BERT Model-based Natural Language to NoSQL Query Conversion using Deep Learning Approach

Databases are commonly used to store complex and distinct information. With the advancement of the database system, non-relational databases have been used to store a vast amount of data as traditional databases are not sufficient for making queries on a wide range of massive data. However, storing data in a database is always challenging for non-expert users. We propose a conversion technique that enables non-expert users to access and filter data as close to human language as possible from the NoSQL database. Researchers have already explored a variety of technologies in order to develop more precise conversion procedures. This paper proposed a generic NoSQL query conversion learning method to generate a Non-Structured Query Language from natural language. The proposed system includes natural language processing-based text preprocessing and the Levenshtein distance algorithm to extract the collection and attributes if there were any spelling errors. The analysis of the result shows that our suggested approach is more efficient and accurate than other state-of-the-art methods in terms of bilingual understudy scoring with the WikiSQL dataset. Additionally, the proposed method outperforms the existing approaches because our method utilizes a bidirectional encoder representation from a transformer multi-text classifier. The classifier process extracts database operations that might increase the accuracy. The model achieves state-of-the-art performance on WikiSQL, obtaining 88.76% average accuracy.

@article{Hossen2023,
  title     = {BERT Model-based Natural Language to NoSQL Query Conversion using Deep Learning Approach},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {14},
  number    = {2},
  year      = {2023},
  publisher = {The Science and Information Organization},
  author    = {Kazi Mojammel Hossen and Mohammed Nasir Uddin and Minhazul Arefin and Md Ashraf Uddin},
  doi       = {10.14569/IJACSA.2023.0140293},
  url       = {https://doi.org/10.14569/IJACSA.2023.0140293}
}