Post-editing of machine translation output is the process of reviewing machine translated content and editing it in such a way that it meets the requirements of the client. In other words, Machine Translation Post-Editing (or MTPE) works by having human oversight over MT output. Original sources are translated en masse by machine translation (MT) engines. Then our trained and fluent reviewers edit the resultant content for readability and accuracy.
While machine translation quality has come on leaps and bounds since the introduction of neural machine translation, it’s not quite ready to replace a human translator. This means that machine translation doesn’t provide flawless translations, but it rather requires the contribution of a professional linguist in order to reach the final result. The process of reviewing, correcting or rearranging an MT output is called Post-Editing. Post-editing differs from editing in that the latter refers to checking a human translator’s work against the source text whereas post-editing refers to checking a text produced by a software. In addition, editing must be bilingual, whereas post-editing may be bilingual or monolingual, although serious clients always opt for bilingual check.