Intelligent Sketch-based Recurrent Neural Networks Models to Handle Text-to-SQL Task

Youssef Mellah, Zakaria Kaddari, Toumi Bouchentouf, Jamal Berrich, Mohammed Ghaouth Belkasmi

2021

Abstract

Databases store a large amount of current data and information, and to access them, users must be proficient in SQL or an equivalent interface language. Therefore, using a system capable of converting a natural language into an equivalent SQL query would make the data more accessible. In this sense, building natural language interfaces with relational databases is an important and difficult problem in natural language processing (NLP) and a widely studied area, and has recently regained momentum due to the introduction of large-scale datasets. In this article, we present our approach based on the inclusion of words and recurrent neural networks (RNNs), more specifically on long-term memory cells (LSTM) and recurrent gated units (GRU). We also present the DataSet used for training and testing our models, based on WikiSQL, and finally we show where we have reached in terms of accuracy.

Paper Citation

in Harvard Style

Mellah Y., Kaddari Z., Bouchentouf T., Berrich J. and Belkasmi M. (2021). Intelligent Sketch-based Recurrent Neural Networks Models to Handle Text-to-SQL Task. In Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML, ISBN 978-989-758-559-3, pages 201-205. DOI: 10.5220/0010731000003101

in Bibtex Style

@conference{bml21,
author={Youssef Mellah and Zakaria Kaddari and Toumi Bouchentouf and Jamal Berrich and Mohammed Ghaouth Belkasmi},
title={Intelligent Sketch-based Recurrent Neural Networks Models to Handle Text-to-SQL Task},
booktitle={Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML,},
year={2021},
pages={201-205},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010731000003101},
isbn={978-989-758-559-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning - Volume 1: BML,
TI - Intelligent Sketch-based Recurrent Neural Networks Models to Handle Text-to-SQL Task
SN - 978-989-758-559-3
AU - Mellah Y.
AU - Kaddari Z.
AU - Bouchentouf T.
AU - Berrich J.
AU - Belkasmi M.
PY - 2021
SP - 201
EP - 205
DO - 10.5220/0010731000003101