Greetings!

I'm Seolhwa Lee, currently an AI researcher at Lotuspetal AI. Before that, I was a postdoctoral researcher at Technical University of Darmstadt and University of Copenhagen, working with the UKP Lab and CoAStaL group, advised by Prof. Iryna Gurevych and Prof. Anders Søgaard, respectively. Prior to that, I received my Ph.D. in Computer Science and Engineering from Korea University in 2021, advised by Prof. Heuiseok Lim at the NLP & AI Lab.

My research interests span LLM, NLP, information retrieval (IR), differential privacy, and neuroscience-inspired computation. I'm particularly interested in dialogue agents, including their evaluation, generation, and summarization, as well as human-inspired computational models of language and cognitive science.

Feel free to reach out for any collaboration and discussion on related projects.

Education

Korea University
- Ph.D. in Computer Science and Engineering, Aug. 2015 - Sep. 2021
- Thesis: Abstractive Dialogue Summarization using Syntax-Aware Multi-task Learning
Johns Hopkins University
- Visiting PhD Student, 2019-2020
- Center for Language and Speech Processing (CLSP), advised by Prof. João Sedoc
- Participated in three different projects:
  - Created a dataset of conversations between people and state-of-the-art chatbots for WOCHAT+DBDC5 workshop
  - Collected crowd-sourced labels for the data and experiment several baseline models for evaluating generative dialogue systems.
  - Built COVID19 QA system (This effort leverages technologies developed under the support of DARPA program.)
Carnegie Mellon University
- LearnLab Summer School (2015), participated in track "CSCL(Computer Supported Collaborative Learning)", advised by Prof. Carolyn Rosè
- Developed the final project based on Google search aided system for education.
Baekseok University
- B.S. in Computer Science, 2011-2015

Experience

Lotuspetal AI, US
- AI Researcher, 2025 - current
- Research Topic: RAG

LinqAlpha, US
- Research Scientist & AI advisor, 2023 - 2024
- Research Topic: Text embedding model

Technical University Darmstadt, Germany
- Postdoctoral Researcher, 2023
- Ubiquitous Knowledge Processing (UKP) Lab, advised by Prof. Iryna Gurevych
- Research Topic: Privacy-aware NLP, Differential Privacy

University of Copenhagen, Denmark
- Postdoctoral Researcher, 2021 - 2022
- CoAStaL group, advised by Prof. Anders Søgaard
- Research Topic: Privacy-aware NLP, Differential Privacy

Selected Papers

Linq-Embed-Mistral Technical Report
Junseong Kim, Seolhwa Lee, Jihoon Kwon, Sangmo Gu, Yejin Kim, Minkyung Cho, Jy-yong Sohn, Chanyeol Choi
arXiv, 2024

Hyper-BTS Dataset: Scalability and Enhanced Analysis of Back TranScription (BTS) for ASR Post-Processing
Chanjun Park, Jaehyung Seo, Seolhwa Lee, Junyoung Son, Hyeonseok Moon, Sugyeong Eo, Chanhee Lee, Heuiseok Lim
EACL 2024 (Findings)

What does the Failure to Reason with "Respectively" in Zero/Few-Shot Settings Tell Us about Language Models?
Ruixiang Cui, Seolhwa Lee, Daniel Hershcovich, Anders Søgaard
ACL 2023

Private Meeting Summarization Without Performance Loss
Seolhwa Lee, Anders Søgaard
International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) 2023

BTS: Back TranScription for Speech-to-Text Post-Processor using Text-to-Speech-to-Text
Chanjun Park, Jaehyung Seo, Seolhwa Lee, Chanhee Lee, Hyeonseok Moon, Sugyeong Eo, Heuiseok Lim
ACL-IJCNLP 2021 (Workshop on Asian Translation, WAT)

Using the Poly-encoder for a COVID-19 Question Answering System
Seolhwa Lee, João Sedoc
EMNLP 2020 (NLP for COVID-19 Workshop)

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

Alternative Speech: Complementary Method to Counter-Narrative for Better Discourse
Seungyoon Lee, Dahyun Jung, Chanjun Park, Seolhwa Lee, Heuiseok Lim
ICDM 2023 (Workshops)

Retrieval-based Evaluation for LLMs: A Case Study in Korean Legal QA
Cheol Ryu, Seolhwa Lee, Subeen Pang, Chanyeol Choi, Hojun Choi, Myeonggee Min, Jy-Yong Sohn
EMNLP 2023 (Natural Legal Language Processing Workshop)

Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Study
Yong Cao, Li Zhou, Seolhwa Lee, Laura Cabello, Min Chen, Daniel Hershcovich
EACL 2023 (Cross-Cultural Considerations in NLP Workshop, C3NLP)

Synthetic Alone: Exploring the Dark Side of Synthetic Data for Grammatical Error Correction
Chanjun Park, Seonmin Koo, Seolhwa Lee, Jaehyung Seo, Sugyeong Eo, Hyeonseok Moon, Heuiseok Lim
ICML 2023 (Data-centric Machine Learning Research Workshop, DMLR)

Mimicking Infants' Bilingual Language Acquisition for Domain Specialized Neural Machine Translation
Chanjun Park, Woo-Young Go, Sugyeong Eo, Hyeonseok Moon, Seolhwa Lee, Heuiseok Lim
IEEE Access, 2022

AI for Patents: A Novel Yet Effective and Efficient Framework for Patent Analysis
Junyoung Son, Hyeonseok Moon, Jeongwoo Lee, Seolhwa Lee, Chanjun Park, Wonkyung Jung, Heuiseok Lim
IEEE Access, 2022

