2004
DOI: 10.1007/978-3-540-30222-3_28
|View full text |Cite
|
Sign up to set email alerts
|

Océ at CLEF 2003

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0

Year Published

2004
2004
2004
2004

Publication Types

Select...
2

Relationship

0
2

Authors

Journals

citations
Cited by 2 publications
(2 citation statements)
references
References 2 publications
0
2
0
Order By: Relevance
“…For the English, Italian and Spanish languages, however, the simple adaptation of the underlying Okapi model parameters only marginally enhanced retrieval effectiveness (from +1.4% to +3.0%). By modifying the values of these parameters, Brand and Brünner (2003) were able to make more detailed evaluations of their effects on retrieval effectiveness, showing that an appropriate value for the parameter k 1 is around 1.6 and for b, the best value seems to be around 0.5. These authors also demonstrate that varying the value of b will have more impact on retrieval effectiveness.…”
Section: Monolingual Ir Learning Curvementioning
confidence: 99%
“…For the English, Italian and Spanish languages, however, the simple adaptation of the underlying Okapi model parameters only marginally enhanced retrieval effectiveness (from +1.4% to +3.0%). By modifying the values of these parameters, Brand and Brünner (2003) were able to make more detailed evaluations of their effects on retrieval effectiveness, showing that an appropriate value for the parameter k 1 is around 1.6 and for b, the best value seems to be around 0.5. These authors also demonstrate that varying the value of b will have more impact on retrieval effectiveness.…”
Section: Monolingual Ir Learning Curvementioning
confidence: 99%
“…We will address some of these approaches in the following sections. Even so, elements of the same blueprint can be detected in some further experiments by other participants in both the multilingual and bilingual tracks, such as Océ (Brand and Brünner 2003), University of Exeter (Lam-Adesina and Jones 2003) and others. The challenge remains to prove that the success of this specific blueprint is generalizable to other test collections and operational settings.…”
Section: A Successful Blueprint For a Multilingual Retrieval Systemmentioning
confidence: 82%