Comparison of the performance of transformer text summarization models in Indonesian language: PEGASUS and GPT-2

Afrah, Ashri Shabrina, Faisal, Muhammad ORCID: https://orcid.org/0000-0003-4884-7254, Aziz, Abdul ORCID: https://orcid.org/0000-0002-9050-9024 and Supriyono, Supriyono ORCID: https://orcid.org/0000-0002-4733-9189 (2025) Comparison of the performance of transformer text summarization models in Indonesian language: PEGASUS and GPT-2. Presented at The 6th International Conference on Cybernetics and Intelligent Systems (ICORIS 2024), 29 Nov - 30 Nov 2024, Universitas Sahid Surakarta, Solo, Indonesia.

Text 23294.pdf - Published Version Restricted to Repository staff only Download (252kB)

Abstract

Manual text summarization is impractical and time-consuming. Therefore, the development of automatic text summarizers has become an interesting topic in Natural Language Processing (NLP). Pre-trained models are often developed from Transformer Models, such as PEGASUS and GPT-2. This research aims to evaluate the performance of Transformer odels trained with Indonesian language datasets for text summarization tasks. The advancement of these models will support the increased utilization of Transformers for developing Indonesian language text summarizers, both for research and industry purposes. Testing with the Confusion Matrix shows that the PEGASUS model achieves the highest mean of precision values, which is 0.887395. On the other hand, the GPT-2 model obtains the best means of recall and f1-score values.

Item Type:	Conference (Paper)
Keywords:	text summarizer; transformer; PEGASUS; GPT-2; confusion matrix
Subjects:	08 INFORMATION AND COMPUTING SCIENCES > 0801 Artificial Intelligence and Image Processing > 080107 Natural Language Processing
Divisions:	Faculty of Technology > Department of Informatics Engineering
Depositing User:	Muhammad Faisal
Date Deposited:	12 Mar 2025 14:20

Downloads

Origin of downloads

Actions (login required)

View Item