{"url":"/dataset/wikitablequestions","name":"WikiTableQuestions","full_name":null,"description_markdown":"**WikiTableQuestions** is a question answering dataset over semi-structured tables. It is comprised of question-answer pairs on HTML tables, and was constructed by selecting data tables from Wikipedia that contained at least 8 rows and 5 columns. Amazon Mechanical Turk workers were then tasked with writing trivia questions about each table. WikiTableQuestions contains 22,033 questions. The questions were not designed by predefined templates but were hand crafted by users, demonstrating high linguistic variance. Compared to previous datasets on knowledge bases it covers nearly 4,000 unique column headers, containing far more relations than closed domain datasets and datasets for querying knowledge bases. Its questions cover a wide range of domains, requiring operations such as table lookup, aggregation, superlatives (argmax, argmin), arithmetic operations, joins and unions.\r\n\r\nSource: [Explaining Queries over Web Tables to Non-Experts](https://arxiv.org/abs/1808.04614)\r\nImage Source: [https://ppasupat.github.io/WikiTableQuestions/](https://ppasupat.github.io/WikiTableQuestions/)","description_withheld":null,"homepage":"https://ppasupat.github.io/WikiTableQuestions/","introduced_date":"2015-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/compositional-semantic-parsing-on-semi","title":"Compositional Semantic Parsing on Semi-Structured Tables","first_author":"Panupong Pasupat","url":null},"license":{"name":"CC-BY-SA-4.0","url":"https://github.com/ppasupat/WikiTableQuestions"},"modalities":[{"name":"Texts","url":"/datasets/modality/texts"},{"name":"Tabular","url":"/datasets/modality/tabular"}],"tasks":[{"name":"Question Answering","url":"/task/question-answering","datasets_with_task":"/datasets/task/question-answering"},{"name":"Semantic Parsing","url":"/task/semantic-parsing","datasets_with_task":"/datasets/task/semantic-parsing"}],"languages":[{"name":"English","url":"/datasets/language/english"}],"variants":["WikiTableQuestions"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/wiki_table_questions","frameworks":["tf","jax"]}],"num_papers_in_archive":79,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/semantic-parsing-on-wikitablequestions","task":"Semantic Parsing","dataset_variant":"WikiTableQuestions","rows":22,"metrics":["Accuracy (Test)","Accuracy (Dev)","Accuracy","Test Accuracy"],"first_row_in_archive_order":{"model":"ARTEMIS-DA","paper":"/paper/advanced-reasoning-and-transformation-engine","metrics":{"Accuracy (Test)":"80.8"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/question-answering-on-wikitablequestions","task":"Question Answering","dataset_variant":"WikiTableQuestions","rows":2,"metrics":["Accuracy","Accuracy (Test)"],"first_row_in_archive_order":{"model":"ChatGPT 3.5 SpatialFormat","paper":"/paper/lapdoc-layout-aware-prompting-for-documents","metrics":{"Accuracy":"47.7"},"code_links":[]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/advanced-reasoning-and-transformation-engine","title":"ARTEMIS-DA: An Advanced Reasoning and Transformation Engine for Multi-Step Insight Synthesis in Data Analytics","date":"2024-12-18","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/accurate-and-regret-aware-numerical-problem","title":"Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering","date":"2024-10-10","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/syntqa-synergistic-table-based-question","title":"SynTQA: Synergistic Table-based Question Answering via Mixture of Text-to-SQL and E2E TQA","date":"2024-09-25","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/normtab-improving-symbolic-reasoning-in-llms","title":"NormTab: Improving Symbolic Reasoning in LLMs Through Tabular Data Normalization","date":"2024-06-25","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/efficient-prompting-for-llm-based-generative","title":"Efficient Prompting for LLM-based Generative Internet of Things","date":"2024-06-14","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/tabsqlify-enhancing-reasoning-capabilities-of","title":"TabSQLify: Enhancing Reasoning Capabilities of LLMs Through Table Decomposition","date":"2024-04-15","rows_on_this_dataset":2,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":15,"samples_ran":7,"samples_unverified":8,"pointer_only_for_licence":15,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lapdoc-layout-aware-prompting-for-documents","title":"LAPDoc: Layout-Aware Prompting for Documents","date":"2024-02-15","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/cabinet-content-relevance-based-noise","title":"CABINET: Content Relevance based Noise Reduction for Table Question Answering","date":"2024-02-02","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":3,"samples_unverified":2,"pointer_only_for_licence":5,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/chain-of-table-evolving-tables-in-the","title":"Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding","date":"2024-01-09","rows_on_this_dataset":1,"code_links":2,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":8,"samples_ran":6,"samples_unverified":2,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/rethinking-tabular-data-understanding-with","title":"Rethinking Tabular Data Understanding with Large Language Models","date":"2023-12-27","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":10,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/lever-learning-to-verify-language-to-code","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","date":"2023-02-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":22,"samples_ran":6,"samples_unverified":16,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/large-language-models-are-versatile","title":"Large Language Models are Versatile Decomposers: Decompose Evidence and Questions for Table-based Reasoning","date":"2023-01-31","rows_on_this_dataset":1,"code_links":2,"syntology":null},{"paper":"/paper/reastap-injecting-table-reasoning-skills","title":"ReasTAP: Injecting Table Reasoning Skills During Pre-training via Synthetic Reasoning Examples","date":"2022-10-22","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":11,"samples_ran":0,"samples_unverified":11,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/binding-language-models-in-symbolic-languages","title":"Binding Language Models in Symbolic Languages","date":"2022-10-06","rows_on_this_dataset":1,"code_links":4,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/omnitab-pretraining-with-natural-and-1","title":"OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering","date":"2022-07-08","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":2,"samples_ran":1,"samples_unverified":1,"pointer_only_for_licence":2,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/unifiedskg-unifying-and-multi-tasking","title":"UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models","date":"2022-01-16","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":5,"samples_ran":1,"samples_unverified":4,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/tapex-table-pre-training-via-learning-a","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","date":"2021-07-16","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/tabert-pretraining-for-joint-understanding-of","title":"TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data","date":"2020-05-17","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/tapas-weakly-supervised-table-parsing-via-pre","title":"TAPAS: Weakly Supervised Table Parsing via Pre-training","date":"2020-04-05","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":14,"samples_ran":0,"samples_unverified":14,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/learning-semantic-parsers-from-denotations","title":"Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs","date":"2019-09-09","rows_on_this_dataset":1,"code_links":1,"syntology":null}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":10,"samples_harvested":96,"samples_ran":36,"samples_unverified":60,"pointer_only_for_licence":22,"papers_with_no_sample_that_ran":2,"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."}