{"url":"/dataset/nordic-langid","name":"Nordic Language Identification","full_name":null,"description_markdown":"Automatic language identification is a challenging problem. Discriminating between closely related languages is especially difficult. This paper presents a machine-learning approach for automatic language identification for the Nordic languages, which often suffer miscategorization by existing state-of-the-art tools. Concretely we will focus on discrimination between six Nordic languages: Danish, Swedish, Norwegian (Nynorsk), Norwegian (Bokmål), Faroese, and Icelandic. This is the data for the tasks. Two variants are provided: 10K and 50K, withholding 10,000 and 50,000 examples for each language respectively.\r\n\r\nThis dataset is in six similar Nordic languages:\r\n1. Danish, da\r\n2. Faroese, fo\r\n3. Icelandic, is\r\n4. Norwegian Bokmål, nb\r\n5. Norwegian Nynorsk, nn\r\n6. Swedish, sv","description_withheld":null,"homepage":"https://huggingface.co/datasets/strombergnlp/nordic_langid","introduced_date":"2020-12-11","introduced_date_note":null,"introduced_by":{"paper":"/paper/discriminating-between-similar-nordic","title":"Discriminating Between Similar Nordic Languages","first_author":"René Haas","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Language Identification","url":"/task/language-identification","datasets_with_task":"/datasets/task/language-identification"}],"languages":[{"name":"Danish","url":"/datasets/language/danish"},{"name":"Faroese","url":"/datasets/language/faroese"},{"name":"Icelandic","url":"/datasets/language/icelandic"},{"name":"Swedish","url":"/datasets/language/swedish"},{"name":"Norwegian Nynorsk","url":"/datasets/language/norwegian-nynorsk"},{"name":"Norwegian Bokmål","url":"/datasets/language/norwegian-bokm-l"}],"variants":["Nordic Language Identification"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/strombergnlp/nordic_langid","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/language-identification-on-nordic-langid","task":"Language Identification","dataset_variant":"Nordic Language Identification","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"FastText","paper":"/paper/discriminating-between-similar-nordic","metrics":{"Accuracy":"0.9711"},"code_links":[{"title":"renhaa/NordicDSL","url":"https://github.com/renhaa/NordicDSL"},{"title":"StrombergNLP/NordicDSL","url":"https://github.com/StrombergNLP/NordicDSL"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/discriminating-between-similar-nordic","title":"Discriminating Between Similar Nordic Languages","date":"2020-12-11","rows_on_this_dataset":1,"code_links":2,"syntology":null}],"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."}