<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=undefined&type=result"></script>');
-->
</script>

COPY SCRIPT

For further information contact us at helpdesk@openaire.eu

Leveraging Artificial Intelligence to enable interoperability in EOSC

Name: Leveraging Artificial Intelligence to enable interoperability in EOSC
Keywords: EOSC, Large Language Models, AI, Semantic interoperability, Semantic artefacts

descriptionPublicationkeyboard_double_arrow_right Presentation 22 Jan 2025Embargo end date: 22 Jan 2025Publisher:Zenodo

Authors: Gonzalez, Esteban; Tykhonov, Vyacheslav;

doi: 10.5281/zenodo.14729679 , 10.5281/zenodo.14729680

Leveraging Artificial Intelligence to enable interoperability in EOSC

- Summary
- Subjects
- Metrics

Abstract

Presentation on Artificial Intelligence developments in the European Open Science Cloud (EOSC) took place at the EOSC Winter School 2025 in Seville, Spain. Recent advancements in semantic interoperability were highlighted, particularly in the FAIR-Impact and Muse-IT projects. These developments focus on AI-powered solutions for automated semantic link prediction, integrated with semantic artifacts catalogues in order to build knowledge graphs where all concepts interlinked with datasets metadata. A demonstrator of decentralized AI based on Croissant for Machine Learning standard was also presented, showcasing the integration of large language models (LLMs) with knowledge graphs to enable the creation and curation of custom resource collections.

Related Organizations

Universidad Politécnica de Madrid
Spain
Royal Netherlands Academy of Arts and Sciences
Netherlands

Keywords

EOSC, Large Language Models, AI, Semantic interoperability, Semantic artefacts

Impact byBIP!

	citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	0
	popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.	Average
	influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).	Average
	impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.	Average

Found an issue? Give us feedback

Average

Green

Related to Research communities

Netherlands Research Portal

Upload OA version

Are you the author? Do you have the OA version of this publication?

uploadUpload now!