Rimvydas Rubavičius | The University of Edinburgh

About Me

I am a PhD student in the Center of Doctoral Training in Natural Language Processing hosted by Institute for Language, Cognition and Computation supervised by Alex Lascarides and Subramanian Ramamoorthy

I am working on Interactive Task Learning and how complexities of natural interaction with human teacher can help to learn new tasks more effectively. In particular, I am studying how complex natural language can help to obtain knowledge about new concepts introduced as part of embodied conversation to guide agent’s understanding about the domain.

Research Interests

Grounding: incrementally learning grounding models as part of human–robot interaction in embodied conversation.
Planning: solving sequencial decision problems in embodied environment
Reasoning: exploring logical, probabilistic, and causal reasoning about the world to be able to answer complex questions about it.

News

[Feb. 2022] Our paper about on incremental symbol grounding with complex referential expressions is accepted to NAACL 2022.

Publications

Interactive Symbol Grounding with Complex Referential Expressions
Rimvydas Rubavicius, Alex Lascarides
2022 Conference of the North American Chapter of the Association for Computational Linguistics. NAACL 2022.
[ACL Anthology] [PDF] [Code]

Services

Conference Reviewers: EMNLP2022