Text-to-SQL: A methodical review of challenges and models

Authors

Ali Buğra KANBUROĞLUFollow
Faik Boray TEKFollow

DOI

10.55730/1300-0632.4077

Abstract

This survey focuses on Text-to-SQL, automated translation of natural language queries into SQL queries. Initially, we describe the problem and its main challenges. Then, by following the PRISMA systematic review methodology, we survey the existing Text-to-SQL review papers in the literature. We apply the same method to extract proposed Text-to-SQL models and classify them with respect to used evaluation metrics and benchmarks. We highlight the accuracies achieved by various models on Text-to-SQL datasets and discuss execution-guided evaluation strategies. We present insights into model training times and implementations of different models. We also explore the availability of Text-to-SQL datasets in non-English languages. Additionally, we focus on large language model (LLM) based approaches for the Text-to-SQL task, where we examine LLM-based studies in the literature and subsequently evaluate the LLMs on the cross-domain Spider dataset. Finally, we conclude with a discussion of future directions for Text-to-SQL research, identifying potential areas of improvement and advancements in this field.

Keywords

Text-to-SQL, large language model, natural language processing, deep learning

First Page

403

Last Page

419

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Recommended Citation

KANBUROĞLU, Ali Buğra and TEK, Faik Boray (2024) "Text-to-SQL: A methodical review of challenges and models," Turkish Journal of Electrical Engineering and Computer Sciences: Vol. 32: No. 3, Article 4. https://doi.org/10.55730/1300-0632.4077
Available at: https://journals.tubitak.gov.tr/elektrik/vol32/iss3/4