{"url":"/dataset/conll-2020","name":"CoNLL-2020","full_name":"CoNLLpp","description_markdown":"A test dataset that annotated articles in 2020 following the CoNLL-2003 NER task.","description_withheld":null,"homepage":"https://github.com/ShuhengL/acl2023_conllpp?tab=readme-ov-file","introduced_date":"2022-12-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/do-conll-2003-named-entity-taggers-still-work","title":"Do CoNLL-2003 Named Entity Taggers Still Work Well in 2023?","first_author":"Shuheng Liu","url":null},"license":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"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["CoNLL-2020"],"data_loaders":[],"num_papers_in_archive":2,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/named-entity-recognition-ner-on-conll-2020","task":"Named Entity Recognition (NER)","dataset_variant":"CoNLL-2020","rows":2,"metrics":["F1"],"first_row_in_archive_order":{"model":"LUKE + SubRegWeigh (K-means)","paper":"/paper/subregweigh-effective-and-efficient","metrics":{"F1":"95.31"},"code_links":[{"title":"4ldk/SubRegWeigh","url":"https://github.com/4ldk/SubRegWeigh"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/subregweigh-effective-and-efficient","title":"SubRegWeigh: Effective and Efficient Annotation Weighing with Subword Regularization","date":"2024-09-10","rows_on_this_dataset":2,"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."}