dongyeopk@berkeley.edu
I am a postdoc at University of California, Berkeley working with Marti A. Hearst, and a part of Berkeley AI Research (BAIR).
I obtained my Ph.D. in the Language Technologies Institute
of the School of Computer Science at Carnegie Mellon University,
under Eduard Hovy.
I interned at Facebook AI, Allen Institute for AI (AI2), and Microsoft Research.
My Ph.D. study has been supported by Allen Institute for AI (AI2) Fellowship, CMU Presidential Fellowship, and ILJU Graduate Fellowship.
In the middle of the study, I completed my alternative military service in South Korea at
Naver Labs and
KAIST Institute.
Before joining CMU, I obtained my BS and MS in Computer Science Engineering at KAIST, Korea.
I am on academic job market this year.
[ CV | Research Statement | Teaching Statement | Diversity Statement ]
I'm interested in building human-centric language generation systems.
My research is focused on developing computational models guided by linguistic theories in a wide range of generation tasks and building real-world NLG systems which can interactively collaborate with human readers and writers.
My Ph.D. dessertation research focused on modeling the three facets that consist of human language;
knowledge,
structure, and
style, based on Halliday’s
Systemic Functional Linguistics (SFL) theory (1978), and presented effective computational methods for handling each facet in a wide range of generation tasks.
During my postdoc, I develop systems that directly involve humans in the loop of NLP pipeline — data collection, model development, and system evaluation — particularly focusing on mixed-initiative AI systems for scientific document reading and writing.
Research Interests:
-
Computational Linguistics ⊕ Machine Learning ⊕ Human-Computer Interaction
-
Neural-symbolic integration for trustworthy and factual generation.
-
Text planning for coherently structured generation.
-
Cross-style language understanding for stylistically appropriate generation.
-
Mixed-initiative interaction for human-machine collaborative generation.