FINE-TUNING MODEL BERT UNTUK NAMED ENTITY RECOGNITION

YANUAR, ACHMAD FARIZ RIZKY and Yusliani, Novi and Rodiah, Desty (2025) FINE-TUNING MODEL BERT UNTUK NAMED ENTITY RECOGNITION. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_55201_09021382126138_cover.jpg - Cover Image Available under License Creative Commons Public Domain Dedication. Download (504kB) | Preview
	Text RAMA_55201_09021382126138.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_55201_09021382126138_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_55201_09021382126138_0008118205_0021128905_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (939kB)
	Text RAMA_55201_09021382126138_0008118205_0021128905_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (549kB) | Request a copy
	Text RAMA_55201_09021382126138_0008118205_0021128905_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (380kB) | Request a copy
	Text RAMA_55201_09021382126138_0008118205_0021128905_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (698kB) | Request a copy
	Text RAMA_55201_09021382126138_0008118205_0021128905_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_55201_09021382126138_0008118205_0021128905_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (191kB) | Request a copy
	Text RAMA_55201_09021382126138_0008118205_0021128905_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (118kB) | Request a copy

Abstract

A sentence can contain various named entities with important meanings, such as names of people, locations, organizations, and time expressions. However, extracting this information manually requires significant time and resources. Named Entity Recognition (NER) offers an automated solution that improves the efficiency of this task. One method for developing an NER system is by using BERT, a transformer-based model that has proven effective in a wide range of natural language processing tasks. The BERT-base-cased model was fine-tuned using several hyperparameter configurations to identify the best combination based on the F1-score. The evaluation results showed that the best configuration was achieved with a learning rate of 5e-5, a batch size of 32, and 2 epochs, yielding an F1-score of 0.836765

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Named Entity Recognition, BERT, Fine-tuning, F1-Score, Natural Language Processing
Subjects:	T Technology > T Technology (General) > T1-995 Technology (General)
Divisions:	09-Faculty of Computer Science > 55201-Informatics (S1)
Depositing User:	Achmad Fariz Rizky Yanuar
Date Deposited:	04 Jun 2025 01:58
Last Modified:	04 Jun 2025 01:58
URI:	http://repository.unsri.ac.id/id/eprint/175150

Actions (login required)

View Item