We present a new reordering model estimated as a standard n-gram language model with units built from morphosyntactic information of the source and target languages. It can be see...
Abstract. Algebraic compilers provide a powerful and convenient mechanism for specifying language translators. With each source language operation one associates a computation for ...
Model M, a novel class-based exponential language model, has been shown to significantly outperform word n-gram models in state-of-the-art machine translation and speech recognit...
In this paper we compare and contrast two approaches to Machine Translation (MT): the CMU-UKA Syntax Augmented Machine Translation system (SAMT) and UPC-TALP N-gram-based Statisti...
This paper proposes a model using associative processors (APs) for real-time spoken language translation. Spoken language translation requires (1) an accurate translation and (2) ...