Mine Rhee
Papers
1
Total Citations
43
H-Index
1
About
Mine Rhee is a researcher at the intersection of natural language processing and robotics, with a primary focus on enabling robots to understand and execute complex human instructions. Her key contributions center on developing methods for grounding natural language into formal, executable representations that machines can use for decision-making. In her highly cited 2018 work, "Learning to Parse Natural Language to Grounded Reward Functions with Weak Supervision" (43 citations), Rhee pioneered a novel approach that translates natural language commands into goal-state reward functions using lambda calculus. This allows robots to infer not just what actions to take, but the underlying objectives of a task, enabling more intuitive and efficient human-robot collaboration. By leveraging weak supervision, her method reduces the need for expensive, hand-labeled training data, making it more scalable for real-world applications. Rhee’s work has been influential in advancing the field of language-conditioned robotics, demonstrating how formal semantic representations can bridge the gap between human communication and machine learning. Her research continues to shape how autonomous systems interpret and act upon natural language in dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1