TAPEX: Table Pre-training via Learning a Neural SQL Executor

By Qian Liu, Jiaqi Guo, Zeqi Lin, Jian-Guang Lou. 2021

368 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Information Systems, Retrieval-Augmented Generation, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

  1. Jianfeng Gao
  2. Luke S. Zettlemoyer
  3. Percy Liang
  4. Caiming Xiong
  5. Mohit Bansal
  6. Graham Neubig
  7. Richard Socher
  8. Noah A. Smith

In Information Systems

  1. Wenhu Chen
  2. Wen-tau Yih
  3. Dragomir R. Radev
  4. Xi Victoria Lin
  5. Tao Yu
  6. Caiming Xiong
  7. Jianfeng Gao
  8. Ji-rong Wen

In Retrieval-Augmented Generation

  1. Wenhu Chen
  2. Jianfeng Gao
  3. Michel Galley
  4. Luke S. Zettlemoyer
  5. Weizhu Chen
  6. Wen-tau Yih
  7. Noah A. Smith
  8. Ji-rong Wen

In Natural Language Processing

  1. Jianfeng Gao
  2. Caiming Xiong
  3. Luke S. Zettlemoyer
  4. Graham Neubig
  5. Percy Liang
  6. Richard Socher
  7. Wen-tau Yih
  8. Mohit Bansal

Citations in the corpus