English español
Búsqueda
 

Repositorio de la Universidad de Oviedo > Producción Bibliográfica de UniOvi: RECOPILA > Capítulos de libros >

Use este identificador para citar o enlazar este ítem: http://hdl.handle.net/10651/11808

Título : Aggregating independent and dependent models to learn multi-label classifiers
Autor(es) y otros: Montañés Roces, Elena
Quevedo Pérez, José Ramón
Coz Velasco, Juan José del
Fecha de publicación : 2011
Editorial : Springer
Versión del editor: http://dx.doi.org/10.1007/978-3-642-23783-6_31
Descripción física: p. 484-500
Resumen : The aim of multi-label classi cation is to automatically obtain models able to tag objects with the labels that better describe them. Despite it could seem like any other classi cation task, it is widely known that exploiting the presence of certain correlations between labels helps to improve the classi cation performance. In other words, object descriptions are usually not enough to induce good models, also label information must be taken into account. This paper presents an aggregated approach that combines two groups of classi ers, one assuming independence between labels, and the other considering fully conditional dependence among them. The framework proposed here can be applied not only for multi-label classi cation, but also in multi-label ranking tasks. Experiments carried out over several datasets endorse the superiority of our approach with regard to other methods in terms of some evaluation measures, keeping competitiveness in terms of others
Descripción : European Conference, ECML PKDD 2011, Athens, Greece, September 5-9, 2011
URI : http://hdl.handle.net/10651/11808
ISBN : 9783642237829
Aparece en las colecciones: Capítulos de libros
Informática
Investigaciones y Documentos OpenAIRE

Ficheros en este ítem:

Fichero Tamaño Formato
Aggregating independent and dependent models to learn multi-label classifiers.pdf316,91 kBAdobe PDFVisualizar/Abrir


Exportar a Mendeley


Los ítems de DSpace están protegidos por copyright, con todos los derechos reservados, a menos que se indique lo contrario.

 

Base de Datos de Autoridades Biblioteca Universitaria Consultas / Sugerencias