Improving Translations by Combining Fuzzy-Match Repair with Automatic Post-Editing

Two of the more predominant technologies that professional translators have at their disposal for improving productivity are machine translation (MT) and computer-aided translation (CAT) tools based on translation memories (TM). When translators use MT, they can use automatic post-editing (APE) systems to automate partof the post-editing work and get further productivity gains. When they use TM-based CAT tools, productivity may improve if they rely on fuzzy-match repair(FMR) methods. In this paper we combine FMR and APE: first a FMR proposal is produced from the translation unit proposed by the TM, then this proposal is further improved by an APE system specially tuned for this purpose. Experiments conducted on the translation of English texts into German show that, with the two combined technologies, the quality of the translations improves up to 23% compared to a pure MT system. The improvement over a pure FMR system is of 16%, showing the effectiveness of our joint solution.