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

TL;DR

This paper introduces a zero-shot text-to-SQL method that leverages table content and meta-learning to improve query generation for unseen tables without extra manual annotations, showing significant experimental gains.

Contribution

It proposes a novel content-based model combined with a meta-learning strategy to enhance zero-shot table understanding in text-to-SQL tasks without additional annotations.

Findings

Significant improvements on WikiSQL and ESQL datasets.

Enhanced zero-shot performance on unseen tables.

Competitive results with larger pre-trained models.

Abstract

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.