Arbitrating Two Extractors: A NER-LLM Consolidation Pipeline for Metadata Extraction from Korean Public Domain Right Documents
Milandu Keith Moussavou Boussougou, SeongHun Hwang, Dong-Joo Park
IC-EEECS 2026 (short paper, to appear)
Master Student 석사과정
SeongHun Hwang 황성훈
Links & Contact링크 · 연락처
About 소개
SeongHun leads the named-entity recognition (NER) work on the lab's copyright rights-metadata project, building and evaluating Korean NER models and NER–LLM consolidation pipelines that extract metadata from openly licensed works. He is a co-author of the lab's JSAV 2025 journal article and the IC-EEECS 2026 papers.
Research Interests 연구 관심사
- Named-entity recognition
- information extraction
- and NER–LLM pipelines for rights metadata
Education 학력
- Now
Master's student, Department of Computer Science, Soongsil University
Publications (4) 논문
Auto-listed from the lab's publication index by author name.
Performance Analysis of KLUE-BERT with B-I-O Training Data Composition for Metadata Extraction from Rights Documents as Korean Openly Licensed Works
SeongHun Hwang, Milandu Keith Moussavou Boussougou, Dong-Joo Park
IC-EEECS 2026 (companion short paper, to appear)
한국어 공공저작물 권리문서 메타데이터 추출을 위한 B-I-O 태깅 기반 학습데이터 구성에 따른 Klue BERT 성능 분석
황성훈 et al.
KCC 2026 (한국컴퓨터종합학술대회) — short paper, submitted
⚠ under verification
공유저작물 자동 정보 추출을 위한 미세조정 BERT-BiLSTM-CRF NER 모델의 성능 및 안정성 분석
황성훈, Milandu Keith Moussavou Boussougou, 박동주
한국소프트웨어감정평가학회 논문지 (Journal of Software Assessment and Valuation) 21(4):53–61