Two Approaches for Generating Size Modifiers

This paper offers a solution to a small problem within a much larger problem. We focus on modelling how people use size in reference, words like "big" and "tall", which is one piece within the much larger problem of how people refer to visible objects. Examining size in isolation allows us to begin untangling a few of the complex and interacting features that affect reference, and we isolate a set of features that may be used in a hand-coded algorithm or a machine learning approach to generate one of six basic size types. The hand-coded algorithm generates a modifier type with a high correspondence to those observed in human data, and achieves 81.3% accuracy in an entirely new domain. This trails oracle accuracy for this task by just 8%. Features used by the hand-coded algorithm are added to a larger set of features in the machine learning approach, and we do not find a statistically significant difference between the precision and recall of the two systems. The input and output of these systems are a novel characterization of the factors that affect referring expression generation, and the methods described here may serve as one building block in future work connecting vision to language.