Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Recolector de Cienci...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
DBLP
Article . 2006
Data sources: DBLP
versions View all 2 versions
addClaim

Un sistema basado en conocimiento para el reconocimiento de implicación textual

Authors: Óscar Ferrández; Rafael M. Terol; Rafael Muñoz 0001; Patricio Martínez-Barco; Manuel Palomar;

Un sistema basado en conocimiento para el reconocimiento de implicación textual

Abstract

Este artículo presenta un sistema para el reconocimiento del fenómeno de implicación textual basado en conocimiento. El sistema propuesto está compuesto por dos componentes: el primero de ellos deriva las formas lógicas asociadas a un par de fragmentos de texto (denominados texto e hipótesis), y una vez obtenidas, el segundo componente aplica varios enfoques con el objetivo de obtener un factor de similitud semántica entre ellas y determinar si se produce implicación textual entre los textos. Todos los enfoques están basados en la base de datos léxica WordNet y las relaciones entre conceptos que esta establece. El sistema ha sido evaluado con los corpus y la metodología de evaluación de la competición PASCAL Second Recognising Textual Entailment consiguiendo un 60% de precisión media.

This paper covers the recognition of textual entailment by means of an approach based on knowledge. Our approach consists of two stages. The first stage infers the logic forms from two fragments of text. These logic forms are obtained by analysing the dependency relations between words. And the second stage carries out several methods in order to achieve a score that determines the semantic similarity between the derived logic forms. Depending on this score the system establishes the existence of an entailment relation. All the methods use the WordNet lexical database as a knowledge source and obtain a semantic similarity score by means of WordNet relations. Our approach has been evaluated within the PASCAL Second RTE Challenge and achieved 60% average precision.

Esta investigación ha sido parcialmente financiada bajo los proyectos CICyT número TIC2003-07158-C04-01

Keywords

Textual entailment, Semantic similarity, WordNet, Logic forms, Implicación textual, Formas lógicas, Similitud semántica

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green