Publications 논문
0
Publication (selected) 주요 논문
- PRIME: Ultra-Low-Rank Principal-Residual Model Merging ACL 2026 Findings 2026
- PURE: Post-hoc Unlocking and REfinement for Discrete Diffusion Decoding ACL 2026 Findings 2026
- EAIR: Entity-aware Inference-Time Knowledge Routing for Multi-Hop Knowledge Editing ACL 2026 Findings 2026
- AlphaMerging: Orthogonal Subspace Projection of Task Vectors to Reduce Task Interference for Multi-Task Model Merging CVPR 2026 Findings 2026
- GateLM: Jointly Injecting Knowledge Graphs and Texts for Reasoning-Enhanced Language Models on Commonsense Question Answering Expert Systems with Applications 2026
- OrthoEdit: Principled and Stable Knowledge Editing via Orthogonal Subspace Projection TACL 2026
- MergePRAG: Orthogonal Merging of Passage-experts for Multi-hop Parametric RAG ICLR 2026
- MECA: Modular Editing via Customized Expert Networks and Adaptors in Large Language Models Expert Systems with Applications 2025
- GenPoE: Generative Passage-level Mixture of Experts for Knowledge Enhancement of LLMs EMNLP Findings 2025
- Optimizing Causality-Based Radiology Reporting with Retrieval-Augmented and Structured Reasoning Approaches for the NTCIR-18 HIDDEN-RAD Task NTCIR-18 2025 PDF
- ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models arXiv 2025 arXiv
- SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editing ACL Findings 2025 PDF
- CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation arXiv 2025 arXiv
- Wasserstein Distance Constraint and Parameter Sparsification for Batched and Iterative Knowledge Editing AAAI 2025 SITE
- SARCAT: Generative Span-Act Guided Response Generation using Copy-enhanced Target Augmentation EMNLP Findings 2024 PDF
- DistillMIKE: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models ACL Findings 2024 PDF
- COMEM: In-Context Retrieval-Augmented Mass-Editing Memory in Large Language Models NAACL Findings 2024 PDF
- RADCoT: Retrieval-Augmented Distillation to Specialization Models for Generating Chain-of-Thoughts in Query Expansion COLING 2024 PDF
- Evaluating Complex Entity Knowledge Propagation for Knowledge Editing in LLMs Applied Sciences 2024 PDF
- Transformer-Based Reranking for Improving Korean Morphological Analysis System ETRI Journal 2024 SITE
- DiffusionRet: Diffusion-Enhanced Generative Retriever using Constrained Decoding EMNLP Findings 2023 PDF
- Feature Structure Distillation with Centered Kernel Alignment in BERT Transferring Expert Systems with Applications 2023 arXiv
- ExplainMeetSum: A Dataset for Explainable Meeting Summarization Aligned with Human Intent ACL 2023 PDF
- MAFiD: Moving Average Equipped Fusion-in-Decoder for Question Answering over Tabular and Textual Data EACL Findings 2023 PDF
- RINK: Reader-Inherited Evidence Reranker for Table-and-Text Open Domain Question Answering AAAI 2023 SITE
- SISER: Semantic-Infused Selective Graph Reasoning for Fact Verification COLING 2022 PDF
- JBNU-CCLab at SemEval-2022 Task 12: Machine Reading Comprehension and Span Pair Classification for Linking Mathematical Symbols to Their Descriptions SemEval at NAACL 2022 Top-ranked PDF
- JBNU-CCLab at SemEval-2022 Task 7: DeBERTa for Identifying Plausible Clarifications in Instructional Texts SemEval at NAACL 2022 PDF
- Frustratingly Easy System Combination for Grammatical Error Correction NAACL 2022 PDF
- LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory ACL 2022 PDF
- Impact of Sentence Representation Matching in Neural Machine Translation Applied Sciences 2022 PDF
