{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":4,"of":4,"counts":{"papers_with_a_benchmark_row":4,"with_a_code_link":4,"where_syntology_ran_a_sample":2,"not_listed_spam_title":0,"listed":4,"listed_where_code_ran":2,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":2,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":2,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/vaediff-docre-end-to-end-data-augmentation","slug":"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","arxiv_id":"2412.13503","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rexel-an-end-to-end-model-for-document-level","slug":"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","arxiv_id":"2404.12788","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["amazon-science/e2e-docie"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rexel-an-end-to-end-model-for-document-level#ran","syntology_url":"https://syntology.ai/paper/2404.12788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12788"}}}},{"paper":"/paper/injecting-knowledge-base-information-into-end","slug":"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","arxiv_id":"2107.02286","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/dwie-an-entity-centric-dataset-for-multi-task","slug":"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","arxiv_id":"2009.12626","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["klimzaporojets/DWIE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dwie-an-entity-centric-dataset-for-multi-task#ran","syntology_url":"https://syntology.ai/paper/2009.12626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12626"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/vaediff-docre-end-to-end-data-augmentation","slug":"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","arxiv_id":"2412.13503","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/rexel-an-end-to-end-model-for-document-level","slug":"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","arxiv_id":"2404.12788","rows_on_this_dataset":4,"code_links":1,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":3,"samples_ran":3,"samples_constructed":0,"samples_ran_checked":1,"samples_ran_instrument_failed":2,"samples_unverified":0,"pointer_only_for_licence":0,"official":{"repos":["amazon-science/e2e-docie"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["found_in_text"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/rexel-an-end-to-end-model-for-document-level#ran","syntology_url":"https://syntology.ai/paper/2404.12788","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.12788"}}}},{"paper":"/paper/injecting-knowledge-base-information-into-end","slug":"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","arxiv_id":"2107.02286","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/dwie-an-entity-centric-dataset-for-multi-task","slug":"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","arxiv_id":"2009.12626","rows_on_this_dataset":3,"code_links":2,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":14,"samples_ran":11,"samples_constructed":0,"samples_ran_checked":7,"samples_ran_instrument_failed":4,"samples_unverified":3,"pointer_only_for_licence":4,"official":{"repos":["klimzaporojets/DWIE"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]},"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/dwie-an-entity-centric-dataset-for-multi-task#ran","syntology_url":"https://syntology.ai/paper/2009.12626","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2009.12626"}}}}],"papers_where_code_ran":2,"papers_where_code_ran_first_page":"/dataset/dwie/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[{"order":"ran","page":1,"of":1,"url":"/dataset/dwie/papers/ran/1","json":"/dataset/dwie/papers/ran/1.json","rows":2}],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":2,"samples_harvested":17,"samples_ran":14,"samples_constructed":0,"samples_ran_checked":8,"samples_ran_instrument_failed":6,"samples_unverified":3,"pointer_only_for_licence":4,"papers_with_no_sample_that_ran":0,"papers_with_a_sample_that_ran":2,"papers_with_a_run_with_no_instrument_failure":2,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"5572c10d89bff6f3645a9be3afc9114393fe5195f5bc5fe65b22dc1fe6eff511","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}