DuoRAT: Towards Simpler Text-to-SQL Models

Recent neural text-to-SQL models can effectively translate natural language questions to corresponding SQL queries on unseen databases. Working mostly on the Spider dataset, researchers have proposed increasingly sophisticated solutions to the problem. Contrary to this trend, in this paper we focus on simplifications. We begin by building DuoRAT, a re-implementation of the state-of-the-art RAT-SQL model that unlike RAT-SQL is using only relation-aware or vanilla transformers as the building blocks. We perform several ablation experiments using DuoRAT as the baseline model. Our experiments confirm the usefulness of some techniques and point out the redundancy of others, including structural SQL features and features that link the question with the schema.

• Publication year

  2020

• Venue

  North American Chapter of the Association for Computational Linguistics

• Publication date

  2020-10-21

• Fields of study

  Computer Science

• Identifiers
  DOI 10.18653/v1/2021.naacl-main.103arXiv 2010.11119
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Exploring Unexplored Generalization Challenges for Cross-Database Semantic Parsing

  2020influential reference
• RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases

  2020cited by this paper
• Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-ranker

  2020cited by this paper
• Semantic Evaluation for Text-to-SQL with Distilled Test Suite

  2020cited by this paper
• Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing

  2019cited by this paper
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

  2019cited by this paper
• RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers

  2019influential reference
• Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions

  2019cited by this paper
• Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation

  2019influential reference
• BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension

  2019cited by this paper
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019influential reference
• Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task

  2018influential reference
• Self-Attention with Relative Position Representations

  2018cited by this paper
• TypeSQL: Knowledge-Based Type-Aware Neural Text-to-SQL Generation

  2018influential reference
• Improving Text-to-SQL Evaluation Methodology

  2018cited by this paper
• TRANX: A Transition-based Neural Abstract Syntax Parser for Semantic Parsing and Code Generation

  2018cited by this paper
• Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

  2017influential reference
• A Corpus of Natural Language for Visual Reasoning

  2017cited by this paper
• Attention is All you Need

  2017cited by this paper
• SQLizer: query synthesis from natural language

  2017cited by this paper
• Adam: A Method for Stochastic Optimization

  2014cited by this paper
• Constructing an Interactive Natural Language Interface for Relational Databases

  2014cited by this paper
• Automated Construction of Database Interfaces: Intergrating Statistical and Relational Learning for Semantic Parsing

  2000cited by this paper
• The Zephyr Abstract Syntax Description Language

  1997cited by this paper
• Learning to Parse Database Queries Using Inductive Logic Programming

  1996cited by this paper

• Addressing Specific and Complex Scenarios in Semantic Parsing

  2025cites this paper
• ConDA: state-based data augmentation for context-dependent text-to-SQL

  2024cites this paper
• Mixed Node and Edge GraphSAGE Based Schema Encoding for Text-to-SQL

  2024cites this paper
• RGISQL: Integrating Refined Grammatical Information into Relational Graph Neural Network for Text-to-SQL Task

  2024cites this paper
• Structured Case-based Reasoning for Inference-time Adaptation of Text-to-SQL parsers

  2023influential citation
• Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness

  2023cites this paper
• On Modern Text-to-SQL Semantic Parsing Methodologies for Natural Language Interface to Databases: A Comparative Study

  2023cites this paper
• QURG: Question Rewriting Guided Context-Dependent Text-to-SQL Semantic Parsing

  2023influential citation
• Benchmarking and Improving Text-to-SQL Generation under Ambiguity

  2023influential citation
• ASTormer: An AST Structure-aware Transformer Decoder for Text-to-SQL

  2023cites this paper
• SUQL: Conversational Search over Structured and Unstructured Data with Large Language Models

  2023cites this paper
• TrojanSQL: SQL Injection against Natural Language Interface to Database

  2023influential citation
• dIR - Discrete Information Retrieval: Conversational Search over Unstructured (and Structured) Data with Large Language Models

  2023cites this paper
• A Copy Mechanism for Handling Knowledge Base Elements in SPARQL Neural Machine Translation

  2022cites this paper
• Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation

  2022cites this paper
• Non-Programmers Can Label Programs Indirectly via Active Examples: A Case Study with Text-to-SQL

  2022cites this paper
• Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Models

  2022cites this paper
• Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect

  2022cites this paper
• SeSQL: Yet Another Large-scale Session-level Chinese Text-to-SQL Dataset

  2022cites this paper
• Diverse Parallel Data Synthesis for Cross-Database Adaptation of Text-to-SQL Parsers

  2022cites this paper
• Active Programming by Example with a Natural Language Prior

  2022influential citation
• Faster and Better Grammar-based Text-to-SQL Parsing via Clause-level Parallel Decoding and Alignment Loss

  2022cites this paper
• Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL

  2021cites this paper
• MT-Teql: Evaluating and Augmenting Neural NLIDB on Real-world Linguistic and Schema Variations

  2021influential citation
• NL-EDIT: Correcting Semantic Parse Errors through Natural Language Interaction

  2021influential citation
• SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL

  2021cites this paper
• The Power of Prompt Tuning for Low-Resource Semantic Parsing

  2021cites this paper
• Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

  2020cites this paper