{"url":"/dataset/frecdo","name":"FreCDo","full_name":"French cross-domain","description_markdown":"**FreCDo** is a corpus for French dialect identification comprising 413,522 French text samples collected from public news websites in Belgium, Canada, France and Switzerland.\r\n\r\nSource: [FreCDo: A Large Corpus for French Cross-Domain Dialect Identification](https://arxiv.org/pdf/2212.07707v1.pdf)","description_withheld":null,"homepage":"https://github.com/MihaelaGaman/FreCDo","introduced_date":"2022-12-15","introduced_date_note":null,"introduced_by":{"paper":"/paper/frecdo-a-large-corpus-for-french-cross-domain","title":"FreCDo: A Large Corpus for French Cross-Domain Dialect Identification","first_author":"Mihaela Gaman","url":null},"license":{"name":"CC0-1.0 license","url":"https://github.com/MihaelaGaman/FreCDo/blob/master/LICENSE"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Dialect Identification","url":"/task/dialect-identification","datasets_with_task":"/datasets/task/dialect-identification"}],"languages":[{"name":"French","url":"/datasets/language/french"}],"variants":["FreCDo"],"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."}