Authors: Eleftherakis, S., Gkini, O., & Koutrika, G.
Published in: 2nd Workshop on Search, Exploration, and Analysis in Heterogeneous Datastores (SEA Data) 2021
Abstract: 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.
Full text article can be found here.