Dongyub (Jude) Lee | U.S. Green Card Holder

I am a computer scientist and AI researcher with deep expertise in natural language processing (NLP) and the engineering of practical AI systems. Since May 2024, I have been working as an AI Research Scientist at Zoom. Before joining Zoom, I was part of the U.S. subsidiary of Naver, a leading Korean tech company, where I contributed significantly to the successful launch of ‘Naver Cue.’ This system, utilizing retrieval augmented generation (RAG), is now widely used across South Korea. Prior to Naver, I served as an AI research engineer at Kakao Corporation, developing my expertise in both task-oriented and open-domain dialogue systems.

[Google Scholar]: link

[Linkdin]:link

Research Interest

Dialogue System, Summarization

Academic Activities

• Reviewer of NAACL 2023, ACL 2023, and ARR 2023.
• Reviewer of ACL 2022 and NAACL 2022.
• Reviewer of ACL 2021 and EMNLP 2021.

News

• May 2024: I have joined Zoom as an AI Research Scientist!
  

• Mar 2024: Our paper “Tree-of-Question: Structured Retrieval Framework for Korean Question Answering Systems” has been accepted to NAACL 2024, Industry Track. Congrats.
  

• Jan 2024: Our paper “Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning” has been accepted to EACL 2024. Congrats.
  

• Oct 2022: Our paper on Dialogue Systems grounding Persona and Knowledge accepted to EACL 2022, Findings. Congrats.
  

• Dec 2021: Started working for Naver Search.
  

• Dec 2021: Our paper on Dialogue State Tracking accepted to AAAI 2022, DSTC10.
  

• Oct 2021: In the Dialogue State Tracking Challenge (DSTC 10) Track2, we achieved 3rd place in Task1 and 5th place in Task2 DSTC10.
  
• SEP 2021: Our paper on dialogue summarization accepted to NewSum, EMNLP 2021.
  
• JUN 2021: Our paper on disfluency detection accepted to INTERSPEECH 2021.
  
• MAY 2021: Our paper on aspect-based sentiment analysis (DCRAN) accepted to ACL 2021.
  
• DEC 2020: Our paper on multi-turn dialog system (UMS) got accepted to AAAI 2021.
  
• OCT 2020: Our paper on summarization (RDASS) accepted to COLING 2020.
  

International Publications

[2024]

Tree-of-Question: Structured Retrieval Framework for Korean Question Answering Systems
Dongyub Lee, Younghun Jeong, Hwayeon Kim, Hongyeon Yu,Seunghyun Han, Taesun Whang, Seungwoo Cho, Chanhee Lee, Gunsu Lee, Youngbum Kim
NAACL 2024, Industry Track

Ask, Assess, and Refine: Rectifying Factual Consistency and Hallucination in LLMs with Metric-Guided Feedback Learning
Dongyub Lee, Eunhwan Park, Hodong Lee, Heuiseok Lim
EACL 2024

[2022]

You Truly Understand What I Need : Intellectual and Friendly Dialog Agents grounding Persona and Knowledge
Jungwoo Lim, Myugnhoon Kang, Yuna Hur, Seung Won Jeong, Jinsung Kim, Yoonna Jang, Dongyub Lee, Hyesung Ji, DongHoon Shin, Seungryong Kim and Heuiseok Lim
EMNLP 2022 (findings)

Towards Filling the Gap between Written and Spoken Dialogues for Multi-Domain Dialogue State Tracking
Taesun Whang, Jungwoo Limm, Dongyub Lee
DSTC10, AAAI 2022

[2021]

Capturing Speaker Incorrectness: Speaker-Focused Post-Correction for Abstractive Dialogue Summarization
Dongyub Lee, Jungwoo Lim, Taesun Whang, chanhee lee, Seungwoo Cho, Mingun Park and Heuiseok Lim
NewSum, EMNLP 2021

Auxiliary Sequence Labeling Tasks for Disfluency Detection
Dongyub Lee, Byeongil Ko, Myeong Cheol Shin, Taesun Whang, Daniel Lee, Eun Hwa Kim, EungGyun Kim, Jaechoon Jo
INTERSPEECH 2021

Deep Context- and Relation-Aware Learning for Aspect-based Sentiment Analysis
{Shinhyeok Oh, Dongyub Lee}^*, Taesun Whang, IlNam Park, Gaeun Seo, EungGyun Kim, Harksoo Kim [^*equal contribution]
ACL 2021 (main)

Do Response Selection Models Really Know What’s Next? Utterance Manipulation Strategies for Multi-turn Response Selection
Taesun Whang^*, Dongyub Lee^*, Dongsuk Oh, Chanhee Lee, Kijong Han, Dong-hun Lee, Saebyeok Lee [^*equal contribution]
AAAI 2021

[2020]

Reference and Document Aware Semantic Evaluation Methods for Korean Language Summarization
Dongyub Lee, Myeongcheol Shin, Taesun Whang, Seungwoo Cho, Byeongil Ko, Daniel Lee, Eunggyun Kim, Jaechoon Jo
COLING 2020

An Effective Domain Adaptive Post-Training Method for BERT in Response Selection
Taesun Whang, Dongyub Lee, Chanhee Lee, Kisu Yang, Dongsuk Oh, HeuiSeok Lim
Interspeech 2020

Development of Fashion Product Retrieval and Recommendations Model Based on Deep Learning
Jaechoon Jo, Seolhwa Lee, Chanhee Lee, Dongyub Lee, Heuiseok Lim
Electronics 9.3 (Mar. 2020) p. 508. Multidisciplinary Digital Publishing Institute, 2020.

[2019]

Integrating breakdown detection into dialogue systems to improve knowledge management: encoding temporal utterances with memory attention
SEOLHWA LEE, DONGYUB LEE, DANIAL, HOOSHYAR JAECHOON JO, HEUISEOK LIM
INFORMATION TECHNOLOGY AND MANAGEMENT-2019 (SCIE)

EmotionX-KU: BERT-Max based Contextual Emotion Classifier
Kisu Yang, Dongyub Lee, Taesun Whang, Seolhwa Lee, Heuiseok Lim
IJCAI 2019 Workshop on the 7th Natural Language Processing for Social Media (Shared Task, EmotionX), 2019, Macau.

Enhanced Sequential Representation Augmented with Utterance-level Attention for Response Selection
Taesun Whang, Dongyub Lee, Chanhee Lee, Heuiseok Lim
AAAI 2019 Workshop on Dialogue System Technology Challenges 7 (DSTC7), 2019, Hawaii, USA.

[2018]

Character-Level Feature Extraction with Densely Connected Networks
Chanhee Lee, Young-Bum Kim, Dongyub Lee, Heuiseok Lim
COLING 2018

Appointments & Awards

Year	Award
2021	3rd place in Task1 and 5th place in Task2, Dialogue State Tracking Challenge (DSTC 10) Track2, AAAI 2022
2019	2nd place in the EmotionX (shared task of SocialNLP), IJCAI 2019
2019	Fourth place in the DSTC-7 tack-1 task, AAAI 2019
2018	Bronze Prize in the Korean Language Information Processing Competition (Dependency Parser), HCLT 2018
2018	Kakao Research Scholarship
2017	Gold Prize in Korean Language Information Processing Competition (Named Entity Recoginition), HCLT 2017
2016	Software Maestro 6th (Completion of Phase 1, Advance to Phase 2)