{"url":"/sota/document-level-closed-information-extraction","task":{"name":"Document-level Closed Information Extraction","url":"/task/document-level-closed-information-extraction","note":null},"dataset":{"name":"DocRED","url":"/dataset/docred"},"category":"Natural Language Processing","categories":["Medical","Natural Language Processing"],"category_note":null,"description":"Document-level closed information extraction (DocIE) is a subtask of information extraction that seeks to extract a set of triplets, or facts, of the form `(subject, relation, object)` from unstructured texts that are fully linked to a reference knowledge base, i.e., consistent with a predefined set of entities and relations from a knowledge base. DocIE entails tasks such as mention detection, entity typing, named entity recognition, entity disambiguation, entity linking, coreference resolution, and document-level relation extraction. DocIE is more challenging than sentence-level closed information extraction as it involves capturing long-range dependencies effectively to extract relations between entities that are further apart from each other in the text. Another difference is that DocIE necessitates a coreference resolution stage to group all the different mentions in the document referring to the same entity. DocIE is crucial for applications such as knowledge graph construction, question answering, knowledge discovery, or text summarization.\r\n\r\n<span class=\"description-source\">Source: [REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking](https://arxiv.org/abs/2404.12788)</span>","description_from":"task","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","rank":"the archive's row order at snapshot; not re-ranked","rows_end_at":"2025-07-28","rows_withheld_as_spam":0,"metric_values":"the archive's strings, untouched"},"metrics":["Relation F1"],"metric_direction":{"note":"inferred from the metric name only (the archive records no direction); null = not inferred, chart draws points only","by_metric":{"Relation F1":"higher"}},"counts":{"rows":1,"rows_with_code":1,"rows_with_paper_page":1,"rows_dated":1,"rows_using_additional_data":0},"rows":[{"rank_in_archive_order":1,"model":"REXEL","metrics":{"Relation F1":"27.96"},"uses_additional_data":false,"paper_date":"2024-04-19","paper":"/paper/rexel-an-end-to-end-model-for-document-level","paper_url":"https://arxiv.org/abs/2404.12788v1","paper_title":"REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking","code":"https://github.com/amazon-science/e2e-docie","n_code_links":1,"syntology":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0}}],"since_archive":{"claim":"Results that newer papers report for their own method, placed here by Syntology. A model pointed at the cell in the paper's own table; the number was read from that cell and checked against this leaderboard's metric, dataset, split and scale; an independent check that saw this leaderboard's other rows and every other leaderboard on the same dataset accepted it. Not reviewed by the paper's authors or by the archive's editors, and not ranked against the archive rows.","extraction_file_present":true,"measurement":{"test_papers":883,"papers_with_output":881,"judged_true":108,"judged":110,"wilson95_lower":0.9361,"measured_on":"2026-09-24","frozen_commit":"0e3de0df94"},"measurement_note":"blind adjudication of accepted entries on a held-out split of archive papers, rules frozen before the test","coverage":{"sentence":"Syntology has checked 6,795 of the 9,581 papers on this site that are newer than the archive; results from the others appear after they are checked.","complete":false,"papers_newer_than_archive":9581,"papers_checked":6795,"papers_extracted_not_yet_verified":0,"boards_without_verdict":2,"papers_not_yet_extracted":2785},"order":"newest first by month (arXiv date, else the arXiv-id month), then arXiv id descending","columns":[],"entries":[]},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per row: N of M harvested code samples from that row's paper executed on a synthesized fixture; the other M-N are unverified. Not a reproduction of the row's number; not a correctness claim. n_pointer_only_licence counts samples the site points at rather than redistributes (a licence axis, independent of ran/unverified).","rows_with_graph_line":1,"rows_with_any_sample_ran":1,"distinct_papers_with_graph_line":1,"distinct_papers_with_any_sample_ran":1,"samples_over_distinct_papers":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"note":"each paper (arXiv id) counted once, however many rows it is behind; this is the page-level figure"},"samples_row_weighted":{"n_ran":3,"n_unverified":0,"n_samples":3,"n_pointer_only_licence":0,"note":"row-weighted: a paper behind several rows is counted once per row; inflated relative to samples_over_distinct_papers by design, kept for readers summing the per-row syntology blocks"}}}