Machine translations go through a post-editing process where a native speaker gives the green light to the final text. We offer different levels of post-editing ranging from a lighter, more superficial service to a more comprehensive, in-depth post-editing, depending on the type of text, its complexity and the customer’s needs.
The processes of translating and post-editing machine-generated content are quite different; each calls for distinct skills and training. Not all linguists are comfortable doing post-editing. It is necessary that translators are trained to focus on what is necessary in this type of Jobs. Academia quite recently started developing curricula to address the growing demand for human post-editors.
In post-editing machine translated content, the process involves the following steps:
- A sentence or segment of the MT output is read (that is, the process begins at the target).
- The MT output is compared to the source text.
- The Post-editors make some quality judgment of the MT output, based on the instructions provided.
- If the MT output is decent enough, they work on that to improve the text.
- If the MT output is of poor quality, they delete whatever the MT is offering and