SOTAVerified

Text-To-SQL

Text-to-SQL is a task in natural language processing (NLP) where the goal is to automatically generate SQL queries from natural language text. The task involves converting the text input into a structured representation and then using this representation to generate a semantically correct SQL query that can be executed on a database.

( Image credit: SyntaxSQLNet )

Papers

Showing 301350 of 424 papers

TitleStatusHype
Faster and Better Grammar-based Text-to-SQL Parsing via Clause-level Parallel Decoding and Alignment Loss0
In-Context Learning for Few-Shot Dialogue State TrackingCode1
Evaluating the Text-to-SQL Capabilities of Large Language Models0
UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQLCode0
S^2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers0
HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing0
Integrating question answering and text-to-SQL in PortugueseCode0
Exploring Example Selection for Few-shot Text-to-SQL Semantic Parsing0
Weakly Supervised Text-to-SQL Parsing through Question Decomposition0
Speech-to-SQL: Towards Speech-driven SQL Query Generation From Natural Language Question0
Pretrained Language Models Are All You Need For Text-to-SQL Schema Linking0
Pay More Attention to History: A Context Modelling Strategy for Conversational Text-to-SQLCode0
Weakly Supervised Text-to-SQL Parsing through Question DecompositionCode1
Hierarchical Neural Data Synthesis for Semantic Parsing0
UniSAr: A Unified Structure-Aware Autoregressive Language Model for Text-to-SQL0
Probing Schema Linking Information from Pre-trained Language Models for Text-to-SQL Parsing0
ST-SQL: Semi-Supervised Self-Training for Text-to-SQL via Column Specificity Meta-LearningCode0
DrugEHRQA: A Question Answering Dataset on Structured and Unstructured Electronic Health Records For Medicine Related Queries0
S^2SQL: Injecting Syntax to Question-Schema Interaction Graph Encoder for Text-to-SQL Parsers0
Speech-to-SQL Parsing: Error Correction with Multi-modal Representations0
HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing0
Towards Robustness of Text-to-SQL Models Against Natural and Realistic Adversarial Table Perturbation0
Evaluating the Text-to-SQL Capabilities of Large Language Models0
SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQLCode1
Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment0
mRAT-SQL+GAP:A Portuguese Text-to-SQL TransformerCode1
Awakening Latent Grounding from Pretrained Language Models for Semantic ParsingCode0
SeaD: End-to-end Text-to-SQL Generation with Schema-aware Denoising0
Prefix-to-SQL: Text-to-SQL Generation from Incomplete User Questions0
SPARQLing Database Queries from Intermediate Question DecompositionsCode1
Leveraging Table Content for Zero-shot Text-to-SQL with Meta-LearningCode1
Exploring Underexplored Limitations of Cross-Domain Text-to-SQL GeneralizationCode0
Natural SQL: Making SQL Easier to Infer from Natural Language SpecificationsCode1
PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language ModelsCode1
Semi-Automatic Construction of Text-to-SQL Data for Domain TransferCode0
Chase: A Large-Scale and Pragmatic Chinese Dataset for Cross-Database Context-Dependent Text-to-SQL0
KaggleDBQA: Realistic Evaluation of Text-to-SQL ParsersCode0
End-to-End Cross-Domain Text-to-SQL Semantic Parsing with Auxiliary Task0
Text-to-SQL in the Wild: A Naturally-Occurring Dataset Based on Stack Exchange DataCode1
