{"url":"/dataset/gap-coreference-dataset","name":"GAP Coreference Dataset","full_name":null,"description_markdown":"GAP is a gender-balanced dataset containing 8,908 coreference-labeled pairs of (ambiguous pronoun, antecedent name), sampled from Wikipedia and released by Google AI Language for the evaluation of coreference resolution in practical applications.\r\n\r\nSource: [GAP Coreference Dataset](https://github.com/google-research-datasets/gap-coreference)\r\nImage Source: [https://arxiv.org/pdf/1810.05201.pdf](https://arxiv.org/pdf/1810.05201.pdf)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/gap-coreference","introduced_date":"2018-10-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/mind-the-gap-a-balanced-corpus-of-gendered","title":"Mind the GAP: A Balanced Corpus of Gendered Ambiguous Pronouns","first_author":"Kellie Webster","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Coreference Resolution","url":"/task/coreference-resolution","datasets_with_task":"/datasets/task/coreference-resolution"},{"name":"Data Augmentation","url":"/task/data-augmentation","datasets_with_task":"/datasets/task/data-augmentation"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["GAP","GAP Coreference Dataset"],"data_loaders":[{"repo":"https://github.com/google-research-datasets/gap-coreference","url":"https://github.com/google-research-datasets/gap-coreference","frameworks":[]}],"num_papers_in_archive":104,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[],"papers_with_a_benchmark_row":[],"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."}