{"url":"/dataset/glot500-c","name":"Glot500-c","full_name":"Glot500 Corpus","description_markdown":"A dataset of natural language data collected by putting together more than 150 existing mono-lingual and multilingual datasets together and crawling known multilingual websites. The focus of this dataset is on 500 extremely low-resource languages. \r\n\r\nGithub: https://github.com/cisnlp/Glot500","description_withheld":null,"homepage":"https://huggingface.co/datasets/cis-lmu/Glot500","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":{"name":"Other","url":"https://huggingface.co/datasets/cis-lmu/Glot500"},"modalities":[],"tasks":[{"name":"Language Modelling","url":"/task/language-modelling","datasets_with_task":"/datasets/task/language-modelling"}],"languages":[{"name":"Multilingual","url":"/datasets/language/multilingual"}],"variants":["Glot500-c"],"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."}