Some insights Towards a Unified Semantic Representation of Explanation for eXplainable Artificial Intelligence (XAI) - Archive ouverte HAL
Communication Dans Un Congrès Année : 2019

Some insights Towards a Unified Semantic Representation of Explanation for eXplainable Artificial Intelligence (XAI)

Résumé

Among challenges for eXplainable Artificial Intelligence (XAI) is explanation generation. In this paper we put the stress on this issue by focusing on a semantic representation of the content of an explanation that could be common to any kind of XAI. We investigate knowledge representations, and discuss the benefits of conceptual graph structures for being a basis to represent explanations in AI.

Domaines

Intelligence artificielle [cs.AI] Machine Learning [stat.ML]
Fichier principal
Vignette du fichier
article_IsmailBaaj_NL4XAI2019_Some insights Towards a Unified Semantic Representation.pdf (109.03 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Wassila Ouerdane  : Connectez-vous pour contacter le contributeur

https://hal.science/hal-03102722

Soumis le : mardi 19 avril 2022-18:05:42

Dernière modification le : jeudi 31 octobre 2024-16:08:06

Archivage à long terme le : mercredi 20 juillet 2022-19:04:02

Télécharger pour visualiser

Dates et versions

hal-03102722 , version 1 (19-04-2022)

Identifiants

Citer

Ismaïl Baaj, Jean-Philippe Poli, Wassila Ouerdane. Some insights Towards a Unified Semantic Representation of Explanation for eXplainable Artificial Intelligence (XAI). The 1st workshop on Interactive Natural Language Technology for Explainable Artificial Intelligence (NL4XAI), Oct 2019, Tokyo, Japan. pp.14-19, ⟨10.18653/v1/W19-8404⟩. ⟨hal-03102722⟩

Exporter

BibTeX XML-TEI Dublin Core DC Terms EndNote DataCite

Collections

CEA CNRS LIP6 CENTRALESUPELEC DRT MICS CEA-UPSAY UNIV-PARIS-SACLAY LIST SORBONNE-UNIVERSITE SU-SCIENCES DM2I GS-ENGINEERING GS-COMPUTER-SCIENCE GS-SPORT-HUMAN-MOVEMENT DIN
235 Consultations
174 Téléchargements

Altmetric

Partager

More