Semantic Parsing with Syntax- and Table-Aware SQL Generation
This work addresses the challenge of semantic parsing for database querying, offering an incremental improvement over existing neural methods.
The paper tackles the problem of generating executable SQL queries from natural language questions by incorporating table structure and SQL syntax, improving execution accuracy from 69.0% to 74.4% on the WikiSQL dataset.
We present a generative model to map natural language questions into SQL queries. Existing neural network based approaches typically generate a SQL query word-by-word, however, a large portion of the generated results are incorrect or not executable due to the mismatch between question words and table contents. Our approach addresses this problem by considering the structure of table and the syntax of SQL language. The quality of the generated SQL query is significantly improved through (1) learning to replicate content from column names, cells or SQL keywords; and (2) improving the generation of WHERE clause by leveraging the column-cell relation. Experiments are conducted on WikiSQL, a recently released dataset with the largest question-SQL pairs. Our approach significantly improves the state-of-the-art execution accuracy from 69.0% to 74.4%.