2021/07/16 by Qian Liu, Bei Chen, Liu, Qian +12 · 43 citations
Computer Science · #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling #Web Data Mining and Analysis #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.2107.07653
ICLR 2022 camera ready version
openalex publication_date 2021/07/16 · arxiv created 2022/03/14 · arxiv updated 2022/03/15 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Recent progress in language model pre-training has achieved a great success via leveraging large-scale unstructured textual data. However, it is still a challenge to apply pre-training on structured tabular data due to the absence of large-scale high-quality tabular data. In this paper, we propose TAPEX to show that table pre-training can be achieved by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries and their execution outputs. TAPEX addresses the data scarcity challenge via guiding the language model to mimic a SQL executor on the diverse, large-scale and high-quality synthetic corpus. We evaluate TAPEX on four benchmark datasets. Experimental results demonstrate that TAPEX outperforms previous table pre-training approaches by a large margin and achieves new state-of-the-art results on all of them. This includes the improvements on the weakly-supervised WikiSQL denotation accuracy to 89.5% (+2.3%), the WikiTableQuestions denotation accuracy to 57.5% (+4.8%), the SQA denotation accuracy to 74.5% (+3.5%), and the TabFact accuracy to 84.2% (+3.2%). To our knowledge, this is the first work to exploit table pre-training via synthetic executable programs and to achieve new state-of-the-art results on various downstream tasks. Our code can be found at https://github.com/microsoft/Table-Pretraining.