- Revisiting Dropout: Escaping Pressure for Training Neural Networks with Multiple Costs Electronics 2021 PDF
- JBNU at SemEval-2020 Task 4: BERT and UniLM for Commonsense Validation and Explanation SemEval '20 2020 PDF
- JBNU at MRP 2020: AMR Parsing Using a Joint State Model for Graph-Sequence Iterative Inference MRP at CoNLL 2020 PDF
- Uniformly Interpolated Balancing for Robust Prediction in Translation Quality Estimation ACM Transactions on Asian and Low-Resource Language Information Processing 2020 PDF
- JBNU at MRP 2019: Multi-level Biaffine Attention for Semantic Dependency Parsing MRP at CoNLL 2019 PDF
- Word Reordering for Translation into Korean Sign Language Using Syntactically-guided Classification ACM Transactions on Asian and Low-Resource Language Information Processing 2019 PDF
- QE BERT: Bilingual BERT Using Multi-task Learning for Neural Quality Estimation WMT '19 2019 PDF
- Multi-task Stack Propagation for Neural Quality Estimation ACM Transactions on Asian and Low-Resource Language Information Processing 2019 PDF
- Improving LSTM CRFs Using Character-based Compositions for Korean Named Entity Recognition Computer Speech and Language 2018 PDF
- Transition-Based Korean Dependency Parsing Using Hybrid Word Representations of Syllables and Morphemes with LSTMs ACM Transactions on Asian and Low-Resource Language Information Processing 2018 PDF
- Phrase-Based Statistical Model for Korean Morpheme Segmentation and POS Tagging IEICE Transactions on Information Systems 2018 PDF
- Verbosity Normalized Pseudo-Relevance Feedback in Information Retrieval Information Processing and Management 2018 PDF
- Concept Equalization to Guide Correct Training of Neural Machine Translation IJCNLP 2017 PDF
- Predictor-Estimator using Multilevel Task Learning with Stack Propagation for Neural Quality Estimation WMT '17 2017 Top-ranked PDF
- Predictor-Estimator: Neural Quality Estimation Based on Target Word Prediction for Machine Translation ACM Transactions on Asian and Low-Resource Language Information Processing 2017 PDF
- Center-shared Sliding Ensemble of Neural Networks for Syntax Analysis of Natural Language Expert Systems with Applications 2017 PDF
- Conditional Random Fields for Korean Morpheme Segmentation and POS Tagging ACM Transactions on Asian and Low-Resource Language Information Processing 2015 PDF
- Two-Stage Document Length Normalization for Information Retrieval ACM Transactions on Information Systems 2015 PDF slide
- Partial-update Dimensionality Reduction for Accumulating Co-occurrence Events Pattern Recognition Letters 2014 PDF
- Probabilistic Co-relevance for Query-sensitive Similarity Measurement in Information Retrieval Information Processing and Management 2013 SITE
- Memory-restricted Latent Semantic Analysis to Accumulate Term-Document Co-occurrence Events Pattern Recognition Letters 2012 PDF
- Enriching Document Representation via Translation for Improved Monolingual Information Retrieval SIGIR 2011 PDF
- RankSVR: Can Preference Data Help Regression? CIKM 2010 PDF
- A 2-Poisson Model for Probabilistic Coreference of Named Entities for Improved Text Retrieval SIGIR 2009 PDF
- Improving Opinion Retrieval Based on Query-Specific Sentiment Lexicon ECIR 2009 PDF
- Exploiting Proximity Feature in Bigram Language Model for Information Retrieval Documents and Application to Language Modeling Approaches SIGIR 2008 PDF
- KLE at TREC 2008 Blog Track: Blog Post and Feed Retrieval TREC 2008 PDF
