A Human-machine Cooperation Protocol for Machine Translation Output Edit Annotation

Abstract

We report on a study exploring automatic edit annotation in a post-editing corpus with a new method for computing edit types. We examine edit type association with quality scores assigned to the machine translation output and the post-edited texts. Finally, we account for shortcomings in our method and point out edit types worth leveraging.

Keywords

• machine translation
• human post-editing
• automatic error analysis
• human-machine cooperation