IncSQL: Training Incremental Text-to-SQL Parsers with Non-Deterministic Oracles

Abstract

We present a sequence-to-action parsing approach for the natural language to SQL task that incrementally fills the slots of a SQL query with feasible actions from a pre-defined inventory. To account for the fact that typically there are multiple correct SQL queries with the same or very similar semantics, we draw inspiration from syntactic parsing techniques and propose to train our sequence-to-action models with non-deterministic oracles. We evaluate our models on the WikiSQL dataset and achieve an execution accuracy of 83.7% on the test set, a 2.1% absolute improvement over the models trained with traditional static oracles assuming a single correct target SQL query. When further combined with the execution-guided decoding strategy, our model sets a new state-of-the-art performance at an execution accuracy of 87.1%.

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• 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
• Effective Approaches to Attention-based Neural Machine Translation
• The Natural Language Decathlon: Multitask Learning as Question Answering
• SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learning
• Lambda Dependency-Based Compositional Semantics
• Language to Logical Form with Neural Attention
• A Syntactic Neural Model for General-Purpose Code Generation
• Learning Dependency-Based Compositional Semantics
• Span-Based Constituency Parsing with a Structure-Label System and Provably Optimal Dynamic Oracles

Cited by in corpus (18)

• A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
• X-SQL: reinforce schema representation with context
• 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
• CrossData: Leveraging Text-Data Connections for Authoring Data Documents
• Introduction to Neural Network based Approaches for Question Answering over Knowledge Graphs
• Natural Language Interfaces to Data
• TaBERT: Pretraining for Joint Understanding of Textual and Tabular Data
• Encoding Database Schemas with Relation-Aware Self-Attention for Text-to-SQL Parsers
• Text-to-SQL Generation for Question Answering on Electronic Medical Records
• Neural Semantic Parsing in Low-Resource Settings with Back-Translation and Meta-Learning
• Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs
• Zero-shot Text-to-SQL Learning with Auxiliary Task
• Self-supervised Text-to-SQL Learning with Header Alignment Training
• Translating Natural Language to SQL using Pointer-Generator Networks and How Decoding Order Matters
• Syntactic Question Abstraction and Retrieval for Data-Scarce Semantic Parsing