{"url":"/method/tapex","slug":"tapex","name":"TAPEX","full_name":"Table Pre-training via Execution","full_name_withheld":false,"description_markdown":"TAPEX is a conceptually simple and empirically powerful pre-training approach to empower existing models with table reasoning skills. TAPEX realizes table pre-training by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesising executable SQL queries.","description_state":"present","introduced_year":null,"introduced_by":{"title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","paper":"/paper/tapex-table-pre-training-via-learning-a","first_author":"Qian Liu","n_authors":7,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/tapex-table-pre-training-via-learning-a"},"source":{"url":"https://arxiv.org/abs/2107.07653v3","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","url_on_a_paper_host":true},"code_snippet_url":"https://github.com/microsoft/Table-Pretraining","code_snippet_url_on_a_code_host":true,"categories":[{"area":"Natural Language Processing","area_id":"natural-language-processing","collection":"Transformers","url":"/methods/category/transformers","pwc_aliases":[]}],"n_papers_tagged":3,"archive_num_papers":3,"papers_newest_first":[{"paper":"/paper/qatch-benchmarking-sql-centric-tasks-with","title":"QATCH: Benchmarking SQL-centric tasks with Table Representation Learning Models on Your Data","date":"2023-09-26","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/tacube-pre-computing-data-cubes-for-answering","title":"TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data","date":"2022-05-25","arxiv_id":"2205.12682","n_code_links":1,"syntology":null},{"paper":"/paper/tapex-table-pre-training-via-learning-a","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","date":"2021-07-16","arxiv_id":"2107.07653","n_code_links":4,"syntology":null}],"papers_shown":3,"tasks":[{"task":"/task/language-modeling","name":"Language Modeling","papers":1},{"task":"/task/language-modelling","name":"Language Modelling","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/semantic-parsing","name":"Semantic Parsing","papers":1},{"task":"/task/table-based-fact-verification","name":"Table-based Fact Verification","papers":1}],"tasks_shown":5,"n_tasks":5,"usage_by_year":[{"year":"2021","papers":1},{"year":"2022","papers":1},{"year":"2023","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/tapex"},"syntology_read_at":"2026-09-24T18:15:14+00:00"}