Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsing
Not on the map. Why?
Abstract (arXiv)
Research on parsing language to SQL has largely ignored the structure of the database (DB) schema, either because the DB was very simple, or because it was observed at both training and test time. In Spider, a recently-released text-to-SQL dataset, new and complex DBs are given at test time, and so the structure of the DB schema can inform the predicted SQL query. In this paper, we present an encoder-decoder semantic parser, where the structure of the DB schema is encoded with a graph neural network, and this representation is later used at both encoding and decoding time. Evaluation shows that encoding the schema structure improves our parser accuracy from 33.8% to 39.4%, dramatically above the current state of the art, which is at 19.7%.
Key facts. Cited by 74 papers in the map (data through 7 Oct 2026). First posted on arXiv 15 May 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 16; 2022: 15; 2023: 13; 2024: 15; 2025: 10; 2026: 5.
74 papers.
Sort:
By area:
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
- 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
- 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
- 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
- 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
- 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
- 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
- 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
- 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 57
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
- 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
38 more
- 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
- 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 51
- 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
- 2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43
- 2021ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parsercited by 35
- 2024PURPLE: Making a Large Language Model a Better SQL Writercited by 34
- 2022Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsingcited by 30
- 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
- 2022HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsingcited by 26
- 2022Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graphcited by 22
- 2022UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQLcited by 20
- 2022N-Best Hypotheses Reranking for Text-To-SQL Systemscited by 19
- 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 19
- 2024Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translationcited by 17
- 2022Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignmentcited by 16
- 2023Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrievalcited by 16
- 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 16
- 2021Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsingcited by 15
- 2025Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQLcited by 14
- 2023Semantic Decomposition of Question and SQL for Text-to-SQL Parsingcited by 13
- 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQLcited by 13
- 2023Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chaincited by 12
- 2022Deep Learning Driven Natural Languages Text to SQL Query Conversion: A Surveycited by 11
- 2023Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasetscited by 9
- 2021SPARQLing Database Queries from Intermediate Question Decompositionscited by 7
- 2024Grounding Natural Language to SQL Translation with Data-Based Self-Explanationscited by 7
- 2022Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Questioncited by 6
- 2025Graph Neural Networks for Databases: A Surveycited by 6
- 2021An Investigation Between Schema Linking and Text-to-SQL Performancecited by 5
- 2021Self-supervised Incremental Deep Graph Learning for Ethereum Phishing Scam Detectioncited by 5
- 2021Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQLcited by 5
- 2022TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pagescited by 4
- 2023Wav2SQL: Direct Generalizable Speech-To-SQL Parsingcited by 4
- 2021DBTagger: Multi-Task Learning for Keyword Mapping in NLIDBs Using Bi-Directional Recurrent Neural Networkscited by 3
- 2021A Globally Normalized Neural Model for Semantic Parsingcited by 2
- 2021Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questionscited by 2
- 2024On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQLcited by 2
- 2024Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injectioncited by 2
50 most cited of 74 All 74 (JSON)
- 2026BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations29 Aug 2026
- 2026SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback31 May 2026
- 2026Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs20 May 2026
- 2026LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL20 Apr 2026
- 2026Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL17 Feb 2026
- 2025Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQL28 Dec 2025
- 2025Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers18 Dec 2025
- 2025GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL16 Sep 2025
- 2025Evaluating NL2SQL via SQL2NL4 Sep 2025
- 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models1 Sep 2025
- 2025Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation18 Aug 2025
- 2025Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL21 Apr 2025
38 more
- 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQL19 Feb 2025
- 2025Graph Neural Networks for Databases: A Survey18 Feb 2025
- 2025Reliable Text-to-SQL with Adaptive Abstention18 Jan 2025
- 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL13 Dec 2024
