Visually Connecting Historical Figures Through Event Knowledge Graphs
Human-Computer Interaction
2021-09-21 v1
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.
Keywords
Cite
@article{arxiv.2109.09380,
title = {Visually Connecting Historical Figures Through Event Knowledge Graphs},
author = {Shahid Latif and Shivam Agarwal and Simon Gottschalk and Carina Chrosch and Felix Feit and Johannes Jahn and Tobias Braun and Yanick Christian Tchenko and Elena Demidova and Fabian Beck},
journal= {arXiv preprint arXiv:2109.09380},
year = {2021}
}
Comments
5 pages, 5 figures, short paper at VIS 2021