This paper investigates the combination of word-alignments computed with the competitive linking algorithm and well-established IBM models. New training methods for phrase-based st...
Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation estimates and low coverage over source and target p...
Often, the training procedure for statistical machine translation models is based on maximum likelihood or related criteria. A general problem of this approach is that there is on...
We describe a methodology for rapid experimentation in statistical machine translation which we use to add a large number of features to a baseline system exploiting features from...
Franz Josef Och, Daniel Gildea, Sanjeev Khudanpur,...
This paper presents a novel filtration criteria to restrict the rule extraction for the hierarchical phrase-based translation model, where a bilingual but relaxed well-formed depe...