Visually Connecting Historical Figures Through Event Knowledge Graphs
This provides a tool for historians and researchers to explore historical connections, but it is incremental as it combines existing methods like knowledge graphs and language models with visualization.
The paper tackled the problem of analyzing relationships between historical figures by developing VisKonnect, a visualization system that uses event knowledge graphs and GPT-3 to generate textual answers and linked visualizations for exploration.
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.