khaled khelif | Université Nice Sophia Antipolis (original) (raw)

Papers by khaled khelif

Semantic Patent Clustering for Biomedical Communities Khaled Khelif Aroua Hedhili INRIA Sophia An... more Semantic Patent Clustering for Biomedical Communities Khaled Khelif Aroua Hedhili INRIA Sophia Antipolis Méditerranée 2004 route des Lucioles BP 93, 06902 Sophia Antipolis, FRANCEkhaled.khelif,aroua.hedhili,martine.collard@sophia.inria.fr Martine Collard Abstract ...

A perceived limitation of the current Web is that it is comprised of static links with no connect... more A perceived limitation of the current Web is that it is comprised of static links with no connection to any underlying domain knowledge. The Semantic Web is seen as a potential solution to this problem by delivering semantically related information to users dynamically. However, the benefit to users is rarely questioned and there have been few real-world user evaluations of semantic systems. In this paper we present a user-centred evaluation of three Semantic Web Browsers (SWB) that have been extended as part of the Sealife project. The results presented are based on analysis of the server logs from each application in relation to time taken to perform pre-defined tasks along with the amount of semantic activity carried out. It was found that the user experience was dependent on the SWB used but there was some indication users will be able to find information more quickly and that users will explore semantic features if present.

... l'apprentissage de profils utilisateurs Khaled Khelif1, Yassine Mrabet1, Rose Dieng-... more ... l'apprentissage de profils utilisateurs Khaled Khelif1, Yassine Mrabet1, Rose Dieng-Kuntz1 1 INRIA Sophia Antipolis Méditerranée 2004, route des lucioles 06902 Sophia Antipolis - FRANCE {khaled.khelif, yassine.mrabet. rose.dieng}@sophia.inria.fr ...

Abstract Semantic web approach seems interesting for supporting content mining of millions of pat... more Abstract Semantic web approach seems interesting for supporting content mining of millions of patents accessible through the Web. In this paper, we describe our approach for generating semantic annotations on patents, by relying on the structure and on a semantic representation of patent documents. We use both the structure of the patent documents and their textual contents processed by Natural Language Processing (NLP) tools. This method, primarily aimed at helping biologists use patent information can be generalized to all ...

Web usage mining can play an important role in supporting the navigation on the future Web. In fa... more Web usage mining can play an important role in supporting the navigation on the future Web. In fact detection of common or professional profiles allows browsers and web sites to personalise the user session and to recommend specific resources to the interested people. Semantic web approach seems interesting for this task. We propose in this paper a generic approach for profile detection relying on semantic web technologies. It takes advantages from ontologies, semantic annotations on web resources and inference engines.

Résumé. Les brevets sont une source d'information très riche puisque ce sont des doc... more Résumé. Les brevets sont une source d'information très riche puisque ce sont des documents qui servent à décrire les inventions. L'accès aux documents de brevets en ligne est possible grâce aux efforts des offices nationaux de la propriété intellectuelle. Par ailleurs, ayant des objectifs différents, la présentation de ces documents a pris des formes variées loin d'être unifiées. Ce papier présente une méthode et un système permettant l'analyse de brevets" Patent Mining" pour générer des annotations sémantiques. L'idée ...

Web usage mining can play an important role in supporting the navigation on the future Web. In fa... more Web usage mining can play an important role in supporting the navigation on the future Web. In fact detection of common or professional profiles allows browsers and web sites to personalise the user session and to recommend specific resources to the interested people. Semantic web approach seems interesting for this task. We propose in this paper a generic approach for profile detection relying on semantic web technologies. It takes advantages from ontologies, semantic annotations on web resources and inference engines.

... Remy Bars from Bayers Cropscience, Didier Bourigault for providing us the results of Syntex o... more ... Remy Bars from Bayers Cropscience, Didier Bourigault for providing us the results of Syntex on our corpus, Laurent Alamarguy for his assistance in linguistic domain, Martine Collard, Nhanh le ... Kim S., Alani H., Hall W., Lewis P., Millard D., Shadbolt N. and Weal M. (2002). ...

