Semantic Parsing with Syntax- and Table-Aware SQL Generation
arXiv:1804.08338
Abstract
We present a generative model to map natural language questions into SQL queries. Existing neural network based approaches typically generate a SQL query word-by-word, however, a large portion of the generated results are incorrect or not executable due to the mismatch between question words and table contents. Our approach addresses this problem by considering the structure of table and the syntax of SQL language. The quality of the generated SQL query is significantly improved through (1) learning to replicate content from column names, cells or SQL keywords; and (2) improving the generation of WHERE clause by leveraging the column-cell relation. Experiments are conducted on WikiSQL, a recently released dataset with the largest question-SQL pairs. Our approach significantly improves the state-of-the-art execution accuracy from 69.0% to 74.4%.
References in corpus (20)
- Sequence to Sequence Learning with Neural Networks
- 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
- Language to Logical Form with Neural Attention
- Compositional Semantic Parsing on Semi-Structured Tables
- A Syntactic Neural Model for General-Purpose Code Generation
- Learning to Reason: End-to-End Module Networks for Visual Question Answering
- Reinforcement Learning Neural Turing Machines - Revised
- Learning Dependency-Based Compositional Semantics
- Pointing the Unknown Words
- A Joint Many-Task Model: Growing a Neural Network for Multiple NLP Tasks
- From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood
- Abstract Syntax Networks for Code Generation and Semantic Parsing
- Neural Enquirer: Learning to Query Tables with Natural Language
- Type- and Content-Driven Synthesis of SQL Queries from Natural Language
- Simpler Context-Dependent Logical Forms via Model Projections
- Inferring Logical Forms From Denotations
- Bidirectional Attention for SQL Generation
Cited by in corpus (5)
- Deep Learning-based Software Engineering: Progress, Challenges, and Opportunities
- TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation
- Question Generation from SQL Queries Improves Neural Semantic Parsing
- A Hybrid Semantic Parsing Approach for Tabular Data Analysis
- Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation