{"url":"/dataset/nci","name":"NCI","full_name":"New Corpus for Ireland","description_markdown":"Contains a wide range of texts in Irish, including fiction, news reports, informative texts and official documents.\r\n\r\nKilgarriff, A., Rundell, M., and Uí Dhonnchadha, E. (2006). Efficient corpus development for lexicography: building the New Corpus for Ireland. Language Resources and Evaluation, 40:127–152. https://link.springer.com/article/10.1007/s10579-006-9011-7","description_withheld":null,"homepage":"","introduced_date":"2006-12-23","introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Irish","url":"/datasets/language/irish"}],"variants":["NCI"],"data_loaders":[],"num_papers_in_archive":2,"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."}