In this paper we describe the components of our statistical machine translation system. This system

The automated translation of one natural language to another, known as machine translation (MT), typically requires successful modeling of the grammars of the languages and the relationship between them. Rather than hand-coding these grammars and relationships, some machine translation e#orts employ data-driven methods, where the goal is to learn from a large amount of training examples of accurate translations. One such data-driven approach is statistical MT, where language and alignment models are automatically induced from parallel corpora. This work has also been extended to probabilistic finite-state approaches, most often via transducers.

In this paper we explore a technique for adding longer phrase translation pairs to a Statistical Machine Translation (SMT) system. New phrases are generated by merging existing phrase-level alignments that have overlapping words on both the source and target sides. The effect on translation quality is reported for an Arabic-English system in the news domain.