200 Union St SE
Minneapolis, MN 55455
My primary research interest focuses on learning better representations for longer textual contexts, such as documents, using discourse structures defined in linguistics. As writers carefully design these (hierarchical) structures to convey meaning systematically, they can serve as meaningful learning signals for document-level representation learning. More specifically, I am interested in modeling discourse structures from various frameworks as (hyper)graphs and merging them with other topological structures that can be induced by learning language models with appropriate self-supervision signals.
Before joining the Ph.D. program, I worked as a researcher at NAVER LABS Europe and Papago team at NAVER Korea, where I researched on various topics in neural machine translation (NMT), such as analysis of language-pair-specific multilingual representation, document-level NMT with discourse information, cross-attention-based website translation, and quality estimation for evaluating NMT models.
I received a B.Eng. degree in Computer Science from Imperial College London in 2011. From 2012 to 2013, I served in the Republic of Korea Army Special Forces as an army interpreter. In 2016, I received an M.S. degree in Computer Science from Korea Advanced Institute of Science and Technology (KAIST).
My Ph.D. program is supported by 3M Science and Technology Fellowships.
|Oct 6, 2022||My summer internship work at Grammarly on improving iterative text revision task is accepted to appear at EMNLP 2022.|
|May 26, 2022||Our work on system demonstration for interactive and iterative text revision was shared in In2Writing workshop at ACL 2022 and received best paper award 🎉.|
|May 23, 2022||Our work on iterative text revision was accepted at ACL 2022.|
|Apr 22, 2022||I am excited for my summer internship at Grammarly where I will be working on interactive and iterative text revision task.|
|Nov 11, 2021||Our work on visualization of cross-lingual discourse relations was shared in CODI workshop at EMNLP 2021.|
|Aug 1, 2021||Our work on analysis of multilingual representation in NMT was accepted at Findings of ACL 2021.|
|Nov 20, 2020||Our work on quality estimation for NMT models was accepted at WMT 2020.|
|Nov 20, 2020||Our work on multilingual NMT model was shared in NLP-COVID19 workshop at EMNLP 2020.|