About Me

I’m interested in Information Extraction and Retrieval.
Currently, I am a graduate student and advised by Prof. Heuiseok Lim in the NLP & AI Lab.

Contact: [email protected] / [email protected]

Research Interest

• Information Extraction
• Information Retrieval
• Text Representation
• Data Engineering
  

Education

• Korea University (2021/09 ~ )
  • M.S & Ph.D in Computer Science & Engineering
• Dongguk University (2014/03 ~ 2021/02)
  • B.S in Information & Communication Engineering
    

Publication

International Conference

• From Ambiguity to Accuracy: The Transformative Effect of Coreference Resolution on Retrieval-Augmented Generation systems
  Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop)
  Youngjoon Jang, Seongtae Hong, Junyoung Son, Sungjin Park, Chanjun Park, and Heuiseok Lim
  
• Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing
  Findings of the Association for Computational Linguistics: EACL 2024
  Chanjun Park, Jaehyung Seo, Seolhwa Lee, Junyoung Son, Hyeonseok Moon, Sugyeong Eo, Chanhee Lee, Heuiseok Lim
  
  
• Post-hoc Utterance Refining Method by Entity Mining for Faithful Knowledge Grounded Conversations
  The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023)
  Yoonna Jang[*], Suhyune Son[*], Jeongwoo Lee[*], Junyoung Son, Yuna Hur, Jungwoo Lim, Hyeonseok Moon, Kisu Yang, Heuiseok Lim (*: equal contributions)
  
  
• Explore the Way: Exploring Reasoning Path by Bridging Entities for Effective Cross-Document Relation Extraction
  Findings of the Association for Computational Linguistics: EMNLP 2023 (EMNLP 2023 findings)
  Junyoung Son, Jinsung Kim, Jungwoo Lim, Yoonna Jang, Heuiseok Lim
  
  
• GRASP: Guiding model with RelAtional Semantics using Prompt (Oral Presentation)
  The 29th International Conference on Computational Linguistics (COLING 2022)
  Junyoung Son[*], Jinsung Kim[*], Jungwoo Lim[*], Heuiseok Lim (*: equal contributions)
  
  
• KoCHET: a Korean Cultural Heritage corpus for Entity-related Tasks
  The 29th International Conference on Computational Linguistics (COLING 2022)
  Gyungmin Kim[*], Jinsung Kim[*], Junyoung Son[*], Heuiseok Lim (*: equal contributions)
  

International Journal

• Prompt Language Learner with Trigger Generation for Dialogue Relation Extraction
  IEEE Access, vol. 10, pp. 59205-59218, 2022
  Jinsung Kim, Gyeongmin Kim, Junyoung Son, and Heuiseok Lim
  
  
• AI for Patents: A Novel yet Effective and Efficient Framework for Patent Analysis
  IEEE Access, vol. 10, pp. 59205-59218, 2022
  Junyoung Son, Hyeonseok Moon, Jeongwoo Lee, Seolhwa Lee, Chanjun Park, Wonkyung Jung and Heuiseok Lim
  
  
• Enhancing Korean Named Entity Recognition With Linguistic Tokenization Strategies
  IEEE Access, vol. 9, pp. 151814-151823, 2021
  Gyeongmin Kim[*], Junyoung Son[*], Jinsung Kim[*], Hyunhee Lee, and Heuiseok Lim (*: equal contributions)
  

Domestic Conference

• Database retrieval augmented generation framework leveraging Large reasoning language models and Schema linking methods
  Annual Conference on Human and Language Technology (HCLT 2025), pp. 77-82
  Myunghoon Kang, Junyoung Son, Chanhee Park, Aram So, and Heuiseok Lim
  
  
• KURE: Embedding Model for Korean-Specific Retrieval
  Annual Conference on Human and Language Technology (HCLT 2025), pp. 129-134
  Youngjoon Jang, Junyoung Son, Taemin Lee, Seongtae Hong, JeongBae Park, and Heuiseok Lim
  
