Browse by topic
Type of publication
Bilingual segmentation for phrasetable pruning in Statistical Machine Translation. Proceedings of the 15th Annual Conference of the European Association for Machine Translation, 2011.Statistical machine translation systems have greatly improved in the last years. However, this boost in performance usually comes at a high computational cost, yielding systems that are often not suitable for integration in hand-held or real-time devices. We describe a novel technique for reducing such cost by performing a Viterbi-style selection of the parameters of the translation model. We present results with finite state transducers and phrase-based models showing a 98% reduction of the number of parameters and a 15-fold increase in translation speed without any significant loss in translation quality.