This paper presents methods to combine large language models trained from diverse text sources and applies them to a state-of-art French–English and Arabic–English machine translation system. We show gains of over 2 BLEU points over a strong baseline by using continuous space language models in re-ranking.
|Title of host publication||Third International Joint Conference on Natural Language Processing, IJCNLP 2008, Hyderabad, India, January 7-12, 2008|
|Number of pages||6|
|Publication status||Published - 2008|