The mathematics of statistical machine translation: parameter estimation
Computational Linguistics - Special issue on using large corpora: II
Termight: identifying and translating technical terminology
ANLC '94 Proceedings of the fourth conference on Applied natural language processing
HLT '91 Proceedings of the workshop on Speech and Natural Language
Graph-based learning for statistical machine translation
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
DEW '09 Proceedings of the Workshop on Semantic Evaluations: Recent Achievements and Future Directions
To cache or not to cache?: experiments with adaptive models in statistical machine translation
WMT '10 Proceedings of the Joint Fifth Workshop on Statistical Machine Translation and MetricsMATR
Context adaptation in statistical machine translation using models with exponentially decaying cache
DANLP 2010 Proceedings of the 2010 Workshop on Domain Adaptation for Natural Language Processing
Consistent translation using discriminative learning: a translation memory-inspired approach
HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1
Cache-based document-level statistical machine translation
EMNLP '11 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Encouraging consistent translation choices
NAACL HLT '12 Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
PORT: a precision-order-recall MT evaluation metric for tuning
ACL '12 Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics: Long Papers - Volume 1
Hi-index | 0.00 |
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.