PEMBANGKITAN PARAFRASA MENGGUNAKAN METODE TRANSFORMER

FADILLAH, ANNISA LUTHFI and Yusliani, Novi and Rodiah, Desty (2024) PEMBANGKITAN PARAFRASA MENGGUNAKAN METODE TRANSFORMER. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282126049.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282126049_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9MB) | Request a copy
	Text RAMA_55201_09021282126049_0008118205_0021128905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (976kB)
	Text RAMA_55201_09021282126049_0008118205_0021128905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (833kB) | Request a copy
	Text RAMA_55201_09021282126049_0008118205_0021128905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (344kB) | Request a copy
	Text RAMA_55201_09021282126049_0008118205_0021128905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_55201_09021282126049_0008118205_0021128905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (856kB) | Request a copy
	Text RAMA_55201_09021282126049_0008118205_0021128905_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (291kB) | Request a copy
	Text RAMA_55201_09021282126049_0008118205_0021128905_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (211kB) | Request a copy
	Text RAMA_55201_09021282126049_0008118205_0021128905_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (192kB) | Request a copy

Abstract

Paraphrase generation is a part of text generation or Natural Language Generation (NLG) that aims to create paraphrased sentences with a different words or structure from the input sentence without altering its original meaning. This research builds a paraphrase generation system using the Transformer method. The results of the study indicate that the paraphrase generation model was successfully built using the hyperparameter configuration num_layers = 4, d_model = 128, dff = 512, num_heads = 8, dropout rate = 0.2, with a total of 25 epochs. Based on the BLEU evaluation metric, the model achieved scores of 0.48 on BLEU-1, 0.36 on BLEU-2, 0.28 on BLEU-3, and 0.22 on BLEU-4. Additionally, the model achieves a score of 0.50 on the METEOR evaluation metric and a score of 0.55 on the ROUGE-L evaluation metric. This indicates that the model can provide different word structure variations while maintaining semantic similarity. However, the generated paraphrased sentences sometimes use synonyms that are less contextually accurate in Indonesian due to the dataset being derived from translated English paraphrase sentence pairs.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Pembangkitan Parafrasa, Transformer, BLEU, METEOR, ROUGE-L
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Annisa Luthfi Fadillah
Date Deposited:	31 Dec 2024 06:44
Last Modified:	31 Dec 2024 06:44
URI:	http://repository.unsri.ac.id/id/eprint/162006

Actions (login required)

View Item