Abstract
Most deep learning approaches for text-to-SQL generation are limited to the WikiSQL dataset, which only supports very simple queries over a single table. We focus on the Spider dataset, a complex and cross-domain text-to-SQL task, which includes complex queries over multiple tables. In this paper, we propose a SQL clause-wise decoding neural architecture with a self-attention based database schema encoder to address Spider task. Each of the clause-specific decoders consists of a set of sub-modules, which is defined by the syntax of each clause. Additionally, our model works recursively to support nested queries. The experimental result shows that our model outperforms the previous state-of-the-art model by 9.8% in the exact matching accuracy on the Spider dev dataset. In addition, we show that our model is significantly more effective to predict complex and nested queries than previous works.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1904.08835