With the emergence of use of Linked Data in different application domains, several problems have arisen, such as data incompleteness.Type detection for entities in RDF data is one of the most important tasks in dealing with the incompleteness of Linked Data.In this paper, we propose an approach based on Deep Learning techniques, using an encoderdecoder model with attention mechanism, embedding layer to extract the features of each subject from the RDF triples and the GRU cells to address the problem of vanishing.We use the DBpedia dataset for the training and test phases.Initial test results showed the effectiveness of our model.

Ontology matching is an efficient method to establish interoperability among heterogeneous ontologies. Large-scale ontology matching still remains a big challenge for its long time and large memory space consumption. The actual solution to this problem is ontology partitioning which is also challenging. This paper presents DeepOM, an ontology matching system to deal with this large-scale heterogeneity problem without partitioning using deep learning techniques. It consists on creating semantic embeddings for concepts of input ontologies using a reference ontology, and use them to train an auto-encoder in order to learn more accurate and less dimensional representations for concepts. The experimental results of its evaluation on large ontologies, and its comparison with different ontology matching systems which have participated to the same test challenge, are very encouraging with a precision score of 0.99. They demonstrate the higher efficiency of the proposed system to increase the performance of the large-scale ontology matching task.

In spite of the undeniable success of the ontologies, where they have been widely applied successfully to represent the knowledge in lots of real-world problems, they cannot represent and reason with uncertain knowledge which inherently appears in most domains. To cope with this issue, this article presents a new approach for dealing with rich-uncertainty domains. In fact, it is mainly based on integrating hybrid models which combine both fuzzy logic and Bayesian networks. On the other hand, the Fuzzy multi-entity Bayesian network (FzMEBN) proposed as a hybrid model which enhances the classical multi-entity Bayesian network using fuzzy logic, it can be used to represent and reason with probabilistic and vague knowledge simultaneously. Thus, as a language belongs to the proposed approach, this study proposes a promising solution to overcome the weakness of the Probabilistic Ontology Web Language (PR-OWL) based on FzMEBN to allow dealing with vague and probabilistic knowledge in ontologies. The proposed extension is evaluated with a case study in the medical field (diabetes diseases).

In this paper we present a new mapping approach of owl ontologies, using the reuse technics. We propose also a refinement technic of mapping, to make it more pertinent. Our Mapping approach focuses on computing semantic similarity between concepts of ontologies to map, it is based on a weighted combination of computing similarity methods, we use syntactic, lexical, structural, and semantic technics. The proposed mapping and refinement process makes use of several types of information in a manner that increases the mapping accuracy.

This work is situated in the general context of stored information heterogeneity in a decisional system such as data, metadata and knowledge, for cohabitation and reconciliation of these information by mediation. In this paper we focus on the heterogeneous metadata integration, with the definition of a structural and semantic mediation model. Our aim is to propose a mediation architecture for the heterogeneous sources metadata, represented by XML, RDF and RuleML model, providing to user the metadata transparency. This, by including data structures, of natures fundamentally different, and allowing the decomposition of a query involving multiple sources, to specific queries to these sources, then recompose the result. We use ontology for managing structural and semantic heterogeneity.