Sciweavers

ACL
2008

Exploiting N-best Hypotheses for SMT Self-Enhancement

13 years 5 months ago
Exploiting N-best Hypotheses for SMT Self-Enhancement
Word and n-gram posterior probabilities estimated on N-best hypotheses have been used to improve the performance of statistical machine translation (SMT) in a rescoring framework. In this paper, we extend the idea to estimate the posterior probabilities on N-best hypotheses for translation phrase-pairs, target language n-grams, and source word reorderings. The SMT system is self-enhanced with the posterior knowledge learned from Nbest hypotheses in a re-decoding framework. Experiments on NIST Chinese-to-English task show performance improvements for all the strategies. Moreover, the combination of the three strategies achieves further improvements and outperforms the baseline by 0.67 BLEU score on NIST-2003 set, and 0.64 on NIST2005 set, respectively.
Boxing Chen, Min Zhang, AiTi Aw, Haizhou Li
Added 29 Oct 2010
Updated 29 Oct 2010
Type Conference
Year 2008
Where ACL
Authors Boxing Chen, Min Zhang, AiTi Aw, Haizhou Li
Comments (0)