Papers by Jaap Kruijt

2 papers
SPOTTER: A Framework for Investigating Convention Formation in a Visually Grounded Human-Robot Reference Task (2024.lrec-main)

Copied to clipboard

Challenge: Existing research has shown that conventions arise in repeated interactions over the same task, leading to a decrease in utterance length while maintaining informative content.
Approach: They propose to elicit conventions for members of an inner circle of well-known individuals in common ground, as opposed to individuals from an outer circle, who are unfamiliar.
Outcome: The proposed game platform elicits conventions for familiar and unfamiliar individuals in human-robot interaction.
Referring Expressions in Human-Robot Common Ground: A Thesis Proposal (2024.naacl-srw)

Copied to clipboard

Challenge: PhD examines the processes through which common ground shapes the pragmatic use of referring expressions in human-robot interaction.
Approach: They investigate the processes through which common ground shapes the pragmatic use of referring expressions in human-robot interaction.
Outcome: The proposed model can model linguistic processes and resolve referring expressions using pragmatic inference.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations