On Modern Text-to-SQL Semantic Parsing Methodologies for Natural Language Interface to Databases: A Comparative Study

• Published in: International Conference on Artificial Intelligence in Information and Communication (ICAIIC) (Online) pp. 390 - 396
• Main Authors: Visperas, Moses, Adoptante, Aunhel John, Borjal, Christalline Joie, Abia, Ma. Teresita, Catapang, Jasper Kyle, Peramo, Elmer
• Format: Conference Proceeding
• Language: English
• Published: IEEE 20.02.2023
• Subjects: Benchmark testing; Decoding; natural language processing; natural language query; Natural languages; NLIDB; semantic parsing; Semantics; Structured Query Language; Syntactics; text-to-SQL
• ISSN: 2831-6983
• DOI: 10.1109/ICAIIC57133.2023.10067134

NLIDB research has gained popularity recently, mainly as a means of enhancing outcomes and performance. This study makes an effort to give readers background information on how the subject has evolved recently using different text-to-SQL procedures and approaches, as well as an appraisal of the advantages and disadvantages of each methodology. In contrast with past studies, this paper describes the search and selection processes and provide an overview of the complete process for each approach under review before making comparisons. The authors also evaluated the performance of each methodology against a widely recognized benchmark dataset. Along with model performance, each model was compared and assessed based on its overall structure and associated processes, such as using pre-trained language models and intermediate representations. The results of this study show that the field of text-to-SQL semantic parsing has advanced significantly in recent years, as seen by the improved performance of the models under consideration. It was clear that most recent developments concentrated on the encoder side, even if each technique follows an encoder-decoder design. The imbalance opens up much room for decoder advancement in subsequent studies. Using pre-trained language models was also noteworthy for improving the models' performances; the authors will consider this for future efforts. The selection of intermediate representations, on the other hand, is wholly arbitrary.