Which Extractive Summarization Method For Malay Texts?

Ranaivo-Malançon, Bali and Hazimah, Iboi (2017) Which Extractive Summarization Method For Malay Texts? Proceedings of the 6th International Conference on Computing and Informatics, ICOCI 2017. ISSN 2289-3784

[img]
Preview
PDF
WHICH EXTRACTIVE SUMMARIZATION METHOD (abstract).pdf

Download (447kB) | Preview
Official URL: http://icoci.cms.net.my/PROCEEDINGS/2017/Pdf_Versi...

Abstract

The number of texts written in Malay increases every day. When these texts are lengthy, interested readers tend to skim through them. Automatic text summarization may assist these readers to get access to the important parts of the texts without scanning from the beginning to the end. As of today, only few Malay text summarizers have been presented in the literature. Therefore, a comparative study of three extractive summarization methods (Luhn’s method, Edmundson’s method, and LexRank method) was undertaken and the results are reported in this paper. The aim of the study is to determine the adequate extractive method. Several experiments were conducted by comparing the results of three extractive methods with human extracts as well as human abstracts. It appears that the Luhn’s method, one of the oldest automatic extractive summarization, shows a good perfor-mance while tested on 14 Malay abstract summaries and 20 Malay extrac-tive summaries.

Item Type: Article
Additional Information: Information, Communication and Creative Technology
Uncontrolled Keywords: extractive summarization, Luhn’s method, Edmundson’s meth-od, LexRank method, Malay text, unimas, university, universiti, Borneo, Malaysia, Sarawak, Kuching, Samarahan, ipta, education, research, Universiti Malaysia Sarawak
Subjects: T Technology > T Technology (General)
Divisions: Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology
Faculties, Institutes, Centres > Faculty of Computer Science and Information Technology
Academic Faculties, Institutes and Centres > Faculty of Computer Science and Information Technology
Depositing User: Karen Kornalius
Date Deposited: 21 Aug 2017 07:35
Last Modified: 29 Sep 2022 03:52
URI: http://ir.unimas.my/id/eprint/17337

Actions (For repository members only: login required)

View Item View Item