Creating Robust Supervised Classifiers via Web-Scale N-gram Data

In this paper, we systematically assess the value of using web-scale N-gram data in state-of-the-art supervised NLP classifiers. We compare classifiers that include or exclude features for the counts of various N-grams, where the counts are obtained from a web-scale auxiliary corpus. We show that including N-gram count features can advance the state-of-the-art accuracy on standard data sets for adjective ordering, spelling correction, noun compound bracketing, and verb part-of-speech dis-ambiguation. More importantly, when operating on new domains, or when labeled training data is not plentiful, we show that using web-scale N-gram features is essential for achieving robust performance.