{"url":"/dataset/metaclir","name":"MetaCLIR","full_name":null,"description_markdown":"This data adds textual meta-infomation data to two existing corpora for cross language information retrieval: BoostCLIR, and the Large Scale CLIR Dataset (wiki-clir).","description_withheld":null,"homepage":"https://www.cl.uni-heidelberg.de/statnlpgroup/metaclir/","introduced_date":"2020-10-30","introduced_date_note":null,"introduced_by":{"paper":"/paper/embedding-meta-textual-information-for","title":"Embedding Meta-Textual Information for Improved Learning to Rank","first_author":"Toshitaka Kuwa","url":null},"license":{"name":"CC BY-NC-SA 4.0","url":"https://creativecommons.org/licenses/by-nc-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":"French","url":"/datasets/language/french"},{"name":"German","url":"/datasets/language/german"},{"name":"Japanese","url":"/datasets/language/japanese"}],"variants":["MetaCLIR"],"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."}