{"url":"/dataset/dwie","name":"DWIE","full_name":"Deutsche Welle corpus for Information Extraction","description_markdown":"The '**Deutsche Welle corpus for Information Extraction**' (**DWIE**) is a multi-task dataset that combines four main Information Extraction (IE) annotation sub-tasks: (i) Named Entity Recognition (NER), (ii) Coreference Resolution, (iii) Relation Extraction (RE), and (iv) Entity Linking. DWIE is conceived as an entity-centric dataset that describes interactions and properties of conceptual entities on the level of the complete document.\r\n\r\nSource: [https://arxiv.org/abs/2009.12626](https://arxiv.org/abs/2009.12626)","description_withheld":null,"homepage":"https://github.com/klimzaporojets/DWIE","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/dwie-an-entity-centric-dataset-for-multi-task","title":"DWIE: an entity-centric dataset for multi-task document-level information extraction","first_author":"Klim Zaporojets","url":null},"license":{"name":"GPL-3.0 License","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Relation Extraction","url":"/task/relation-extraction","datasets_with_task":"/datasets/task/relation-extraction"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"},{"name":"Document-level Relation Extraction","url":"/task/document-level-relation-extraction","datasets_with_task":"/datasets/task/document-level-relation-extraction"},{"name":"Document-level Closed Information Extraction","url":"/task/document-level-closed-information-extraction","datasets_with_task":"/datasets/task/document-level-closed-information-extraction"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["DWIE"],"data_loaders":[{"repo":"https://github.com/klimzaporojets/DWIE","url":"https://github.com/klimzaporojets/DWIE","frameworks":[]}],"num_papers_in_archive":18,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/coreference-resolution-on-dwie","task":"Coreference Resolution","dataset_variant":"DWIE","rows":3,"metrics":["Avg. F1"],"first_row_in_archive_order":{"model":"REXEL","paper":"/paper/rexel-an-end-to-end-model-for-document-level","metrics":{"Avg. F1":"95.12"},"code_links":[{"title":"amazon-science/e2e-docie","url":"https://github.com/amazon-science/e2e-docie"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/named-entity-recognition-on-dwie","task":"Named Entity Recognition (NER)","dataset_variant":"DWIE","rows":3,"metrics":["F1-Hard"],"first_row_in_archive_order":{"model":"REXEL","paper":"/paper/rexel-an-end-to-end-model-for-document-level","metrics":{"F1-Hard":"90.59"},"code_links":[{"title":"amazon-science/e2e-docie","url":"https://github.com/amazon-science/e2e-docie"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/relation-extraction-on-dwie","task":"Relation Extraction","dataset_variant":"DWIE","rows":3,"metrics":["F1-Hard"],"first_row_in_archive_order":{"model":"REXEL","paper":"/paper/rexel-an-end-to-end-model-for-document-level","metrics":{"F1-Hard":"65.8"},"code_links":[{"title":"amazon-science/e2e-docie","url":"https://github.com/amazon-science/e2e-docie"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-level-closed-information-extraction-1","task":"Document-level Closed Information Extraction","dataset_variant":"DWIE","rows":1,"metrics":["F1-Hard"],"first_row_in_archive_order":{"model":"REXEL","paper":"/paper/rexel-an-end-to-end-model-for-document-level","metrics":{"F1-Hard":"53.77"},"code_links":[{"title":"amazon-science/e2e-docie","url":"https://github.com/amazon-science/e2e-docie"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/document-level-relation-extraction-on-dwie","task":"Document-level Relation Extraction","dataset_variant":"DWIE","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"VaeDiff-DocRE","paper":"/paper/vaediff-docre-end-to-end-data-augmentation","metrics":{"F1":"0.7307"},"code_links":[{"title":"khaitran22/vaediff-docre","url":"https://github.com/khaitran22/vaediff-docre"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/vaediff-docre-end-to-end-data-augmentation","title":"VaeDiff-DocRE: End-to-end Data Augmentation Framework for Document-level Relation Extraction","date":"2024-12-18","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rexel-an-end-to-end-model-for-document-level","title":"REXEL: An End-to-end Model for Document-Level Relation Extraction and Entity Linking","date":"2024-04-19","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":3,"samples_unverified":0,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/injecting-knowledge-base-information-into-end","title":"Injecting Knowledge Base Information into End-to-End Joint Entity and Relation Extraction and Coreference Resolution","date":"2021-07-05","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/dwie-an-entity-centric-dataset-for-multi-task","title":"DWIE: an entity-centric dataset for multi-task document-level information extraction","date":"2020-09-26","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":5,"samples_unverified":9,"pointer_only_for_licence":3,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":17,"samples_ran":8,"samples_unverified":9,"pointer_only_for_licence":3,"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."}