TypeSQL: Knowledge-based Type-Aware Neural Text-to-SQL Generation
Not on the map. Why?
Abstract (arXiv)
Interacting with relational databases through natural language helps users of any background easily query and analyze a vast amount of data. This requires a system that understands users' questions and converts them to SQL queries automatically. In this paper we present a novel approach, TypeSQL, which views this problem as a slot filling task. Additionally, TypeSQL utilizes type information to better understand rare entities and numbers in natural language questions. We test this idea on the WikiSQL dataset and outperform the prior state-of-the-art by 5.5% in much less time. We also show that accessing the content of databases can significantly improve the performance when users' queries are not well-formed. TypeSQL gets 82.6% accuracy, a 17.5% absolute improvement compared to the previous content-sensitive model.
Key facts. Cited by 81 papers in the map (data through 14 Oct 2026). First posted on arXiv 25 Apr 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 15; 2022: 12; 2023: 11; 2024: 16; 2025: 19; 2026: 8.
81 papers.
Sort:
By area:
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
- 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
- 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
- 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
- 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
- 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
- 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 52
- 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 50
- 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
- 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46
- 2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43
38 more
- 2022A Survey on Table Question Answering: Recent Advancescited by 41
- 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generationcited by 36
- 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
- 2024Semantic Operators: A Declarative Model for Rich, AI-based Data Processingcited by 34
- 2024Text2SQL is Not Enough: Unifying AI and Databases with TAGcited by 34
- 2022Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsingcited by 30
- 2021Awakening Latent Grounding from Pretrained Language Models for Semantic Parsingcited by 28
- 2023Large Language Models are Complex Table Parserscited by 28
- 2021SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoisingcited by 27
- 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
- 2021Improving Text-to-SQL with Schema Dependency Learningcited by 25
- 2021Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answeringcited by 25
- 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 20
- 2022N-Best Hypotheses Reranking for Text-To-SQL Systemscited by 19
- 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 17
- 2021mRAT-SQL+GAP:A Portuguese Text-to-SQL Transformercited by 15
- 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
- 2024Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queriescited by 12
- 2024SQL-to-Schema Enhances Schema Linking in Text-to-SQLcited by 12
- 2022Deep Learning Driven Natural Languages Text to SQL Query Conversion: A Surveycited by 11
- 2024Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answeringcited by 10
- 2024A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challengescited by 10
- 2023Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasetscited by 9
- 2023Marrying Dialogue Systems with Data Visualization: Interactive Data Visualization Generation from Natural Language Conversationscited by 9
- 2025BASE-SQL: A powerful open source Text-To-SQL baseline approachcited by 9
- 2022SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parserscited by 7
- 2022Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Questioncited by 6
- 2024Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systemscited by 6
- 2025Enhancing Text2Cypher with Schema Filteringcited by 6
- 2021GP: Context-free Grammar Pre-training for Text-to-SQL Parserscited by 5
- 2021An Investigation Between Schema Linking and Text-to-SQL Performancecited by 5
- 2021Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQLcited by 5
- 2025Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphscited by 5
- 2022TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pagescited by 4
- 2026Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agentscited by 4
- 2021DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networkscited by 3
- 2021Leveraging Table Content for Zero-shot Text-to-SQL with Meta-Learningcited by 3
- 2023SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translationcited by 3
50 most cited of 81 All 81 (JSON)
- 2026SQuaD-SQL: Efficient Text-to-SQL with Small Language Models via LLM-Guided Knowledge Distillation9 Jul 2026
- 2026Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards5 Jun 2026
- 2026Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL3 Jun 2026
- 2026Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents30 May 2026
- 2026Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering11 May 2026
- 2026Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions24 Mar 2026
- 2026An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data8 Mar 2026
