What's in a Preposition? Dimensions of Sense Disambiguation for an Interesting Word Class

Choosing the right parameters for a word sense disambiguation task is critical to the success of the experiments. We explore this idea for prepositions, an often overlooked word class. We examine the parameters that must be considered in preposition disambiguation, namely context, features, and granularity. Doing so delivers an increased performance that significantly improves over two state-ofthe-art systems, and shows potential for improving other word sense disambiguation tasks. We report accuracies of 91.8% and 84.8% for coarse and fine-grained preposition sense disambiguation, respectively.