DARE Lab

Bridging the gap between users and data.

Athena Research Center
Athens, Greece
Data is considered the 21st century's most valuable commodity and is growing at an exponential rate. Despite technological advances both in the data exploration and data management domains, our ability to leverage data still falls behind in bridging the chasm between users and data.

Our research emerges at the intersection of data management, deep learning, natural language processing, and the ethical aspects of AI. We are specifically investigating how AI can help us build tools that enable us to seamlessly access different types of data, starting from the lowest level of how to understand data and queries and learn how to best process user queries, going up the data stack closer to the user, where the goal is to understand user intention and enable a more natural dialogue with the data, ensuring that fairness and ethical considerations are integral to this process.


Research Areas

News

Nov 20, 2023 ScienceBenchmark has been accepted at VLDB’24! This is a joint work with ZHAW on Text-to-SQL benchmarking and data augmentation for complex scientific DBs.
Sep 29, 2023 Our paper “QPSeeker: An Efficient Neural Planner combining both data and queries through Variational Inference” has been accepted at EDBT/ICDT 2024!
May 25, 2023 Our tutorial titled “Natural Language Interfaces for Databases with Deep Learning” has been accepted at VLDB’23!
Apr 11, 2023 Congratulations to George Katsogiannis for successfully defending his MSc thesis on “SQL Translation from and to Natural Language”!
Mar 28, 2023 We presented a vision paper on NL Data Interfaces at the BigVis Workshop, held in conjunction with EDBT/ICDT 2023.

Selected Publications

  1. VLDBJ
    A survey on deep learning approaches for text-to-SQL
    The VLDB Journal
  2. VLDB
    DatAgent: the imminent age of intelligent data assistants
    Proceedings of the VLDB Endowment

Funding