{"url":"/dataset/tydi-qa","name":"TyDiQA","full_name":"Typologically Diverse Question Answering","description_markdown":"TyDi QA is a question answering dataset covering 11 typologically diverse languages with 200K question-answer pairs. The languages of TyDi QA are diverse with regard to their typology — the set of linguistic features that each language expresses — such that the authors expect models performing well on this set to generalize across a large number of the languages in the world.\r\n\r\nSource: [Google Research](https://ai.google.com/research/tydiqa)","description_withheld":null,"homepage":"https://ai.google.com/research/tydiqa","introduced_date":"2020-03-10","introduced_date_note":null,"introduced_by":{"paper":"/paper/tydi-qa-a-benchmark-for-information-seeking","title":"TyDi QA: A Benchmark for Information-Seeking Question Answering in Typologically Diverse Languages","first_author":"Jonathan H. Clark","url":null},"license":{"name":"Unknown","url":null},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Reading Comprehension","url":"/task/reading-comprehension","datasets_with_task":"/datasets/task/reading-comprehension"}],"languages":[],"variants":["TyDiQA","tydiqa_primary"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/neulab/PangeaBench-tydiqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/tydiqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/khalidalt/tydiqa-goldp","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/juletxara/tydiqa_xtreme","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/khalidalt/tydiqa-primary","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/copenlu/tydiqa_copenlu","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/copenlu/nlp_course_tydiqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/google-research-datasets/tydiqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/neulab/tydiqa","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/tydi_qa","frameworks":["tf","jax"]}],"num_papers_in_archive":148,"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."}