Using Suffix Arrays as Language Models: Scaling the n-gram

In this article, we propose the use of suffix arrays to implement n-gram language models with practically unlimited size n. These unbounded n-grams are called ∞-grams. This approach allows us to use large contexts efficiently to distinguish between different alternative sequences while applying synchronous back-off. From a practical point of view, the approach has been applied within the context of spelling confusibles, verb and noun agreement and prenominal adjective ordering. These initial experiments show promising results and we relate the performance to the size of the n-grams used for disambiguation.