Skripsi

PENERAPAN MODEL BIDIRECTIONAL AND AUTOREGRESSIVE TRANSFORMER-BASE UNTUK ABSTRACTIVE TEXT SUMMARIZATION PADA TEKS BERITA BERBAHASA INGGRIS

---

The massive growth of digital information, especially in the form of news articles, demands a system that is able to filter important information efficiently. Abstractive text summarization is a strategic solution in summarizing information by producing new sentences that still represent the main content of the source text. This study aims to apply the Bidirectional and Auto-Regressive Transformers (BART-base) model in the abstractive summarization task of English news texts. The training process is carried out by fine-tuning the BART-base model using the CNN/DailyMail dataset 20.000 data. Performance evaluation is carried out using the ROUGE-1, ROUGE-2, and ROUGE-L metrics to measure the suitability of the summary to human references. The training results show that the model is able to produce relevant summaries with competitive ROUGE scores. In addition, the model results are integrated into the application interface using Streamlit to make it easier for users to generate automatic summaries online. This study not only expands the study of the application of the BART model to news texts, but also provides a practical contribution in the form of a system prototype that can be used to support fast and efficient information consumption.

---

Availability

Detail Information

Series Title

-

Call Number

T1897212025

Publisher

Indralaya : Prodi Teknik Informatika, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xii, 120 hlm.; ilus.; tab.; 29 cm

Language

Indonesia

ISBN/ISSN

-

Classification

006.350 7

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Pemrosesan Bahasa Alami
Prodi Teknik Informatika

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment