A Deep Dive into Deep Learning Approaches for Text-to-SQL Systems

Presented at the 2021 International Conference on Management of Data (SIGMOD)

Abstract

Data is a prevalent part of every business and scientific domain, but its explosive volume and increasing complexity make data querying challenging even for experts. For this reason, numerous text-to-SQL systems have been developed that enable querying relational databases using natural language. The recent advances on deep neural networks along with the creation of two large datasets specifically made for training text-to-SQL systems, have paved the path for a novel and very promising research area. The purpose of this tutorial is a deep dive into this area, covering state-of-the-art techniques for natural language representation in neural networks, benchmarks that sparked research and competition, recent text-to-SQL systems using deep learning techniques, as well as open problems and research opportunities.

Outline

  1. The Text-to-SQL Problem
  2. Text-to-SQL Landscape
  3. Available Benchmarks
  4. Natural Language Representation
  5. Text-to-SQL Deep Learning Taxonomy
  6. Key Text-to-SQL Systems
  7. Challenges & Research Opportunities

Presenters

George Katsogiannis

Georgia Koutrika

Material

Feel free to download the slides of the tutorial here.