Machine Translation Quality Estimation - MTQE

The machine translation quality estimation algorithm (MTQE) assesses the factual accuracy of machine translated text. Using a rating scale, it is possible to determine which segments of a machine translated text have a minimal risk of substantial error and which segments require more editing.

Analysis of machine translation post-editing, on the other hand, determines how much work was required by linguists to improve the translation. That knowledge is extremely important from the point of view of optimal management of multilingual content translation. For example, knowing that certain segments have required a disproportionate amount of editing can help in future projects: perhaps the source text can be adjusted or useful reference documents made available to post-editors.