TY - GEN
T1 - Exploiting N-best hypotheses for smt self-enhancement
AU - Chen, Boxing
AU - Zhang, Min
AU - Aw, Aiti
AU - Li, Haizhou
PY - 2008
Y1 - 2008
N2 - 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 NIST- 2005 set, respectively.
AB - 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 NIST- 2005 set, respectively.
UR - https://www.scopus.com/pages/publications/80053044956
U2 - 10.3115/1557690.1557733
DO - 10.3115/1557690.1557733
M3 - 会议稿件
AN - SCOPUS:80053044956
SN - 9781932432046
T3 - ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
SP - 157
EP - 160
BT - ACL-08
PB - Association for Computational Linguistics (ACL)
T2 - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT
Y2 - 15 June 2008 through 20 June 2008
ER -