Skripsi

CLINICAL NAMED ENTITY RECOGNITION PADA DATA BIOMEDIS MENGGUNAKAN MODEL BERT

---

Penilaian

---

Named Entity Recognition (NER) is one of the key tasks in natural language processing (NLP), especially within the biomedical domain, which is complex and filled with specific terminologies. This research focuses on the application of a Clinical Named Entity Recognition model to extract biomedical entities from three datasets: BC2GM, JNLPBA, and NCBI-Disease. Several BERT-based model approaches are used, namely BERT, BERT combined with BiGRU (BERT-BiGRU), and BERT combined with Support Vector Machine (BERT-SVM). Performance evaluation is conducted using precision, recall, and F1-score metrics to assess the effectiveness of entity extraction. Experimental results show that the standard BERT model delivers the best performance on two datasets, BC2GM and NCBI-Disease, with F1-scores of 90% and 92%, respectively. Meanwhile, the BERT-BiGRU model achieves the best performance on the JNLPBA dataset, with an F1-score of 80%. These findings indicate that while BERT generally excels in understanding biomedical context and terminology, combining BERT with BiGRU can provide additional advantages in specific cases, such as with the JNLPBA dataset.

---

Availability

Inventory Code	Barcode	Call Number	Location	Status
2507003418	T175808	T1758082025	Central Library (Reference)	Available but not for loan - Not for Loan

Detail Information

Series Title

-

Call Number

T1758082025

Publisher

Indralaya : Prodi Sistem Komputer, Fakultas Ilmu Komputer Universitas Sriwijaya., 2025

Collation

xviii, 166 hlm.; ilus.; tab.; 29 cm.

Language

Indonesia

ISBN/ISSN

-

Classification

004.07

Content Type

Text

Media Type

-

Carrier Type

-

Edition

-

Subject(s)

Sistem komputer

Specific Detail Info

-

Statement of Responsibility

MI

Other version/related

File Attachment

Comments

---

You must be logged in to post a comment