Gary Geunbae Lee, Ph.D. Professor 

Gary Geunbae Lee has been a professor at CSE department of POSTECH in Korea since 1991. He is a director of Natural Language Processing (NLP) Laboratory which focuses on natural language processing including spoken dialog processing, intelligent computer assisted language learning, question answering, speech synthesis and web/text mining. Professor Lee has authored more than 250 papers in international journals and conferences, and has more than 35 patents registered in speech and language technology area. Prof Lee has served as a technical committee member for international conferences such as ACL, COLING, IJCAI, SIGIR, IUI, Interspeech, ASRU/SLT and ICASSP. He has been in a steering committee for Asian Information Retrieval Symposium (AIRS), International workshop on spoken dialog systems (IWSDS), and has been an executive board member of Asia Federation of NLP. He has served as an associate editor of IEEE/ACM transactions on Audio, Speech and Language Processing (TASLP) and ACM transactions on Asian Language Information Processing (TALIP). He has been a PC co-chair for AIRS2009, AIRS 2005, workshop chair for IUI 2007, and a PC area chair for IJCNLP 2004, 2005, 2008, and COLING2010, and also a senior program committee member for IJCAI 2011 and ACM IUI 2011. He was a local organization co-chair of ACL 2012 (50th anniversary meeting) and general chair of SIGDIAL 2012 and IWSDS2015. He has edited several special issues of journals including ACM Trans. on Asian Language Information Processing and Information Processing & Management. He co-founded DiQuest and has been a CTO, which becomes now one of the major search engine company in Korea, and has been a technical advisor for SK Telecom, Samsung Electronics, and many other start-up companies.  He founded AI research center at Samsung Research and served as a director during 2015-2019. He was a winner of IR52 Jangyoungsil award with DiQuest, which is one of the most prestigious technology innovation awards in Korea. He has been leading several national and industry projects for robust spoken dialog systems, dialog-based English tutoring agents, multimedia search/recommendation systems and expressive TTS. Professor Lee holds a Ph.D. in computer science from UCLA, and BS/MS in computer engineering from Seoul National University. 

Publications (For the full list, go to Google Scholars.)

2025

Conference

• PicPersona-TOD: A Dataset for Personalizing Utterance Style in Task-Oriented Dialogue with Image Persona

Jihyun Lee, Yejin Jeon, Seungyeon Seo, Gary Geunbae Lee

NAACL 2025

• Revisiting Early Detection of Sexual Predators via Turn-level Optimization

Jinmyeong An, Sangwon Ryu, Heejin Do, Yunsu Kim, Jungseul Ok, Gary Geunbae Lee

NAACL 2025

• Multimodal Cognitive Reframing Therapy via Multi-hop Psychotherapeutic Reasoning

Subin Kim*, Hoonrae Kim*, Heejin Do, Gary Geunbae Lee

NAACL 2025

• DyPCL: Dynamic Phoneme-level Contrastive Learning for Dysarthric Speech Recognition

Wonjun Lee*, Solee Im*, Heejin Do, Yunsu Kim, Jungseul Ok, Gary Geunbae Lee

NAACL 2025

• K-COMP: Retrieval-Augmented Medical Domain Question Answering With Knowledge-Injected Compressor

Jeonghun Cho, Gary Geunbae Lee

NAACL 2025

• Towards Prompt Generalization: Grammar-aware Cross-Prompt Automated Essay Scoring

Heejin Do, Taehee Park, Sangwon Ryu, Gary Geunbae Lee

NAACL Findings 2025

• Prompt-Guided Selective Masking Loss for Context-Aware Emotive Text-to-Speech

Yejin Jeon, Youngjae Kim, Jihyun Lee, Gary Geunbae Lee

NAACL Findings 2025

• A Domain-Specific Multilingual Speech Translation Corpus via Simultaneous Interpretation

Seunghee Han, Gary Geunbae Lee, Hyung Soon Kim, Sunhee Kim, Minhwa Chung

ICASSP 2025

Journal

• Structured Reasoning and Answer Verification: Enhancing Question Answering System Accuracy and Explainability

