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 ont...
Searching online information is increasingly a daily activity for many people. The multilinguality of online content is also increasing (e.g. the proportion of English web users, ...
Yaser Al-Onaizan, Radu Florian, Martin Franz, Hany...
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...
In Chinese texts, words composed of single or multiple characters are not separated by spaces, unlike most western languages. Therefore Chinese word segmentation is considered an ...
Extracting tree transducer rules for syntactic MT systems can be hindered by word alignment errors that violate syntactic correspondences. We propose a novel model for unsupervise...