SciELO - Scientific Electronic Library Online

 
vol.36 número53En torno a la solución del problema de Orwell en la comunicación gubernamental: Investigación experimental de la estructura de la información en los sitios web índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

Links relacionados

Compartir


Revista signos

versión On-line ISSN 0718-0934

Resumen

VENEGAS V., René. Latent Semantic Analysis: an Overview of its Development. Rev. signos [online]. 2003, vol.36, n.53, pp.121-138. ISSN 0718-0934.  http://dx.doi.org/10.4067/S0718-09342003005300008.

This paper focuses on the development of one of the most recent computational psycholinguistics tools, Latent Semantic Analysis (LSA), considered in its beginning like a human knowledge representation theory and method. This semantic analysis is a statistic model that allows to compare the similarities among textual information segments. This comparison is made in a multidimensional semantic space, based on a singular decomposition value (SVD). This analysis enables to determine the distance and relationships between words, between words and paragraphs, and between paragraphs. This type of analysis concentrates on one of the most important issues for computational psycholinguistics, the possibility to explain the learning generation by means of relationship inference in a great quantity of texts. The theoretical and methodological development frame of the semantic analysis method has been tunned by extended discussion that has taken place between psycholinguistic scientists during the last 12 years. In this paper we present an overview and a critical discussion of the most recent advances on this topic.

Palabras clave : computational psycholinguistics; latent semantic analysis; semantic space.

        · resumen en Español     · texto en Español

 

Creative Commons License Todo el contenido de esta revista, excepto dónde está identificado, está bajo una Licencia Creative Commons