An Information-Based Cross-Language Information Retrieval Model

Bo Li 1 Éric Gaussier 1, *
* Auteur correspondant
Abstract : We present in this paper well-founded cross-language extensions of the recently introduced models in the information-based family for information retrieval, namely the LL (log-logistic) and SPL (smoothed power law) models of [4]. These extensions are based on (a) a generalization of the notion of information used in the information-based family, (b) a generalization of the random variables also used in this family, and (c) the direct expansion of query terms with their translations. We then review these extensions from a theoretical point-of-view, prior to assessing them experimentally. The results of the experimental comparisons between these extensions and existing CLIR systems, on three collections and three language pairs, reveal that the cross-language extension of the LL model provides a state-of-the-art CLIR system, yielding the best performance overall.
Type de document :
Communication dans un congrès
Ricardo Baeza-Yates, Arjen P. de Vries, Hugo Zaragoza, B. Barla Cambazoglu, Vanessa Murdock, Ronny Lempel and Fabrizio Silvestri. 34th European Conference on IR Research, ECIR 2012, Apr 2012, Barcelone, Spain. Springer, 7224, pp.281-292, 2012, Lecture Notes in Computer Science (LNCS). <10.1007/978-3-642-28997-2_24>


https://hal.archives-ouvertes.fr/hal-00741099
Contributeur : Eric Gaussier <>
Soumis le : jeudi 11 octobre 2012 - 16:52:36
Dernière modification le : mardi 28 octobre 2014 - 18:35:13

Fichier

Li-ecir2012.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Citation

Bo Li, Éric Gaussier. An Information-Based Cross-Language Information Retrieval Model. Ricardo Baeza-Yates, Arjen P. de Vries, Hugo Zaragoza, B. Barla Cambazoglu, Vanessa Murdock, Ronny Lempel and Fabrizio Silvestri. 34th European Conference on IR Research, ECIR 2012, Apr 2012, Barcelone, Spain. Springer, 7224, pp.281-292, 2012, Lecture Notes in Computer Science (LNCS). <10.1007/978-3-642-28997-2_24>. <hal-00741099>

Exporter

Partager

Métriques

Consultations de
la notice

327

Téléchargements du document

77