NAMED ENTITY RECOGNITION (NER) PADA TEKS BERBAHASA INDONESIA DENGAN FINE-TUNING INDOBERT

ARRIZAL, AFFANDI and Abdiansah, Abdiansah (2024) NAMED ENTITY RECOGNITION (NER) PADA TEKS BERBAHASA INDONESIA DENGAN FINE-TUNING INDOBERT. Undergraduate thesis, Sriwijaya University.

[thumbnail of RAMA_55201_09021182126027.pdf] Text
RAMA_55201_09021182126027.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (6MB) | Request a copy
[thumbnail of RAMA_55201_09021182126027_TURNITIN.pdf] Text
RAMA_55201_09021182126027_TURNITIN.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy
[thumbnail of RAMA_55201_09021182126027_0001108401_01_front_ref.pdf] Text
RAMA_55201_09021182126027_0001108401_01_front_ref.pdf - Accepted Version
Available under License Creative Commons Public Domain Dedication.

Download (1MB)
[thumbnail of RAMA_55201_09021182126027_0001108401_02.pdf] Text
RAMA_55201_09021182126027_0001108401_02.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (539kB) | Request a copy
[thumbnail of RAMA_55201_09021182126027_0001108401_03.pdf] Text
RAMA_55201_09021182126027_0001108401_03.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (560kB) | Request a copy
[thumbnail of RAMA_55201_09021182126027_0001108401_04.pdf] Text
RAMA_55201_09021182126027_0001108401_04.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (598kB) | Request a copy
[thumbnail of RAMA_55201_09021182126027_0001108401_05.pdf] Text
RAMA_55201_09021182126027_0001108401_05.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (1MB) | Request a copy
[thumbnail of RAMA_55201_09021182126027_0001108401_06.pdf] Text
RAMA_55201_09021182126027_0001108401_06.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (183kB) | Request a copy
[thumbnail of RAMA_55201_09021182126027_0001108401_07_ref.pdf] Text
RAMA_55201_09021182126027_0001108401_07_ref.pdf - Bibliography
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (194kB) | Request a copy
[thumbnail of RAMA_55201_09021182126027_0001108401_08_lamp.pdf] Text
RAMA_55201_09021182126027_0001108401_08_lamp.pdf - Accepted Version
Restricted to Repository staff only
Available under License Creative Commons Public Domain Dedication.

Download (4MB) | Request a copy

Abstract

Pengolahan dokumen tekstual sering kali membutuhkan identifikasi informasi penting seperti nama orang, tempat, dan lembaga, namun proses manual memakan waktu dan kurang efisien. Named Entity Recognition (NER) menjadi solusi otomatis untuk tugas ini, tetapi penerapannya dalam bahasa Indonesia menghadapi tantangan seperti variasi dialek dan struktur linguistik yang kompleks. Penelitian ini menggunakan metodologi fine-tuning pada model 'indobenchmark/indobert-base-p2' dengan dataset NER-Grit dari repositori GitHub untuk menghadapi tantangan struktur linguistik bahasa Indonesia yang beragam. Model diuji menggunakan berbagai konfigurasi parameter untuk memperoleh hasil optimal. Evaluasi menunjukkan bahwa konfigurasi terbaik dengan learning rate 5e-6, batch size 8, dan 10 epoch menghasilkan nilai f1-score 0,7420 (atau 74,20%) dan nilai loss 0,3673. Penelitian ini berkontribusi pada pengembangan sistem NER yang lebih adaptif terhadap variasi domain dan dialek dalam bahasa Indonesia, sehingga mendukung pengolahan informasi secara lebih cepat dan akurat untuk berbagai kebutuhan analitik dan aplikasi praktis. Kata Kunci: Named Entity Recognition, IndoBERT, Fine-tuning, Pemrosesan Bahasa Alami

Item Type: Thesis (Undergraduate)
Uncontrolled Keywords: Named Entity Recognition, IndoBERT, Fine-tuning, Pemrosesan Bahasa Alami
Subjects: Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions: 09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User: Affandi Arrizal
Date Deposited: 02 Jan 2025 04:04
Last Modified: 02 Jan 2025 04:04
URI: http://repository.unsri.ac.id/id/eprint/161994

Actions (login required)

View Item View Item