Methods › Natural Language Processing › Transformers › TAPEX
Table Pre-training via Execution
TAPEX
Introduced by Qian Liu et al. in TAPEX: Table Pre-training via Learning a Neural SQL Executor
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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.
Papers archive 2025-07-28
3 shown of 3, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
QATCH: Benchmarking SQL-centric tasks with Table Representation Learning Models on Your Data 26 Sep 2023 · 1 repository
-
TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data 25 May 2022 · 1 repository · arXiv:2205.12682
-
TAPEX: Table Pre-training via Learning a Neural SQL Executor 16 Jul 2021 · 4 repositories · arXiv:2107.07653
Tasks archive 2025-07-28
5 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Language Modeling | 1 |
| Language Modelling | 1 |
| Question Answering | 1 |
| Semantic Parsing | 1 |
| Table-based Fact Verification | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections