Smooth Bilingual N-Gram Translation

We address the problem of smoothing translation probabilities in a bilingual N-grambased statistical machine translation system. It is proposed to project the bilingual tuples onto a continuous space and to estimate the translation probabilities in this representation. A neural network is used to perform the projection and the probability estimation. Smoothing probabilities is most important for tasks with a limited amount of training material. We consider here the BTEC task of the 2006 IWSLT evaluation. Improvements in all official automatic measures are reported when translating from Italian to English. Using a continuous space model for the translation model and the target language

• Type: Conference
• Year: 2007
• Where: EMNLP
• Authors: Holger Schwenk, Marta R. Costa-Jussà, José A. R. Fonollosa
• Keywords: Continuous Space, EMNLP 2007, Natural Language Processing, Smoothing Translation Probabilities, Translation Probabilities