Semantic Parsing with Syntax- and Table-Aware SQL Generation

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%.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract
No code implementations yet. Submit your code now

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Code Generation WikiSQL STAMP (Sun et al., 2018)+ Execution Accuracy 74.4 # 5
Exact Match Accuracy 60.7 # 6
Code Generation WikiSQL STAMP+RL (Sun et al., 2018)+ Execution Accuracy 74.6 # 4
Exact Match Accuracy 61.0 # 5


No methods listed for this paper. Add relevant methods here