UI - Disertasi Membership :: Back

UI - Disertasi Membership :: Back

Pendekatan Hybrid Rule Based Dan Deep Learning Untuk Named Entity Recognition Pada Dokumen Kepegawaian Pemerintah Di Indonesia = A Hybrid Rule-Based And Deep Learning Approach For Named Entity Recognition In Indonesian Government Personnel Documents

Tosan Wiar Ramdhani; Indra Budi, promotor; Betty Purwandari, co-promotor; Elin Cahyaningsih, examiner; Dana Indra Sensuse, examiner; Yudho Giri Sucahyo, examiner; Alfan Farizki Wicaksono, examiner; Evi Yulianti, examiner (Fakultas Ilmu Komputer Universitas Indonesia, 2025)

 Abstract

Penerapan Named Entity Recognition (NER) dalam pengelolaan dokumen kepegawaian pemerintah menghadapi tantangan khas, seperti struktur semi-terstruktur, keberadaan entitas dengan pola tetap, serta kebutuhan akurasi tinggi dalam proses ekstraksi informasi. Model deep learning telah menunjukkan performa unggul dalam tugas NER berbahasa Indonesia, namun belum sepenuhnya efektif dalam menangani kekhususan struktur dokumen administratif. Untuk menjawab permasalahan tersebut, penelitian ini mengembangkan pendekatan hybrid yang menggabungkan kekuatan generalisasi dari beberapa model deep learning (IndoBERT, T5, Qwen, dan SahabatAI) dengan ketelitian pendekatan rule based linguistik sebagai mekanisme label refinement. Sistem NER hybrid ini dirancang untuk meminimalkan kesalahan prediksi, khususnya pada entitas-entitas dengan struktur tetap seperti nama, NIP, golongan, atau jabatan. Eksperimen dilakukan pada sepuluh jenis dokumen kepegawaian hasil pindai dari instansi pemerintah daerah, dengan total lebih dari 6.000 dokumen. Hasil penelitian menunjukkan bahwa pendekatan hybrid mampu meningkatkan performa model deep learning, dengan skor rata-rata F1 score 98% pada sepuluh jenis dokumen kepegawaian. Temuan ini mengindikasikan bahwa integrasi metode rule-based ke dalam sistem NER berbasis deep learning dapat secara signifikan meningkatkan akurasi dan efisiensi pengelolaan dokumen kepegawaian di lingkungan pemerintahan.

The application of Named Entity Recognition (NER) in managing government personnel documents faces unique challenges, such as semi-structured formats, the presence of entities with fixed patterns, and the need for high accuracy in information extraction. Deep learning models have demonstrated strong performance in Indonesian NER tasks; however, they are not yet fully effective in handling the specific structural characteristics of administrative documents. To address this issue, this study proposes a hybrid approach that combines the generalization capabilities of several deep learning models (IndoBERT, T5, Qwen, and SahabatAI) with the precision of linguistic rule-based methods as a label refinement mechanism. The hybrid NER system is designed to minimize prediction errors, particularly for fixed-structure entities such as names, employee identification numbers (NIP), ranks, and job titles. Experiments were conducted on eight types of scanned personnel documents collected from regional government agencies, totaling over 6,000 documents. The results indicate that the hybrid approach enhances the performance of deep learning models, achieving an average F1 score of 98% across the ten document types. These findings suggest that integrating rule based methods into deep learning-based NER systems can significantly improve the accuracy and efficiency of personnel document management in the public sector.

 Digital Files: 1

Shelf
 D-Tosan Wiar Ramdhani.pdf :: Download

LOGIN required

 Metadata

Collection Type : UI - Disertasi Membership
Call Number : D-pdf
Main entry-Personal name :
Additional entry-Personal name :
Additional entry-Corporate name :
Study Program :
Subject :
Publishing : Depok: Fakultas Ilmu Komputer Universitas Indonesia, 2025
Cataloguing Source LibUI ind rda
Content Type text
Media Type computer
Carrier Type online resource
Physical Description xi, 114 pages : illustration + appendix
Concise Text
Holding Institution Universitas Indonesia
Location Perpustakaan UI
  • Availability
  • Review
  • Cover
Call Number Barcode Number Availability
D-pdf 07-25-09224815 TERSEDIA
Review:
No review available for this collection: 9999920578029
Cover