Services on Demand
Journal
Article
Indicators
- Cited by SciELO
- Access statistics
Related links
- Cited by Google
- Similars in SciELO
- Similars in Google
Share
Tecciencia
Print version ISSN 1909-3667
Abstract
ESPINOSA-OVIEDO, Jorge E.; ZULUAGA-MAZO, Abdul and GOMEZ-MONTOYA, Rodrigo A.. Kernel Methods for Improving Text Search Engines Transductive Inference by Using Support Vector Machines. Tecciencia [online]. 2017, vol.12, n.22, pp.51-60. ISSN 1909-3667. https://doi.org/10.18180/tecciencia.2017.22.6.
This paper is intended to present the implementation and testing methodology of Transductive Support Vector Machines (TSVM) proposed by Joachims et al., and extended by Li et al. Initially, Support Vector Machines are explained as optimal classifiers, along with the concept of transductive inference. Along the implementation process, several tests were performed. The data used for such tests was very diverse especially with respect to the dimensionality (number of samples, features, etc.). The ultimate objective was the evaluation of the transductive inference tool in the already developed Intelligent Interface Web Engine from the SISTA group at the Catholic University of Leuven (Belgium).
Keywords : Support Vector Machines; Text Classification; Transductive Inference; Data mining.