Can translationese features help users select an MT system for post-editing?

Nora Aranberri


This work explores the possibility of using translationese features as indicators of machine translation quality for users to select an MT system for post-editing assuming that a lower level of translationese will reveal a reduced need for editing. Results reveal that translationese and automatic metrics rank systems differently, opening an avenue for further research into the information each provides.

Texto completo: