2006
DOI: 10.3166/dn.9.1.43-60
|View full text |Cite
|
Sign up to set email alerts
|

Calcul de pertinence basée sur la proximité pour la recherche d'information

Abstract: Annabelle.Mercier@emse.fr RÉSUMÉ. Le domaine de la recherche d'information, bien connu à travers les moteurs de recherche sur le web, utilise différents modèles comme le modèle booléen, le modèle vectoriel et la recherche de passage. D'autres approches prenant en compte la proximité des termes de la requête retrouvés dans les documents ont aussi prouvé leur efficacité. Dans ce contexte, nous posons l'hypothèse suivante : plus les termes de la requête se retrouvent proches (et ceci le plus grand nombre de fois… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1

Citation Types

0
1
0

Year Published

2014
2014
2014
2014

Publication Types

Select...
1

Relationship

0
1

Authors

Journals

citations
Cited by 1 publication
(1 citation statement)
references
References 5 publications
0
1
0
Order By: Relevance
“…With Cross Lingual Information Retrieval (CLIR), unlike monolingual IR, we cannot evaluate the adequacy of given result by merely applying a similarity function to queries and documents based, for example, on the vector model [29]. Because the central problem in CLIR is how to retrieve relevant documents in the target language, most CLIR systems include an automatic translation module that is applied to documents and/or queries in order to bring both into a single repository.…”
Section: Introductionmentioning
confidence: 99%
“…With Cross Lingual Information Retrieval (CLIR), unlike monolingual IR, we cannot evaluate the adequacy of given result by merely applying a similarity function to queries and documents based, for example, on the vector model [29]. Because the central problem in CLIR is how to retrieve relevant documents in the target language, most CLIR systems include an automatic translation module that is applied to documents and/or queries in order to bring both into a single repository.…”
Section: Introductionmentioning
confidence: 99%