Affordable Access

Test of complementarity on sentence extraction methods

Sociedad Española para el Procesamiento del Lenguaje Natural
Publication Date


Test of Complementarity on Sentence Extraction Methods Prueba de complementariedad para me´todos de extraccio´n de oraciones Alberto Ban˜uelos Moro, Jose´ de Jesu´s Lavalle Mart´ınez B. Universidad Auto´noma de Puebla Fac. de Ciencias de la Computacio´n [email protected], [email protected] He´ctor Jime´nez Salazar Universidad Auto´noma Metropolitana Dept. de Tecnolog´ıas de la Informacio´n [email protected] Resumen: Analizamos tres enfoques para la generacio´n del extracto de un texto con el fin de saber si algu´n me´todo provee a otro caracter´ısticas complementarias. Se aplicaron los me´todos en forma combinada para analizar sus resultados, en un marco teo´rico propuesto. Los tres enfoques tratados fueron los basados: en gra´ficas, en te´rminos clave, y en la representatividad de las oraciones. Utilizando la coleccio´n DUC 2002, el me´todo basado en representatividad fue el mejor. Sin embargo, no se encontraron caracter´ısticas complementarias entre ellos, aunque a partir del ana´lisis se identificaron algunos rasgos relevantes de los me´todos. Palabras clave: extracto automa´tico, caracter´ısticas complementarias de me´todos Abstract: In this work three approaches to sentence extraction methods are an- alyzed. We try to find if the used methods show some complementary features. In order to accomplish this goal, the methods of sentence extraction were applied and combined, analyzing the results in the theoretical framework that we propose. We test three approaches: graph-based, keyword-based and representation-based. The methods were tested using the text collection DUC 2002, obtaining the best performance for a very simple method based on representation index. Even though no complementary methods were found, the results allow to identify some relevant features of the methods. Keywords: sentence extraction method, complementary features of methods 1 Introduction The huge volume of available text in the web contrasts with the quantity of tools to make the gro

There are no comments yet on this publication. Be the first to share your thoughts.


Seen <100 times

More articles like this

The sentence preference test.

on Folia psychiatrica et neurolog... December 1955

The sentence composition test.

on Journal of Clinical Psychology April 1957

[Study of DNA extraction methods for testing for g...

on Shokuhin eiseigaku zasshi. Jou... 2008
More articles like this..