Contextual word similarity and estimation from sparse data

A method is presented that makes local analogies between each specific unobserved cooccurrence and other cooccurrences that contain similar words, as determined by an appropriate word similarity metric, and may provide an alternative to class based models.

Abstract

In recent years there is much interest in word cooccurrence relations, such as n-grams, verbobject combinations, or cooccurrence within a limited context. This paper discusses how to estimate the probability of cooccurrences that do not occur in the training data. We present a method that makes local analogies between each specific unobserved cooccurrence and other cooccurrences that contain simi- lar words, as determined by an appropriate word similarity metric. Our evaluation suggests that this method performs better than existing smoothing methods, and may provide an alternative to class based models.