{"url":"/dataset/mkqa","name":"MKQA","full_name":"Multilingual Knowledge Questions and Answers","description_markdown":"Multilingual Knowledge Questions and Answers (MKQA) is an open-domain question answering evaluation set comprising 10k question-answer pairs aligned across 26 typologically diverse languages (260k question-answer pairs in total). The goal of this dataset is to provide a challenging benchmark for question answering quality across a wide set of languages. Answers are based on a language-independent data representation, making results comparable across languages and independent of language-specific passages. With 26 languages, this dataset supplies the widest range of languages to-date for evaluating question answering.","description_withheld":null,"homepage":"https://github.com/apple/ml-mkqa/","introduced_date":null,"introduced_date_note":null,"introduced_by":{"paper":"/paper/mkqa-a-linguistically-diverse-benchmark-for","title":"MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering","first_author":"Shayne Longpre","url":null},"license":null,"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Machine Translation","url":"/task/machine-translation","datasets_with_task":"/datasets/task/machine-translation"},{"name":"Open-Domain Question Answering","url":"/task/open-domain-question-answering","datasets_with_task":"/datasets/task/open-domain-question-answering"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"French","url":"/datasets/language/french"},{"name":"Spanish","url":"/datasets/language/spanish"},{"name":"German","url":"/datasets/language/german"},{"name":"Italian","url":"/datasets/language/italian"},{"name":"Chinese","url":"/datasets/language/chinese"},{"name":"Japanese","url":"/datasets/language/japanese"},{"name":"Russian","url":"/datasets/language/russian"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Danish","url":"/datasets/language/danish"},{"name":"Dutch","url":"/datasets/language/dutch"},{"name":"Finnish","url":"/datasets/language/finnish"},{"name":"Hebrew","url":"/datasets/language/hebrew"},{"name":"Hungarian","url":"/datasets/language/hungarian"},{"name":"Korean","url":"/datasets/language/korean"},{"name":"Norwegian","url":"/datasets/language/norwegian"},{"name":"Polish","url":"/datasets/language/polish"},{"name":"Swedish","url":"/datasets/language/swedish"},{"name":"Thai","url":"/datasets/language/thai"},{"name":"Turkish","url":"/datasets/language/turkish"},{"name":"Vietnamese","url":"/datasets/language/vietnamese"},{"name":"Central Khmer","url":"/datasets/language/central-khmer"},{"name":"Malay (individual language)","url":"/datasets/language/malay-individual-language"}],"variants":["MKQA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/apple/mkqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/mkqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/apple/ml-mkqa","url":"https://github.com/apple/ml-mkqa","frameworks":[]}],"num_papers_in_archive":49,"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."}