{"url":"/dataset/information-extraction-from-tables","name":"Information Extraction from Tables","full_name":"Extraction materials compositions from tables of materials science research papers","description_markdown":"Click to add a brief description of the dataset (Markdown and LaTeX enabled).\r\n\r\nProvide:\r\n\r\n* a high-level explanation of the dataset characteristics\r\n* explain motivations and summary of its content\r\n* potential use cases of the dataset","description_withheld":null,"homepage":"https://github.com/M3RG-IITD/DiSCoMaT","introduced_date":"2022-07-03","introduced_date_note":null,"introduced_by":{"paper":"/paper/discomat-distantly-supervised-composition","title":"DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles","first_author":"Tanishq Gupta","url":null},"license":null,"modalities":[{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Table annotation","url":"/task/table-annotation","datasets_with_task":"/datasets/task/table-annotation"},{"name":"Key Information Extraction","url":"/task/key-information-extraction","datasets_with_task":"/datasets/task/key-information-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Information Extraction from Tables"],"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."}