Interactive Learning of State Representation through Natural Language Instruction and Explanation

no code implementations • 7 Oct 2017 • Qiaozi Gao, Lanbo She, Joyce Y. Chai

One significant simplification in most previous work on robot learning is the closed-world assumption where the robot is assumed to know ahead of time a complete set of predicates describing the state of the physical world.

Interactive Learning of Grounded Verb Semantics towards Human-Robot Communication

no code implementations • ACL 2017 • Lanbo She, Joyce Chai

To enable human-robot communication and collaboration, previous works represent grounded verb semantics as the potential change of state to the physical world caused by these verbs.

Reinforcement Learning

Incremental Acquisition of Verb Hypothesis Space towards Physical World Interaction

no code implementations • ACL 2016 • Lanbo She, Joyce Chai

Probabilistic Labeling for Efficient Referential Grounding based on Collaborative Discourse

no code implementations • ACL 2014 • Changsong Liu, Lanbo She, Rui Fang, Joyce Y. Chai

Graph Matching

Back to the Blocks World: Learning New Actions through Situated Human-Robot Dialogue

no code implementations • WS 2014 • Lanbo She, Shaohua Yang, Yu Cheng, Yunyi Jia, Joyce Chai, Ning Xi

Towards Situated Dialogue: Revisiting Referring Expression Generation

no code implementations • EMNLP 2013 • Rui Fang, Changsong Liu, Lanbo She, Joyce Y. Chai

Referring Expression Referring expression generation

Modeling Collaborative Referring for Situated Referential Grounding

no code implementations • WS 2013 • Changsong Liu, Rui Fang, Lanbo She, Joyce Chai

Graph Matching