Using Probabilistic Feature Matching to Understand Spoken Descriptions

Abstract. We describe a probabilistic reference disambiguation mechanism developed for a spoken dialogue system mounted on an autonomous robotic agent. Our mechanism performs probabilistic comparisons between features specified in referring expressions (e.g., size and colour) and features of objects in the domain. The results of these comparisons are combined using a function weighted on the basis of the specified features. Our evaluation shows high reference resolution accuracy across a range of spoken referring expressions.

• Type: Conference
• Year: 2008
• Where: AUSAI
• Authors: Ingrid Zukerman, Enes Makalic, Michael Niemann
• Keywords: Artificial Intelligence, AUSAI 2008, Probabilistic Comparisons, Probabilistic Reference Disambiguation, Spoken Referring Expressions