  
• KomuRet: Korean Community-style Retrieval Benchmark
  Annual Conference on Human and Language Technology (HCLT 2025), pp. 619-624
  Junyoung Son, Youngjoon Jang, Taemin Lee, SeongTae Hong, Yuna Hur, and Heuiseok Lim
  
• An Analysis of Named Entity Recognition System using MLM-based Language Transfer Learning
  The 33rd Annual Conference on Human & Cognitive Language Technology (HCLT 2022)
  Junyoung Son, Gyeongmin Kim, Jinsung Kim, Yuna Hur, and Heuiseok Lim
  
  
• Methodology of Trigger Generation optimized for Dialogue Relation Extraction task
  The 33rd Annual Conference on Human & Cognitive Language Technology (HCLT 2022)
  Gyeongmin Kim, Junyoung Son, Jinsung Kim, Jaechoon Jo, and Heuiseok Lim
  
  
• A Study on Prompt-based Persona Dialogue Generation
  The 33rd Annual Conference on Human & Cognitive Language Technology (HCLT 2022)
  Yoona Jang, Kisu Yang, Hyeonseok Moon, Jaehyung Seo, Jungwoo Lim, Junyoung Son, Chanjun Park, Kinam Park, and Heuiseok Lim
  
  
• Dialogue Relation Extraction using Dialogue Graph
  The 33rd Annual Conference on Human & Cognitive Language Technology (HCLT 2022)
  Jungwoo Lim, Junyoung Son, Jinsung Kim, Yuna Hur, Jaehyung Seo, Yoonna Jang, JeongBae Park, and Heuiseok Lim
  
  
• Categorization and Analysis of Error Types in the Korean Speech Recognition System
  The 33rd Annual Conference on Human & Cognitive Language Technology (HCLT 2021)
  Junyoung Son, Chanjun Park, Jaehyung Seo, and Heuiseok Lim
  
  
• An Effective Segmentation Scheme for Korean Sentence Classification tasks
  The 33rd Annual Conference on Human & Cognitive Language Technology (HCLT 2021)
  Jinsung Kim, Gyeongmin Kim, Junyoung Son, and Heuiseok Lim

Domestic Journal

• A Comparative study on the Effectiveness of Segmentation Strategies for Korean Word and Sentence Classification tasks
  Journal of the Korea Convergence Society
  Jinsung Kim, Gyeongmin Kim, Junyoung Son, Jeongbae Park, and Heuiseok Lim

Preprint

• Improving Korean-English Cross-Lingual Retrieval: A Data-Centric Study of Language Composition and Model Merging
  arXiv, 2025
  Youngjoon Jang, Junyoung Son, Taemin Lee, Seongtae Hong, and Heuiseok Lim
  

Project

• 실감형 문화유산 체험을 위한 애셋 기반 지능형 큐레이션 및 서비스 운영기술 개발: 지식 기반 관계 네트워크 생성을 위한 텍스트 마이닝 연구
  Participation Period: 2021.04.01 ~ 2022.12.31
  
  
• 전문지식 대상 판단결과의 이유/근거를 설명가능한 전문가 의사 결정 지원 인공지능 기술개발: 기관 PM
  Participation Period: 2021.04 ~ Present
  
  
• 특허 문서의 발명 목적 문장 추출 및 Key phrase 추출 기술 개발
  Participation Period: 2021.06.01 ~ 2021.10.31
  
  
• 삼성 모바일 제품 디자인 분석 기술 개발
  Participation Period: 2022.08 ~ 2022.12
  
  
• 영화 추천시스템 개발을 위한 메타데이터 증강 및 구조화 기술 개발
  Participation Period: 2023.02 ~ 2023.05
  
  
• 벡터 임베딩 구축과 유사도 검색 원천기술 개발
  Participation Period: 2024.01.01 ~ 2024.12.31
  
  
• KURE: Korea University Retrieval Embedding Model 개발
  Participation Period: 2024.08 ~ 2024.12
  
  
• 독자 AI 파운데이션 모델 프로젝트: NCAI팀 데이터 리더
  Participation Period: 2025.08.01 ~ 2025.12.31