Home // WEB 2025, The Thirteenth International Conference on Building and Exploring Web Based Environments // View article


ORKGEx: Leveraging Language and Vision Models with Knowledge Graphs for Research Contribution Annotation

Authors:
Hassan Hussein
Fahad Ahmed
Allard Oelen
Ralph Ewerth
Sören Auer

Keywords: Human; Multimodal AI; Knowledge Graphs; Human- Machine Collaboration

Abstract:
A major challenge in scholarly information retrieval is the semantic description of research contributions. While Generative Artificial Intelligence (AI) can assist in this regard, we need minimally invasive approaches for engaging users in the process. We introduce an innovative approach to annotating research articles directly within the browser and seamlessly integrate this approach with the Open Research Knowledge Graph (ORKG). This approach combines human intelligence with advanced neural and symbolic AI techniques to extract semantic research contribution descriptions and integrates the resulting AI-driven annotation tool within a web browser environment. Thus, we aim to facilitate user interaction and improve the creation and curation of scholarly knowledge. We evaluate the effectiveness of our neuro- symbolic approach through a comprehensive user study measuring the quality of the AI-assisted annotation process. Additionally, we illustrate the model’s applicability and effectiveness with two use cases in sports analytics and environmental science

Pages: 1 to 8

Copyright: Copyright (c) IARIA, 2025

Publication date: March 9, 2025

Published in: conference

ISSN: 2308-4421

ISBN: 978-1-68558-243-2

Location: Lisbon, Portugal

Dates: from March 9, 2025 to March 13, 2025