{"url":"/dataset/gum","name":"GUM","full_name":"Georgetown University Multilayer corpus","description_markdown":"GUM is an open source multilayer English corpus of richly annotated texts from twelve text types. Annotations include:\r\n\r\n  * Multiple POS tags, morphological features and lemmatization\r\n  * Sentence segmentation and rough speech act\r\n  * Document structure in TEI XML (paragraphs, headings, figures, etc.)\r\n  * ISO date/time annotations\r\n  * Speaker and addressee information (where relevant)\r\n  * Constituent and dependency syntax\r\n  * Information status (given, accessible, new, split antecedent)\r\n  * Entity and coreference annotation, including bridging anaphora\r\n  * Entity linking (Wikification)\r\n  * Discourse parses in Rhetorical Structure Theory and discourse dependencies","description_withheld":null,"homepage":"https://gucorpling.org/gum/","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"CC-BY-NC-SA","url":"https://github.com/amir-zeldes/gum/blob/master/LICENSE.txt"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Speech","url":"/datasets/modality/speech"}],"tasks":[{"name":"Named Entity Recognition (NER)","url":"/task/named-entity-recognition-ner","datasets_with_task":"/datasets/task/named-entity-recognition-ner"},{"name":"Entity Linking","url":"/task/entity-linking","datasets_with_task":"/datasets/task/entity-linking"},{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"},{"name":"Part-Of-Speech Tagging","url":"/task/part-of-speech-tagging","datasets_with_task":"/datasets/task/part-of-speech-tagging"},{"name":"Relation Classification","url":"/task/relation-classification","datasets_with_task":"/datasets/task/relation-classification"},{"name":"Named Entity Recognition","url":"/task/named-entity-recognition-1","datasets_with_task":"/datasets/task/named-entity-recognition-1"},{"name":"Entity Typing","url":"/task/entity-typing","datasets_with_task":"/datasets/task/entity-typing"},{"name":"Nested Named Entity Recognition","url":"/task/nested-named-entity-recognition","datasets_with_task":"/datasets/task/nested-named-entity-recognition"},{"name":"Discourse Parsing","url":"/task/discourse-parsing","datasets_with_task":"/datasets/task/discourse-parsing"},{"name":"Nested Mention Recognition","url":"/task/nested-mention-recognition","datasets_with_task":"/datasets/task/nested-mention-recognition"},{"name":"Timex normalization","url":"/task/timex-normalization","datasets_with_task":"/datasets/task/timex-normalization"},{"name":"Bridging Anaphora Resolution","url":"/task/bridging-anaphora-resolution","datasets_with_task":"/datasets/task/bridging-anaphora-resolution"},{"name":"Lemmatization","url":"/task/lemmatization","datasets_with_task":"/datasets/task/lemmatization"},{"name":"Discourse Segmentation","url":"/task/discourse-segmentation","datasets_with_task":"/datasets/task/discourse-segmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GUM"],"data_loaders":[],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/entity-linking-on-gum","task":"Entity Linking","dataset_variant":"GUM","rows":1,"metrics":["F1"],"first_row_in_archive_order":{"model":"baseline","paper":"/paper/wikigum-exhaustive-entity-linking-for","metrics":{"F1":"26.4"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/wikigum-exhaustive-entity-linking-for","title":"WikiGUM: Exhaustive Entity Linking for Wikification in 12 Genres","date":"2021-09-15","rows_on_this_dataset":1,"code_links":0,"syntology":null}],"syntology_totals":{"read_at":"2026-09-25T09:33:49+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."}