Research Article Open Access

SQL Generation from Natural Language: A Sequence-to-Sequence Model Powered by the Transformers Architecture and Association Rules

Youssef Mellah1, Abdelkader Rhouati2, El Hassane Ettifouri2, Toumi Bouchentouf1 and Mohammed Ghaouth Belkasmi1
  • 1 Mohammed First University Oujda, Morocco
  • 2 NovyLab Research, France

Abstract

Using Natural Language (NL) to interacting with relational databases allows users from any background to easily query and analyze large amounts of data. This requires a system that understands user questions and automatically converts them into structured query language such as SQL. The best performing Text-to-SQL systems use supervised learning (usually formulated as a classification problem) by approaching this task as a sketch-based slot-filling problem, or by first converting questions into an Intermediate Logical Form (ILF) then convert it to the corresponding SQL query. However, non-supervised modeling that directly converts questions to SQL queries has proven more difficult. In this sense, we propose an approach to directly translate NL questions into SQL statements. In this study, we present a Sequence-to-Sequence (Seq2Seq) parsing model for the NL to SQL task, powered by the Transformers Architecture exploring the two Language Models (LM): Text-To-Text Transfer Transformer (T5) and the Multilingual pre-trained Text-To-Text Transformer (mT5). Besides, we adopt the transformation-based learning algorithm to update the aggregation predictions based on association rules. The resulting model achieves a new state-of-the-art on the WikiSQL DataSet, for the weakly supervised SQL generation.

Journal of Computer Science
Volume 17 No. 5, 2021, 480-489

DOI: https://doi.org/10.3844/jcssp.2021.480.489

Submitted On: 12 March 2021 Published On: 23 May 2021

How to Cite: Mellah, Y., Rhouati, A., Ettifouri, E. H., Bouchentouf, T. & Belkasmi, M. G. (2021). SQL Generation from Natural Language: A Sequence-to-Sequence Model Powered by the Transformers Architecture and Association Rules. Journal of Computer Science, 17(5), 480-489. https://doi.org/10.3844/jcssp.2021.480.489

  • 4,946 Views
  • 4,321 Downloads
  • 3 Citations

Download

Keywords

  • SQL
  • Text-to-SQL
  • Sequence-to-Sequence
  • Transformers Architecture
  • Multilingual Pre-Trained Text-To-Text Transformer
  • WikiSQL