Publications
2024
[W7] Faithfulness Hallucination Detection in Healthcare AI
P. R. Vishwanath, S. Tiwari, T. G. Naik, S. Gupta, D. N. Thai, W. Zhao, S. Kwon, V. Ardulov, K. Tarabishy, A. McCallum,
W. Salloum
AIDSH@KDD 2024 (Oral)
[W6] ClinicalMamba: A Generative Clinical Language Model on Longitudinal Clinical Notes
Z. Yang, A. Mitra, S. Kwon, H. Yu
ClinicalNLP@NAACL 2024
[W5] TEAM at MEDIQA-M3G 2024: DermPrompt - A Systematic Exploration of Prompt Engineering with GPT-4V for Dermatological Diagnosis
P. Vashisht, A. Lodha, M. Maddipatla, Z. Yao, A. Mitra, Z. Yang, S. Kwon, J. Wang, H. Yu
ClinicalNLP@NAACL 2024
[C9] Is it safe to cross? Interpretable Risk Assessment with GPT-4V for Safety-Aware Street Crossing
H. Hwang, S. Kwon, Y. Kim, and D. Kim
UR 2024 (Outstanding Paper)
[C8] ODD: A Benchmark Dataset for the Natural Language Processing based Opioid Related Aberrant Behavior Detection
S. Kwon, X. Wang, W. Liu, E. Druhl, M. L. Sung, J. I. Reisman, W. Li, R. D. Kerns, W. Becker, and .H. Yu
NAACL 2024
2023
[C7] CR-COPEC: Causal Rationale of Corporate Performance Changes to Learn from Financial Reports
Y. Chun*, S. Kwon*, K. Sohn, N. Sung, J. Lee, B. Seo, K. Compher, S. Hwang, J. Choi
EMNLP Findings 2023
[C6] Vision Meets Definitions: Unsupervised Visual Word Sense Disambiguation Incorporating Gloss Information
S. Kwon, R. Garodia, M. Lee, Z. Yang and H. Yu
ACL 2023
[C5] Multi-label Few-Shot ICD Coding as Autoregressive Generation with Prompt
Z. Yang, S. Kwon, Z. Yao, and H. Yu
AAAI 2023 (Oral)
2022
[C4] MedJEx: A Medical Jargon Extraction Model with Wiki’s Hyperlink Information and Contextualized Masked Language Model Score
S. Kwon, Z. Yao, H. S. Jordan; D. A. Levy, B. Corner, and H. Yu
EMNLP 2022
2021
[W4] The Global Banking Standards QA Dataset (GBS-QA)
K. Sohn, S. Kwon, and J. Choi
EcoNLP@EMNLP 2021
[J2] Word Sense Disambiguation Based on Context Selection Using Knowledge-based Word Similarity
S. Kwon*, D. Oh*, and Y. Ko (* equal contribution)
Information Processing & Management, vol. 58, no. 4, p. 102551
2020
[W3] Why Do Masked Neural Language Models Still Need Commonsense Repositories to Handle Semantic Variations in Question Answering?
S. Kwon, C. Kang, J. Han, and J. Choi
RCQA@AAAI 2020 (Oral)
2019
[J1] Effective Vector Representation for the Korean Named-Entity Recognition
S. Kwon, Y. Ko, and J. Seo
Pattern Recognition Letters, vol. 117, pp. 52–57
2018
[C3] Word sense disambiguation based on word similarity calculation using word vector representation from a knowledge-based graph
D. O*, S. Kwon*, K. Kim, and Y. Ko (* equal contribution)
COLING 2018
2017
[W2] A Method to Generate a Machine-labeled Data for Biomedical Named Entity Recognition with Various Sub-Domains
J. Kim, S. Kwon, Y. Ko, and J. Seo
DDDSM@IJCNLP 2017
[C2] A Robust Named-Entity Recognition System Using Syllable Bigram Embedding with Eojeol Prefix Information
S. Kwon, Y. Ko, and J. Seo
CIKM 2017
[C1] UNIST SAIL System for TAC 2017 Cold Start Slot Filling
S. Lim*, S. Kwon*, S. Lee, and J. Choi
TAC 2017
2016
[W1] KSAnswer: Question-Answering System of Kangwon National University and Sogang University in the 2016 BioASQ Challenge
H. Lee, M. Kim, H. Kim, J. Kim, S. Kwon, J. Seo, Y. Kim, and J. Choi,
BioASQ@ACL 2016
Work in Progress
S. Kwon, C. Kang, J. Han, and J. Choi, "Why do neural language models still need common sense knowledge?" arXiv preprint arXiv:2209.00599
Yao, Z., Kantu, N. S., Wei, G., Tran, H., Duan, Z., Kwon, S., Yang, Z., and Yu, H. "README: Bridging Medical Jargon and Lay Understanding for Patient Education through Data-Centric NLP." arXiv preprint arXiv:2312.15561.