{"url":"/dataset/first-harem","name":"First HAREM","full_name":"Primeiro HAREM","description_markdown":"HAREM, an initiative by Linguateca, boasts a Golden Collection—a meticulously curated repository of annotated Portuguese texts. This resource serves as a pivotal benchmark for evaluating systems in recognizing mentioned entities within documents. It stands as a cornerstone, supporting advancements and innovations in Portuguese language processing research, providing a comprehensive foundation for evaluating system performances and fostering ongoing developments in this domain.","description_withheld":null,"homepage":"https://www.linguateca.pt/primeiroHAREM/harem.html","introduced_date":"2004-09-02","introduced_date_note":null,"introduced_by":null,"license":{"name":"CC","url":"https://www.linguateca.pt/primeiroHAREM/harem.html"},"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"},{"name":"Named Entity Recognition","url":"/task/named-entity-recognition-1","datasets_with_task":"/datasets/task/named-entity-recognition-1"},{"name":"NER","url":"/task/cg","datasets_with_task":"/datasets/task/cg"}],"languages":[{"name":"Portuguese","url":"/datasets/language/portuguese"}],"variants":["First HAREM"],"data_loaders":[],"num_papers_in_archive":1,"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."}