# T5QL: Taming language models for SQL generation

arXiv: https://arxiv.org/abs/2209.10254 · HTML: https://mlsanity.com/paper/2209.10254/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 38 references that are in the map.
- First posted on arXiv 21 Sep 2022.

## Builds on (most cited first, 28 of 28)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [CodeBERT: A Pre-Trained Model for Programming and Natural Languages](https://mlsanity.com/paper/2002.08155/) (2020)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [Autoregressive Entity Retrieval](https://mlsanity.com/paper/2010.00904/) (2020)
- [UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models](https://mlsanity.com/paper/2201.05966/) (2022)
- [IntelliCode Compose: Code Generation Using Transformer](https://mlsanity.com/paper/2005.08025/) (2020)
- [CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases](https://mlsanity.com/paper/1909.05378/) (2019)
- [GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsing](https://mlsanity.com/paper/2009.13845/) (2020)
- [Synchromesh: Reliable code generation from pre-trained language models](https://mlsanity.com/paper/2201.11227/) (2022)
- [Compositional Generalization and Natural Language Variation: Can a Semantic Parsing Approach Handle Both?](https://mlsanity.com/paper/2010.12725/) (2020)
- [Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2012.12627/) (2020)
- [SmBoP: Semi-autoregressive Bottom-up Semantic Parsing](https://mlsanity.com/paper/2010.12412/) (2020)
- [RnG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering](https://mlsanity.com/paper/2109.08678/) (2021)
- [Neuro-Symbolic Program Synthesis](https://mlsanity.com/paper/1611.01855/) (2016)
- [RankGen: Improving Text Generation with Large Ranking Models](https://mlsanity.com/paper/2205.09726/) (2022)
- [Natural SQL: Making SQL Easier to Infer from Natural Language Specifications](https://mlsanity.com/paper/2109.05153/) (2021)
- [Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training](https://mlsanity.com/paper/2012.10309/) (2020)
- [A Survey on Semantic Parsing](https://mlsanity.com/paper/1812.00978/) (2018)
- [Deep Learning for Source Code Modeling and Generation: Models, Applications and Challenges](https://mlsanity.com/paper/2002.05442/) (2020)
- [Provable Limitations of Acquiring Meaning from Ungrounded Form: What Will Future Language Models Understand?](https://mlsanity.com/paper/2104.10809/) (2021)
- [Retrieval-Based Neural Code Generation](https://mlsanity.com/paper/1808.10025/) (2018)
- [Simple and Effective Noisy Channel Modeling for Neural Machine Translation](https://mlsanity.com/paper/1908.05731/) (2019)
- [A Grammar-Based Structural CNN Decoder for Code Generation](https://mlsanity.com/paper/1811.06837/) (2018)
- [Relation Aware Semi-autoregressive Semantic Parsing for NL2SQL](https://mlsanity.com/paper/2108.00804/) (2021)
- [Type- and Content-Driven Synthesis of SQL Queries from Natural Language](https://mlsanity.com/paper/1702.01168/) (2017)
- [GP: Context-free Grammar Pre-training for Text-to-SQL Parsers](https://mlsanity.com/paper/2101.09901/) (2021)

## Built on by (most cited first, 8 of 8)

- [Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code](https://mlsanity.com/paper/2311.07989/) (2023)
- [Benchmarking and Improving Text-to-SQL Generation under Ambiguity](https://mlsanity.com/paper/2310.13659/) (2023)
- [Error Detection for Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2305.13683/) (2023)
- [Retrieval-Enhanced Machine Learning: Synthesis and Opportunities](https://mlsanity.com/paper/2407.12982/) (2024)
- [Towards Tailored Recovery of Lexical Diversity in Literary Machine Translation](https://mlsanity.com/paper/2408.17308/) (2024)
- [Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models](https://mlsanity.com/paper/2309.12294/) (2023)
- [PExA: Parallel Exploration Agent for Complex Text-to-SQL](https://mlsanity.com/paper/2604.22934/) (2026)
- [Natural language to SQL in low-code platforms](https://mlsanity.com/paper/2308.15239/) (2023)

## 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.