SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL

TL;DR

SADGA introduces a structure-aware dual graph aggregation network that enhances cross-domain Text-to-SQL translation by unifying encoding and improving question-schema mapping, achieving competitive results on the Spider benchmark.

Contribution

The paper proposes a novel structure-aware dual graph aggregation network that unifies encoding of questions and schemas and improves cross-domain generalization in Text-to-SQL.

Findings

Achieved 3rd place on the Spider benchmark.

Demonstrated improved generalization to unseen schemas.

Validated effectiveness through empirical studies.

Abstract

The Text-to-SQL task, aiming to translate the natural language of the questions into SQL queries, has drawn much attention recently. One of the most challenging problems of Text-to-SQL is how to generalize the trained model to the unseen database schemas, also known as the cross-domain Text-to-SQL task. The key lies in the generalizability of (i) the encoding method to model the question and the database schema and (ii) the question-schema linking method to learn the mapping between words in the question and tables/columns in the database schema. Focusing on the above two key issues, we propose a Structure-Aware Dual Graph Aggregation Network (SADGA) for cross-domain Text-to-SQL. In SADGA, we adopt the graph structure to provide a unified encoding model for both the natural language question and database schema. Based on the proposed unified modeling, we further devise a structure-aware aggregation method to learn the mapping between the question-graph and schema-graph. The structure-aware aggregation method is featured with Global Graph Linking, Local Graph Linking, and Dual-Graph Aggregation Mechanism. We not only study the performance of our proposal empirically but also achieved 3rd place on the challenging Text-to-SQL benchmark Spider at the time of writing.