YJ Choe

Research Scientist at Kakao Brain
PhD Student (on leave) at Carnegie Mellon University

yj201709 — (Happy me in Copenhagen during EMNLP 2017.)

Hi there!

I am a Research Scientist at Kakao Brain, where I work in the areas of deep learning and natural language processing. I am also a PhD Student on leave from the Machine Learning Department and the Department of Statistics and Data Science at Carnegie Mellon University, where I've worked on high-dimensional statistics and neuroscience projects with Aarti Singh, Sivaraman Balakrishnan, and Timothy Verstynen. Before starting my PhD, I did my undergraduate in Mathematics and Computer Science at the University of Chicago, where I worked with John Lafferty and at the Knowledge Lab.

Check out my research page for a selection of my current and previous projects.

Updates

2019/08: Our paper "Predicting Drug-Target Interaction Using 3D Structure-Embedded Graph Representations from Graph Neural Networks" got accepted to the Journal of Chemical Information and Modeling! This is joint work with Jaechang Lim, Seongok Ryu, and Woo Youn Kim from KAIST ACE Team, along with Kyubyong Park and Jiyeon Ham from Kakao Brain.
2019/08: Our paper "A Neural Grammatical Error Correction System Built On Better Pre-training and Sequential Transfer Learning", accompanying our submission to the GEC shared task, was presented at the ACL 2019 Workshop on Building Educational Applications. We also released our code.
2019/05: Our paper "Discovery of Natural Language Concepts in Individual Units" was presented at the ICLR 2019! This is joint work with Seil Na, Dong-Hyun Lee, and Gunhee Kim.
2019/04: Our team "Kakao&Brain" won the second place in two tracks of the BEA 2019 Shared Task on Grammatical Error Correction! Our work will be presented at the ACL 2019 BEA Workshop in Florence, Italy. We also received some media coverage in Korea.
2018/12: I started a blog.
2018/10: Our paper "Local White Matter Architecture Defines Functional Brain Dynamics" won the Franklin V. Taylor Memorial (Best Paper) Award at the IEEE SMC 2018! I am truly grateful to my advisors and collaborators Siva Balakrishnan, Aarti Singh, Jean Vettel, and Tim Verstynen.