Grammar-based Neural Text-to-SQL Generation
arXiv:1905.13326
Abstract
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.
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
- SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
- Incorporating Copying Mechanism in Sequence-to-Sequence Learning
- Improving Text-to-SQL Evaluation Methodology
Cited by in corpus (11)
- Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
- Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker
- Global Reasoning over Database Structures for Text-to-SQL Parsing
- Photon: A Robust Cross-Domain Text-to-SQL System
- Self-supervised Text-to-SQL Learning with Header Alignment Training
- A Pilot Study for Chinese SQL Semantic Parsing
- CLTR: An End-to-End, Transformer-Based System for Cell Level Table Retrieval and Table Question Answering
- ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser
- ShopTalk: A System for Conversational Faceted Search
- Awakening Latent Grounding from Pretrained Language Models for Semantic Parsing
- Few-Shot Semantic Parsing for New Predicates