Discourse connectors Discourse Connectors on Indonesian Document Summary

Main Article Content

Irwan Darmawan
Nirwana Haidar Hari


Documents that have a lot of content will make it difficult for readers to find the essence or topics in a document. Therefore, a system that can summarize documents is needed to find the topics discussed by the document. In the research, the documents used as test materials were the final project papers of informatics engineering students, Madura University. Various methods have been applied in summarizing a document, including using the cosine of similarity to determine the weight and the relationship between one sentence and another and then dumping the sentences which have small weight based on the threshold value of the user. If the length of a sentence has little weight, it does not mean that the sentence is not important when it comes to other sentences. Therefore a discourse connector is needed to connect one sentence to another sentence and then it is given weight according to the discourse connector formula. In this study, it is expected that the document has a better value than before as evidenced by a size that is higher than 70%

Article Details

How to Cite
I. Darmawan and N. Haidar Hari, “Discourse connectors Discourse Connectors on Indonesian Document Summary ”, SMARTICS, vol. 7, no. 1, pp. 33-41, Apr. 2021.


[1] Adriani, M., & Nazief, B. 1996. Confix-Stripping: Approach to Stemming Algorithm for Bahasa Indonesia. Faculty of Computer Science University of Indonesia.
[2] Ailin Li, Tao Jiang, Qingshuai Wang, Hongzhi Yu (2016), “The Mixture of TextRank and LexRank Techniques of Single Document Automatic Summarization Research in Tiben”, Journal of International Conference on Intelligent Human-Machine Systems and Cybernetics, IEEE (2016) hal. 514-519.
[3] Alex Alifimoff, “Abstraktive sentence Summarization with Attentive Deep RecurrentNeural Networks,” Journal of stanford, (2015)
[4] Anonymous, 2015. The Rouge Resource Network. [Online] Available at:http://rxnlp.com/rouge-2-0 [Accessed 21 Mei 2019].
[5] Anyman El-Kilany,Iman Saleh (2012), “Unsupervised Document Summarization Using Clusters of Dependency Graph Nodes”, Journal of International Conference on Intelligent Systems Design and Applications (ISDA), IEEE (2012),hal557-561.
[6] Anonymous, 2015. The Rouge Resource Network. [Online] Available at:https://github.com/ nmfpack/code/nmfsc.m [Accessed 22Januari 2018].
[7] Asian J. (2007) “Effective Techniques for Indonesian Text Retrieval”. PhD thesis School of Computer Science and Information Technology RMIT University Australia.
[8] Asian, J., Williams, H. E., & Tahaghoghi, S. M. M. (2005). Stemming Indonesian. In Conferences in Research and Practice in Information Technology Series, Vol. 38, Hal. 307–314.
[9] Babuska, R. (2009). Fuzzy and Neural Control. Netherlands: Delft University of Technology. Daniel D. Lee dan H. Sebastian Seung,Algorithms for Non-negative Matrix Factorization
[10] Jyoti Bora, D. dan Anil Kumar Gupta. (2014) . A Comparative Study Between Fuzzy Clustering Algorithm and Hard Clustering Algorithm dalam

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.