The NRC Publications Archive is now operational; however, not all the features of the site are available at this time.
The following features remain unavailable:
- Viewing/Downloading of full text publications
NRC is currently working to restore these features and we will update this notice as these features become available. Thank you for your patience.
The trouble with SMT consistency
; Carpuat, Marine
Information and Communication Technologies; National Research Council Canada
7th Workshop on Statistical Machine Translation, June 7-8, 2012, Montreal, Quebec
Proceedings of the 7th Workshop on Statistical Machine Translation
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