CLINICAL NAMED ENTITY RECOGNITION PADA DATA BIOMEDIS MENGGUNAKAN MODEL BIDIRECTIONAL LONG SHORT TERM MEMORY - CONDITIONAL RANDOM FIELD

LAILANI, TRIA and firdaus, firdaus (2025) CLINICAL NAMED ENTITY RECOGNITION PADA DATA BIOMEDIS MENGGUNAKAN MODEL BIDIRECTIONAL LONG SHORT TERM MEMORY - CONDITIONAL RANDOM FIELD. Undergraduate thesis, Sriwijaya University.

Preview	Image RAMA_56201_09011282126121_cover.jpg - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (376kB) | Preview
	Text RAMA_56201_09011282126121.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8MB) | Request a copy
	Text RAMA_56201_09011282126121_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (12MB) | Request a copy
	Text RAMA_56201_09011282126121_0221017801_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (797kB)
	Text RAMA_56201_09011282126121_0221017801_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (327kB) | Request a copy
	Text RAMA_56201_09011282126121_0221017801_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011282126121_0221017801_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (6MB) | Request a copy
	Text RAMA_56201_09011282126121_0221017801_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (197kB) | Request a copy
	Text RAMA_56201_09011282126121_0221017801_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (184kB) | Request a copy
	Text RAMA_56201_09011282126121_0221017801_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (561kB) | Request a copy

Abstract

Advancements in Natural Language Processing (NLP) have improved the extraction of information from unstructured biomedical text, particularly in recognizing clinical named entities like diseases, genes, and proteins. This study evaluates the performance of Bi-LSTM and Bi-LSTM-CRF models for Clinical Named Entity Recognition (CNER) using three benchmark datasets: NCBI-Disease, BC2GM, and JNLPBA. It also investigates the effect of integrating GloVe word embeddings. Results show that Bi-LSTM generally outperforms Bi-LSTM-CRF in precision and recall, while Bi-LSTM-CRF maintains better label consistency. Evaluation is based on precision, recall, and F1-score, with findings supporting the development of more effective CNER models for clinical applications.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Clinical Named Entity Recognition, Bi-LSTM, CRF, GloVe, Biomedical Text, NLP.
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Tria Lailani
Date Deposited:	17 Jul 2025 04:32
Last Modified:	17 Jul 2025 04:32
URI:	http://repository.unsri.ac.id/id/eprint/178860

Actions (login required)

View Item