mlsanityData to 7 Oct 2026

Natural language to SQL in low-code platforms

arXiv 2308.15239 ↗First posted 29 Aug 2023cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

One of the developers' biggest challenges in low-code platforms is retrieving data from a database using SQL queries. Here, we propose a pipeline allowing developers to write natural language (NL) to retrieve data. In this study, we collect, label, and validate data covering the SQL queries most often performed by OutSystems users. We use that data to train a NL model that generates SQL. Alongside this, we describe the entire pipeline, which comprises a feedback loop that allows us to quickly collect production data and use it to retrain our SQL generation model. Using crowd-sourcing, we collect 26k NL and SQL pairs and obtain an additional 1k pairs from production data. Finally, we develop a UI that allows developers to input a NL query in a prompt and receive a user-friendly representation of the resulting SQL query. We use A/B testing to compare four different models in production and observe a 240% improvement in terms of adoption of the feature, 220% in terms of engagement rate, and a 90% decrease in failure rate when compared against the first model that we put into production, showcasing the effectiveness of our pipeline in continuously improving our feature.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 36 references that are in the map. First posted on arXiv 29 Aug 2023.

Builds on

17 of 36 references.

References · 17

  1. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  2. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  3. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  4. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  5. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  6. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 402
  7. 2021LongT5: Efficient Text-To-Text Transformer for Long Sequencescited by 232
  8. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 180
  9. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  10. 2018A Survey on Data Collection for Machine Learning: a Big Data -- AI Integration Perspectivecited by 111
  11. 2020SmBoP: Semi-autoregressive Bottom-up Semantic Parsingcited by 97
  12. 2022A Comparative Survey of Deep Active Learningcited by 88
5 more
  1. 2020Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Trainingcited by 65
  2. 2022ItemSage: Learning Product Embeddings for Shopping Recommendations at Pinterestcited by 23
  3. 2019X-SQL: reinforce schema representation with contextcited by 22
  4. 2022T5QL: Taming language models for SQL generationcited by 8
  5. 2021An Empirical Study of Developer Discussions on Low-Code Software Development Challengescited by 2

Built on by

Not cited yet.