- Improving Term Frequency Normalization for Multi-topical Documents and Application to Language Modeling Approaches ECIR 2008 PDF slide
- Collins-LA: Head-Driven Model with Latent Annotation CICLing 2008 PDF
- POSTECH at NTCIR-5: Combining Evidences of Multiple Term Extractions for Mono-Lingual and Cross-Lingual Retrieval in Korean and Japanese NTCIR-5 2005 PDF
Publication (all) 전체 논문
International Journal 국제 학술지
- MECA: Modular Editing via Customized Expert Networks and Adaptors in Large Language Models Expert Systems with Applications accepted 2025
- Transformer-Based Reranking for Improving Korean Morphological Analysis System ETRI Journal accepted
- Impact of Sentence Representation Matching in Neural Machine Translation Applied Sciences 12(3):1313 2022 PDF
- Revisiting Dropout: Escaping Pressure for Training Neural Networks with Multiple Costs Electronics 10(9):989 2021 PDF
- Uniformly Interpolated Balancing for Robust Prediction in Translation Quality Estimation ACM Transactions on Asian and Low-Resource Language Information Processing accepted
- Word Reordering for Translation into Korean Sign Language Using Syntactically-guided Classification ACM Transactions on Asian and Low-Resource Language Information Processing accepted
- Multi-task Stack Propagation for Neural Quality Estimation ACM Transactions on Asian and Low-Resource Language Information Processing accepted
- Improving LSTM CRFs Using Character-based Compositions for Korean Named Entity Recognition Computer Speech and Language accepted
- Transition-Based Korean Dependency Parsing Using Hybrid Word Representations of Syllables and Morphemes with LSTMs ACM Transactions on Asian and Low-Resource Language Information Processing accepted
- Phrase-Based Statistical Model for Korean Morpheme Segmentation and POS Tagging IEICE Transactions on Information Systems accepted
- Verbosity Normalized Pseudo-Relevance Feedback in Information Retrieval Information Processing and Management accepted
- Predictor-Estimator: Neural Quality Estimation Based on Target Word Prediction for Machine Translation ACM Transactions on Asian and Low-Resource Language Information Processing 17(1) 2017 PDF
- Center-shared Sliding Ensemble of Neural Networks for Syntax Analysis of Natural Language Expert Systems with Applications 83 2017 PDF
- Conditional Random Fields for Korean Morpheme Segmentation and POS Tagging ACM Transactions on Asian and Low-Resource Language Information Processing 14(3) 2015 PDF
- Two-Stage Document Length Normalization for Information Retrieval ACM Transactions on Information Systems 33(2) 2015 PDF
- Partial-Update Dimensionality Reduction for Accumulating Co-occurrence Events Pattern Recognition Letters 36, pp.62–73 2014
- Probabilistic Co-relevance for Query-Sensitive Similarity Measurement in Information Retrieval Information Processing and Management 49(2), pp.558–575 2013
- Utilizing Local Evidence for Blog Feed Search Information Retrieval 15(2), pp.157–177 2012
- Memory-Restricted Latent Semantic Analysis to Accumulate Term-Document Co-occurrence Events Pattern Recognition Letters 33(12), pp.1623–1631 2012
- On Co-authorship for Author Disambiguation Information Processing and Management 45(1), pp.84–97 2009
- English-Chinese Transliteration Word Pair Extraction from Parallel Corpora International Journal of Computer Processing of Oriental Languages 21(2), pp.169–182 2008
- Parsimonious Translation Models for Information Retrieval Information Processing and Management 43(1), pp.121–145 2007
