Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning


  • Yongrui Chen Southeast University
  • Xinnan Guo Southeast University
  • Chaojie Wang Alibaba Group
  • Jian Qiu Alibaba Group
  • Guilin Qi Southeast University
  • Meng Wang Southeast University
  • Huiying Li Southeast University




Intelligent Query Processing


Single-table text-to-SQL aims to transform a natural language question into a SQL query according to one single table. Recent work has made promising progress on this task by pre-trained language models and a multi-submodule framework. However, zero-shot table, that is, the invisible table in the training set, is currently the most critical bottleneck restricting the application of existing approaches to real-world scenarios. Although some work has utilized auxiliary tasks to help handle zero-shot tables, expensive extra manual annotation limits their practicality. In this paper, we propose a new approach for the zero-shot text-to-SQL task which does not rely on any additional manual annotations. Our approach consists of two parts. First, we propose a new model that leverages the abundant information of table content to help establish the mapping between questions and zero-shot tables. Further, we propose a simple but efficient meta-learning strategy to train our model. The strategy utilizes the two-step gradient update to force the model to learn a generalization ability towards zero-shot tables. We conduct extensive experiments on a public open-domain text-to-SQL dataset WikiSQL and a domain-specific dataset ESQL. Compared to existing approaches using the same pre-trained model, our approach achieves significant improvements on both datasets. Compared to the larger pre-trained model and the tabular-specific pre-trained model, our approach is still competitive. More importantly, on the zero-shot subsets of both the datasets, our approach further increases the improvements.




How to Cite

Chen, Y., Guo, X., Wang, C., Qiu, J., Qi, G., Wang, M., & Li, H. (2021). Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 35(5), 3992-4000. https://doi.org/10.1609/aaai.v35i5.16519



AAAI Technical Track on Data Mining and Knowledge Management