Jihyung Lee, Gary Geunbae Lee

Knowledge-Based Systems, Volume 311, 2025

[paper]

2024

Conference

• Autoregressive Multi-trait Essay Scoring via Reinforcement Learning with Scoring-aware Multiple Rewards

Heejin Do, Sangwon Ryu, Gary Geunbae Lee

EMNLP 2024

• Cross-lingual Back-Parsing: Utterance Synthesis from Meaning Representation for Zero-Resource Semantic Parsing

Deokhyung Kang, Seonjeong Hwang, Yunsu Kim, Gary Geunbae Lee

EMNLP 2024

• Cross-lingual Transfer for Automatic Question Generation by Learning Interrogative Structures in Target Languages

Seonjeong Hwang, Yunsu Kim and Gary Geunbae Lee

EMNLP 2024

• Audio-Based Linguistic Feature Extraction for Enhancing Multi-lingual and Low-Resource Text-to-Speech

Youngjae Kim, Yejin Jeon, Gary Geunbae Lee

EMNLP Findings 2024

• DiagESC: Dialogue Synthesis for Integrating Depression Diagnosis into Emotional Support Conversation

Seungyeon Seo, Gary Geunbae Lee

SIGDial 2024

• Enhancing Dialogue Speech Recognition with Robust Contextual Awareness via Noise Representation Learning

Wonjun Lee*, San Kim*, Gary Geunbae Lee

SIGDial 2024

• An Investigation Into Explainable Audio Hate Speech Detection

Jinmyeong An*, Wonjun Lee*, Yejin Jeon, Jungseul Ok, Yunsu Kim, Gary Geunbae Lee

SIGDial 2024

• Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment

Heejin Do, Wonjun Lee, Gary Geunbae Lee

Interspeech 2024

• Key-Element-Informed sLLM Tuning for Document Summarization

Sangwon Ryu*, Heejin Do*, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok

Interspeech 2024

• Multi-Dimensional Optimization for Text Summarization via Reinforcement Learning

Sangwon Ryu*, Heejin Do*, Yunsu Kim, Gary Geunbae Lee, Jungseul Ok

ACL 2024

• Adversarial DPO: Harnessing Harmful Data for Reducing Toxicity with Minimal Impact on Coherence and Evasiveness in Dialogue Agents

San Kim and Gary Geunbae Lee

NAACL Findings 2024

• Aspect-based Semantic Textual Similarity for Educational Test Items

Heejin Do and Gary Geunbae Lee

AIED 2024

• Leveraging the Interplay Between Syntatic and Acoustic Cues for Optimizing Korean TTS Pause Formation

Yejin Jeon, Yunsu Kim, Gary Geunbae Lee

LREC-COLING 2024

• Denoising Table-Text Retrieval for Open-Domain Question Answering

Deokhyung Kang, Baikjin Jung, Yunsu Kim, Gary Geunbae Lee

LREC-COLING 2024

• Explainable Multi-hop Question Generation: An End-to-End Approach without Intermediate Question Labeling

Seonjeong Hwang, Yunsu Kim and Gary Geunbae Lee

LREC-COLING 2024

• Leveraging Effective Language and Speaker Conditioning in Indic TTS for LIMMITS 2024 Challenge

Yejin Jeon*,  Youngjae Kim*, Gary Geunbae Lee

ICASSP 2024 (Grand Challenge)

• Multi-Level Attention Aggregation for Language-Agnostic Speaker Replication

Yejin Jeon, Gary Geunbae Lee

EACL, 2024

• Autoregressive Score Generation for Multi-trait Essay Scoring

Heejin Do, Yunsu Kim and Gary Geunbae Lee

EACL, 2024 findings

• Enhancing Zero-Shot Multi-Speaker TTS with Negated Speaker Representations

Yejin Jeon, Yunsu Kim and Gary Geunbae Lee

AAAI, 2024

Research interests (in general)

Natural Language Processing

Spoken Dialog Systems

Text-to-Speech Systems

Text mining and Information Retrieval

Computer Assisted Language Learning