Turing: an Accurate and Interpretable Multi-Hypothesis Cross-Domain Natural Language Database Interface0
Decoupled Dialogue Modeling and Semantic Parsing for Multi-Turn Text-to-SQL0
LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local RelationsCode1
Towards Robustness of Text-to-SQL Models against Synonym SubstitutionCode1
SeaD: End-to-end Text-to-SQL Generation with Schema-aware DenoisingCode2
Unlocking Compositional Generalization in Pre-trained Models Using Intermediate RepresentationsCode1
Learning to Synthesize Data for Semantic ParsingCode1
ShadowGNN: Graph Projection Neural Network for Text-to-SQL ParserCode0
NL-EDIT: Correcting semantic parse errors through natural language interactionCode0
Self-supervised Text-to-SQL Learning with Header Alignment Training0
Improving Text-to-SQL with Schema Dependency Learning0
Show:102550
← PrevPage 7 of 9Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1Human PerformanceExecution Accurarcy (Human)92.96Unverified
2XiYan-SQLExecution Accuracy % (Test)75.63Unverified
3DSAIR + GPT-4oExecution Accuracy % (Test)74.12Unverified
4CHASE-SQL + GeminiExecution Accuracy % (Test)74.06Unverified
5ExSL + granite-34b-codeExecution Accuracy % (Test)73.17Unverified
6OpenSearch-SQL+ v2 + GPT-4oExecution Accuracy % (Test)72.28Unverified
7Distillery + GPT-4oExecution Accuracy % (Test)71.83Unverified
8Insights AIExecution Accuracy % (Test)70.26Unverified
9PURPLE + RED + GPT-4oExecution Accuracy % (Test)70.21Unverified
10MCTS-SQLExecution Accuracy % (Test)69.4Unverified
#ModelMetricClaimedVerifiedStatus
1XiYan-SQLExecution Accuracy (Test)89.65Unverified
2PET-SQLExecution Accuracy (Test)87.6Unverified
3datagpt-sql-7B + InvalidSQL-FeedbackExecution Accuracy (Dev)87.2Unverified
4DAIL-SQL + GPT-4 + Self-ConsistencyExecution Accuracy (Test)86.6Unverified
5DIN-SQL + GPT-4Execution Accuracy (Test)85.3Unverified
6datagpt-sql-7BExecution Accuracy (Dev)84.8Unverified
7MSc-SQLExecution Accuracy (Test)84.7Unverified
8MARLO + Claude 2.1Execution Accuracy (Test)84Unverified
9C3 + ChatGPT + Zero-ShotExecution Accuracy (Test)82.3Unverified
10code-davinci-002 175B (LEVER)Execution Accuracy (Dev)81.9Unverified
#ModelMetricClaimedVerifiedStatus
1Spider-Agent + o1-previewSuccess Rate17.03Unverified
2Spider-Agent + GPT-4oSuccess Rate10.13Unverified
3Spider-Agent + Claude-3.5-SonnectSuccess Rate9.02Unverified
4Spider-Agent + GPT-4Success Rate8.86Unverified
5Spider-Agent + Qwen2.5-72BSuccess Rate6.17Unverified
6Spider-Agent + DeepSeek-V2.5Success Rate5.22Unverified
7Spider-Agent + Gemini-Pro-1.5Success Rate2.53Unverified
8Spider-Agent + Llama-3.1-405BSuccess Rate2.21Unverified
#ModelMetricClaimedVerifiedStatus
1RASAT+PICARDinteraction match accuracy45.2Unverified
2RAT-SQL-TC + GAPinteraction match accuracy43.2Unverified
3HIE-SQL + GraPPainteraction match accuracy42.9Unverified
4RAT-SQL + SCoReinteraction match accuracy38.1Unverified
5EditSQL + BERTinteraction match accuracy25.3Unverified
6GAZP + BERTinteraction match accuracy23.5Unverified
7SyntaxSQL-coninteraction match accuracy5.2Unverified
#ModelMetricClaimedVerifiedStatus
1RAT-SQLExact Match (EM)26.77Unverified
2Edit-SQLExact Match (EM)11.73Unverified
#ModelMetricClaimedVerifiedStatus
1T5-LargePCM-F1 (dev)48.2Unverified
#ModelMetricClaimedVerifiedStatus
1XiYan-SQLExecution Accuracy69.86Unverified
#ModelMetricClaimedVerifiedStatus
1Orange-mini0-shot MRR74.17Unverified