Computer Science Seminar Series

Abstract

Standard algorithms for generating referring expressions assume that every entity has a true or false value for each property: a book is either yellow or not. Generating a referring expression is equated to finding a (minimal or cognitively motivated) set of properties which are all true for the target entity, but not all true for any distractor.

However, human language relies on highly flexible, context dependent qualitative concepts such as graded properties or colour terms which cannot be uniquely mapped to quantitative measurements. Moreover, humans are capable of grounding reference in dialogue by flexibly adapting conceptualizations in order to reach mutual understanding.

I will present the Probabilistic Reference And GRounding mechanism PRAGR which generates and resolves referring expressions based on perceptual data. PRAGR is geared towards maximizing referential success by flexibly assigning linguistic concepts to objects, depending on context. I will present recent studies evaluating PRAGR in robot-robot and human-robot communication and demonstrate the potential of PRAGR for referential grounding dialogues.

Keywords: Situated Human-Robot Interaction, Natural Language Generation

Bio

Vivien Mast is a PhD candidate at the University of Bremen, Germany. She is currently working on completing her thesis in computer science, for which she has developed a probabilistic reference and grounding mechanism (PRAGR) that enables referential grounding dialogues in situated interaction. After completing her M.A. degree in Linguistics and Digital Media, Vivien Mast worked as a research assistant in the project I5-[DiaSpace] in the collaborative research center Spatial Cognition at Bremen University, searching for ways of creating satisfying natural language communication between humans and machines.

Host: Verena Rieser

• Back to list