Paper: Statistical Post-Editing of a Rule-Based Machine Translation System

ACL ID N09-2055
Title Statistical Post-Editing of a Rule-Based Machine Translation System
Venue Human Language Technologies
Session Short Paper
Year 2009
Authors

Automatic post-editing (APE) systems aim at correcting the output of machine translation systems to produce better quality translations, i.e. produce translations can be manually post- edited with an increase in productivity. In this work, we present an APE system that uses sta- tistical models to enhance a commercial rule- based machine translation (RBMT) system. In addition, a procedure for effortless human eva- luation has been established. We have tested the APE system with two corpora of differ- ent complexity. For the Parliament corpus, we show that the APE system significantly com- plements and improves the RBMT system. Re- sults for the Protocols corpus, although less conclusive, are promising as well. Finally, several possible sources of errors have been identified which will help...