You are here

Machine Translation

Our main research interest is the symbiotic integration of human and machine translation (MT). Human translation is typically very accurate but also a very time consuming and demanding activity. On the other hand, MT is fast and cheap but still far from publication quality. Indeed, machine and human translation can strongly benefit from each other, in multiple ways. In recent years, there has been increasing evidence that MT can boost productivity of human translators, by providing them with draft translations to post-edit. These results paved the way to new interesting application scenarios and research challenges for MT:

  • generating useful translations from speech and text
  • adapting the translation style to a document or user
  • learning from human feedback, e.g. corrections 
  • estimating the quality of given translations
  • improving existing translations