The Nuts and Bolts of Natural Language to SQL Translation: A Systematic Analysis of Model Pipeline Optimisation Approaches and their Interactions
Not on the map. Why?
Abstract (arXiv)
In the age of large language models, Natural Language to SQL (NL2SQL) translation remains an open problem with many useful applications. We explore interactions between several NL2SQL pipeline extensions to inspire development of more lightweight models. Specifically, we integrate the NatSQL intermediate representation, include a preprocessing step and a fine-tuning step based on synthetic data, and develop a novel reranker model to improve SQL selection in the final beam. We perform an ablation study supplemented by a Shapley analysis of these different components integrated with two backbone architectures, SmBoP and RASAT. We find that simply combining all of them does not lead to best results, but that their impact depends on their interactions with the baseline system, as well as each other.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 35 references that are in the map. First posted on arXiv 12 Jul 2026.
Builds on
29 of 35 references.
References · 29
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
- 2017Get To The Point: Summarization with Pointer-Generator Networkscited by 1,292
- 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
- 2021Deduplicating Training Data Makes Language Models Bettercited by 714
- 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
- 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 477
- 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
- 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
- 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
- 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
- 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 185
17 more
- 2020GraPPa: Grammar-Augmented Pre-Training for Table Semantic Parsingcited by 171
- 2016Language to Logical Form with Neural Attentioncited by 158
- 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 144
- 2017SQLNet: Generating Structured Queries From Natural Language Without Reinforcement Learningcited by 135
- 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
- 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
- 2023A comprehensive evaluation of ChatGPT's zero-shot Text-to-SQL capabilitycited by 119
- 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
- 2019A Comprehensive Exploration on WikiSQL with Table-Aware Word Contextualizationcited by 88
- 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
- 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
- 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 68
- 2021Improving Text-to-SQL with Schema Dependency Learningcited by 25
- 2023Improving Generalization in Language Model-Based Text-to-SQL Semantic Parsing: Two Simple Semantic Boundary-Based Techniquescited by 24
- 2022N-Best Hypotheses Reranking for Text-To-SQL Systemscited by 19
- 2025AGENTIQL: An Agent-Inspired Multi-Expert Framework for Text-to-SQL Generationcited by 2
- 2018Is it worth it? Budget-related evaluation metrics for model selectioncited by 1
Built on by
Not cited yet.