AI summary

This paper introduces a new continuous space translation model (CSTM) for phrase-based statistical machine translation, using neural networks to learn translation probabilities from phrase pairs. The CSTM, evaluated on the English/French IWSLT task, improves BLEU score and translation semantic quality.

Abstract

This paper presents a new approach to perform the estimation of the translation model probabilities of a phrase-based statistical machine translation system. We use neural networks to directly learn the translation probability of phrase pairs using continuous representations. The system can be easily trained on the same data used to build standard phrase-based systems. We provide experimental evidence that the approach seems to be able to infer meaningful translation probabilities for phrase pairs not seen in the training data, or even predict a list of the most likely translations given a source phrase. The approach can be used to rescore n-best lists, but we also discuss an integration into the Moses decoder. A preliminary evaluation on the English/French IWSLT task achieved improvements in the BLEU score and a human analysis showed that the new model often chooses semantically better translations. Several extensions of this work are discussed.