{"url":"/dataset/mr-tydi","name":"Mr. TYDI","full_name":null,"description_markdown":"**Mr. TyDi** is a multi-lingual benchmark dataset for mono-lingual retrieval in eleven typologically diverse languages, designed to evaluate ranking with learned dense representations. The goal of this resource is to spur research in dense retrieval techniques in non-English languages, motivated by recent observations that existing techniques for representation learning perform poorly when applied to out-of-distribution data.","description_withheld":null,"homepage":"https://github.com/castorini/mr.tydi","introduced_date":"2021-08-19","introduced_date_note":null,"introduced_by":{"paper":"/paper/mr-tydi-a-multi-lingual-benchmark-for-dense","title":"Mr. TyDi: A Multi-lingual Benchmark for Dense Retrieval","first_author":"Xinyu Zhang","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[],"languages":[],"variants":["Mr. TYDI"],"data_loaders":[],"num_papers_in_archive":19,"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."}