Grammar-based Neural Text-to-SQL Generation
This work improves text-to-SQL generation for database querying, though it is incremental as it adapts existing grammar-based methods to handle SQL complexities.
The paper tackled the problem of generating SQL queries from natural language by addressing the lack of hierarchical grammar-based decoding in neural models, resulting in a 14-18% relative reduction in error on ATIS and Spider datasets.
The sequence-to-sequence paradigm employed by neural text-to-SQL models typically performs token-level decoding and does not consider generating SQL hierarchically from a grammar. Grammar-based decoding has shown significant improvements for other semantic parsing tasks, but SQL and other general programming languages have complexities not present in logical formalisms that make writing hierarchical grammars difficult. We introduce techniques to handle these complexities, showing how to construct a schema-dependent grammar with minimal over-generation. We analyze these techniques on ATIS and Spider, two challenging text-to-SQL datasets, demonstrating that they yield 14--18\% relative reductions in error.