Get Started for FREE
Sign up with Facebook Sign up with X
I don't have a Facebook or a X account
|
Bonnes pratiques en documentation
Dernieres informations sur les bonnes pratiques en recherche documentaire, analyse de la documentation, moteurs de recherche,... Curated by Stéphane Cottin |
Your new post is loading...
|
Scooped by
Stéphane Cottin
March 17, 1:16 PM
|
Scoop.it!
Par Antony Belin Note au lecteur : Les article de lois cités ici font référence au contexte juridique français. Différents cas sont possibles concernant la mise-en-place d’un système d’archivage électronique (SAE), qu’il s’agisse de l’Autorité juridique (entité, organisme, collectivité…) propriétaire des données déposées, Autorité d’archivage (AA), ou d’un prestataire tiers-archiveur, Autorité de tiers-archivage (ATA), le tout…
|
|
Scooped by
Stéphane Cottin
March 14, 2:34 AM
|
Scoop.it!
This chapter examines the European Union’s Artificial Intelligence Act (AI Act) through the framework of digital constitutionalism. It explores how the AI
|
|
Scooped by
Stéphane Cottin
March 13, 2:36 PM
|
Scoop.it!
![[2503.05388] Ontology Generation using Large Language Models | Bonnes pratiques en documentation | Scoop.it](https://img.scoop.it/R3Nf-aV-zFCPDr3s1jV_-zl72eJkfbmt4t8yenImKBVvK0kTmF0xjctABnaLJIm9)
The ontology engineering process is complex, time-consuming, and error-prone, even for experienced ontology engineers. In this work, we investigate the potential of Large Language Models (LLMs) to provide effective OWL ontology drafts directly from ontological requirements described using user stories and competency questions. Our main contribution is the presentation and evaluation of two new prompting techniques for automated ontology development: Memoryless CQbyCQ and Ontogenia. We also emphasize the importance of three structural criteria for ontology assessment, alongside expert qualitative evaluation, highlighting the need for a multi-dimensional evaluation in order to capture the quality and usability of the generated ontologies. Our experiments, conducted on a benchmark dataset of ten ontologies with 100 distinct CQs and 29 different user stories, compare the performance of three LLMs using the two prompting techniques. The results demonstrate improvements over the current state-of-the-art in LLM-supported ontology engineering. More specifically, the model OpenAI o1-preview with Ontogenia produces ontologies of sufficient quality to meet the requirements of ontology engineers, significantly outperforming novice ontology engineers in modelling ability. However, we still note some common mistakes and variability of result quality, which is important to take into account when using LLMs for ontology authoring support. We discuss these limitations and propose directions for future research.
|
|
Scooped by
Stéphane Cottin
March 12, 4:25 PM
|
Scoop.it!
Economics Job Market Rumors (EJMR) is an online forum and clearinghouse for information on the academic job market for economists. It also includes content that
|
|
Scooped by
Stéphane Cottin
March 12, 3:40 AM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
March 11, 3:52 AM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
March 6, 11:23 AM
|
Scoop.it!
Cram, Lawrence and Docampo, Domingo and Safón, Vicente, Screening articles by citation reputation (July 22, 2024). Quantitative Science Studies, 0[10.1162/qss_a_00355], Available at SSRN: https://ssrn.com/abstract=5129969
|
|
Scooped by
Stéphane Cottin
February 26, 3:22 AM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
February 25, 2:43 AM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
February 16, 2:21 PM
|
Scoop.it!
Depuis le début du siècle, de nouveaux modèles de diffusion de la recherche scientifique sont apparus. Marchandisant à leur profit l’injonction à l’open access, ils piègent les chercheurs mal informés ou souhaitant répondre plus facilement aux demandes de leurs institutions. Pour éviter la dégradation de la qualité scientifique provoquée par ces mégarevues, il est urgent de repenser les modalités d’expertise et d’évaluation de la recherche.
|
|
Scooped by
Stéphane Cottin
February 9, 1:23 PM
|
Scoop.it!
Par Florence Maraninchi L’année 2025 est déjà particulièrement féconde en nouvelles plus fracassantes les unes que les autres sur les financements, la course aux armements entre la Chine et les USA, le sommet intergalactique sur l’IA à Paris, et les … Continuer la lecture →
|
|
Scooped by
Stéphane Cottin
February 6, 3:18 AM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
February 6, 2:26 AM
|
Scoop.it!
Parsons, Patrick and Niedringhaus, Kristina L. and Zhang, Alex, Artificial Intelligence & the Future of Law Libraries (December 01, 2024). Georgia State University College of Law, Legal Studies Research Paper Forthcoming, Available at SSRN: https://ssrn.com/abstract=5118446 or http://dx.doi.org/10.2139/ssrn.5118446
|
|
Scooped by
Stéphane Cottin
February 4, 3:57 AM
|
Scoop.it!
Le règlement européen sur l'intelligence artificielle (IA) du 13 juin 2024 est paru au Journal officiel de l'Union européenne du 12 juillet. Le Conseil de l'Europe a adopté le 17 mai 2024 un traité international visant à garantir une IA respectueuse des droits fondamentaux. Retour sur l'IA dans l'UE en sept questions avec Vie-publique. |
|
|
Scooped by
Stéphane Cottin
January 29, 2:21 AM
|
Scoop.it!
The creative capacities of generative artificial intelligence (AI) systems can be attributed to an extensive training of the underlying models. This training ut
|
|
Scooped by
Stéphane Cottin
January 29, 2:19 AM
|
Scoop.it!
Purpose: This review evaluates the Citationchaser tool as a research support application for systematic reviews, specifically focusing on its functionali
|
|
Scooped by
Stéphane Cottin
January 28, 2:55 PM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
January 28, 2:47 PM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
January 21, 5:50 PM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
January 21, 2:02 PM
|
Scoop.it!
|
|
Scooped by
Stéphane Cottin
January 17, 1:31 AM
|
Scoop.it!
Ce billet est composé de deux sections : la première est une infographie qui s’inspire de l’article Where does ChatGPT fit into the Framework for Information Literacy? The possibilities and problem…
