| Title | Generation of Textual Explanations in XAI: The Case of Semantic Annotation |
| Publication Type | Conference Paper |
| Year of Publication | 2021 |
| Authors | Poli, Jean-Philippe, Ouerdane, Wassila, Pierrard, Régis |
| Conference Name | 2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) |
| Date Published | July 2021 |
| Publisher | IEEE |
| ISBN Number | 978-1-6654-4407-1 |
| Keywords | annotations, Deep Learning, explanation, fuzzy constraint satisfaction problems, Fuzzy logic, image segmentation, natural language generation, Natural languages, pubcrawl, resilience, Resiliency, Scalability, semantic annotation, Semantics, Vocabulary, xai |
| Abstract | Semantic image annotation is a field of paramount importance in which deep learning excels. However, some application domains, like security or medicine, may need an explanation of this annotation. Explainable Artificial Intelligence is an answer to this need. In this work, an explanation is a sentence in natural language that is dedicated to human users to provide them clues about the process that leads to the decision: the labels assignment to image parts. We focus on semantic image annotation with fuzzy logic that has proven to be a useful framework that captures both image segmentation imprecision and the vagueness of human spatial knowledge and vocabulary. In this paper, we present an algorithm for textual explanation generation of the semantic annotation of image regions. |
| URL | https://ieeexplore.ieee.org/document/9494589 |
| DOI | 10.1109/FUZZ45933.2021.9494589 |
| Citation Key | poli_generation_2021 |
Generation of Textual Explanations in XAI: The Case of Semantic Annotation