Post-editing is the process of improving a machine-generated translation with a minimum of manual labour. In the process of translating content via machine translation, best results may be gained by post-editing the machine output.
Post-editing involves the correction of machine translation output to ensure it meets a level of quality. There are two broad types of post-editing :-
Light post-editing (sometimes referred to as Rapid post-editing) aims at making the translation simply understandable while ignoring all stylistic issues. Common light post-editing tasks include replacing unknown words, removing redundant words, fixing machine-induced meaning distortion, and partially or completely rewriting sentences.
Full post-editing aims at making the translation stylistically appropriate. This degree of post-editing is most similar to standard editing and involves all of the practices that a translator/editor follows which includes checking terminology, making grammatical and syntactic adjustments, adjusting for target language fluency etc.
Using KantanMT full post-editing is a viable alternative to manual translation, especially since most translators are used to post-editing pre-translated materials.
Post-editing MT output is a technique that can be mastered with a little bit of practice and can lead to significant productivity gains in translation throughput.