Yonsei University, Mirae Campus
Natural Language Processing Lab (NLPLAB) is a research laboratory in the Department of Software, College of Science & Technology at Yonsei University, Mirae Campus. Led by Prof. Sugyeong Eo, our lab focuses on advancing the field of NLP through innovative research and practical applications.
In NLPLAB, our goal is to design principled methods for advancing LLM-based intelligent systems capable of adapting to specialized domains while maintaining strong robustness, generalization capability, and reliability. In pursuit of this goal, our research focuses on several key areas, including Domain Specialization, Language Modeling, AI Agents, and Trustworthy AI.
μμ°μ΄μ²λ¦¬ λΆμΌμ κ΄μ¬μ κ°κ³ ν¨κ» μ°κ΅¬ λ° λ Όλ¬Έ μμ±μ μ§νν λνμμ(μμ¬, λ°μ¬, μλ°μ¬ν΅ν©)μ λͺ¨μ§ν©λλ€.
μ μΆ λ΄μ©: CV (κ°λ¨ν μ΄λ ₯μ), μμ°μ΄μ²λ¦¬ κ΄μ¬ λΆμΌ λ° μ°κ΅¬ κ²½ν κ°λ¨ν κΈ°μ
μ μΆ λ©μΌ μ£Όμ: s.eo@yonsei.ac.kr
LATEST PUBLICATION ('23~Present)
MIXTURE-OF-CLUSTERED-EXPERTS: Advancing Expert Specialization and Generalization in Instruction Tuning
Sugyeong Eo, Jungjun Lee, Chanjun Park, Heuiseok Lim
EMNLP 2025 (Oral Presentation, Oral Acceptance Rate: 3.97%)
Detecting Critical Errors Considering Cross-Cultural Factors in English-Korean Translation
Sugyeong Eo, Jungwoo Lim, Chanjun Park, Dahyun Jung, Seonmin Koo, Hyeonseok Moon, Jaehyung Seo, Heuiseok Lim
LREC-COLING 2024 (Oral Presentation)
Towards Precise Localization of Critical Errors in Machine Translation
Dahyun Jung, Sugyeong Eo, Heuiseok Lim
ACL-Findings 2024
Length-aware Byte Pair Encoding for Mitigating Over-segmentation in Korean Machine Translation
Jungseob Lee, Hyeonseok Moon, Seungjun Lee, Chanjun Park, Sugyeong Eo, Hyunwoong Ko, Jaehyung Seo, Seungyoon Lee, Heuiseok Lim
ACL-Findings 2024
Hyper-BTS Dataset: Scalability and Enhanced Analysis of BackTranScription (BTS) for ASR Post-Processing
Chanjun Park, Jaehyung Seo, Seolhwa Lee, Junyoung Son, Hyeonseok Moon, Sugyeong Eo, Chanhee Lee, Heuiseok Lim
EACL-Findings 2024
Generative Interpretation: Toward Human-Like Evaluation for Educational Question-Answer Pair Generation
Hyeonseok Moon, Jaewook Lee, Sugyeong Eo, Chanjun Park, Jaehyung Seo and Heuiseok Lim
EACL-Findings 2024
Leveraging Pre-existing Resources for Data-Efficient Counter-Narrative Generation in Korean
Seungyoon Lee, Chanjun Park, DaHyun Jung, Hyeonseok Moon, Jaehyung Seo, Sugyeong Eo, Heuiseok Lim
LREC-COLING 2024 (Oral Presentation)
Exploiting Hanja-Based Resources in Processing Korean Historic Documents Written by Common Literati
Hyeonseok Moon, Myunghoon Kang, Jaehyung Seo, Sugyeong Eo, Chanjun Park, Yeongwook Yang, Heuiseok Lim
IEEE Access 2024
Towards Diverse and Effective Question-Answer Pair Generation from Children Storybooks
Sugyeong Eo, Hyeonseok Moon, Jinsung Kim, Yuna Hur, Jeongwook Kim, Songeun Lee, Changwoo Chun, Sungsoo Park, Heuiseok Lim
ACL-Findings 2023
Informative Evidence-guided Prompt-based Fine-tuning for English-Korean Critical Error Detection
Dahyun Jung, Sugyeong Eo, Chanjun Park, Hyeonseok Moon, Jaehyung Seo, Heuiseok Lim
IJCNLP-AACL 2023
CHEF in the Language Kitchen: A Generative Data Augmentation Leveraging Korean Morpheme Ingredients
Jaehyung Seo, Hyeonseok Moon, Jaewook Lee, Sugyeong Eo, Chanjun Park and Heuiseok Lim
EMNLP 2023
KEBAP: Korean Error Explainable Benchmark Dataset for ASR and Post-processing
Seonmin Koo, Chanjun Park, Jinsung Kim, Jaehyung Seo, Sugyeong Eo, Hyeonseok Moon, Heuiseok Lim
EMNLP 2023
Doubts on the reliability of parallel corpus filtering
Hyeonseok Moon, Chanjun Park, Seonmin Koo, Jungseob Lee, Seungjun Lee, Jaehyung Seo, Sugyeong Eo, Yoonna Jang, Hyunjoong Kim, Hyoung-gyu Lee, Heuiseok Lim
Expert Systems with Applications 2023
Uncovering the Risks and Drawbacks Associated With the Use of Synthetic Data for Grammatical Error Correction
Seonmin Koo, Chanjun Park, Seolhwa Lee, Jaehyung Seo, Sugyeong Eo, Hyeonseok Moon, Heuiseok Lim
IEEE Access 2023
A Survey on Evaluation Metrics for Machine Translation
Seungjun Lee, Jungseob Lee, Hyeonseok Moon, Chanjun Park, Jaehyung Seo, Sugyeong Eo, Seonmin Koo, Heuiseok Lim
Mathematics 2023
Enhancing Machine Translation Quality Estimation via Fine-Grained Error Analysis and Large Language Model
Dahyun Jung, Chanjun Park, Sugyeong Eo, Heuiseok Lim
Mathematics 2023