The ASR Post-Processor Performance Challenges of BackTranScription (BTS): Data-Centric and Model-Centric Approaches
Chanjun Park, Jaehyung Seo, Seolhwa Lee, Chanhee Lee, Heuiseok Lim
Mathematics, 2022

Empirical Analysis of Parallel Corpora and In-Depth Analysis Using LIWC
Chanjun Park, Midan Shim, Sugyeong Eo, Seolhwa Lee, Jaehyung Seo, Hyeonseok Moon, Heuiseok Lim
Applied Sciences, 2022

PicTalky: Augmentative and Alternative Communication for Language Developmental Disabilities
Chanjun Park, Yoonna Jang, Seolhwa Lee, Jaehyung Seo, Kisu Yang, Heuiseok Lim
AACL-IJCNLP 2022 (Demo)

Priming Ancient Korean Neural Machine Translation
Chanjun Park, Seolhwa Lee, Jaehyung Seo, Hyeonseok Moon, Sugyeong Eo, Heuiseok Lim
LREC 2022

Empirical Analysis of Noising Scheme based Synthetic Data Generation for Automatic Post-editing
Hyeonseok Moon, Chanjun Park, Seolhwa Lee, Jaehyung Seo, Jungseob Lee, Sugyeong Eo, Heuiseok Lim
LREC 2022

FreeTalky: Don't Be Afraid! Conversations Made Easier by a Humanoid Robot using Persona-based Dialogue
Chanjun Park, Yoonna Jang, Seolhwa Lee, Sungjin Park, Heuiseok Lim
LREC 2022

FreeTalky: Don't Be Afraid! Conversations Made Easier by a Humanoid Robot using Persona-based Dialogue
Chanjun Park, Yoonna Jang, Seolhwa Lee, Sungjin Park, Heuiseok Lim
AAAI 2022 (Artificial Intelligence for Education Workshop, AI4EDU)

Two Heads are Better than One? Verification of Ensemble Effect in Neural Machine Translation
Chanjun Park, Sungjin Park, Seolhwa Lee, Taesun Whang, Heuiseok Lim
EMNLP 2021 (Insights from Negative Results in NLP Workshop)

Syntax-enhanced Dialogue Summarization using Syntax-aware information
Seolhwa Lee, Kisu Yang, Chanjun Park, João Sedoc, Heuiseok Lim
NeurIPS 2021 (Women in Machine Learning Workshop, WiML)

Who Speaks Like a Style of Vitamin: Towards Syntax-Aware Dialogue Summarization Using Multi-Task Learning
Seolhwa Lee, Kisu Yang, Chanjun Park, João Sedoc, Heuiseok Lim
IEEE Access, 2021

Collecting Verified COVID-19 Question Answer Pairs
Adam Poliak, Max Fleming, Cash Costello, Kenton Murray, Mahsa Yarmohammadi, Shivani Pandya, Darius Irani, Milind Agarwal, Udit Sharma, Shuo Sun, Nicola Ivanov, Lingxi Shang, Kaushik Srinivasan, Seolhwa Lee, Xu Han, Smisha Agarwal, João Sedoc
EMNLP 2020 (NLP for COVID-19 Workshop)

Development of Fashion Product Retrieval and Recommendations Model Based on Deep Learning
Jaechoon Jo, Seolhwa Lee, Chanhee Lee, Dongyub Lee, Heuiseok Lim
Electronics, 2020

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 & Management, 2020

An Evaluation Protocol for Generative Conversational Systems
Seolhwa Lee, Heuiseok Lim, João Sedoc
arXiv, 2020

Long-term Effects of Adaptive Customization Support on Elderly People
Danial Hooshyar, Seolhwa Lee, YeongWook Yang, Jaechoon Jo, Heuiseok Lim
Cognition, Technology & Work, 2019

SmartSenior: Automatic Content Personalization Through Semi-supervised Learning
Heuiseok Lim, Danial Hooshyar, Hyesung Ji, Seolhwa Lee, Jaechoon Jo
Wireless Personal Communications, 2019

An Adaptable UI/UX Considering User's Cognitive and Behavior Information in Distributed Environment
Hyesung Ji, Youdong Yun, Seolhwa Lee, Kuekyeng Kim, Heuiseok Lim
Cluster Computing, 2018

Mining Biometric Data to Predict Programmer Expertise and Task Difficulty
Seolhwa Lee, Danial Hooshyar, Hyesung Ji, Kichun Nam, Heuiseok Lim
Cluster Computing, 2018

A Novel Density-Based Clustering Method Using Word Embedding Features for Dialogue Intention Recognition
Jungsun Jang, Yeonsoo Lee, Seolhwa Lee, Dongwon Shin, Dongjun Kim, Hae-Chang Rim
Cluster Computing, 2016

Comparing Programming Language Comprehension between Novice and Expert Programmers Using EEG Analysis
Seolhwa Lee, Andrew Matteson, Danial Hooshyar, SongHyun Kim, JaeBum Jung, GiChun Nam, Heuiseok Lim
IEEE International Conference on Bioinformatics and Bioengineering (BIBE) 2016

See full list on Google Scholar.

Honors & Awards

Best Paper Award (2020), Korea University
Naver PhD fellowship Award (2019), Naver corporation
Best Paper Award (2018), The Korean Association of Computer Education
Best Paper Award (2018), The Korean Society of Fashion Business
Best Paper Award (2016), The Korean Association of Computer Education
Information Technology Master Scholarship (2013), KT corporation