Hello, my name is Gyubok (pronounced as KYOO-bok), and I am a Ph.D. student at KAIST, advised by Edward Choi. My primary research areas are natural language processing and machine learning for healthcare. Specifically, I am interested in developing models and datasets to improve the interaction between large databases (i.e., electronic health records (EHRs)) and users, including both experts and non-experts.

Research Interest

• Natural language processing (text-to-SQL, dialog systems, question answering)

• Machine learning for healthcare (question answering on EHRs, clinical decision support systems) [Clinical NLP Shared Task @ NAACL '24]

Publications (C: Conference / J: Journal / W: Workshop / P: Preprint / *: Equal contribution)

2024

• [P2] EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records

Yeonsu Kwon*, Jiho Kim*, Gyubok Lee, Seongsu Bae, Daeun Kyung, Wonchul Cha, Tom Pollard, Alistair Johnson, Edward Choi

• [P1] TrustSQL: Benchmarking Text-to-SQL Reliability with Penalty-Based Scoring

Gyubok Lee, Woosog Chay, Seonhee Cho, Edward Choi

• [C8] Publicly Shareable Clinical Large Language Model Built on Synthetic Clinical Notes

Sunjun Kweon, Junu Kim, Jiyoun Kim, Sujeong Im, Eunbyeol Cho, Seongsu Bae, Jungwoo Oh, Gyubok Lee, Jong Hak Moon, Seng Chan You, Seungjin Baek, Chang Hoon Han, Yoon Bin Jung, Yohan Jo, Edward Choi

ACL 2024 Findings

• [C7] EHR-SeqSQL: A Sequential Text-to-SQL Dataset For Interactively Exploring Electronic Health Records

Jaehee Ryu*, Seonhee Cho*, Gyubok Lee, Edward Choi

ACL 2024 Findings

• [W2] Overview of the EHRSQL 2024 Shared Task on Reliable Text-to-SQL Modeling on Electronic Health Records

Gyubok Lee, Sunjun Kweon, Seongsu Bae, Edward Choi

NAACL 2024 Clinical NLP Workshop - EHRSQL 2024 Shared Task (Oral)

• [W1] Towards Unbiased Evaluation of Detecting Unanswerable Questions in EHRSQL

Yongjin Yang*, Sihyeon Kim*, SangMook Kim*, Gyubok Lee, Se-Young Yun, Edward Choi

ICLR 2024 Data Problems for Foundation Models (DPFM) Workshop

2023

• [C6] EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

Seongsu Bae*, Daeun Kyung*, Jaehee Ryu, Eunbyeol Cho, Gyubok Lee, Sunjun Kweon, Jungwoo Oh, Lei Ji, Eric I-Chao Chang, Tackeun Kim, Edward Choi

NeurIPS 2023 Datasets and Benchmarks (21/322)

• [C5] ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram

Jungwoo Oh, Gyubok Lee, Seongsu Bae, Joon-myoung Kwon, Edward Choi

NeurIPS 2023 Datasets and Benchmarks (77/322)

• [C4] Exploration into Translation-Equivariant Image Quantization

Woncheol Shin, Gyubok Lee, Jiyoung Lee, Eunyi Lyou, Joonseok Lee, Edward Choi

ICASSP 2023 (Oral, Top 3% recognition)

2022

• [C3] EHRSQL: A Practical Text-to-SQL Benchmark for Electronic Health Records

Gyubok Lee, Hyeonji Hwang, Seongsu Bae, Yeonsu Kwon, Woncheol Shin, Seongjun Yang, Minjoon Seo, Jong-Yeup Kim, Edward Choi

NeurIPS 2022 Datasets and Benchmarks (3/163)

• [J3] Machine Learning Improves the Prediction Rate of Non-Curative Resection of Endoscopic Submucosal Dissection in Patients with Early Gastric Cancer

Hae-Ryong Yun, Da Hyun Jung, Cheal Wung Huh, Gyubok Lee, Nak-Hoon Son, Jie-Hyun Kim, Young Hoon Youn, Jun Chul Park, Sung Kwan Shin, Sang Kil Lee, Yong Chan Lee

Cancers 2022 (IF: 6.575)

2021

• [J2] Erythropoiesis Stimulating Agent Recommendation Model Using Recurrent Neural Networks for Patient with Kidney Failure with Replacement Therapy

Hae-Ryong Yun*, Gyubok Lee*, Myeong Jun Jeon, Hyung Woo Kim, Young Su Joo, Hyoungnae Kim, Tae Ik Chang, Jung Tak Park, Seung Hyeok Han, Shin-Wook Kang, Wooju Kim, Tae-Hyun Yoo

Computers in Biology and Medicine 2021 (IF: 6.698)

• [C2] Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Prediction

Gyubok Lee*, Seongjun Yang*, Edward Choi

ACL 2021 (Oral)

2020

• [C1] Diverse and Admissible Trajectory Forecasting Through Multimodal Context Understanding

Seong Hyeon Park, Gyubok Lee, Manoj Bhat*, Jimin Seo*, Minseok Kang, Jonathan Francis, Ashwin Jadhav, Paul Pu Liang, Louis-Philippe Morency

ECCV 2020

2019

• [J1] Unsupervised learning approach for network intrusion detection system using autoencoders

Hyunseung Choi, Mintae Kim, Gyubok Lee, Wooju Kim

Journal of Supercomputing 2019 (IF: 2.469)

Work Experience

• Amazon Lab126, Sunnyvale, United States (2022.07 - 2023.01)

Applied Scientist Intern at Alexa AI-Natural Understanding Team

Worked on building pre-trained models for task-oriented dialog systems in collaboration with AlexaTM team

Education

• Korea Advanced Institute of Science and Technology (KAIST) (2020.09 - Current)

Ph.D. in Artificial Intelligence (Advisor: Edward Choi)

Area: Natural Language Processing and Machine Learning for Healthcare

• Yonsei University (2018.03 - 2020.08)

M.S. in Industrial Engineering - Data Science Track (Advisor: Wooju Kim)

Thesis: Improving Domain-Specific Neural Machine Translation by Leveraging In-Domain Monolingual Data

• Carnegie Mellon University (2019.08 - 2020.02)

Visiting student at Language Technologies Institute (Advisor: John Kang and Jaime Carbonell)

• University of Wisconsin–Madison (2010.09 - 2016.12)

B.B.A. in Actuarial Science