- An Empirical Study of Query Expansion and Cluster-Based Retrieval in Language Modeling Approach Information Processing and Management 43(2), pp.302–314 2007
- Adaptive Document Clustering Based on Query-Based Similarity Information Processing and Management 43(4), pp.887–891 2007
- Cluster-Based Patent Retrieval Information Processing and Management 43(5), pp.1173–1182 2007
- Pruning-Based Unsupervised Segmentation for Korean IEICE Transactions 89-D(10), pp.2670–2677 2006
- Combination Approaches in Korean Information Retrieval: Words vs. N-Grams, and Query Translation vs. Document Translation International Journal of Computer Processing of Oriental Languages 19(2/3), pp.153–187 2006
- Collection-Based Compound Noun Segmentation for Korean Information Retrieval Information Retrieval 9(5), pp.613–631 2006
- Translation Probabilities in Cross-Language Information Retrieval International Journal of Computer Processing of Oriental Languages 18(2), pp.115–136 2005
International Conference 국제 학술대회
- PRIME: Ultra-Low-Rank Principal-Residual Model Merging ACL 2026 Findings 2026
- PURE: Post-hoc Unlocking and REfinement for Discrete Diffusion Decoding ACL 2026 Findings 2026
- EAIR: Entity-aware Inference-Time Knowledge Routing for Multi-Hop Knowledge Editing ACL 2026 Findings 2026
- AlphaMerging: Orthogonal Subspace Projection of Task Vectors to Reduce Task Interference for Multi-Task Model Merging CVPR 2026 Findings 2026
- GenPoE: Generative Passage-level Mixture of Experts for Knowledge Enhancement of LLMs EMNLP Findings 2025
- Optimizing Causality-Based Radiology Reporting with Retrieval-Augmented and Structured Reasoning Approaches for the NTCIR-18 HIDDEN-RAD Task NTCIR-18 2025 PDF
- ROSAQ: Rotation-based Saliency-Aware Weight Quantization for Efficiently Compressing Large Language Models arXiv 2025 arXiv
- SeqMMR: Sequential Model Merging and LLM Routing for Enhanced Batched Sequential Knowledge Editing ACL Findings 2025
- CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation arXiv 2025 arXiv
- Wasserstein Distance Constraint and Parameter Sparsification for Batched and Iterative Knowledge Editing AAAI accepted 2025
- SARCAT: Generative Span-Act Guided Response Generation using Copy-enhanced Target Augmentation EMNLP Findings 2024
- DistillMIKE: Editing Distillation of Massive In-Context Knowledge Editing in Large Language Models ACL Findings 2024
- COMEM: In-Context Retrieval-Augmented Mass-Editing Memory in Large Language Models NAACL Findings 2024
- RADCoT: Retrieval-Augmented Distillation to Specialization Models for Generating Chain-of-Thoughts in Query Expansion COLING accepted 2024
- DiffusionRet: Diffusion-Enhanced Generative Retriever using Constrained Decoding EMNLP Findings 2023 PDF
- ExplainMeetSum: A Dataset for Explainable Meeting Summarization Aligned with Human Intent ACL accepted 2023
- MAFiD: Moving Average Equipped Fusion-in-Decoder for Question Answering over Tabular and Textual Data EACL Findings 2023
- RINK: Reader-Inherited Evidence Reranker for Table-and-Text Open Domain Question Answering AAAI accepted 2023
- SISER: Semantic-Infused Selective Graph Reasoning for Fact Verification COLING accepted 2022
- JBNU-CCLab at SemEval-2022 Task 12: Machine Reading Comprehension and Span Pair Classification for Linking Mathematical Symbols to Their Descriptions SemEval@NAACL top-ranked 2022
- JBNU-CCLab at SemEval-2022 Task 7: DeBERTa for Identifying Plausible Clarifications in Instructional Texts SemEval@NAACL 2022
