A comparison of models of word meaning in context

This paper compares a number of recently proposed models for computing context sensitive word similarity. We clarify the connections between these models, simplify their formulation and evaluate them in a unified setting. We show that the models are essentially equivalent if syntactic information is ignored, and that the substantial performance differences previously reported disappear to a large extent when these simplified variants are evaluated under identical conditions. Furthermore, our reformulation allows for the design of a straightforward and fast implementation.