BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Statistical phrase-based translation
NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Accurate unlexicalized parsing
ACL '03 Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - Volume 1
Clause restructuring for statistical machine translation
ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Improving a statistical MT system with automatically learned rewrite patterns
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Local phrase reordering models for statistical machine translation
HLT '05 Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing
Moses: open source toolkit for statistical machine translation
ACL '07 Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions
SSST '07 Proceedings of the NAACL-HLT 2007/AMTA Workshop on Syntax and Structure in Statistical Translation
A syntactic transformation model for statistical machine translation
ICCPOL'06 Proceedings of the 21st international conference on Computer Processing of Oriental Languages: beyond the orient: the research challenges ahead
Hi-index | 0.00 |
In machine translation, the re-ordering of word from source to target language is one of the major steps that affect mainly the performance of the system. Among many approaches for this type of problem, syntactic is an effective method for handling word-order in a statistical machine translation (SMT) system. In this paper, we introduce a word re-ordering approach that makes use the syntactic rules extracted from parse tree for the English-Vietnamese SMT system. Our word re-ordering rule set includes rules in noun phrase, verb phrase and adjective phrase. According to the experiment result, the noun phrase rules are the most significant rules of all. Compared with the MOSES phrase-based SMT system [1], these rules can improve BLEU score of 3.24 on our testing corpus. Moreover, we also conduct other experiments by using different combinations of rules to study their effectiveness. And we find that the translation performance for each corpus can be tuned by different ways of combination.