ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser

TL;DR

ShadowGNN is a novel graph-based neural network architecture designed to improve the generalization of Text-to-SQL models across unseen schemas by leveraging abstract schema representations and relation-aware transformers, outperforming state-of-the-art methods especially with limited data.

Contribution

The paper introduces ShadowGNN, a new architecture that processes schemas at abstract and semantic levels to enhance cross-domain Text-to-SQL parsing.

Findings

Outperforms state-of-the-art models on the Spider benchmark.

Achieves over 5% performance gain with only 10% training data.

Demonstrates strong generalization to unseen schemas.

Abstract

Given a database schema, Text-to-SQL aims to translate a natural language question into the corresponding SQL query. Under the setup of cross-domain, traditional semantic parsing models struggle to adapt to unseen database schemas. To improve the model generalization capability for rare and unseen schemas, we propose a new architecture, ShadowGNN, which processes schemas at abstract and semantic levels. By ignoring names of semantic items in databases, abstract schemas are exploited in a well-designed graph projection neural network to obtain delexicalized representation of question and schema. Based on the domain-independent representations, a relation-aware transformer is utilized to further extract logical linking between question and schema. Finally, a SQL decoder with context-free grammar is applied. On the challenging Text-to-SQL benchmark Spider, empirical results show that ShadowGNN outperforms state-of-the-art models. When the annotated data is extremely limited (only 10\% training set), ShadowGNN gets over absolute 5\% performance gain, which shows its powerful generalization ability. Our implementation will be open-sourced at \url{https://github.com/WowCZ/shadowgnn}.