Answers are grounded in this paper and cite their sources.
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.
No takes yet. Share an insight, caveat, or question.
Nora Aranberri (2020) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: