A Tale of Two Linkings: Dynamically Gating between Schema Linking and Structural Linking for Text-to-SQL Parsing
This addresses a key bottleneck in semantic parsing for database query generation, though it is incremental as it builds on existing graph neural network parsers.
The paper tackles the challenge of selecting correct database entities in Text-to-SQL parsing by dynamically gating between schema linking and structural linking, achieving substantial gains in parsing accuracy on the Spider dataset.
In Text-to-SQL semantic parsing, selecting the correct entities (tables and columns) for the generated SQL query is both crucial and challenging; the parser is required to connect the natural language (NL) question and the SQL query to the structured knowledge in the database. We formulate two linking processes to address this challenge: schema linking which links explicit NL mentions to the database and structural linking which links the entities in the output SQL with their structural relationships in the database schema. Intuitively, the effectiveness of these two linking processes changes based on the entity being generated, thus we propose to dynamically choose between them using a gating mechanism. Integrating the proposed method with two graph neural network-based semantic parsers together with BERT representations demonstrates substantial gains in parsing accuracy on the challenging Spider dataset. Analyses show that our proposed method helps to enhance the structure of the model output when generating complicated SQL queries and offers more explainable predictions.