Kang is interested in developing human-centered language technologies. His research is focused on developing interdisciplinary methods for natural language processing (NLP) models and building interactive NLP systems for scientists and creative writers.
Unsupervised Natural Language Video Localization, Jinwoo Nam, Daechul Ahn, Dongyeop Kang, Seong Jong Ha, Jonghyun Choi, International Conference on Computer Vision (ICCV) 2021 (Oral, 3%)
Style is NOT a single variable: Case Studies for Cross-Stylistic Language Understanding, Dongyeop Kang, Eduard Hovy, Annual Meeting of the Association for Computational Linguistics (ACL), 2021
Augmenting Scientific Papers with Just-in-Time, Position-Sensitive Definitions of Terms and Symbols, Andrew Head, Kyle Lo, Dongyeop Kang, Raymond Fok, Sam Skjonsberg, Daniel S. Weld, Marti A. Hearst, SIGCHI Conference on Human Factors in Computing Systems (CHI), 2021
GenAug: Data Augmentation for Finetuning Text Generators, Steven Y. Feng*, Varun Gangal*, Dongyeop Kang, Teruko Mitamura, Eduard Hovy, Deep Learning Inside Out (DeeLIO) Workshop at EMNLP 2020
Document-Level Definition Detection in Scholarly Documents: Existing Models, Error Analyses„ Future Directions, Dongyeop Kang Andrew Head, Risham Sidhu, Kyle Lo, Daniel Weld, Marti A. Hearst , Workshop on Scholarly Document Processing (SDP) at EMNLP 2020
Plan ahead: Self-Supervised Text Planning for Paragraph Completion Task, Dongyeop Kang, Eduard Hovy, Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020
INSPIRED: Toward Sociable Recommendation Dialog Systems , Shirley Anugrah Hayati, Dongyeop Kang, Qingxiaoyang Zhu, We
Linguistically Informed Language Generation: A Multifaceted Approach , Dongyeop Kang, Ph.D. Dissertation, Carnegie Mellon University (Committee: Eduard Hovy, Jeffrey Bigham, Alan W Black, Jason Weston, Dan Jurafsky