{"url":"/dataset/chaii-hindi-and-tamil-question-answering","name":"ChAII - Hindi and Tamil Question Answering","full_name":null,"description_markdown":"The dataset covers Hindi and Tamil, collected without the use of translation. It provides a realistic information-seeking task with questions written by native-speaking expert data annotators.","description_withheld":null,"homepage":"https://www.kaggle.com/c/chaii-hindi-and-tamil-question-answering","introduced_date":null,"introduced_date_note":null,"introduced_by":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"}],"languages":[{"name":"Hindi","url":"/datasets/language/hindi"},{"name":"Tamil","url":"/datasets/language/tamil"}],"variants":["ChAII - Hindi and Tamil Question Answering"],"data_loaders":[],"num_papers_in_archive":1,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/question-answering-on-chaii-hindi-and-tamil","task":"Question Answering","dataset_variant":"ChAII - Hindi and Tamil Question Answering","rows":1,"metrics":["Jaccard"],"first_row_in_archive_order":{"model":"MuCoT","paper":"/paper/mucot-multilingual-contrastive-training-for","metrics":{"Jaccard":"0.53"},"code_links":[{"title":"gokulkarthik/mucot","url":"https://github.com/gokulkarthik/mucot"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/mucot-multilingual-contrastive-training-for","title":"MuCoT: Multilingual Contrastive Training for Question-Answering in Low-resource Languages","date":"2022-04-12","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"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."}