{"url":"/dataset/nordial","name":"NorDial","full_name":null,"description_markdown":"**NorDial** is the first step to creating a corpus of dialectal variation of written Norwegian. It consists of small corpus of tweets manually annotated as Bokmål, Nynorsk, any dialect, or a mix.","description_withheld":null,"homepage":"https://github.com/jerbarnes/norwegian_dialect","introduced_date":"2021-04-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/nordial-a-preliminary-corpus-of-written","title":"NorDial: A Preliminary Corpus of Written Norwegian Dialect Use","first_author":"Jeremy Barnes","url":null},"license":{"name":"CC BY-NC 4.0","url":"https://creativecommons.org/licenses/by-nc/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[{"name":"Norwegian","url":"/datasets/language/norwegian"},{"name":"Norwegian Nynorsk","url":"/datasets/language/norwegian-nynorsk"},{"name":"Norwegian Bokmål","url":"/datasets/language/norwegian-bokm-l"}],"variants":["NorDial"],"data_loaders":[{"repo":"https://github.com/jerbarnes/norwegian_dialect","url":"https://github.com/jerbarnes/norwegian_dialect","frameworks":["pytorch"]}],"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."}