Journal of Universal Computer Science, 2007

... Rose Dieng-Kuntz INRIA Sophia Antipolis 2004, route des lucioles 06902 Sophia Antipolis - FRA... more ... Rose Dieng-Kuntz INRIA Sophia Antipolis 2004, route des lucioles 06902 Sophia Antipolis - FRANCE Rose.dieng@sophia.inria.fr ... A view on related experiments: trying to identify rela-tions between experiments (local databases, on-line data…) and to discover new research ...

We present an ontology-driven word sense disambiguation process. The main idea consists of using ... more We present an ontology-driven word sense disambiguation process. The main idea consists of using the context of the ambiguous word to decide which class can be assigned to it. The disambiguation relies on similarities between classes assigned to the ambiguous word, classes assigned to terms close to it in the text, and on the type of properties that could occur between them. The computation of the similarity uses domain ontologies to provide semantic distances based on definitions in intension. We tested our approach in the extraction of annotations from biomedical texts.

In this paper, we present the Corese-NeLI semantic Web browser dedicated to navigating resources ... more In this paper, we present the Corese-NeLI semantic Web browser dedicated to navigating resources in the infectious disease domain. We describe an overview of the semantic Web browser and outline its functionality and the knowledge organization system used as a background knowledge for both the annotation and search processes. The evaluation of the vocabulary-based annotation, essential for the semantic browser, uses the National Electronic Library of Infection as a test bed and demonstrates over 96% correct annotations.

Résumé. Cet article décrit le projet MEAT (Mémoire d'Expériences pour l&... more Résumé. Cet article décrit le projet MEAT (Mémoire d'Expériences pour l'Analyse du Transcriptome) dont le but est d'assister les biologistes travaillant dans le domaine des puces à ADN, pour l'interprétation et la validation de leurs résultats. Nous proposons une ...

Semantic web approach seems interesting for supporting content mining of millions of patents acce... more Semantic web approach seems interesting for supporting content mining of millions of patents accessible through the Web. In this paper, we describe our approach for generating semantic annotations on patents, by relying on the structure and on a semantic representation of patent documents. We use both the structure of the patent documents and their textual contents processed by Natural Language Processing (NLP) tools. This method, primarily aimed at helping biologists use patent information can be generalized to all kinds of domains or of structured documents.

Semantic Patent Clustering for Biomedical Communities Khaled Khelif Aroua Hedhili INRIA Sophia An... more Semantic Patent Clustering for Biomedical Communities Khaled Khelif Aroua Hedhili INRIA Sophia Antipolis Méditerranée 2004 route des Lucioles BP 93, 06902 Sophia Antipolis, FRANCEkhaled.khelif,aroua.hedhili,martine.collard@sophia.inria.fr Martine Collard Abstract ...

A perceived limitation of the current Web is that it is comprised of static links with no connect... more A perceived limitation of the current Web is that it is comprised of static links with no connection to any underlying domain knowledge. The Semantic Web is seen as a potential solution to this problem by delivering semantically related information to users dynamically. However, the benefit to users is rarely questioned and there have been few real-world user evaluations of semantic systems. In this paper we present a user-centred evaluation of three Semantic Web Browsers (SWB) that have been extended as part of the Sealife project. The results presented are based on analysis of the server logs from each application in relation to time taken to perform pre-defined tasks along with the amount of semantic activity carried out. It was found that the user experience was dependent on the SWB used but there was some indication users will be able to find information more quickly and that users will explore semantic features if present.

... l'apprentissage de profils utilisateurs Khaled Khelif1, Yassine Mrabet1, Rose Dieng-... more ... l'apprentissage de profils utilisateurs Khaled Khelif1, Yassine Mrabet1, Rose Dieng-Kuntz1 1 INRIA Sophia Antipolis Méditerranée 2004, route des lucioles 06902 Sophia Antipolis - FRANCE {khaled.khelif, yassine.mrabet. rose.dieng}@sophia.inria.fr ...

Abstract Semantic web approach seems interesting for supporting content mining of millions of pat... more Abstract Semantic web approach seems interesting for supporting content mining of millions of patents accessible through the Web. In this paper, we describe our approach for generating semantic annotations on patents, by relying on the structure and on a semantic representation of patent documents. We use both the structure of the patent documents and their textual contents processed by Natural Language Processing (NLP) tools. This method, primarily aimed at helping biologists use patent information can be generalized to all ...

