publications | George Katsogiannis

2024

VLDB

ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systems

Yi Zhang, Jan Deriu, George Katsogiannis-Meimarakis, and 3 more authors

Proceedings of the VLDB Endowment, 2024

2023

VLDB

Natural Language Interfaces for Databases with Deep Learning

George Katsogiannis-Meimarakis, Mike Xydas, and Georgia Koutrika

Proc. VLDB Endow., Sep 2023

Abs HTML

In the age of the Digital Revolution, almost all human activities, from industrial and business operations to medical and academic research, are reliant on the constant integration and utilisation of ever-increasing volumes of data. However, the explosive volume and complexity of data makes data querying and exploration challenging even for experts, and makes the need to democratise the access to data, even for non-technical users, all the more evident. It is time to lift all technical barriers, by empowering users to access relational databases through conversation. We consider 3 main research areas that a natural language data interface is based on: Text-to-SQL, SQL-to-Text, and Data-to-Text. The purpose of this tutorial is a deep dive into these areas, covering state-of-the-art techniques and models, and explaining how the progress in the deep learning field has led to impressive advancements. We will present benchmarks that sparked research and competition, and discuss open problems and research opportunities with one of the most important challenges being the integration of these 3 research areas into one conversational system.
MSc Thesis

Data Democratisation with Deep Learning: Structured Query Translation from and to Natural Language

George Katsogiannis-Meimarakis

Sep 2023

Abs HTML

While data guides and influences many human activities, the barriers posed by the tools that are needed to retrieve it, such as Structured Query Language (SQL), make data inaccessible for many users. To lift these barriers, researchers have been working on creating natural language interfaces that would allow users to access databases solely through natural language. Natural language interfaces employ Text-to-SQL systems that can translate a natural language question from the user to an SQL query that can retrieve the data they need. Recently, novel Text-to-SQL systems are adopting deep learning methods with very promising results. At the same time, several challenges remain open, making this area an active and flourishing field of research and development. To make real progress in building Text-to-SQL systems, we need to de-mystify what has been done, understand how and when each approach can be used, and, finally, identify the research challenges ahead of us. We present a detailed taxonomy of neural Text-to-SQL systems that will enable a deeper study of all the parts of such a system. This taxonomy will allow us to make a better comparison between different approaches, as well as highlight specific challenges in each step of the process, thus enabling researchers to better strategize their quest towards the “holy grail" of database accessibility. However, how can the user verify that the generated SQL query matches their intent if they are not familiar with SQL? To tackle this problem, a system that can translate the SQL query back to natural language is needed (also known as an SQL-to-Text system). We explore the SQL-to-Text problem, we examine its challenges and peculiarities, and present a Transformer-based model that can generate fluent query explanations. Additionally, we look into the difficulties of automatically evaluating the performance of such a system and we examine how different metrics behave in the SQL-to-Text setting.
BigVis

Natural Language Data Interfaces: From Keyword Search to ChatGPT, are we there yet?

George Katsogiannis-Meimarakis, Christos Tsapelas, and Georgia Koutrika

In Proceedings of the 6th International Workshop on Big Data Visual Exploration and Analytics co-located with EDBT/ICDT 2023 Joint Conference, Sep 2023

HTML
WSDM

Data Democratisation with Deep Learning: The Anatomy of a Natural Language Data Interface

George Katsogiannis-Meimarakis, Mike Xydas, and Georgia Koutrika

In Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining, Sep 2023

Abs HTML

In the age of the Digital Revolution, almost all human activities, from industrial and business operations to medical and academic research, are reliant on the constant integration and utilisation of ever-increasing volumes of data. However, the explosive volume and complexity of data makes data querying and exploration challenging even for experts, and makes the need to democratise the access to data, even for non-technical users, all the more evident. It is time to lift all technical barriers, by empowering users to access relational databases through conversation. We consider 3 main research areas that a natural language data interface is based on: Text-to-SQL, SQL-to-Text, and Data-to-Text. The purpose of this tutorial is a deep dive into these areas, covering state-of-the-art techniques and models, and explaining how the progress in the deep learning field has led to impressive advancements. We will present benchmarks that sparked research and competition, and discuss open problems and research opportunities with one of the most important challenges being the integration of these 3 research areas into one conversational system.
VLDBJ
A survey on deep learning approaches for text-to-SQL

