GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing

This repository contains code for the ICLR 2021 paper "GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing".

Code and running commands for running experiments can be found in each subdirectory.

If you use GraPPa in your work, please cite it as follows:

@inproceedings{yu2021grappa,
  title={GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing},
  author={Tao Yu and Chien-Sheng Wu and Xi Victoria Lin and Bailin Wang and Yi Chern Tan and Xinyi Yang and Dragomir Radev and Richard Socher and Caiming Xiong},
  booktitle={International Conference on Learning Representations},
  year={2021},
  url={https://arxiv.org/abs/2009.13845}
}

All datasets in this repository are released under the CC BY 4.0 International license. All source files in this repository are released under the Apache 2.0 license.

lifengjin/grappa

GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing