{"url":"/dataset/mintaka","name":"MINTAKA","full_name":null,"description_markdown":"**MINTAKA** is a complex, natural, and multilingual dataset designed for experimenting with end-to-end question-answering models. It is composed of 20,000 question-answer pairs collected in English, annotated with Wikidata entities, and translated into Arabic, French, German, Hindi, Italian, Japanese, Portuguese, and Spanish for a total of 180,000 samples. Mintaka includes 8 types of complex questions, including superlative, intersection, and multi-hop questions, which were naturally elicited from crowd workers.\r\n\r\nSource: [Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering](https://paperswithcode.com/paper/mintaka-a-complex-natural-and-multilingual)\r\n\r\nImage Source: [https://arxiv.org/pdf/2210.01613v1.pdf](https://arxiv.org/pdf/2210.01613v1.pdf)","description_withheld":null,"homepage":"https://github.com/amazon-research/mintaka","introduced_date":"2022-10-04","introduced_date_note":null,"introduced_by":{"paper":"/paper/mintaka-a-complex-natural-and-multilingual","title":"Mintaka: A Complex, Natural, and Multilingual Dataset for End-to-End Question Answering","first_author":"Priyanka Sen","url":null},"license":{"name":"Creative Commons Attribution 4.0 International","url":"https://github.com/amazon-research/mintaka/blob/main/LICENSE.md"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/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":"Japanese","url":"/datasets/language/japanese"},{"name":"Portuguese","url":"/datasets/language/portuguese"},{"name":"Arabic","url":"/datasets/language/arabic"},{"name":"Hindi","url":"/datasets/language/hindi"}],"variants":["MINTAKA"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/msalnikov/mintaka","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/AmazonScience/mintaka","frameworks":["tf","pytorch","jax"]}],"num_papers_in_archive":20,"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."}