George Katsogiannis-Meimarakis, and Georgia Koutrika

The VLDB Journal, Sep 2023

Abs Bib HTML

To bridge the gap between users and data, numerous text-to-SQL systems have been developed that allow users to pose natural language questions over relational databases. Recently, novel text-to-SQL systems are adopting deep learning methods with very promising results. At the same time, several challenges remain open making this area an active and flourishing field of research and development. To make real progress in building text-to-SQL systems, we need to de-mystify what has been done, understand how and when each approach can be used, and, finally, identify the research challenges ahead of us. The purpose of this survey is to present a detailed taxonomy of neural text-to-SQL systems that will enable a deeper study of all the parts of such a system. This taxonomy will allow us to make a better comparison between different approaches, as well as highlight specific challenges in each step of the process, thus enabling researchers to better strategise their quest towards the “holy grail” of database accessibility.
@article{katsogiannis2023survey, author = {Katsogiannis-Meimarakis, George and Koutrika, Georgia}, title = {A survey on deep learning approaches for text-to-SQL}, journal = {The VLDB Journal}, year = {2023}, issn = {0949-877X}, doi = {10.1007/s00778-022-00776-8}, url = {https://doi.org/10.1007/s00778-022-00776-8}, }

2022

TWC

Data Democratisation with Deep Learning: An Analysis of Text-to-SQL Systems

George Katsogiannis-Meimarakis, and Georgia Koutrika

In Companion Proceedings of the Web Conference 2022, Sep 2022

Abs HTML

In the age of the Digital Revolution, almost all human activities, from industrial and business operations to medical and academic research, are reliant on the constant integration and utilisation of ever-increasing volumes of data. However, the explosive volume and increasing complexity of data makes data querying all the more 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.

2021

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

George Katsogiannis-Meimarakis, and Georgia Koutrika

In Proceedings of the 2021 International Conference on Management of Data, Sep 2021

Abs Bib HTML

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.
@inproceedings{10.1145/3448016.3457543, author = {Katsogiannis-Meimarakis, George and Koutrika, Georgia}, title = {A Deep Dive into Deep Learning Approaches for Text-to-SQL Systems}, year = {2021}, isbn = {9781450383431}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3448016.3457543}, doi = {10.1145/3448016.3457543}, booktitle = {Proceedings of the 2021 International Conference on Management of Data}, pages = {2846–2851}, numpages = {6}, keywords = {deep learning, text-to-SQL}, location = {Virtual Event, China}, series = {SIGMOD/PODS '21}, }

EDBT

Deep Learning Approaches for Text-to-SQL Systems.

George Katsogiannis-Meimarakis, and Georgia Koutrika

In EDBT, Sep 2021

Bib

@inproceedings{katsogiannis2021deep,
  title = {Deep Learning Approaches for Text-to-SQL Systems.},
  author = {Katsogiannis-Meimarakis, George and Koutrika, Georgia},
  booktitle = {EDBT},
  pages = {710--713},
  year = {2021},
}

2020

BSc Thesis

Translating Natural Language to SQL using Deep Learning

George Katsogiannis-Meimarakis

Sep 2020

Abs HTML

Databases contain a vast amount of data, used to support a range of operations, from business operations, scientific experiments to activities in our everyday lives. However they are still inaccessible for non-technical users, without knowledge of Structured Query Language (SQL). Natural language interfaces to databases lift these obstacles for such users and they have recently bloomed. In this thesis, we will start by presenting the NL2SQL problem (translating Natural Language to Structured Query Language), its most important aspects and the anatomy of a NL2SQL system. We will compare some systems and see how each one of them chooses to tackle the problem. In the main part of this work, we will focus on the SQLNet system which uses deep learning methods to tackle the NL2SQL problem. We will also test our own implementation of the system, investigate possible improvements and test how well it works on various cases.