IROS 2022

Givenness Hierarchy Informed Optimal Document Planning for Situated Human-Robot Interaction

Robots that use natural language in collaborative tasks must refer to objects in their environment. Recent work has shown the utility of the linguistic theory of the Givenness Hierarchy (GH) in generating appropriate referring forms. But before referring expression generation, collaborative robots must determine the content and structure of a sequence of utterances, a task known as document planning in the natural language… Continue reading Givenness Hierarchy Informed Optimal Document Planning for Situated Human-Robot Interaction

Published

INLG 2022

Evaluating Referring Form Selection Models in Partially-Known Environments

This paper won the Best Long-Paper Award at INLG 2022: For autonomous agents such as robots to effectively communicate with humans, they must be able to refer to different entities in situated contexts. In service of this goal, researchers have recently attempted to model the selection of referring forms on the basis of cognitive… Continue reading Evaluating Referring Form Selection Models in Partially-Known Environments

Published

HRI 2022 LBR

A Task Design for Studying Referring Behaviors for Linguistic HRI

Two of four quadrants of the task environment to study referring behaviors for linguistic HRI. Two rule cards are placed on each table, with learners' on the left hand side and instructors' (dashed box) on the right hand side (solid box). Objects are intentionally placed at the intersections of a 3×3 grid to encourage use of different referring forms whose use varies according to distance. Instructors teach learners to construct buildings whose constituents blocks are distributed across the visible and non-visible quadrants.

In many domains, robots must be able to communicate to humans through natural language. One of the core capabilities needed for task-based natural language communication is the ability to refer to objects, people, and locations. Existing work on robot referring expression generation has focused nearly exclusively on generation of definite descriptions to visible objects.… Continue reading A Task Design for Studying Referring Behaviors for Linguistic HRI

Published