{"url":"/dataset/kaggledbqa","name":"KaggleDBQA","full_name":"KaggleDBQA: Realistic Text-to-SQL dataset","description_markdown":"KaggleDBQA is a challenging cross-domain and complex evaluation dataset of real Web databases, with domain-specific data types, original formatting, and unrestricted questions. \r\n\r\nIt expands upon contemporary cross-domain text-to-SQL datasets in three key aspects:\r\n(1) Its databases are pulled from real-world data sources and not normalized.\r\n(2) Its questions are authored in environments that mimic natural question answering.\r\n(3) It also provides database documentation that contains rich in-domain knowledge.","description_withheld":null,"homepage":"https://github.com/chiahsuan156/KaggleDBQA","introduced_date":"2021-06-22","introduced_date_note":null,"introduced_by":{"paper":"/paper/kaggledbqa-realistic-evaluation-of-text-to","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","first_author":"Chia-Hsuan Lee","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":"Text-To-SQL","url":"/task/text-to-sql","datasets_with_task":"/datasets/task/text-to-sql"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["KaggleDBQA"],"data_loaders":[],"num_papers_in_archive":28,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/text-to-sql-on-kaggledbqa","task":"Text-To-SQL","dataset_variant":"KaggleDBQA","rows":2,"metrics":["Exact Match (EM)"],"first_row_in_archive_order":{"model":"RAT-SQL","paper":"/paper/kaggledbqa-realistic-evaluation-of-text-to","metrics":{"Exact Match (EM)":"26.77"},"code_links":[{"title":"saparina/text2sql-nlvariation","url":"https://github.com/saparina/text2sql-nlvariation"},{"title":"chiahsuan156/KaggleDBQA","url":"https://github.com/chiahsuan156/KaggleDBQA"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/kaggledbqa-realistic-evaluation-of-text-to","title":"KaggleDBQA: Realistic Evaluation of Text-to-SQL Parsers","date":"2021-06-22","rows_on_this_dataset":2,"code_links":2,"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."}