SciELO - Scientific Electronic Library Online

 
vol.7 número1Linux embebido en FPGA para sistemas de monitoreo industrialEstudio de viabilidad de una herramienta software para monitorización de tráfico IP en Windows Phone índice de autoresíndice de materiabúsqueda de artículos
Home Pagelista alfabética de revistas  

Servicios Personalizados

Revista

Articulo

Indicadores

  • No hay articulos citadosCitado por SciELO

Links relacionados

  • No hay articulos similaresSimilares en SciELO

Compartir


Revista Cubana de Ciencias Informáticas

versión On-line ISSN 2227-1899

Resumen

RODRIGUEZ BLANCO, Aramis  y  SIMON CUEVAS, Alfredo J.. Method to extract structured information from texts. Rev cuba cienc informat [online]. 2013, vol.7, n.1, pp.55-67. ISSN 2227-1899.

In this work a method for extraction of information structured from Spanish texts is presented, as a base for a Mining of Text proposal development. Extracted information is structured in graph form, specifically in a Concept Map, which constitutes a knowledge representation form based on significant concepts and its relationships in a propositional structure. The proposed method allows to process documents of different formats, and it combines the superficial and deep syntactic analysis or of dependences, entities recognition, linguistic patterns and reference knowledge stored in a Concept Maps corpus, to identify conceptual sentences and relationships among them, to be extracted and represented in the Concept Map. SEINET constitutes the tool that implements the proposed method, and to which have been incorporated a group of benefits that facilitate the efficient and flexible use of the method. Simple cases of study are exposed to exemplify the operation method, and in turn SEINET.

Palabras clave : text mining; information extraction; concept maps; automatic construction of graph from text.

        · resumen en Español     · texto en Español     · Español ( pdf )

 

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