{"url":"/dataset/docoie","name":"DocOIE","full_name":null,"description_markdown":"We manually annotate 800 sentences from 80 documents in two domains (Healthcare and Transportation) to form a DocOIE dataset for evaluation.","description_withheld":null,"homepage":"https://github.com/daviddongkc/DocOIE","introduced_date":"2021-05-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/docoie-a-document-level-context-aware-dataset","title":"DocOIE: A Document-level Context-Aware Dataset for OpenIE","first_author":"Kuicai Dong","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Open Information Extraction","url":"/task/open-information-extraction","datasets_with_task":"/datasets/task/open-information-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DocOIE","DocOIE-healthcare","DocOIE-transportation"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/open-information-extraction-on-docoie","task":"Open Information Extraction","dataset_variant":"DocOIE-healthcare","rows":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"DocIE w transformer","paper":"/paper/docoie-a-document-level-context-aware-dataset","metrics":{"F1":"60.8"},"code_links":[{"title":"daviddongkc/DocOIE","url":"https://github.com/daviddongkc/DocOIE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/open-information-extraction-on-docoie-1","task":"Open Information Extraction","dataset_variant":"DocOIE-transportation","rows":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"DocIE w transformer","paper":"/paper/docoie-a-document-level-context-aware-dataset","metrics":{"F1":"56.9"},"code_links":[{"title":"daviddongkc/DocOIE","url":"https://github.com/daviddongkc/DocOIE"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/docoie-a-document-level-context-aware-dataset","title":"DocOIE: A Document-level Context-Aware Dataset for OpenIE","date":"2021-05-10","rows_on_this_dataset":4,"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."}