Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
This addresses the challenge of complex text-to-SQL conversion for database users, representing a strong incremental advance in a specific domain.
The paper tackles the problem of generating SQL queries from natural language in cross-domain databases by introducing IRNet, which uses an intermediate representation to bridge intent mismatches and out-of-domain words, achieving 46.7% accuracy on the Spider benchmark with a 19.5% absolute improvement over previous state-of-the-art.
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% accuracy, obtaining 19.5% absolute improvement over previous state-of-the-art approaches. At the time of writing, IRNet achieves the first position on the Spider leaderboard.