{"url":"/dataset/wili-2018","name":"WiLI-2018","full_name":null,"description_markdown":"WiLI-2018 is a benchmark dataset for monolingual written natural language identification. WiLI-2018 is a publicly available, free of charge dataset of short text extracts from Wikipedia. It contains 1000 paragraphs of 235 languages, totaling in 23500 paragraphs. WiLI is a classification dataset: Given an unknown paragraph written in one dominant language, it has to be decided which language it is.\r\n\r\nSource: [The WiLI benchmark dataset for written language identification](/paper/the-wili-benchmark-dataset-for-written)","description_withheld":null,"homepage":"https://doi.org/10.5281/zenodo.841984","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/the-wili-benchmark-dataset-for-written","title":"The WiLI benchmark dataset for written language identification","first_author":"Martin Thoma","url":null},"license":{"name":"ODC Open Database License v1.0","url":"http://www.opendatacommons.org/licenses/odbl/1.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Natural Language Inference","url":"/task/natural-language-inference","datasets_with_task":"/datasets/task/natural-language-inference"},{"name":"Dependency Parsing","url":"/task/dependency-parsing","datasets_with_task":"/datasets/task/dependency-parsing"},{"name":"Language Identification","url":"/task/language-identification","datasets_with_task":"/datasets/task/language-identification"}],"languages":[],"variants":["WiLI-2018"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MAximeSobrier/WiLI-2018-fixed","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/MartinThoma/wili_2018","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/wili_2018","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":3,"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."}