KEYPHRASE EXTRACTION MENGGUNAKAN PRE-TRAINED LANGUAGE MODEL ROBERTA DAN TOPIC GUIDED GRAPH ATTENTION NETWORK

HABIBULLAH, MUHAMMAD RAIHAN and Yusliani, Novi (2023) KEYPHRASE EXTRACTION MENGGUNAKAN PRE-TRAINED LANGUAGE MODEL ROBERTA DAN TOPIC GUIDED GRAPH ATTENTION NETWORK. Undergraduate thesis, Sriwijaya University.

	Text RAMA_55201_09021282025087.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_55201_09021282025087_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12MB) | Request a copy
	Text RAMA_55201_09021282025087_0008118205_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_55201_09021282025087_0008118205_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (750kB) | Request a copy
	Text RAMA_55201_09021282025087_0008118205_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (579kB) | Request a copy
	Text RAMA_55201_09021282025087_0008118205_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_09021282025087_0008118205_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (747kB) | Request a copy
	Text RAMA_55201_09021282025087_0008118205_06.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (9kB) | Request a copy
	Text RAMA_55201_09021282025087_0008118205_07_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (305kB) | Request a copy
	Text RAMA_55201_09021282025087_0008118205_08_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (536kB) | Request a copy

Abstract

In the current digital information era, the vast amount of text from various sources such as websites and academic documents poses a challenge for humans to comprehend the information contained in readings. Keyphrase extraction can be one solution to determine the most relevant words from a scholarly publication. One of the keyphrase extraction methods is the Pre-trained Language Model RoBERTa (Robustly Optimized BERT Pretraining Approach) and TgGAT (Topic Guided Graph Attention Networks). This research aims to perform keyphrase extraction in the Indonesian language using RoBERTa and TgGAT. The dataset utilized for this study consists of 100 scholarly publications from previous research by Plakasa (2022), specifically in the field of Computer Science. Based on the research findings, the configuration of the parameter for the number of keywords or top keyphrases has an impact on the generated keyphrase f-score and accuracy. The evaluation results of this study obtained an f-score of 4.65% and an accuracy of 59.3% with a parameter configuration of 15 top keyphrases.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Keyphrase Extraction, RoBERTa, Topic Guided Graph Attention Networks, f-score, accuracy
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Muhammad Raihan Habibullah
Date Deposited:	17 Jan 2024 03:17
Last Modified:	17 Jan 2024 03:17
URI:	http://repository.unsri.ac.id/id/eprint/138358

Actions (login required)

View Item