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

Citations Over TimeTop 1% of 2019 papers

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 recentlyreleased 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%.

Related Papers

• → Incremental scannerless generalized LR parsing(2019)5 cited
• → The fitted parse(1983)28 cited
• → An Extended Theory of Head-Driven Parsing(1994)5 cited
• A New Technique for DXF File Parsing Based on Spirit Parser Framework(2012)
• Computational parsing : syntactic analysis - semanitic analysis - semantic interpretation - parsing algorithms - parsing strategies : bibliography(1994)