Pseudo genetic and probabilistic-based feature selection method for extractive single document summarization
Date
2011
ISBN
Journal Title
Journal ISSN
Volume Title
Resource Type
Article
Publisher
Asian Research Publishing Network (ARPN)
Journal Title
Pseudo genetic and probabilistic-based feature selection method for extractive single document summarization
Recommended by
Abstract
Text features, as a scoring mechanism, are used to identify the key ideas in a given document to be represented in the text summary. Considering all features within same the level of importance may lead to generate a summary with low quality. In this paper, we present a feature selection method using (pseudo) Genetic probabilistic-based Summarization (PGPSum) model for extractive single document summarization. The proposed method, working as features selection mechanism, is used to extract the weights of features from texts. Then, the weights will be used to tune features' scores in order to optimize the summarization process. In this way, important sentences will be selected for representing the document summary. The results show that, our PGPSum model outperformed Ms-Word and Copernic summarizers benchmarks by obtaining a similarity ratio closest to human benchmark summary. © 2005 - 2011 JATIT & LLS. All rights reserved.
Description
Citation
Journal of Theoretical and Applied Information Technology