Mohand Boughanem
Microsoft
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Mohand Boughanem.
INEX'05 Proceedings of the 4th international conference on Initiative for the Evaluation of XML Retrieval | 2005
Karen Sauvagnat; Lobna Hlaoua; Mohand Boughanem
This paper describes experiments carried out with the XFIRM system in the INEX 2005 framework. The XFIRM system uses a relevance propagation method to answer CO and CAS queries. Runs were submitted to the ad-hoc and relevance feedback tracks.
Archive | 2000
Mohand Boughanem; Claude Chrisment; Josiane Mothe; Chantal Soulé-Dupuy; Lynda Tamine
In the past few decades, knowledge based techniques have made an impressive contribution to intelligent information retrieval (IR). These techniques stem from research on artificial intelligence, neural networks (NN) and genetic algorithms (GA) and are used to answer three main IR tasks: information modelling, query evaluation and relevance feedback. The paper describes IR approaches based on connectionist and genetic approaches. Our goal is to take benefits of these techniques to fulfill the user information needs. More precisely a multi-layer NN, Mercure, is used to represent the document space in an associative way, to evaluate the query using spreading activation and to implement a relevance feedback process by relevance back-propagation. Another query reformulation technique is investigated which uses the GA approach. The GA generates several queries that explore different areas of the document space. Experiments and results obtained with both techniques are shown and discussed.
Archive | 2007
Mustapha Baziz; Mohand Boughanem; Yannick Loiseau; Henri Prade
Most of information retrieval (IR) approaches relies on the hypothesis that keywords extracted from a document are sufficient to evaluate the relevance of that document with respect to the query. Such an approach may insufficiently lay bare the semantic contents of the documents. In addition to keywords, automatic indexing methods need external knowledge such as thesauri and ontologies for improving the representation of documents or for expanding queries to related keywords. Moreover, ontologies may be combined with a view of for estimating the relevance of documents, the “proximity” between words, or for expressing flexible queries. In this chapter, we survey several recent approaches. Then, two types of methods are discussed in detail. The first one uses a symbolic pattern matching approach, which is based on possibilistic ontologies (where qualitative necessity and possibility degrees estimate to what extent two terms refer to the same thing). The second type of approaches projects fuzzy set representations of queries and documents on a classical ontology, and compare these projections for rank ordering the documents according to a retrieval status value.
INEX'04 Proceedings of the Third international conference on Initiative for the Evaluation of XML Retrieval | 2004
Karen Sauvagnat; Mohand Boughanem
This paper describes the evaluation of the XFIRM system in INEX 2004 framework. The XFIRM system uses a relevance propagation method to answer queries composed of content conditions and/or structure conditions. Runs were submitted to the ad-hoc (for both CO and VCAS task) and heterogeneous tracks.
engineering of computer-based systems | 2008
M. Ben Aouicha; Mohand Boughanem; Mohamed Tmar; Mohamed Abid
This paper presents an information retrieval model in XML documents based on tree matching. Queries and documents are represented by extended trees. Therefore only one level separates between each node and its indirect descendants. This allows to compare easily structural constraints of the user query and the document structure with flexibility. Thus document fragments (elements) returned in response to the query are the most similar ones to the query tree.
International Workshop of the Initiative for the Evaluation of XML Retrieval | 2006
Lobna Hlaoua; Mouna Torjmen; Karen Pinel-Sauvagnat; Mohand Boughanem
This paper describes experiments carried out with the XFIRM system in the INEX 2006 framework. The XFIRM system uses a relevance propagation method to answer CO and CO+S queries. Runs were submitted to the ad-hoc, relevance feedback and multimedia tracks.
International Workshop of the Initiative for the Evaluation of XML Retrieval | 2011
Cyril Laitang; Karen Pinel-Sauvagnat; Mohand Boughanem
In this paper we present our structured information retrieval model based on subgraphs similarity. Our approach combines a content propagation technique which handles sibling relationships with a document query matching process on structure. The latter is based on tree edit distance (TED) which is the minimum set of insert, delete, and replace operations to turn one tree to another. As the effectiveness of TED relies both on the input tree and the edit costs, we experimented various subtree extraction techniques as well as different costs based on the DTD associated to the Datacentric collection.
Document numérique | 2012
Ines Krichen; Arlind Kopliku; Karen Pinel-Sauvagnat; Mohand Boughanem
La recherche d’information agregee permet, en reponse a une requete, d’agreger des granules d’information provenant de plusieurs sources et de renvoyer a l’utilisateur un ensemble d’informations bien organisees. Le resultat agrege est une alternative a la traditionnelle liste de documents repondant chacun a une partie du besoin utilisateur. Nous nous interessons particulierement dans cet article a la recherche agregee relationnelle, qui se focalise sur les granules d’information classe - instance - attributs. Nous presentons une approche d’agregation des resultats repondant a une requete de type classe, basee sur la detection d’attributs pertinents et presentant les resultats sous forme de tableau. Notre approche s’appuie sur 3 etapes que sont la selection des instances et attributs pertinents a la classe, leur filtrage et le tri des attributs pertinents. Afin de tester cette approche, nous avons evalue la qualite des tableaux retournes a partir du dataset DBpedia. L’evaluation montre que le score des attributs est influence par les instances selectionnees, et que la fonction de ponderation utilisee impacte significativement la qualite des resultats renvoyes.
Document numérique | 2011
Guillaume Cabanac; Gilles Hubert; Mohand Boughanem; Claude Chrisment
Cet article considere la problematique de l’evaluation en recherche d’information, en particulier dans le cadre de Trec avec le programme trec_eval. Nous montrons que les systemes de RI ne sont pas uniquement evalues en fonction de la pertinence des documents qu’ils restituent. En effet, dans le cas de documents ex aequo (trouves avec le meme score) leur nom est utilise pour les departager. Nous assimilons cette facon de departager les ex aequo a un biais experimental qui influence les scores attribues aux systemes, et argumentons en faveur d’une strategie pour les departager plus equitablement. L’etude de 22 editions de Trec revele une difference significative entre la strategie conventionnelle et inequitable de trec_eval et les strategies equitables proposees. Ces resultats experimentaux suggerent l’integration des strategies proposees dans trec_eval afin d’encourager la realisation d’experimentations plus equitables.
text retrieval conference | 1997
Steve Walker; Stephen E. Robertson; Mohand Boughanem; Gareth J. F. Jones; Karen Sparck Jones