Universiti Teknologi Malaysia Institutional Repository

Multi document summarization based on cross-document relation using voting technique

Kumar, Yogan Jaya and Salim, Naomie and Abuobieda, Albaraa and Tawfik, Ameer (2013) Multi document summarization based on cross-document relation using voting technique. In: 2013 International Conference on Computer, Electrical and Electronics Engineering: 'Research Makes a Difference', ICCEEE 2013, 2013, Sudan.

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1109/ICCEEE.2013.6634009

Abstract

News articles which are available through online search often provide readers with large collection of texts. Especially in the case of news story, different news sources reporting on the same event usually returns multiple articles in response to a reader's search. In this work, we first identify cross-document relations from un-annotated texts using Genetic-CBR approach. Following that, we develop a new sentence scoring model based on voting technique over the identified cross-document relations. Our experiments show that incorporating the proposed methods in the summarization process yields substantial improvement over the mainstream methods. The performances of all methods were evaluated using ROUGE - a standard evaluation metric used in text summarization.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:case-based reasoning, cross-document relation, genetic algorithm, machine learning, multi document summarization, voting technique
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:Computing
ID Code:51184
Deposited By: Haliza Zainal
Deposited On:27 Jan 2016 01:53
Last Modified:27 Jun 2017 04:36

Repository Staff Only: item control page