... propose a novel discrim-inative language model, which can be ap-plied quite generally. Compared to thewell known N-gram language models, dis-criminative language models can achievemore accurate ... verb.Discriminative language models (DLMs) havebeen proposed to classify sentences directly as cor-rect or incorrect (Gao et al., 2005; Roark et al.,2007), and these models can handle both non-local and overlapping ... theprobability of word strings or sentences. Amongthese models, N-gram language models (NLMs) arewidely used. NLMs approximate the probability by conditioning only on the precedingwords.For example,...