{"url":"/dataset/lazaro-corpus","name":"Lazaro Corpus","full_name":null,"description_markdown":"A corpus of 21,570 newspaper headlines written in European Spanish annotated with emergent anglicisms.\r\n\r\nSource: [An Annotated Corpus of Emerging Anglicisms in Spanish Newspaper Headlines](/paper/an-annotated-corpus-of-emerging-anglicisms-in)","description_withheld":null,"homepage":"https://github.com/lirondos/lazaro","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/an-annotated-corpus-of-emerging-anglicisms-in","title":"An Annotated Corpus of Emerging Anglicisms in Spanish Newspaper Headlines","first_author":"Elena Álvarez-Mellado","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Spanish","url":"/datasets/language/spanish"}],"variants":["Lazaro Corpus"],"data_loaders":[{"repo":"https://github.com/lirondos/lazaro","url":"https://github.com/lirondos/lazaro","frameworks":[]}],"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."}