Mingzhi Yu
Papers
2
Total Citations
10
H-Index
2
About
Mingzhi Yu investigates the intersection of human-robot interaction, collaborative learning, and dialogue systems, with a focus on how teachable robots can enhance educational outcomes. Her work examines the dynamics of lexical alignment—how conversational partners adapt their language—in interactions involving a robot learner. In her highly cited paper "Comparison of Lexical Alignment with a Teachable Robot in Human-Robot and Human-Human-Robot Interactions" (2022, 6 citations), co-authored with Asano, Litman, and others, she demonstrates how alignment patterns shift when a robot is part of a teaching dyad or triad. Her follow-up study, "It Takes Two: Examining the Effects of Collaborative Teaching of a Robot Learner" (2022, 4 citations), explores how pairs of human teachers jointly instruct a robot, revealing that collaborative teaching fosters richer dialogue and improved learning outcomes. These contributions advance our understanding of social learning in human-robot teams, with implications for designing adaptive educational technologies. Yu’s research, grounded in computational linguistics and cognitive science, highlights the potential of robots as active participants in collaborative learning environments, offering insights for both AI and education researchers.
Research Focus
Key Achievements
Top Papers
- 1
- 2