{"url":"/dataset/docbank-tb","name":"DocBank-TB","full_name":"DocBank-Table","description_markdown":"This dataset consisting 500 set of caption, table and coresponding paper page, processed from [DocBank](docbank).","description_withheld":null,"homepage":"https://github.com/junj2ejj/GCCE2021_materials","introduced_date":"2021-08-18","introduced_date_note":null,"introduced_by":{"paper":"/paper/table-caption-generation-in-scholarly","title":"Table Caption Generation in Scholarly Documents Leveraging Pre-trained Language Models","first_author":"Junjie H. Xu","url":null},"license":{"name":"Apache-2.0 License","url":"https://github.com/junj2ejj/GCCE2021_materials/blob/main/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Text Generation","url":"/task/text-generation","datasets_with_task":"/datasets/task/text-generation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DocBank-TB"],"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."}