Optimizing abstractive summarization with fine-tuned PEGASUS

This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.

Manylion Llyfryddiaeth
Prif Awduron:	Rafi, Sadiul Arefin, Rahman, Naimur, Islam, Kazi Nazibul, Ahmad, Ha-mim
Awduron Eraill:	Sadeque, Farig Yousuf
Fformat:	Traethawd Ymchwil
Iaith:	English
Cyhoeddwyd:	Brac University 2024
Pynciau:	Text summarization Transformer PEGASUS
Mynediad Ar-lein:	http://hdl.handle.net/10361/23571

id	10361-23571
record_format	dspace
spelling	10361-235712024-06-25T21:01:53Z Optimizing abstractive summarization with fine-tuned PEGASUS Rafi, Sadiul Arefin Rahman, Naimur Islam, Kazi Nazibul Ahmad, Ha-mim Sadeque, Farig Yousuf Department of Computer Science and Engineering, Brac University Text summarization Transformer PEGASUS This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023. Cataloged from the PDF version of the thesis. Includes bibliographical references (pages 47-49). Abstractive text summarization is the technique of generating a short and concise summary comprising the salient ideas of a source text without making a subset of the salient sentences from the source text. The introduction of transformer models such as BART, T5, and PEGASUS has made this sort of summarization process more efficient and accurate. The objective of this paper is to analyze the performance of different transformer models, compare them to find an efficient model and fine-tune the model on csebuetnlp/xlsum English corpus. The performance of the generated summaries from the fine-tuned PEGASUS models is evaluated using the ROUGE metric, which basically compares the auto-generated summaries with human-created summaries. The fine-tuned PEGASUS model gives a state-of-the-art performance on the XLSum English Corpus. Sadiul Arefin Rafi Naimur Rahman Kazi Nazibul Islam Ha-mim Ahmad B.Sc in Computer Science 2024-06-25T05:23:39Z 2024-06-25T05:23:39Z 2023 2023-09 Thesis ID 20101120 ID 20101284 ID 20101372 ID 20101286 http://hdl.handle.net/10361/23571 en Brac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission. 49 pages application/pdf Brac University
institution	Brac University
collection	Institutional Repository
language	English
topic	Text summarization Transformer PEGASUS
spellingShingle	Text summarization Transformer PEGASUS Rafi, Sadiul Arefin Rahman, Naimur Islam, Kazi Nazibul Ahmad, Ha-mim Optimizing abstractive summarization with fine-tuned PEGASUS
description	This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2023.
author2	Sadeque, Farig Yousuf
author_facet	Sadeque, Farig Yousuf Rafi, Sadiul Arefin Rahman, Naimur Islam, Kazi Nazibul Ahmad, Ha-mim
format	Thesis
author	Rafi, Sadiul Arefin Rahman, Naimur Islam, Kazi Nazibul Ahmad, Ha-mim
author_sort	Rafi, Sadiul Arefin
title	Optimizing abstractive summarization with fine-tuned PEGASUS
title_short	Optimizing abstractive summarization with fine-tuned PEGASUS
title_full	Optimizing abstractive summarization with fine-tuned PEGASUS
title_fullStr	Optimizing abstractive summarization with fine-tuned PEGASUS
title_full_unstemmed	Optimizing abstractive summarization with fine-tuned PEGASUS
title_sort	optimizing abstractive summarization with fine-tuned pegasus
publisher	Brac University
publishDate	2024
url	http://hdl.handle.net/10361/23571
work_keys_str_mv	AT rafisadiularefin optimizingabstractivesummarizationwithfinetunedpegasus AT rahmannaimur optimizingabstractivesummarizationwithfinetunedpegasus AT islamkazinazibul optimizingabstractivesummarizationwithfinetunedpegasus AT ahmadhamim optimizingabstractivesummarizationwithfinetunedpegasus
_version_	1814307675635187712

Optimizing abstractive summarization with fine-tuned PEGASUS

Eitemau Tebyg