mlsanityData to 7 Oct 2026

T5QL: Taming language models for SQL generation

arXiv 2209.10254 ↗First posted 21 Sep 2022cs.LG cs.DBcited by 8

Not on the map. Why?

Abstract (arXiv)

Automatic SQL generation has been an active research area, aiming at streamlining the access to databases by writing natural language with the given intent instead of writing SQL. Current SOTA methods for semantic parsing depend on LLMs to achieve high predictive accuracy on benchmark datasets. This reduces their applicability, since LLMs requires expensive GPUs. Furthermore, SOTA methods are ungrounded and thus not guaranteed to always generate valid SQL. Here we propose T5QL, a new SQL generation method that improves the performance in benchmark datasets when using smaller LMs, namely T5-Base, by 13pp when compared against SOTA methods. Additionally, T5QL is guaranteed to always output valid SQL using a context-free grammar to constrain SQL generation. Finally, we show that dividing semantic parsing in two tasks, candidate SQLs generation and candidate re-ranking, is a promising research avenue that can reduce the need for large LMs.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 28 of its 38 references that are in the map. First posted on arXiv 21 Sep 2022.

Builds on

28 of 38 references.

References · 28

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  4. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  5. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  6. 2020Autoregressive Entity Retrievalcited by 333
  7. 2022UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Modelscited by 231
  8. 2020IntelliCode Compose: Code Generation Using Transformercited by 225
  9. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  10. 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
  11. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  12. 2020Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?cited by 147
16 more
  1. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  2. 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
  3. 2021RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answeringcited by 86
  4. 2016Neuro-Symbolic Program Synthesiscited by 84
  5. 2022RankGen: Improving Text Generation with Large Ranking Modelscited by 72
  6. 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
  7. 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
  8. 2018A Survey on Semantic Parsingcited by 62
  9. 2020Deep Learning for Source Code Modeling and Generation: Models, Applications and Challengescited by 55
  10. 2021Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?cited by 55
  11. 2018Retrieval-Based Neural Code Generationcited by 41
  12. 2019Simple and Effective Noisy Channel Modeling for Neural Machine Translationcited by 37
  13. 2018A Grammar-Based Structural CNN Decoder for Code Generationcited by 29
  14. 2021Relation Aware Semi-autoregressive Semantic Parsing for NL2SQLcited by 8
  15. 2017Type- and Content-Driven Synthesis of SQL Queries from Natural Languagecited by 5
  16. 2021GP: Context-free Grammar Pre-training for Text-to-SQL Parserscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 2; 2025: 0; 2026: 1.

8 papers.

  1. 2023Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Codecited by 62
  2. 2023Benchmarking and Improving Text-to-SQL Generation under Ambiguitycited by 31
  3. 2023Error Detection for Text-to-SQL Semantic Parsingcited by 11
  4. 2024Retrieval-Enhanced Machine Learning: Synthesis and Opportunitiescited by 11
  5. 2024Towards Tailored Recovery of Lexical Diversity in Literary Machine Translationcited by 5
  6. 2023Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Modelscited by 1
  7. 2026PExA: Parallel Exploration Agent for Complex Text-to-SQLcited by 1
  8. 2023Natural language to SQL in low-code platformscited by 0