Web usage mining can play an important role in supporting the navigation on the future Web. In fa... more Web usage mining can play an important role in supporting the navigation on the future Web. In fact detection of common or professional profiles allows browsers and web sites to personalise the user session and to recommend specific resources to the interested people. Semantic web approach seems interesting for this task. We propose in this paper a generic approach for profile detection relying on semantic web technologies. It takes advantages from ontologies, semantic annotations on web resources and inference engines.

Résumé. Les brevets sont une source d'information très riche puisque ce sont des doc... more Résumé. Les brevets sont une source d'information très riche puisque ce sont des documents qui servent à décrire les inventions. L'accès aux documents de brevets en ligne est possible grâce aux efforts des offices nationaux de la propriété intellectuelle. Par ailleurs, ayant des objectifs différents, la présentation de ces documents a pris des formes variées loin d'être unifiées. Ce papier présente une méthode et un système permettant l'analyse de brevets" Patent Mining" pour générer des annotations sémantiques. L'idée ...

Web usage mining can play an important role in supporting the navigation on the future Web. In fa... more Web usage mining can play an important role in supporting the navigation on the future Web. In fact detection of common or professional profiles allows browsers and web sites to personalise the user session and to recommend specific resources to the interested people. Semantic web approach seems interesting for this task. We propose in this paper a generic approach for profile detection relying on semantic web technologies. It takes advantages from ontologies, semantic annotations on web resources and inference engines.

... Remy Bars from Bayers Cropscience, Didier Bourigault for providing us the results of Syntex o... more ... Remy Bars from Bayers Cropscience, Didier Bourigault for providing us the results of Syntex on our corpus, Laurent Alamarguy for his assistance in linguistic domain, Martine Collard, Nhanh le ... Kim S., Alani H., Hall W., Lewis P., Millard D., Shadbolt N. and Weal M. (2002). ...

Journal of Universal Computer Science, 2007

... Rose Dieng-Kuntz INRIA Sophia Antipolis 2004, route des lucioles 06902 Sophia Antipolis - FRA... more ... Rose Dieng-Kuntz INRIA Sophia Antipolis 2004, route des lucioles 06902 Sophia Antipolis - FRANCE Rose.dieng@sophia.inria.fr ... A view on related experiments: trying to identify rela-tions between experiments (local databases, on-line data…) and to discover new research ...

We present an ontology-driven word sense disambiguation process. The main idea consists of using ... more We present an ontology-driven word sense disambiguation process. The main idea consists of using the context of the ambiguous word to decide which class can be assigned to it. The disambiguation relies on similarities between classes assigned to the ambiguous word, classes assigned to terms close to it in the text, and on the type of properties that could occur between them. The computation of the similarity uses domain ontologies to provide semantic distances based on definitions in intension. We tested our approach in the extraction of annotations from biomedical texts.

In this paper, we present the Corese-NeLI semantic Web browser dedicated to navigating resources ... more In this paper, we present the Corese-NeLI semantic Web browser dedicated to navigating resources in the infectious disease domain. We describe an overview of the semantic Web browser and outline its functionality and the knowledge organization system used as a background knowledge for both the annotation and search processes. The evaluation of the vocabulary-based annotation, essential for the semantic browser, uses the National Electronic Library of Infection as a test bed and demonstrates over 96% correct annotations.

Résumé. Cet article décrit le projet MEAT (Mémoire d'Expériences pour l&... more Résumé. Cet article décrit le projet MEAT (Mémoire d'Expériences pour l'Analyse du Transcriptome) dont le but est d'assister les biologistes travaillant dans le domaine des puces à ADN, pour l'interprétation et la validation de leurs résultats. Nous proposons une ...

Semantic web approach seems interesting for supporting content mining of millions of patents acce... more Semantic web approach seems interesting for supporting content mining of millions of patents accessible through the Web. In this paper, we describe our approach for generating semantic annotations on patents, by relying on the structure and on a semantic representation of patent documents. We use both the structure of the patent documents and their textual contents processed by Natural Language Processing (NLP) tools. This method, primarily aimed at helping biologists use patent information can be generalized to all kinds of domains or of structured documents.