Linguistically Enriched Word-Sequence Kernels for Discriminative Language Modeling
Pierre Joachim Mahe, Nicola Cancedda · The MIT Press eBooks · 2008
This chapter introduces a method for taking advantage of background linguistic resources in statistical machine translation. It starts with a brief introduction to word-sequence kernels, followed by a description of the notion of factored representation and details of the kernel formulation. The next section validates the kernel construction on an artificial discrimination task reproducing some of the conditions encountered in translation. The chapter concludes with a discussion of related and future work.