{"url":"/dataset/wikiclir","name":"WikiCLIR","full_name":null,"description_markdown":"**WikiCLIR** is a large-scale (German-English) retrieval data set for Cross-Language Information Retrieval (CLIR). It contains a total of 245,294 German single-sentence queries with 3,200,393 automatically extracted relevance judgments for 1,226,741 English Wikipedia articles as documents. Queries are well-formed natural language sentences that allow large-scale training of (translation-based) ranking models.\r\n\r\nSource: []()","description_withheld":null,"homepage":"https://www.cl.uni-heidelberg.de/statnlpgroup/wikiclir/","introduced_date":"2014-06-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/learning-translational-and-knowledge-based","title":"Learning Translational and Knowledge-based Similarities from Relevance Rankings for Cross-Language Retrieval","first_author":"Shigehiko Schamoni","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"},{"name":"German","url":"/datasets/language/german"}],"variants":["WikiCLIR"],"data_loaders":[],"num_papers_in_archive":4,"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."}