Title: Towards an interface for translating natural language questions to SQL: a conceptual framework from a systematic review
Authors: Karam Ahkouk; Mustapha Machkour
Addresses: Team of Engineering and Information Systems, Information Systems and Vision Laboratory, Faculty of Sciences, Ibn Zohr University, Agadir, Morocco ' Team of Engineering and Information Systems, Information Systems and Vision Laboratory, Faculty of Sciences, Ibn Zohr University, Agadir, Morocco
Abstract: Querying relational databases using human language is a complex process that must take into consideration the lack of knowledge of SQL by the end users who use the content of these systems. Many studies published in the last decade are based on limited, unbalanced or even small datasets, thing that is by far not realistic for training and evaluating a model. The SQL structure is rich and the scale of complexity is very large. Moreover, the difference between the natural language, which is a language of communication, and the SQL language that contains details of implementation specific to relational databases, adds more complications to the problem. In this paper, we present a full systematic review of the existing approaches in the task of text to SQL and we introduce the details of our suggested architecture as well as our new approach to tackle the problem of nested queries.
Keywords: natural language; machine translation; deep learning; relational databases; text to SQL translation.
International Journal of Reasoning-based Intelligent Systems, 2020 Vol.12 No.4, pp.264 - 275
Received: 07 Feb 2020
Accepted: 12 May 2020
Published online: 03 Dec 2020 *