Papers by Sarra ben abbes
Communications in computer and information science, Dec 31, 2022
HAL (Le Centre pour la Communication Scientifique Directe), Jan 27, 2020
Le besoin d'anonymisation de données digitales s'accentue dans un contexte de Big Data. Ce consta... more Le besoin d'anonymisation de données digitales s'accentue dans un contexte de Big Data. Ce constat concerne tous les types de données et implique donc les graphes de connaissances. Dans cet article, nous présentons une extension de l'approche d'anatomisation aux données représentées avec le modèle de données RDF.
HAL (Le Centre pour la Communication Scientifique Directe), Jun 25, 2012
HAL (Le Centre pour la Communication Scientifique Directe), Jun 8, 2010
L'essor du Web Sémantique a permis la multiplication des ontologies en ligne, donnant un large ch... more L'essor du Web Sémantique a permis la multiplication des ontologies en ligne, donnant un large choix de ressources mais soulevant par là-même le problème de leurévaluation. La diversité des motivations de construction des ontologies et la complexité des domaines de spécialité rend difficile l'évaluation de la "qualité" des ontologies. Nous mettons ici l'accent sur l'acquisition des classes sémantiques, une des sous-tâches de l'acquisition des connaissances. Nous définissons un cadre d'évaluation permettant de comparer la liste de classes sémantiques produite par un système d'acquisition avec une ontologie de référence où les concepts sont eux-mêmes représentés par un ensemble de termes ou de labels. L'originalité de notre approche consisteà tenir compte des cas d'appariement partiel entre les classes sémantiques et les concepts de référence et donc entre la sortie d'un système d'acquisition et une ontologie de référence. Les premiers résultats expérimentaux montrent l'intérêt de nos propositions. Mots-clés : ontologie, concepts, termes, classes sémantiques,évaluation.
A large effort has been devoted to the development of ontology building tools but it is still dif... more A large effort has been devoted to the development of ontology building tools but it is still difficult to assess their strengths and limitations. Proposed evaluations are hardly reproducible and there is a lack of wellaccepted protocols and data. In this paper, we propose to decompose the evaluation of ontology acquisition process into independent functionalities. We focus on the evaluation of semantic class acquisition considered as a main step in the ontology acquisition process. We propose an approach to automatically evaluate semantic classes of ontologies that offer lexical entries for concepts. It is based on the comparative paradigm (to a gold standard). Its main focus is to compare how similar the generated semantic classes are to the gold standard concerning the disposition of concepts frontiers. This comparison relies on the lexical level and on the hierarchical structure of the "gold" concepts. The propositions are implemented, two experiments are settled on different domains and prove that the measures give a more accurate information on quality of systems' performances.
CRC Press eBooks, Jun 28, 2023
Knowledge Graphs and Semantic Web, 2021
Since large monolithic ontologies are difficult to handle and reuse, ontology modularization has ... more Since large monolithic ontologies are difficult to handle and reuse, ontology modularization has attracted increasing attention. Several approaches and tools have been developed to support ontology modularization. Despite these efforts, a lack of knowledge about characteristics of modularly organized ontologies prevents further development. This work aims at characterizing modular ontologies. Therefore, we analyze existing modular ontologies by applying selected metrics from software engineering in order to identify recurring structures, i.e. patterns in modularly organized ontologies. The contribution is a set of four patterns which characterize modularly organized ontologies.
Résumé. Le chatbot est un agent conversationnel qui communique avec les utilisateurs en langage n... more Résumé. Le chatbot est un agent conversationnel qui communique avec les utilisateurs en langage naturel. Il est fondé sur un système de questions-réponses, les questions traitant l’intention de l’utilisateur. Dans ce contexte, des travaux récents ont été abordés présentant certaines limites. L’originalité de notre approche consiste à combiner les méthodes de traitement automatique du langage naturel avec les techniques du web sémantique. Une ontologie de domaine sert de base de connaissances pour décrire les informations dans un triplestore RDF. Les premiers résultats expérimentaux montrent l’intérêt de nos propositions.
Springer International Publishing eBooks, 2022
CERN European Organization for Nuclear Research - Zenodo, Oct 13, 2022
The European Commission has promoted the deployment of the Digitalisation of Energy Action Plan (... more The European Commission has promoted the deployment of the Digitalisation of Energy Action Plan (DoEAP), in order to develop an efficient, competitive market for a digital energy infrastructure and digital energy services that are both cyber-secure and sustainable. A central aspect of DoEAP is represented by the concept of Energy Data Spaces. Data exchange is crucial for emerging energy data services in the digital energy market and will help suppliers and energy service providers to innovate and cope with an increasing share of renewables in a more decentralised energy system. The data includes metering data, data from consumers such as home appliances, building automation, EV charging stations, or prosumers PV panel & inverters. Its availability and timely sharing and use among the relevant players is key for the energy transition. This document addresses main issues of data exchange in the three interconnected key sectors: energy, buildings and mobility; the analyses focus on existing concepts of data formats and data standards, reflecting on how to facilitate data sharing across the different sectors based on a common data framework. The foremost use cases of European projects and initiatives in the specific sector or at cross-sector level are presented, depicting the current state of data exchange deployments and identifying the necessary actions for the upcoming developments.
