{"url":"/dataset/wec-eng","name":"WEC-Eng","full_name":null,"description_markdown":"WEC-eng is a cross-document event coreference resolution dataset extracted from English Wikipedia. Coreference links are not restricted within predefined topics. The training set includes 40,529 mentions distributed into 7,042 coreference clusters.","description_withheld":null,"homepage":"https://github.com/AlonEirew/extract-wec","introduced_date":"2021-04-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/wec-deriving-a-large-scale-cross-document","title":"WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia","first_author":"Alon Eirew","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Cross Document Coreference Resolution","url":"/task/cross-document-coreference-resolution","datasets_with_task":"/datasets/task/cross-document-coreference-resolution"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WEC-Eng"],"data_loaders":[{"repo":"https://github.com/AlonEirew/extract-wec","url":"https://github.com/AlonEirew/extract-wec","frameworks":[]}],"num_papers_in_archive":4,"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."}