mlsanityData to 14 Oct 2026

Natural SQL: Making SQL Easier to Infer from Natural Language Specifications

arXiv 2109.05153 ↗First posted 11 Sep 2021cs.CLcited by 68

Not on the map. Why?

Abstract (arXiv)

Addressing the mismatch between natural language descriptions and the corresponding SQL queries is a key challenge for text-to-SQL translation. To bridge this gap, we propose an SQL intermediate representation (IR) called Natural SQL (NatSQL). Specifically, NatSQL preserves the core functionalities of SQL, while it simplifies the queries as follows: (1) dispensing with operators and keywords such as GROUP BY, HAVING, FROM, JOIN ON, which are usually hard to find counterparts for in the text descriptions; (2) removing the need for nested subqueries and set operators; and (3) making schema linking easier by reducing the required number of schema items. On Spider, a challenging text-to-SQL benchmark that contains complex and nested SQL queries, we demonstrate that NatSQL outperforms other IRs, and significantly improves the performance of several previous SOTA models. Furthermore, for existing models that do not support executable SQL generation, NatSQL easily enables them to generate executable SQL queries, and achieves the new state-of-the-art execution accuracy.

Key facts. Cited by 68 papers in the map (data through 14 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 11 Sep 2021.

Builds on

18 of 32 references.

References · 18

  1. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  2. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  3. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  4. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
  5. 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
  6. 2018Improving Text-to-SQL Evaluation Methodologycited by 135
  7. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  8. 2018Coarse-to-Fine Decoding for Neural Semantic Parsingcited by 110
  9. 2017Learning a Neural Semantic Parser from User Feedbackcited by 99
  10. 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
  11. 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
  12. 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
6 more
  1. 2018SyntaxSQLNet: Syntax Tree Networks for Complex and Cross-DomainText-to-SQL Taskcited by 74
  2. 2019Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsingcited by 74
  3. 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
  4. 2021Unlocking Compositional Generalization in Pre-trained Models Using Intermediate Representationscited by 55
  5. 2018Robust Text-to-SQL Generation with Execution-Guided Decodingcited by 52
  6. 2019Global Reasoning over Database Structures for Text-to-SQL Parsingcited by 43

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 9; 2023: 18; 2024: 17; 2025: 13; 2026: 11.

68 papers.

Sort:

By area:

  1. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
  2. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
  3. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  4. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  5. 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
  6. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 58
  7. 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
  8. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 50
  9. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  10. 2023ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systemscited by 45
  11. 2024FinSQL: Model-Agnostic LLMs-based Text-to-SQL Framework for Financial Analysiscited by 36
  12. 2023Benchmarking and Improving Text-to-SQL Generation under Ambiguitycited by 34
38 more
  1. 2024PURPLE: Making a Large Language Model a Better SQL Writercited by 34
  2. 2022Importance of Synthesizing High-quality Data for Text-to-SQL Parsingcited by 28
  3. 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
  4. 2022HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsingcited by 26
  5. 2023Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniquescited by 24
  6. 2023Text-to-SQL Error Correction with Language Models of Codecited by 21
  7. 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 20
  8. 2024Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translationcited by 17
  9. 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 17
  10. 2022Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignmentcited by 16
  11. 2023Semantic Decomposition of Question and SQL for Text-to-SQL Parsingcited by 14
  12. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
  13. 2023Error Detection for Text-to-SQL Semantic Parsingcited by 12
  14. 2024Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queriescited by 12
  15. 2024SQL-to-Schema Enhances Schema Linking in Text-to-SQLcited by 12
  16. 2025ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialectscited by 12
  17. 2023Knowledge Graphs in Practice: Characterizing their Users, Challenges, and Visualization Opportunitiescited by 9
  18. 2022NL2INTERFACE: Interactive Visualization Interface Generation from Natural Language Queriescited by 8
  19. 2022T5QL: Taming language models for SQL generationcited by 8
  20. 2024Grounding Natural Language to SQL Translation with Data-Based Self-Explanationscited by 8
  21. 2022Towards Generalizable and Robust Text-to-SQL Parsingcited by 7
  22. 2023Exploring Equation as a Better Intermediate Meaning Representation for Numerical Reasoningcited by 7
  23. 2025Are Your LLM-based Text-to-SQL Models Secure? Exploring SQL Injection via Backdoor Attackscited by 6
  24. 2024Improving Generalization in Semantic Parsing by Increasing Natural Language Variationcited by 4
  25. 2026FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agentscited by 4
  26. 2022Cross-TOP: Zero-Shot Cross-Schema Task-Oriented Parsingcited by 3
  27. 2024Towards Automated Data Sciences with Natural Language and SageCopilot: Practices and Lessons Learnedcited by 3
  28. 2025MultiTEND: A Multilingual Benchmark for Natural Language to NoSQL Query Translationcited by 3
  29. 2023T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsingcited by 2
  30. 2024On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQLcited by 2
  31. 2024Infusing Prompts with Syntax and Semanticscited by 2
  32. 2025End-to-End Text-to-SQL with Dataset Selection: Leveraging LLMs for Adaptive Query Generationcited by 2
  33. 2023On the Structural Generalization in Text-to-SQLcited by 1
  34. 2023Decoupling SQL Query Hardness Parsing for Text-to-SQLcited by 1
  35. 2023Dynamic Retrieval-Augmented Generationcited by 1
  36. 2023Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databasescited by 1
  37. 2024Schema-Aware Multi-Task Learning for Complex Text-to-SQLcited by 1
  38. 2024Understanding the Effect of Algorithm Transparency of Model Explanations in Text-to-SQL Semantic Parsingcited by 1

50 most cited of 68 All 68 (JSON)