Search

the extraction of terms is an important step in building a resource for indexing and many powerful tools are available for several languages. This complex process, which identifies candidate terms may become indexes for annotations or documents, is often subject to the problem of lack of relevance of calculated terms. Consequently, the extraction of terminology from the texts must be strong and solid to handle the errors and suggest better results, without encumbering the user with too many proposals of indexes. It is, in this perspective that we propose here a new indexing approach based on a hybrid model of terminologies extraction using a filtering by elimination terms and which operates on a corpus of annotated images with legends .

This paper focuses on the approach inherent to human learning systems which aims to bring logistical supports to the learning process. Our main concern is to improve this approach which does not fully meet the needs of the entire community of learners. Therefore, our proposed approach includes the learners of the educational system and those who want to upgrade their competences (learning throughout life). In this paper, we present on one hand, the gaps identified in the pedagogical approach of existing learning systems, on the other hand, we pass in review the computing support improvements to these systems. At the end, we propose an architecture of a learning system meeting these objectives.