- Frustratingly Easy System Combination for Grammatical Error Correction NAACL accepted 2022
- LM-BFF-MS: Improving Few-Shot Fine-tuning of Language Models based on Multiple Soft Demonstration Memory ACL accepted 2022
- Impact of Sentence Representation Matching in Neural Machine Translation Applied Sciences 12(3):1313 2022 PDF
- A Comparison of Speech Features between Mild Cognitive Impairment and Healthy Aging Groups Dementia and Neurocognitive Disorder 20(4) 2021 PDF
- Revisiting Dropout: Escaping Pressure for Training Neural Networks with Multiple Costs Electronics 10(9):989 2021 PDF
- JBNU at SemEval-2020 Task 4: BERT and UniLM for Commonsense Validation and Explanation SemEval 2020 PDF
- JBNU at MRP 2020: AMR Parsing Using a Joint State Model for Graph-Sequence Iterative Inference MRP@CoNLL 2020 PDF
- QE BERT: Bilingual BERT Using Multi-task Learning for Neural Quality Estimation WMT 2019
- JBNU at MRP 2019: Multi-level Biaffine Attention for Semantic Dependency Parsing MRP@CoNLL 2019 PDF poster blitz
- Refining Sentence Similarity with Discourse Information in Dialog System INTERSPEECH pp. 3742–3746 2013
- A Comparison of Classifiers for Detecting Hedges UNESST 2011 (LNCS/CCIS) CCIS 264, pp. 251–257 2011
- Disambiguating Author Names Using Automatic Relevance Feedback UNESST 2011 (LNCS/CCIS) CCIS 264, pp. 239–224 2011
- Enriching Document Representation via Translation for Improved Monolingual Information Retrieval SIGIR full paper, accept rate 19.8% 2011
- RankSVR: Can Preference Data Help Regression? CIKM full paper, accept rate 13.4% 2010
- An Improved Feedback Approach Using Relevant Local Posts for Blog Feed Retrieval CIKM pp. 1971–1974 (accept rate 31.3%) 2009
- A 2-Poisson Model for Probabilistic Coreference of Named Entities for Improved Text Retrieval SIGIR pp. 275–282 (full) 2009
- Improving Opinion Retrieval Based on Query-Specific Sentiment Lexicon ECIR LNCS 5478, pp. 734–738 2009
- DiffPost: Filtering Non-relevant Content Based on Content Difference between Two Consecutive Blog Posts ECIR LNCS 5478, pp. 791–795 2009
- Partially Supervised Phrase-Level Sentiment Classification ICCPOL LNCS 5459, pp. 225–235 2009
- Exploiting Proximity Feature in Bigram Language Model for Information Retrieval Documents and Application to Language Modeling Approaches SIGIR 2008
- Improving Term Frequency Normalization for Multi-topical Documents and Application to Language Modeling Approaches ECIR LNCS 4956, pp. 382–393 (accept rate 23.7%) 2008
- Structural Re-ranking with Cluster-Based Retrieval ECIR LNCS 4956, pp. 658–662 2008
- Revisit of Nearest Neighbor Test for Direct Evaluation of Inter-document Similarities ECIR LNCS 4956, pp. 674–678 2008
- Query-Based Inter-document Similarity Using Probabilistic Co-relevance Model ECIR LNCS 4956, pp. 684–688 2008
- Collins-LA: Head-Driven Model with Latent Annotation CICLing 2008
- Completely-Arbitrary Passage Retrieval in Language Modeling Approach AIRS LNCS 4993 2008 slide
- Applying Completely-Arbitrary Passage for Pseudo-Relevance Feedback in Language Modeling Approach AIRS LNCS 4993 2008 slide
- Automatic Extraction of English-Chinese Transliteration Pairs using Dynamic Window and Tokenizer IJCNLP (SIGNAN-6 Workshop) pp. 9–15 2008
- Search Result Clustering Using Label Language Model IJCNLP 2008
- An Empirical Study of Query Expansion and Cluster-Based Retrieval in Language Modeling Approach AIRS LNCS 3689, pp. 274–287 (best paper nominee) 2005
- Effective Query Model Estimation Using Parsimonious Translation Model in Language Modeling Approach AIRS LNCS 3689, pp. 288–298 2005
