Stavroula Eleftherakis

2021

1. VLDB

   DatAgent: the imminent age of intelligent data assistants

   Mandamadiotis, Antonis, Eleftherakis, Stavroula, Glenis, Apostolos, Skoutas, Dimitrios, Stavrakas, Yannis, and Koutrika, Georgia

   Proceedings of the VLDB Endowment 2021

   Abs Bib HTML

   In this demonstration, we present DatAgent, an intelligent data assistant system that allows users to ask queries in natural language, and can respond in natural language as well. Moreover, the system actively guides the user using different types of recommendations and hints, and learns from user actions. We will demonstrate different exploration scenarios that show how the system and the user engage in a human-like interaction inspired by the interaction paradigm of chatbots and virtual assistants.

   @article{mandamadiotis2021datagent,
     title = {DatAgent: the imminent age of intelligent data assistants},
     author = {Mandamadiotis, Antonis and Eleftherakis, Stavroula and Glenis, Apostolos and Skoutas, Dimitrios and Stavrakas, Yannis and Koutrika, Georgia},
     journal = {Proceedings of the VLDB Endowment},
     volume = {14},
     number = {12},
     pages = {2815--2818},
     year = {2021},
     publisher = {VLDB Endowment},
     bibtex_show = {true},
     abbr = {VLDB},
     html = {http://vldb.org/pvldb/vol14/p2815-mandamadiotis.pdf},
     selected = {true}
   }

2. VLDB

   Let the Database Talk Back: Natural Language Explanations for SQL

   Eleftherakis, Stavroula, Gkini, Orest, and Koutrika, Georgia

   Proceedings of the 2nd Workshop on Search, Exploration, and Analysis in Heterogeneous Datastores, co-located with VLDB 2021 2021

   Abs Bib HTML

   Database interaction is often characterized as a non-trivial and time consuming process due to user’s inexperience with the data or the query language. Therefore, there is a need for the databases to be able to "talk back" in order to assist the users during data exploration and eventually lead them to the desired results. In this paper, we tackle the problem of SQL-to-NL by extending the graph-based model of Logos. Our novel extensions include improvements in terms of the system’s translation capabilities and the fluency of the generated explanations. Finally, we report several challenges, highlighted by experiments on different user cases, i.e, astronomy and policy making.

   @article{eleftherakis2021NLforSQL,
     title = {Let the Database Talk Back: Natural Language Explanations for SQL},
     author = {Eleftherakis, Stavroula and Gkini, Orest and Koutrika, Georgia},
     journal = {Proceedings of the 2nd Workshop on Search, Exploration, and Analysis in Heterogeneous Datastores, co-located with VLDB 2021},
     publisher = {CEUR-WS.org},
     year = {2021},
     abbr = {VLDB},
     bibtex_show = {true},
     html = {http://ceur-ws.org/Vol-2929/paper3.pdf}
   }