- 2026SpectraQuery: A Hybrid Retrieval-Augmented Conversational Assistant for Battery Science14 Jan 2026
- 2025A Multi-agent Text2SQL Framework using Small Language Models and Execution Feedback21 Dec 2025
- 2025Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers18 Dec 2025
- 2025Multi-Agent GraphRAG: A Text-to-Cypher Framework for Labeled Property Graphs11 Nov 2025
- 2025LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL27 Sep 2025
38 more
- 2025MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction27 Sep 2025
- 2025Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation18 Aug 2025
- 2025LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA12 Aug 2025
- 2025HI-SQL: Optimizing Text-to-SQL Systems through Dynamic Hint Integration11 Jun 2025
- 2025Meta-aware Learning in text-to-SQL Large Language Model25 May 2025
- 2025SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databases23 May 2025
- 2025Enhancing Text2Cypher with Schema Filtering8 May 2025
- 2025Domain Specific Question to SQL Conversion with Embedded Data Balancing Technique28 Mar 2025
- 2025Valid Text-to-SQL Generation with Unification-based DeepStochLog17 Mar 2025
- 2025A Survey on Knowledge-Oriented Retrieval-Augmented Generation11 Mar 2025
- 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQL19 Feb 2025
- 2025BASE-SQL: A powerful open source Text-To-SQL baseline approach15 Feb 2025
- 2025What Really Matters for Table LLMs? A Meta-Evaluation of Model and Data Effects24 Jan 2025
- 2025Reliable Text-to-SQL with Adaptive Abstention18 Jan 2025
- 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errors16 Jan 2025
- 2024Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents8 Dec 2024
- 2024A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challenges6 Dec 2024
- 2024Accurate and Regret-aware Numerical Problem Solver for Tabular Question Answering10 Oct 2024
- 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQL25 Sep 2024
- 2024Text2SQL is Not Enough: Unifying AI and Databases with TAG27 Aug 2024
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?9 Aug 2024
- 2024Semantic Operators: A Declarative Model for Rich, AI-based Data Processing16 Jul 2024
- 2024Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threats25 Jun 2024
- 2024AnnotatedTables: A Large Tabular Dataset with Language Model Annotations24 Jun 2024
- 2024Unmasking Database Vulnerabilities: Zero-Knowledge Schema Inference Attacks in Text-to-SQL Systems20 Jun 2024
- 2024RH-SQL: Refined Schema and Hardness Prompt for Text-to-SQL13 Jun 2024
- 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generation24 May 2024
- 2024SQL-to-Schema Enhances Schema Linking in Text-to-SQL15 May 2024
- 2024ERATTA: Extreme RAG for Table To Answers with Large Language Models7 May 2024
- 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Survey27 Feb 2024
- 2024Evaluating the Data Model Robustness of Text-to-SQL Systems Based on Real User Queries13 Feb 2024
- 2023Large Language Models are Complex Table Parsers13 Dec 2023
- 2023Fine-Tuning Language Models for Context-Specific SQL Query Generation4 Dec 2023
- 2023SQLformer: Deep Auto-Regressive Query Graph Generation for Text-to-SQL Translation27 Oct 2023
- 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey27 Oct 2023
- 2023Marrying Dialogue Systems with Data Visualization: Interactive Data Visualization Generation from Natural Language Conversations29 Jul 2023
- 2023Feature Representation Learning for NL2SQL Generation Based on Coupling and Decoupling30 Jun 2023
- 2023Skill-Based Few-Shot Selection for In-Context Learning23 May 2023
50 newest of 81 All 81 (JSON)
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 688
- 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
- 2024Large Language Models(LLMs) on Tabular Data: Prediction, Generation, and Understanding -- A Surveycited by 159
- 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
- 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
- 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 56
- 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 52
- 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 50
- 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
- 2023Skill-Based Few-Shot Selection for In-Context Learningcited by 46
- 2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43
12 most cited of 72 All 72 (JSON)
- 2026Schema-Aware Localisation (SAL): Live Schema Grounding and Hallucination Validation for Oracle NL2SQL3 Jun 2026
- 2026Learning to Retrieve: Dual-Level Long-Term Memory for Text-to-SQL Agents30 May 2026
- 2026Extending Confidence-Based Text2Cypher with Grammar and Schema Aware Filtering11 May 2026
- 2026Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions24 Mar 2026
- 2026An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data8 Mar 2026
- 2025Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers18 Dec 2025
- 2025LLMSQL: Upgrading WikiSQL for the LLM Era of Text-to-SQL27 Sep 2025
- 2025MaskSQL: Safeguarding Privacy for LLM-Based Text-to-SQL via Abstraction27 Sep 2025
- 2025Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation18 Aug 2025
- 2025LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA12 Aug 2025
- 2025HI-SQL: Optimizing Text-to-SQL Systems through Dynamic Hint Integration11 Jun 2025
- 2025Meta-aware Learning in text-to-SQL Large Language Model25 May 2025
12 newest of 72 All 72 (JSON)