Proceedings of the 11th International Conference on Pattern Recognition Applications and Methods
Exploiting experts' domain knowledge represented in the ontology can significantly enhance the qu... more Exploiting experts' domain knowledge represented in the ontology can significantly enhance the quality of the Bayesian network (BN) structure learning. However, in practice, using such information is not a trivial task. In fact, knowledge encompassed in ontologies doesn't share the same semantics as those represented in a BN. To tackle this issue, a large effort has been devoted to create a bridge between both models. But, as far as we know, most state-of-the-art approaches require a Bayesian network-specific ontology for which the BN structure could be easily derived. In this paper, we propose a generic method that allows deriving knowledge from ontology to enhance the learning process of BN. We provide several steps to infer dependencies as well as orientations of some edges between variables. The proposition is implemented and applied to the wind energy domain.
2019 18th IEEE International Conference On Machine Learning And Applications (ICMLA), 2019
Text detection and recognition have witnessed drastic improvements in the field of computer visio... more Text detection and recognition have witnessed drastic improvements in the field of computer vision. This end-toend model comprising of the detection and recognition models scales to provide higher accuracy. The most important phase in this end-to-end approach is the detection phase, as it plays an important role to identify the text. To address this issue, different approaches have been proposed. However, most of the methods produce lower efficiency to detect and recognize real world text. In this paper, we propose a new approach to investigate the challenges that the existing models possess and improve the efficiency of the detection and in turn increases the accuracy of text recognition. The proposed method outperforms the state-ofthe-art approaches due to the use of deblurring and sharpening to reduce noise in the pre-processing stage, followed by the cascade region proposal network model to improve the detection of real world text using non max suppression. Experimentations on real word datasets highlight the effectiveness of our method.
Textual data are available in large unstructured volumes. Processing this data is becoming crucia... more Textual data are available in large unstructured volumes. Processing this data is becoming crucial and document classification is a way of structuring and processing this information based on its content. This paper introduces an effective semantic text mining approach for document classification. The proposed approach Semantic Enriched Deep Learning Architecture (SE-DLA) allows the model to learn simultaneously from the generated semantic vector representations and the original document vectors. We evaluated the proposed method on topic categorizations and multi-label classification. The experiments demonstrate that the proposed hybrid architecture with the additional semantic knowledge improves the results. This approach was compared to some state-of-the-art text classification approaches not including semantic knowledge. The proposed SE-DLA achieved higher accuracy and maintained great results during the experimental process.
2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), 2020
The overflowing of textual data on the web needs an efficient tool that is able to manage and pro... more The overflowing of textual data on the web needs an efficient tool that is able to manage and process data. In this context, automatic text summarization has shown a great importance in several application areas. It aims to create a coherent and fluent short version of a document while preserving of the main information. This method allows for a reduction in reading time by condensing relevant information from a large collection of documents. Several automatic text summarization approaches have been proposed in order to entail shorten parts of the document. These methods have good results, but they still need improvements related to the reliability of sentences extraction, redundancy, semantic relationships between sentences, etc. This paper introduces a new hybrid architecture, combining a 2-layer recurrent neural network (RNN) extractive model and a sequence-to-sequence attentional abstractive model. This method uses the advantages of both extractive and abstractive approaches. A ...
Chatbot is a conversational agent that communicates with users based on natural language. It is f... more Chatbot is a conversational agent that communicates with users based on natural language. It is founded on a question answering system which tries to understand the intent of the user. Several chatbot methods deal with a model based template of question answering. However, these approaches are not able to cope with various questions and can affect the quality of the results. To address this issue, we propose a new semantic question answering approach combining Natural Language Processing (NLP) methods and Semantic Web techniques to analyze user's question and transform it into SPARQL query. An ontology has been developed to represent the domain knowledge of the chatbot. Experimentations show that our approach outperforms state of the art methods.
Chatbot is a conversational agent that communicates with users based on natural language. It is f... more Chatbot is a conversational agent that communicates with users based on natural language. It is founded on a question answering system which tries to understand the intent of the user. Several chatbot methods deal with a model based template of question answering. However, these approaches are not able to cope with various questions and can affect the quality of the results. To address this issue, we propose a new semantic question answering approach combining Natural Language Processing (NLP) methods and Semantic Web techniques to analyze user’s question and transform it into SPARQL query. An ontology has been developed to represent the domain knowledge of the chatbot. Experimentations show that our approach outperforms state of the art methods.
HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific r... more HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L’archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d’enseignement et de recherche français ou étrangers, des laboratoires publics ou privés. Anonymisation de graphes de connaissances par anatomisation Maxime Thouvenot, Olivier Curé, Lynda Temal, Sarra Ben Abbès, Philippe Calvez
Uploads
Papers by Sarra ben abbes