{"url":"/dataset/ontogum","name":"OntoGUM","full_name":null,"description_markdown":"**OntoGUM** is an OntoNotes-like coreference dataset converted from GUM, an English corpus covering 12 genres using deterministic rules.","description_withheld":null,"homepage":"https://github.com/yilunzhu/ontogum","introduced_date":"2021-06-02","introduced_date_note":null,"introduced_by":{"paper":"/paper/ontogum-evaluating-contextualized-sota","title":"OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres","first_author":"YIlun Zhu","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["OntoGUM"],"data_loaders":[],"num_papers_in_archive":9,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/coreference-resolution-on-ontogum","task":"Coreference Resolution","dataset_variant":"OntoGUM","rows":2,"metrics":["Avg F1"],"first_row_in_archive_order":{"model":"MTL-coref","paper":"/paper/incorporating-singletons-and-mention-based","metrics":{"Avg F1":"68.2"},"code_links":[{"title":"yilunzhu/coref-mtl","url":"https://github.com/yilunzhu/coref-mtl"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/incorporating-singletons-and-mention-based","title":"Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization","date":"2023-09-20","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/ontogum-evaluating-contextualized-sota","title":"OntoGUM: Evaluating Contextualized SOTA Coreference Resolution on 12 More Genres","date":"2021-06-02","rows_on_this_dataset":1,"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."}