The conditional phrase translation probabilities constitute the principal components of phrase-based machine translation systems. These probabilities are estimated using a heurist...
Information retrieval systems conventionally assess document relevance using the bag of words model. Consequently, relevance scores of documents retrieved for different queries a...
Deepak Agarwal, Evgeniy Gabrilovich, Robert Hall, ...
Statistical models in machine translation exhibit spurious ambiguity. That is, the probability of an output string is split among many distinct derivations (e.g., trees or segment...
This paper presents a novel online relevant set algorithm for a linearly-scored block sequence translation model. The key component is a new procedure to directly optimize the glob...
This paper reports on the benefits of largescale statistical language modeling in machine translation. A distributed infrastructure is proposed which we use to train on up to 2 t...
Thorsten Brants, Ashok C. Popat, Peng Xu, Franz Jo...