BESKlus : BERT Extractive Summarization with K-Means Clustering in Scientific Paper

Samosir, Feliks Victor Parningotan and Toba, Hapnes and Ayub, Mewati (2022) BESKlus : BERT Extractive Summarization with K-Means Clustering in Scientific Paper. Jurnal Teknik Informatika dan Sistem Informasi, 8 (1). pp. 202-217. ISSN 2443-2229

[img] Text
2022-BESKlus_Lengkap.pdf
Download (3003Kb)
[img] Text
8. Turnitin_BESKlus.pdf
Download (7Mb)

Abstract

This study aims to propose methods and models for extractive text summarization with contextual embedding. To build this model, a combination of traditional machine learning algorithms such as K-Means Clustering and the latest BERT-based architectures such as Sentence-BERT (SBERT) is carried out. The contextual embedding process will be carried out at the sentence level by SBERT. Embedded sentences will be clustered and the distance calculated from the centroid. The top sentences from each cluster will be used as summary candidates. The dataset used in this study is a collection of scientific journals from NeurIPS. Performance evaluation carried out with ROUGE-L gave a result of 15.52% and a BERTScore of 85.55%. This result surpasses several previous models such as PyTextRank and BERT Extractive Summarizer. The results of these measurements prove that the use of contextual embedding is very good if applied to extractive text summarization which is generally done at the sentence level.

Item Type: Article
Contributors:
ContributionContributorsNIDN/NIDKEmail
UNSPECIFIEDSamosir, Feliks Victor ParningotanUNSPECIFIEDUNSPECIFIED
UNSPECIFIEDToba, HapnesUNSPECIFIEDUNSPECIFIED
UNSPECIFIEDAyub, MewatiUNSPECIFIEDUNSPECIFIED
Uncontrolled Keywords: contextual embedding; extractive summarization; k-means clustering; scientific paper; sentence-bert.
Subjects: T Technology > T Technology (General)
Depositing User: Perpustakaan Maranatha
Date Deposited: 09 Nov 2023 06:47
Last Modified: 09 Nov 2023 06:47
URI: http://repository.maranatha.edu/id/eprint/32229

Actions (login required)

View Item View Item
MCUrepository is powered by EPrints 3 which is developed by the School of Electronics and Computer Science at the University of Southampton. More information and software credits.