- 2024Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models10 Dec 2024
- 2024Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents8 Dec 2024
- 2024Grounding Natural Language to SQL Translation with Data-Based Self-Explanations5 Nov 2024
- 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generation31 Oct 2024
- 2024An Actor-Critic Approach to Boosting Text-to-SQL Large Language Model28 Oct 2024
- 2024Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injection24 Sep 2024
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?9 Aug 2024
- 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMs6 Aug 2024
- 2024A Survey on Employing Large Language Models for Text-to-SQL Tasks21 Jul 2024
- 2024Beyond Text-to-SQL for IoT Defense: A Comprehensive Framework for Querying and Classifying IoT Threats25 Jun 2024
- 2024An Automated SQL Query Grading System Using An Attention-Based Convolutional Neural Network22 Jun 2024
- 2024On Linearizing Structured Data in Encoder-Decoder Language Models: Insights from Text-to-SQL3 Apr 2024
- 2024PURPLE: Making a Large Language Model a Better SQL Writer29 Mar 2024
- 2024Metasql: A Generate-then-Rank Framework for Natural Language to SQL Translation27 Feb 2024
- 2023Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases22 Dec 2023
- 2023Translating Natural Language Queries to SQL Using the T5 Model12 Dec 2023
- 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Survey27 Oct 2023
- 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought26 Oct 2023
- 2023Semantic Decomposition of Question and SQL for Text-to-SQL Parsing20 Oct 2023
- 2023Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chain11 Jul 2023
- 2023CSS: A Large-scale Cross-schema Chinese Text-to-SQL Medical Dataset25 May 2023
- 2023Wav2SQL: Direct Generalizable Speech-To-SQL Parsing21 May 2023
- 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settings19 May 2023
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs4 May 2023
- 2023Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrieval26 Apr 2023
- 2023Towards Understanding the Generalization of Medical Text-to-SQL Models and Datasets22 Mar 2023
- 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsing18 Jan 2023
- 2022DocuT5: Seq2seq SQL Generation with Table Documentation11 Nov 2022
- 2022N-Best Hypotheses Reranking for Text-To-SQL Systems19 Oct 2022
- 2022AskYourDB: An end-to-end system for querying and visualizing relational databases using natural language16 Oct 2022
- 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions29 Aug 2022
- 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expect22 Aug 2022
- 2022Deep Learning Driven Natural Languages Text to SQL Query Conversion: A Survey8 Aug 2022
- 2022Semantic Enhanced Text-to-SQL Parsing via Iteratively Learning Schema Linking Graph8 Aug 2022
50 newest of 74 All 74 (JSON)
- 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
- 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 16
- 2025Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQLcited by 14
- 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Modelscited by 0
- 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models1 Sep 2025
- 2025Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL21 Apr 2025
- 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQL19 Feb 2025
- 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought26 Oct 2023
- 2024Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agentscited by 1
- 2025GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQLcited by 1
- 2026Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIscited by 1
- 2026Beyond Text-to-SQL: An Agentic LLM System for Governed Enterprise Analytics APIs20 May 2026
- 2025GBV-SQL: Guided Generation and SQL2Text Back-Translation Validation for Multi-Agent Text2SQL16 Sep 2025
- 2024Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents8 Dec 2024
- 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
- 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
- 2021Towards Robustness of Text-to-SQL Models against Synonym Substitutioncited by 110
- 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
- 2021Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalizationcited by 92
- 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
- 2024A Survey on Employing Large Language Models for Text-to-SQL Taskscited by 67
- 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
- 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 57
- 2024A Survey of Text-to-SQL in the Era of LLMs: Where are we, and where are we going?cited by 54
- 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
- 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
12 most cited of 66 All 66 (JSON)
- 2026BIRD-History: A Benchmark for History-Driven Text-to-SQL with Fine-Grained Knowledge Annotations29 Aug 2026
- 2026SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback31 May 2026
- 2026LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL20 Apr 2026
- 2026Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQL17 Feb 2026
- 2025Bridging Global Intent with Local Details: A Hierarchical Representation Approach for Semantic Validation in Text-to-SQL28 Dec 2025
- 2025Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankers18 Dec 2025
- 2025Evaluating NL2SQL via SQL2NL4 Sep 2025
- 2025Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation18 Aug 2025
- 2025Graph Neural Networks for Databases: A Survey18 Feb 2025
- 2025Reliable Text-to-SQL with Adaptive Abstention18 Jan 2025
- 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL13 Dec 2024
- 2024Towards Automated Cross-domain Exploratory Data Analysis through Large Language Models10 Dec 2024
12 newest of 66 All 66 (JSON)