{"url":"/dataset/tydiqa-goldp","name":"TyDiQA-GoldP","full_name":"TyDiQA-GoldP","description_markdown":"**TyDiQA** is the gold passage version of the Typologically Diverse Question Answering (TyDiWA) dataset, a benchmark for information-seeking question answering, which covers nine languages. The gold passage version is a simplified version of the primary task, which uses only the gold passage as context and excludes unanswerable questions. It is thus similar to XQuAD and MLQA, while being more challenging as questions have been written without seeing the answers, leading to 3× and 2× less lexical overlap compared to XQuAD and MLQA respectively.\r\n\r\nSource: [XTREME](https://arxiv.org/pdf/2003.11080.pdf)","description_withheld":null,"homepage":"https://github.com/google-research-datasets/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":null,"modalities":[],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Meta-Learning","url":"/task/meta-learning","datasets_with_task":"/datasets/task/meta-learning"},{"name":"Cross-Lingual Transfer","url":"/task/cross-lingual-transfer","datasets_with_task":"/datasets/task/cross-lingual-transfer"},{"name":"Cross-Lingual Question Answering","url":"/task/cross-lingual-question-answering","datasets_with_task":"/datasets/task/cross-lingual-question-answering"}],"languages":[],"variants":["TyDiQA-GoldP"],"data_loaders":[{"repo":"https://github.com/google-research-datasets/tydiqa","url":"https://github.com/google-research-datasets/tydiqa","frameworks":["tf"]}],"num_papers_in_archive":38,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/cross-lingual-question-answering-on-tydiqa","task":"Cross-Lingual Question Answering","dataset_variant":"TyDiQA-GoldP","rows":11,"metrics":["EM","F1"],"first_row_in_archive_order":{"model":"ByT5 (fine-tuned)","paper":"/paper/byt5-towards-a-token-free-future-with-pre","metrics":{"EM":"81.9"},"code_links":[{"title":"huggingface/transformers","url":"https://github.com/huggingface/transformers/tree/master/src/transformers/models/byt5"},{"title":"google-research/byt5","url":"https://github.com/google-research/byt5"},{"title":"ufal/multilexnorm2021","url":"https://github.com/ufal/multilexnorm2021"},{"title":"2024-MindSpore-1/Code2","url":"https://github.com/2024-MindSpore-1/Code2/tree/main/model-1/byt5"},{"title":"yoreG123/Paddle-ByT5","url":"https://github.com/yoreG123/Paddle-ByT5"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/palm-2-technical-report-1","title":"PaLM 2 Technical Report","date":"2023-05-17","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/transcending-scaling-laws-with-0-1-extra","title":"Transcending Scaling Laws with 0.1% Extra Compute","date":"2022-10-20","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/scaling-instruction-finetuned-language-models","title":"Scaling Instruction-Finetuned Language Models","date":"2022-10-20","rows_on_this_dataset":2,"code_links":9,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":17,"samples_ran":8,"samples_unverified":9,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/palm-scaling-language-modeling-with-pathways-1","title":"PaLM: Scaling Language Modeling with Pathways","date":"2022-04-05","rows_on_this_dataset":1,"code_links":7,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":37,"samples_ran":30,"samples_unverified":7,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/byt5-towards-a-token-free-future-with-pre","title":"ByT5: Towards a token-free future with pre-trained byte-to-byte models","date":"2021-05-28","rows_on_this_dataset":2,"code_links":5,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":6,"samples_ran":0,"samples_unverified":6,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-embedding-coupling-in-pre-trained-1","title":"Rethinking embedding coupling in pre-trained language models","date":"2020-10-24","rows_on_this_dataset":1,"code_links":4,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":3,"samples_harvested":60,"samples_ran":38,"samples_unverified":22,"pointer_only_for_licence":2,"papers_with_no_sample_that_ran":1,"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."}