I’m a PhD Student at the Linguistic Department at Georgetown University, advised by Ethan Wilcox. I am interested in information theoretic approaches to linguistics and the representations of syntactic and semantic structures in models of language and text, including annotated corpora and LLMs.

Before coming to Georgetown, I was NLP engineer at NCSOFT, where I worked on NLU and information extraction.

Outside of classes and assistantships, I like to participate in intramural sports as both player and coach and attend free food events around campus.

You can reach me at jm3743@georgetown.edu.

News

• Sep 2025: I will be attending EMNLP 2025–see you in Suzhou!
• Aug 2025: I will be serving as Teaching Assistant for LING1000 at Georgetown University as well as Course Assistant for CSC494 at the University of Toronto during the fall.
• May 2025: I will be working with Annie Lee and her students at the University of Toronto and Ontario Tech University on topics around multilingual and low-resource NLP.
• Jan 2025: I will be attending NAACL 2025–see you in Albuquerque!

Publications

Junghyun Min, Xiulin Yang, Shira Wein. When does meaning backfire? Investigating the role of AMRs in NLI. *SEM 2025.

Lauren Levine, Junghyun Min, Amir Zeldes. Building UD Cairo for Old English in the Classroom. UDW at SyntaxFest 2025.

Junghyun Min, Minho Lee, Woochul Lee, Yeonsoo Lee. Punctuation restoration improves structure understanding without supervision. RepL4NLP at NAACL 2025.

Junghyun Min, R. Thomas McCoy, Dipanjan Das, Emily Pitler, and Tal Linzen. Syntactic data augmentation increases robustness to inference heuristics. ACL 2020.

R. Thomas McCoy, Junghyun Min, and Tal Linzen. BERTs of a feather do not generalize together: Large variability in generalization across models with similar test set performance. BlackboxNLP at EMNLP 2020.

Education and work experience