News

  • January, 2022: Elected to the VLDB Endowment Board of Trustees
  • May 3, 2022: Giving an invited talk on "Fairness in Algorithmic Systems: A Reality or a Fantasy?", Distinguished Lecture Series, Hong Kong Baptist University.
  • April 26, 2022: Presenting our tutorial on "Data Democratisation with Deep Learning: An Analysis of Text-to-SQL Systems" at TheWebConf 2022 (with G. Katsogiannis-Meimarakis).
  • April 12, 2022: Participating in the "Futuristic Data Interfaces" panel at DASFAA (online).
  • April 7, 2022: Giving a class on "Fairness in Algorithmic Systems: A Reality or a Fantasy?" at the 1st DEDSSchool on "Ethical and Legal Aspects on Data", April 4 – 8, 2022.
  • April 4, 2022: Giving a talk at the BIFOLD Colloquium on "Intelligent Data Assistants: Democratizing Data Access".
  • March 8, 2022: Participating in the "#BreakTheBias in Science and Technology" panel , co-organized by the Gender Equality Board of the Athena RC with the support of the Innovation Unit for Women. On Youtube.
  • February 24-25 , 2022: Co-organizing the " 1st Greek ACM-W Chapter Winter School on Fairness in AI ".
  • November, 2021: Our survey,"Fairness in Rankings and Recommendations: An Overview", has been accepted at The VLDB Journal (with E. Pitoura and K. Stefanidis).

Highlights

Publications

Georgia has authored and co-authored more than 100 research papers and articles on natural language interfaces, personalization, recommendations, information extraction, entity resolution, and information integration, combining methods from databases, information retrieval, natural language processing and machine learning. For a complete list of publications, please visit DBLP. Citations of Georgia's work can be found in Google Scholar.

Talks/Tutorials

Georgia has given talks and tutorials on text-to-SQL systems, recommendations, personalization, and fairness.

Patents

Georgia's work has been incorporated in commercial products (HP, IBM, CourseRank), and is described in 14 granted patents and 26 patent applications in the US and worldwide. Partial lists of issued patents and patent applications can be found with the help of US Patent and Trademark Office (issued and published), and PatentBuddy ( here ).

Projects

Georgia has participated in several projects in the industry. Currently, she is the technical coordinator for INODE, an EU-funded H2020 project on intelligent data exploration, and member of the EOSC Future project , an EU-funded H2020 project that is implementing the European Open Science Cloud (EOSC) that will give European researchers access to a wide variety of research data and professionally provided services. .

Professional Activities

Georgia is Editor-in-chief for VLDB Journal, Editor-in-Chief for PVLDB Vol 16, PC co-chair for VLDB 2023, a member of the VLDB Endowment Board of Trustees. She is an ACM SIGMOD Associate Information Director and editor of ACM SIGMOD Blog. She is an IEEE Senior member and ACM Senior member. She is EDBT 2023 sponsorship chair.

Exploration

Natural Language Queries

Data is a prevalent part of every business and scientific domain, but its explosive volume and increasing complexity make data querying and exploration challenging even for experts. In an attempt to bridge the gap between users and data, text-to-SQL systems enable users to pose natural language queries over relational databases. We test their limits and build novel systems.

Explanations

One of the biggest hurdles in today's exploration systems is that the system provides no explanations of the results or system choices. Nor does it trigger input from the user, for example, by asking the user to provide more information. We enable a conversational setting, wherethe system can explain results in natural language and can ask clarifications.

Recommendations

In a mixed-initiative setting, the system actively guides the user in what possible actions to perform or data to look at next. We are interested in recommendations in both cold-start (where the user has not given any input) and warm-start settings (where the user has asked one or more queries but may not know what to do next). In the formercase, the goal is to show a set of example or starter queries that the users could use to get some initial answers from the dataset. In the latter case, the system can leverage the users' interactions (queries) to show possible next queries.

Fairness

As we increasingly depend on a variety of data-driven systems to assist us in many aspects of life, such as search engines and recommendation systems, we need to think about the fairness of such systems.