An IRS based on multi-granular linguistic information
Identificadores
URI: http://hdl.handle.net/10481/1210Metadata
Show full item recordEditorial
ISKO Conference
Materia
Information retrieval system Fuzzy multi-granular linguistic
Date
2002Referencia bibliográfica
Herrera-Viedma, E.; Cordón, O.; Herrera, J.C.; Luque, M. "An IRS Based on Multi-Granular Linguistic Information". In: 7th International ISKO Conference, ISKO'2002. Granada (Spain), 2002, pp. 372-378.
Sponsorship
Departamento de Biblioteconomía y Documentación. Departamento de Ciencias de la Computación e Inteligencia Artificial. Universidad de Granada.Abstract
An information retrieval system (IRS) based on fuzzy multi-granular linguistic information is proposed. The system has an evaluation method to process multi-granular linguistic information, in such a way that the inputs to the IRS are represented in a different linguistic domain than the outputs. The system accepts Boolean queries whose terms are weighted by means of the ordinal linguistic values represented by the linguistic variable "Importance" assessed on a label set S. The system evaluates the weighted queries according to a threshold semantic and obtains the linguistic retrieval status values (RSV) of documents represented by a linguistic variable "Relevance" expressed in a different label set S". The advantage of this linguistic IRS with respect to others is that the use of the multi-granular linguistic information facilitates and improves the IRS-user interaction