- Parsimonious Translation Models for Information Retrieval SIGIR (MF/IR Workshop) pp. 1–9 2005
- Query Model Estimation for Relevance Feedback in Language Modeling Approach AIRS LNCS 3411, pp. 215–226 2004
- Estimation of Query Model from Parsimonious Translation Model AIRS LNCS 3411, pp. 239–250 2004
- Improving Relevance Feedback in Language Modeling Approach: Maximum a Posteriori Probability Criterion and Three-Component Mixture Model IJCNLP LNAI 3248, pp. 130–138 2004
- Influence of WSD on Cross-Language Information Retrieval IJCNLP LNAI 3248, pp. 358–366 2004
- Lightweight Natural Language Database Interfaces NLDB LNCS 3136, pp. 76–88 2004
International Conference (Non-Refereed) 국제 학술대회 (비심사)
- IR-based k-Nearest Neighbor Approach for Identifying Abnormal Chat Users CLEF 2012
- KLE at TREC 2008 Blog Track: Blog Post and Feed Retrieval TREC oral 2008
- POSTECH at NTCIR-6: Combining Evidences of Multiple Term Extractions for Mono-lingual and Cross-lingual Retrieval NTCIR-6 oral 2007
- POSTECH at NTCIR-6 English Patent Retrieval Subtask NTCIR-6 2007
- POSTECH at NTCIR-5 Combining Evidences of Multiple Term Extractions for Mono-Lingual and Cross-Lingual Retrieval in Korean and Japanese NTCIR-5 oral 2005
- POSTECH at NTCIR-5 Patent Retrieval: Smoothing Experiments in a Language Modeling Approach to Patent Retrieval NTCIR-5 2005
- POSTECH Question-Answering Experiments at NTCIR-4 QAC NTCIR-4 2004
- POSTECH at NTCIR-4: CJKE Monolingual and Korean-related Cross-Language Experiments NTCIR-4 oral 2004
- Question Answering Approach Using a WordNet-based Answer Type Taxonomy TREC 2002
Domestic Journal and Report (selected) 주요 국내 학술지 및 보고서
- 거대 언어 모델의 손실 피드백을 통한 검색 모델 개선 정보과학회 논문지 2024 accepted
- Plug-and-Play Language Model을 활용한 한국어 언어모델 독성 제어 정보과학회 컴퓨팅의 실제 논문지 2024 link
- SCA: Cross-Attention 지도 학습에 기반한 문서기반 응답 생성 모델의 성능 향상 정보과학회 논문지 2024 link
- R2FID: Joint Reranker기반 Fusion-In-Decoder를 이용한 오픈 도메인 테이블 질의 응답 정보과학회 논문지 2023 accepted
- BERT 기반 2단계 분류 모델과 Co-Attention 메커니즘을 이용한 치매와 조현병 진단 정보과학회 논문지 2022 2022.9 link
- 기계독해 기반 서브트리 연결 방법을 적용한 한국어 의존 파싱 정보과학회 논문지 2022 2022.8 accepted
- PrefixLM에 기반한 한국어 텍스트 요약 정보과학회 논문지 2022 2022.4 accepted
- LUKE를 이용한 한국어 자연어 처리: 개체명 인식, 개체 연결 정보과학회 논문지 2022 2022.1 accepted
- A Comparison of Speech Features between Mild Cognitive Impairment and Healthy Aging Groups Dementia and Neurocognitive Disorder 20(4) 2021 PDF
- RoBERTa를 이용한 한국어 기계독해 정보과학회 논문지, 컴퓨팅의 실제 2021 2021.4
- 심층학습에 기반한 자연언어처리 정보과학회지 33(10), 28–39 2015
- 래티스상의 구조적 분류에 기반한 한국어 형태소 분석 및 품사 태깅 정보과학회논문지 : 소프트웨어 및 응용 41(7), 523–532 2014 PDF
- 빅데이터 기반 음성언어 처리 기술 전자통신동향분석 2013
- 랭킹 데이타를 활용한 회귀분석 성능 개선 데이타베이스연구 2010
- 동적 윈도우와 토크나이저를 이용한 영-중 음차표기 대역쌍자동 추출 정보과학회논문지 : 컴퓨팅의 실제 및 레터 13(6), 417–421 2007
- 세종 전자 사전의 전산적 활용 가능성 : 질의 응답 시스템을 중심으로 한국사전학회, 한국사전학 4, 131–151 2004
Domestic Conference (selected, since 2012) 주요 국내 학술대회 (2012년~)
- 다중모달 특성을 활용한 객체 합성 오류 탐지 한국정보과학회 2024 한국소프트웨어종합학술대회 2024
- ChatGPT를 이용한 한국어 AI 모델 평가 자동화 시스템 개발 한국정보과학회 2024 한국소프트웨어종합학술대회 2024
- Transformer 기반 음성인식 모델의 데이터 효율성 개선을 위한 스펙트로그램 데이터 증강 기법 연구 한국음성학회 학술대회 2023
- AI Hub 데이터를 활용한 한국어 음성인식 모델 구축 한국음성학회 학술대회 2023
- CNN 기반 객체 인식 성능 개선을 위한 시각적 주의 메커니즘 한국정보과학회 2022 한국소프트웨어종합학술대회 2022
- 한국어 문서요약 데이터셋 개발과 BART 요약모델 학습 한국정보과학회 2021 한국소프트웨어종합학술대회 2021
- 멀티스케일 특징 학습을 통한 객체 탐지 성능 향상 한국정보과학회 2021 한국소프트웨어종합학술대회 2021
- BERT 기반 한국어 기계독해 성능 개선을 위한 데이터 확장 기법 한국정보과학회 2019 한국소프트웨어종합학술대회 2019
- 딥러닝 기반 한국어 기계독해 성능 개선을 위한 데이터 전처리 기법 한국정보과학회 2018 한국소프트웨어종합학술대회 2018