Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2021 IEEE Visualization Conference |
| Untertitel | (VIS) |
| Herausgeber (Verlag) | Institute of Electrical and Electronics Engineers Inc. |
| Seiten | 156-160 |
| Seitenumfang | 5 |
| ISBN (elektronisch) | 9781665433358 |
| Publikationsstatus | Veröffentlicht - 2021 |
| Veranstaltung | 2021 IEEE Visualization Conference, VIS 2021 - Virtual, Online, USA / Vereinigte Staaten Dauer: 24 Okt. 2021 → 29 Okt. 2021 |
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.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Angewandte Informatik
- Ingenieurwesen (insg.)
- Medientechnik
- Mathematik (insg.)
- Modellierung und Simulation
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2021 IEEE Visualization Conference : (VIS). Institute of Electrical and Electronics Engineers Inc., 2021. S. 156-160.
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Visually Connecting Historical Figures Through Event Knowledge Graphs
AU - Latif, Shahid
AU - Agarwal, Shivam
AU - Gottschalk, Simon
AU - Chrosch, Carina
AU - Feit, Felix
AU - Jahn, Johannes
AU - Braun, Tobias
AU - Tchenko, Yanick Christian
AU - Demidova, Elena
AU - Beck, Fabian
N1 - Funding Information: This work is partially funded by the German Research Foundation (DFG, Deutsche Forschungsgemeinschaft) under the projects “vgiReports” (424960846) and “WorldKG” (424985896), and the Federal Ministry of Education and Research (BMBF), Germany under “Simple-ML” (01IS18054).
PY - 2021
Y1 - 2021
N2 - 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.
AB - 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.
KW - general public
KW - Knowledge graphs
KW - natural language generation
KW - question answering
KW - visualization
UR - http://www.scopus.com/inward/record.url?scp=85123782645&partnerID=8YFLogxK
U2 - 10.48550/arXiv.2109.09380
DO - 10.48550/arXiv.2109.09380
M3 - Conference contribution
AN - SCOPUS:85123782645
SP - 156
EP - 160
BT - 2021 IEEE Visualization Conference
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2021 IEEE Visualization Conference, VIS 2021
Y2 - 24 October 2021 through 29 October 2021
ER -