mlsanityData to 7 Oct 2026

ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser

arXiv 2104.04689 ↗First posted 10 Apr 2021cs.CL cs.HCcited by 35

Not on the map. Why?

Abstract (arXiv)

Given a database schema, Text-to-SQL aims to translate a natural language question into the corresponding SQL query. Under the setup of cross-domain, traditional semantic parsing models struggle to adapt to unseen database schemas. To improve the model generalization capability for rare and unseen schemas, we propose a new architecture, ShadowGNN, which processes schemas at abstract and semantic levels. By ignoring names of semantic items in databases, abstract schemas are exploited in a well-designed graph projection neural network to obtain delexicalized representation of question and schema. Based on the domain-independent representations, a relation-aware transformer is utilized to further extract logical linking between question and schema. Finally, a SQL decoder with context-free grammar is applied. On the challenging Text-to-SQL benchmark Spider, empirical results show that ShadowGNN outperforms state-of-the-art models. When the annotated data is extremely limited (only 10% training set), ShadowGNN gets over absolute 5% performance gain, which shows its powerful generalization ability. Our implementation will be open-sourced at urlhttps://github.com/WowCZ/shadowgnn.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 33 of its 44 references that are in the map. First posted on arXiv 10 Apr 2021.

Builds on

33 of 44 references.

References · 33

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
  4. 2016Layer Normalizationcited by 5,579
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  6. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  7. 2018Self-Attention with Relative Position Representationscited by 1,112
  8. 2015Gated Graph Sequence Neural Networkscited by 792
  9. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 679
  10. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  11. 2020TaBERT: Pretraining for Joint Understanding of Textual and Tabular Datacited by 395
  12. 2019Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representationcited by 210
21 more
  1. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  2. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  3. 2018Coarse-to-Fine Decoding for Neural Semantic Parsingcited by 110
  4. 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
  5. 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
  6. 2019Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsingcited by 74
  7. 2020RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databasescited by 63
  8. 2019Compositional generalization in a deep seq2seq model by separating syntax and semanticscited by 56
  9. 2019Global Reasoning over Database Structures for Text-to-SQL Parsingcited by 43
  10. 2020IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generationcited by 29
  11. 2019Semantic Parsing with Dual Learningcited by 28
  12. 2020Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Trackingcited by 27
  13. 2019Grammar-based Neural Text-to-SQL Generationcited by 23
  14. 2020Unsupervised Dual Paraphrasing for Two-stage Semantic Parsingcited by 20
  15. 2021Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsingcited by 15
  16. 2021LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matchingcited by 15
  17. 2019AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learningcited by 12
  18. 2020Bertrand-DR: Improving Text-to-SQL using a Discriminative Re-rankercited by 12
  19. 2020Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Managementcited by 12
  20. 2020"What Do You Mean by That?" A Parser-Independent Interactive Approach for Enhancing Text-to-SQLcited by 11
  21. 2020Structured Hierarchical Dialogue Policy with Graph Neural Networkscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 9; 2023: 10; 2024: 4; 2025: 6; 2026: 1.

35 papers.

Sort:

By area:

  1. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  2. 2022State-of-the-art generalisation research in NLP: A taxonomy and reviewcited by 97
  3. 2023Graphix-T5: Mixing Pre-Trained Transformers with Graph-Aware Layers for Text-to-SQL Parsingcited by 93
  4. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  5. 2023How to Prompt LLMs for Text-to-SQL: A Study in Zero-shot, Single-domain, and Cross-domain Settingscited by 57
  6. 2022A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directionscited by 51
  7. 2024RSL-SQL: Robust Schema Linking in Text-to-SQL Generationcited by 51
  8. 2022Recent Advances in Text-to-SQL: A Survey of What We Have and What We Expectcited by 47
  9. 2021SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLcited by 43
  10. 2022S2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parserscited by 41
  11. 2022Proton: Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsingcited by 30
  12. 2023Natural Language Interfaces for Tabular Data Querying and Visualization: A Surveycited by 27
23 more
  1. 2022HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsingcited by 26
  2. 2022N-Best Hypotheses Reranking for Text-To-SQL Systemscited by 19
  3. 2023Prompting GPT-3.5 for Text-to-SQL with De-semanticization and Skeleton Retrievalcited by 16
  4. 2021Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQLcited by 13
  5. 2023Retrieval-augmented GPT-3.5-based Text-to-SQL Framework with Sample-aware Prompting and Dynamic Revision Chaincited by 12
  6. 2025Text2SQL-Flow: A Robust SQL-Aware Data Augmentation Framework for Text-to-SQLcited by 11
  7. 2022SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parserscited by 7
  8. 2023Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tablescited by 6
  9. 2025Graph Neural Networks for Databases: A Surveycited by 6
  10. 2021Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQLcited by 5
  11. 2022TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pagescited by 4
  12. 2025SchemaGraphSQL: Efficient Schema Linking with Pathfinding Graph Algorithms for Text-to-SQL on Large-Scale Databasescited by 3
  13. 2023T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsingcited by 2
  14. 2024Towards Automated Cross-domain Exploratory Data Analysis through Large Language Modelscited by 2
  15. 2025Evaluating NL2SQL via SQL2NLcited by 2
  16. 2021Linking-Enhanced Pre-Training for Table Semantic Parsingcited by 1
  17. 2023On the Structural Generalization in Text-to-SQLcited by 1
  18. 2024Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agentscited by 1
  19. 2025REFORMER: A ChatGPT-Driven Data Synthesis Framework Elevating Text-to-SQL Modelscited by 1
  20. 2025Scaling Text2SQL via LLM-efficient Schema Filtering with Functional Dependency Graph Rerankerscited by 1
  21. 2023Translating Natural Language Queries to SQL Using the T5 Modelcited by 0
  22. 2024An Automated SQL Query Grading System Using An Attention-Based Convolutional Neural Networkcited by 0
  23. 2026text2ql: Multi-Target Natural Language Querying via a Language-Agnostic Intermediate Representationcited by 0