In adding syntax to statistical MT, there is a tradeoff between taking advantage of linguistic analysis, versus allowing the model to exploit linguistically unmotivated mappings l...
We present two methods for estimating replacement probabilities without using parallel corpora. The first method proposed exploits the possible translation probabilities latent in ...
Statistical Machine Translation (MT) systems have achieved impressive results in recent years, due in large part to the increasing availability of parallel text for system trainin...
Zhiyi Song, Stephanie Strassel, Gary Krug, Kazuaki...
This paper describes CzEng 0.7, a new release of Czech-English parallel corpus freely available for research and educational purposes. We provide basic statistics of the corpus an...
A good decoding algorithm is critical to the success of any statistical machine translation system. The decoder's job is to find the translation that is most likely according...
Ulrich Germann, Michael Jahr, Kevin Knight, Daniel...