Answers are grounded in this paper and cite their sources.
This experimental evaluation demonstrates effective SQL query generation from natural language using a transformer model.
The application of Natural Language Interfaces to Databases (NLIDB) serves as an important means ofreducing the technical and IT competence requirements for database users. The objective of this study isthe development and experimental evaluation of an NLIDB system that leverages a transformer-basedarchitecture to generate SQL queries from user inputs formulated in natural language. The paper presentsa generalized scheme of user interaction with the database via the NLIDB system and describes the mainstages of input query preprocessing, including tokenization, embedding, positional encoding, and thearchitecture of the transformer-based neural network. The proposed model incorporates multi-headattention, which enables effective modeling of input query contexts, as well as the ADAM optimizer. TheSpider corpus was utilized for training and evaluating the model. To assess the performance of the resultingmodel, in addition to accuracy, the BLEU metric was employed to quantitatively evaluate the degree ofcorrespondence between the generated and expected queries, taking lexical similarity into account. Thebest experimental accuracy reached 69% using the BERT-base tokenizer and 63% with the basic Kerastokenizer. The highest BLEU score for the model with the BERT-base tokenizer was 46%, and 43.3% for themodel with the basic Keras tokenizer. A comparative analysis demonstrated the competitiveness of theproposed model, indicating the effectiveness of the adopted solutions. The model performed best on simpleand short queries, while the most challenging cases involved queries with literals that required inter-tablerelationships and domain-specific knowledge.
No takes yet. Share an insight, caveat, or question.
Yalova et al. (2025) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: