Content Enhanced BERT-based Text-to-SQL Generation

Abstract

We present a simple methods to leverage the table content for the BERT-based model to solve the text-to-SQL problem. Based on the observation that some of the table content match some words in question string and some of the table header also match some words in question string, we encode two addition feature vector for the deep model. Our methods also benefit the model inference in testing time as the tables are almost the same in training and testing time. We test our model on the WikiSQL dataset and outperform the BERT-based baseline by 3.7% in logic form and 3.7% in execution accuracy and achieve state-of-the-art.

arXiv commentworking in progress

References in corpus (2)

• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning
• A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualization

Cited by in corpus (7)

• GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing
• Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing
• ColloQL: Robust Cross-Domain Text-to-SQL Over Search Queries
• Query Understanding for Natural Language Enterprise Search
• CLTR: An End-to-End, Transformer-Based System for Cell Level Table Retrieval and Table Question Answering
• Turing: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface
• Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering