/videos"},{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Audio","url":"/datasets/modality/audio"}],"tasks":[{"name":"Text Summarization","url":"/task/text-summarization","datasets_with_task":"/datasets/task/text-summarization"},{"name":"Multimodal Reasoning","url":"/task/multimodal-reasoning","datasets_with_task":"/datasets/task/multimodal-reasoning"},{"name":"Meeting Summarization","url":"/task/meeting-summarization","datasets_with_task":"/datasets/task/meeting-summarization"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["MeetingBank"],"data_loaders":[{"repo":"https://github.com/YebowenHu/MeetingBank-utils","url":"https://github.com/YebowenHu/MeetingBank-utils","frameworks":[]}],"num_papers_in_archive":16,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-summarization-on-meetingbank","task":"Text Summarization","dataset_variant":"MeetingBank","rows":2,"metrics":["ROUGE-L","Rouge-1","ROUGE-2"],"first_row_in_archive_order":{"model":"CriSPO 3-shot","paper":"/paper/crispo-multi-aspect-critique-suggestion","metrics":{"ROUGE-2":"46.5","ROUGE-L":"54.1","Rouge-1":"58.5"},"code_links":[{"title":"amazon-science/crispo","url":"https://github.com/amazon-science/crispo"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/salient-information-prompting-to-steer","title":"Salient Information Prompting to Steer Content in Prompt-based Abstractive Summarization","date":"2024-10-03","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/crispo-multi-aspect-critique-suggestion","title":"CriSPO: Multi-Aspect Critique-Suggestion-guided Automatic Prompt Optimization for Text Generation","date":"2024-10-03","rows_on_this_dataset":1,"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."}