Evaluating Text Summaries using Divergences of the Probability Distribution

Autores/as

  • Juan Manuel Torres Moreno Université d'Avignon et des Pays de Vaucluse - Laboratoire Informatique d'Avignon
  • Ligia Quintana Torres Universidad Veracruzana
  • Porfirio Toledo Hernández Universidad Veracruzana

DOI:

https://doi.org/10.13053/cys-24-4-3433

Palabras clave:

Kullback-Leibler/Jensen-Shannon divergences, probability distribution, natural language processing, automatic text summarization

Resumen

This paper aims to show that generating and evaluating summaries are two linked but different tasks even when the same Divergence of the Probability Distribution (DPD) is used in both. This result allows the use of DPD functions for evaluating summaries automatically without references and also for generating summaries without falling into inconsistencies.

Biografía del autor/a

Juan Manuel Torres Moreno, Université d'Avignon et des Pays de Vaucluse - Laboratoire Informatique d'Avignon

LIA

Descargas

Publicado

2020-12-02

Número

Sección

Artículos