Paper: Improving A General-Purpose Statistical Translation Engine By Terminological Lexicons

ACL ID W02-1405
Title Improving A General-Purpose Statistical Translation Engine By Terminological Lexicons
Venue CompuTerm International Workshop On Computational Terminology
Session
Year 2002
Authors

The past decade has witnessed exciting work in the fleld of Statistical Machine Translation (SMT). However, accurate evaluation of its po- tential in real-life contexts is still a questionable issue. In this study, we investigate the behavior of an SMT engine faced with a corpus far difier- ent from the one it has been trained on. We show that terminological databases are obvious resources that should be used to boost the per- formance of a statistical engine. We propose and evaluate a way of integrating terminology into a SMT engine which yields a signiflcant re- duction in word error rate.