Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation

05/20/2019
by   Jiaqi Guo, et al.
0

We present a neural approach called IRNet for complex and cross-domain Text-to-SQL. IRNet aims to address two challenges: 1) the mismatch between intents expressed in natural language (NL) and the implementation details in SQL; 2) the challenge in predicting columns caused by the large number of out-of-domain words. Instead of end-to-end synthesizing a SQL query, IRNet decomposes the synthesis process into three phases. In the first phase, IRNet performs a schema linking over a question and a database schema. Then, IRNet adopts a grammar-based neural model to synthesize a SemQL query which is an intermediate representation that we design to bridge NL and SQL. Finally, IRNet deterministically infers a SQL query from the synthesized SemQL query with domain knowledge. On the challenging Text-to-SQL benchmark Spider, IRNet achieves 46.7 state-of-the-art approaches. At the time of writing, IRNet achieves the first position on the Spider leaderboard.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset