This project translates both datasets, MS MARCO and Natural Questions using the Paracrawl dataset as training base. Testing in the Paracrawl dataset we achieved 37.8114 for the sacrebleu metric. We ...
The aim of this project is to implement statistical machine translation (SMT) using IBM Models 1 and 2. In particular, we attempt to translate between Dutch and English. SMT was taught during the ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback