AskYourDB: An end-to-end system for querying and visualizing relational databases using natural language
This addresses the challenge for business users who lack database expertise, but it is incremental as it builds on existing models with pre- and post-processing steps.
The paper tackles the problem of enabling business users to query relational databases using natural language by proposing an end-to-end system that converts natural language to SQL and visualizes results, achieving unspecified performance improvements through modifications to state-of-the-art models.
Querying databases for the right information is a time consuming and error-prone task and often requires experienced professionals for the job. Furthermore, the user needs to have some prior knowledge about the database. There have been various efforts to develop an intelligence which can help business users to query databases directly. However, there has been some successes, but very little in terms of testing and deploying those for real world users. In this paper, we propose a semantic parsing approach to address the challenge of converting complex natural language into SQL and institute a product out of it. For this purpose, we modified state-of-the-art models, by various pre and post processing steps which make the significant part when a model is deployed in production. To make the product serviceable to businesses we added an automatic visualization framework over the queried results.