{"url":"/dataset/large-scale-clir-dataset","name":"Large-Scale CLIR Dataset","full_name":null,"description_markdown":"The Large-Scale CLIR Dataset is a retrieval dataset built for Cross-Language Information Retrieval (CLIR).\r\nThe dataset is derived from Wikipedia and contains more 2.8 million English single-sentence queries with relevant documents from 25 other selected languages.","description_withheld":null,"homepage":"https://www.cs.jhu.edu/~kevinduh/a/wikiclir2018/","introduced_date":"2018-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/cross-lingual-learning-to-rank-with-shared","title":"Cross-Lingual Learning-to-Rank with Shared Representations","first_author":"Shota Sasaki","url":null},"license":{"name":"CC BY-SA 4.0","url":"https://creativecommons.org/licenses/by-sa/4.0/"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Information Retrieval","url":"/task/information-retrieval","datasets_with_task":"/datasets/task/information-retrieval"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["Large-Scale CLIR Dataset"],"data_loaders":[],"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":"2026-09-25T09:33:49+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."}