Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing

Abstract

We present BRIDGE, a powerful sequential architecture for modeling dependencies between natural language questions and relational databases in cross-DB semantic parsing. BRIDGE represents the question and DB schema in a tagged sequence where a subset of the fields are augmented with cell values mentioned in the question. The hybrid sequence is encoded by BERT with minimal subsequent layers and the text-DB contextualization is realized via the fine-tuned deep attention in BERT. Combined with a pointer-generator decoder with schema-consistency driven search space pruning, BRIDGE attained state-of-the-art performance on popular cross-DB text-to-SQL benchmarks, Spider (71.1\% dev, 67.5\% test with ensemble model) and WikiSQL (92.6\% dev, 91.9\% test). Our analysis shows that BRIDGE effectively captures the desired cross-modal dependencies and has the potential to generalize to more text-DB related tasks. Our implementation is available at \url{https://github.com/salesforce/TabularSemanticParsing}.

EMNLP Findings 2020 long paper extended; 23 pages

References in corpus (12)

• Longformer: The Long-Document Transformer
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization
• Memory Augmented Policy Optimization for Program Synthesis and Semantic Parsing
• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• X-SQL: reinforce schema representation with context
• Hybrid Ranking Network for Text-to-SQL
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions
• Content Enhanced BERT-based Text-to-SQL Generation
• SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Task
• Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker

Cited by in corpus (7)

• Text-to-OverpassQL: A Natural Language Interface for Complex Geodata Querying of OpenStreetMap
• GP: Context-free Grammar Pre-training for Text-to-SQL Parsers
• Ember: No-Code Context Enrichment via Similarity-Based Keyless Joins
• End-to-End Cross-Domain Text-to-SQL Semantic Parsing with Auxiliary Task
• Learning to Synthesize Data for Semantic Parsing
• mRAT-SQL+GAP:A Portuguese Text-to-SQL Transformer
• Turing: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface