Bidirectional Attention for SQL Generation
This addresses a long-standing open problem in database querying, but it is incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of generating SQL queries from natural language by modeling interactions between table columns and questions, achieving state-of-the-art results on the WikiSQL dataset.
Generating structural query language (SQL) queries from natural language is a long-standing open problem. Answering a natural language question about a database table requires modeling complex interactions between the columns of the table and the question. In this paper, we apply the synthesizing approach to solve this problem. Based on the structure of SQL queries, we break down the model to three sub-modules and design specific deep neural networks for each of them. Taking inspiration from the similar machine reading task, we employ the bidirectional attention mechanisms and character-level embedding with convolutional neural networks (CNNs) to improve the result. Experimental evaluations show that our model achieves the state-of-the-art results in WikiSQL dataset.