Efficient statistical machine translation with constrained reordering
Evgeny Matusov, Stephan Kanthak, Hermann Ney · RWTH Publications (RWTH Aachen) · 2005
Abstract. This paper describes how word alignment information makes machine translation more efficient. Following a statistical approach based on finite-state transducers, we perform reordering of source sentences in training using automatic word alignments and estimate a phrase-based translation model. Using this model, we translate monotonically taking a permutation graph as input. The permutation graph is constrained using an efficient and flexible reordering framework. We then propose to automatically identify source word sequences which should always be translated monotonically and keep the word order of these sequences in search. This allows us to obtain fast good-quality translations. We present competitive experimental results on the Verbmobil German-to-English and BTEC Chinese-to-English translation tasks. 1