The Trouble with SMT Consistency
Marine Jacinthe Carpuat, Michel G. Simard · NPARC · 2012
SMT typically models translation at the sentence level, ignoring wider document context. Does this hurt the consistency of translated documents? Using a phrase-based SMT system in various data conditions, we show that SMT translates documents remarkably consistently, even without document knowledge. Nevertheless, translation inconsistencies often indicate translation errors. However, unlike in human translation, these errors are rarely due to terminology inconsistency. They are more often symptoms of deeper issues with SMT models instead. 1