Learning and application of differential grammars

We examine the Differential Grammar, a representation designed to discriminate which of a set of confusable alternatives is most likely in the context it occurs in. This approach is useful whereever uncertainty may exist about the identity of a token or sequence of tokens, including in speech recognition, optical character recognition and machine translation. In this paper our application is word processing: we discuss multiple models of confusion which may be used in the identification of confused words, we show how significant contexts may be identified and condensed into Differential Grammars, and we contrast the performance of our implementation with that of two commercial grammar checkers which purport to handle the confused word problem.