Combining an explainable model based on ontologies with an explanation interface to classify images

Bellucci, Matthieu; Delestre, Nicolas; Malandain, Nicolas; Zanni-Merk, Cécilia

doi:10.1016/j.procs.2022.09.298

Cited by 3 publications

(4 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Verma et al [30] add a penalty function to encourage sparsity in the optimization problem, as shown in Equation (5).…”

Section: Sparsitymentioning

confidence: 99%

“…The goal of the user study is to verify the relevance and comprehensibility of the explanations. In this preliminary study, the experimental context described in [5] is used. 5 This choice is motivated by privileged access to experts in this domain.…”

Section: Preliminary User Studymentioning

confidence: 99%

“…In this preliminary study, the experimental context described in [5] is used. 5 This choice is motivated by privileged access to experts in this domain.…”

Section: Preliminary User Studymentioning

confidence: 99%

“…We used the Pellet reasoner for the experiments 5. Code, ontology and evaluation data of this experiment are available at this link: https://github.com/matt-bellucci/CEO.…”

mentioning

confidence: 99%

See 3 more Smart Citations

Towards counterfactual explanations for ontologies

Bellucci,

Delestre,

Malandain

et al. 2024

Self Cite

View full text Add to dashboard Cite

Debugging and repairing Web Ontology Language (OWL) ontologies has been a key field of research since OWL became a W3C recommendation. One way to understand errors and fix them is through explanations. These explanations are usually extracted from the reasoner and displayed to the ontology authors as is. In the meantime, there has been a recent call in the eXplainable AI (XAI) field to use expert knowledge in the form of knowledge graphs and ontologies. In this paper, a parallel between explanations for machine learning and for ontologies is drawn. This link enables the adaptation of XAI methods to explain ontologies and their entailments. Counterfactual explanations have been identified as a good candidate to solve the explainability problem in machine learning. The CEO (Counterfactual Explanations for Ontologies) method is thus proposed to explain inconsistent ontologies using counterfactual explanations. A preliminary user study is conducted to ensure that using XAI methods for ontologies is relevant and worth pursuing.

show abstract

“…Verma et al [30] add a penalty function to encourage sparsity in the optimization problem, as shown in Equation (5).…”

Section: Sparsitymentioning

confidence: 99%

Section: Preliminary User Studymentioning

confidence: 99%

“…In this preliminary study, the experimental context described in [5] is used. 5 This choice is motivated by privileged access to experts in this domain.…”

Section: Preliminary User Studymentioning

confidence: 99%

“…We used the Pellet reasoner for the experiments 5. Code, ontology and evaluation data of this experiment are available at this link: https://github.com/matt-bellucci/CEO.…”

mentioning

confidence: 99%

See 2 more Smart Citations