Minimum error rate training in statistical machine translation
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Systran's Chinese word segmentation
SIGHAN '03 Proceedings of the second SIGHAN workshop on Chinese language processing - Volume 17
Mixture-model adaptation for SMT
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
(Meta-) evaluation of machine translation
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
NRC's PORTAGE system for WMT 2007
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
Rule-based translation with statistical phrase-based post-editing
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
Statistical post-editing on SYSTRAN's rule-based translation system
StatMT '07 Proceedings of the Second Workshop on Statistical Machine Translation
Semantic roles for SMT: a hybrid two-pass model
NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
Statistical post editing and dictionary extraction: Systran/Edinburgh submissions for ACL-WMT2009
StatMT '09 Proceedings of the Fourth Workshop on Statistical Machine Translation
DFKI hybrid machine translation system for WMT 2011: on the integration of SMT and RBMT
WMT '11 Proceedings of the Sixth Workshop on Statistical Machine Translation
Hi-index | 0.00 |
Recent papers have described machine translation (MT) based on an automatic post-editing or serial combination strategy whereby the input language is first translated into the target language by a rule-based MT (RBMT) system, then the target language output is automatically post-edited by a phrase-based statistical machine translation (SMT) system. This approach has been shown to improve MT quality over RBMT or SMT alone. In this previous work, there was a very loose coupling between the two systems: the SMT system only had access to the final 1-best translations from RBMT. Furthermore, the previous work involved European language pairs and relatively small training corpora. In this paper, we describe a more tightly integrated serial combination for the Chinese-to-English MT task. We will present experimental evaluation results on the 2008 NIST constrained data track where a significant gain in terms of both automatic and subjective metrics is achieved through the tighter coupling of the two systems.