Visually Connecting Historical Figures Through Event Knowledge Graphs

Year: 2021

Conference: IEEE VIS

Authors: Shahid Latif, Shivam Agarwal, Simon Gottschalk, Carina Chrosch, Felix Feit, Johannes Jahn, Tobias Braun, Yannick Christian Tchenko, Elena Demidova, and Fabian Beck

DOI: 10.1109/VIS49827.2021.9623313

Abstract

Knowledge graphs store information about historical figures and their relationships indirectly through shared events. We developed a visualization system, VisKonnect, for analyzing the intertwined lives of historical figures based on the events they participated in. A user's query is parsed for identifying named entities, and related data is retrieved from an event knowledge graph. While a short textual answer to the query is generated using the GPT-3 language model, various linked visualizations provide context, display additional information related to the query, and allow exploration.

Citation

@inproceedings{Latif2021Visually,
  author     = {Shahid Latif, Shivam Agarwal, Simon Gottschalk, Carina Chrosch, Felix Feit, Johannes Jahn, Tobias Braun, Yannick Christian Tchenko, Elena Demidova, and Fabian Beck},
  title      = {Visually Connecting Historical Figures Through Event Knowledge Graphs},
  booktitle  = {IEEE VIS},
  pages      = {156-160},
  year       = {2021},
  publisher  = {IEEE},
  doi        = {10.1109/VIS49827.2021.9623313},
  paperurl   = {/publications/Latif2021Visually/Latif2021Visually.pdf},
  abstract   = {Knowledge graphs store information about historical figures and their relationships indirectly through shared events. We developed a visualization system, VisKonnect, for analyzing the intertwined lives of historical figures based on the events they participated in. A user's query is parsed for identifying named entities, and related data is retrieved from an event knowledge graph. While a short textual answer to the query is generated using the GPT-3 language model, various linked visualizations provide context, display additional information related to the query, and allow exploration.}
}