Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing

Abstract

Research on parsing language to SQL has largely ignored the structure of the database (DB) schema, either because the DB was very simple, or because it was observed at both training and test time. In Spider, a recently-released text-to-SQL dataset, new and complex DBs are given at test time, and so the structure of the DB schema can inform the predicted SQL query. In this paper, we present an encoder-decoder semantic parser, where the structure of the DB schema is encoded with a graph neural network, and this representation is later used at both encoding and decoding time. Evaluation shows that encoding the schema structure improves our parser accuracy from 33.8% to 39.4%, dramatically above the current state of the art, which is at 19.7%.

Accepted as a short paper at ACL 2019

References in corpus (5)

• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• Improving Text-to-SQL Evaluation Methodology
• Modeling Semantics with Gated Graph Neural Networks for Knowledge Base Question Answering
• Grammar-based Neural Text-to-SQL Generation

Cited by in corpus (19)

• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• Graph Neural Networks for Natural Language Processing: A Survey
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
• CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases
• Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
• TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
• Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker
• Semantic Evaluation for Text-to-SQL with Distilled Test Suites
• Global Reasoning over Database Structures for Text-to-SQL Parsing
• DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networks
• Text-to-SQL Generation for Question Answering on Electronic Medical Records
• A Pilot Study for Chinese SQL Semantic Parsing
• Improving the Long-Range Performance of Gated Graph Neural Networks
• ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser
• Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions
• End-to-End Cross-Domain Text-to-SQL Semantic Parsing with Auxiliary Task
• Lightweight, Dynamic Graph Convolutional Networks for AMR-to-Text Generation
• A Globally Normalized Neural Model for Semantic Parsing
• Generation of complex database queries and API calls from natural language utterances