Skripsi

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

---

Penilaian

---

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.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2407000547	T138358	T1383582024	Central Library (Referens)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1383582024

Publisher

Inderalaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2024

Collation

xxv, 221 hlm.; Ilus.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

004.650 7

Content Type

Text

Media Type

unmediated

Carrier Type

-

Edition

-

Subject(s)

Jaringan Komunikasi Komputer
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

SEPTA

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment