Not Everybody´s Special: Using Neighbors in Referring Expressions with Uncertain Attributes

Referring expression generation is widely considered a basic building block of any natural language generation system. Generating these phrases, which can point out a single object from a group of objects, has been studied extensively in that community. However, to build systems which can discuss images in an intelligent way, it is necessary to consider additional factors unique to the visual domain. In this paper we consider the use of neighbors as anchors to create a referring expression for a person in a group image. We describe a target person using the people around him, when we cannot find a reliable set of attributes to describe the target himself. We first present a method for including neighbors in a referring expression, and discuss several ways of presenting this data to a user. We show through experiments that using descriptions with neighbors can significantly improve the probability of conveying the correct information to a user.