Confusion Network Based System Combination for Statistical Machine Translation
DU Jin-hua1, WEI Wei 1, XU Bo1, 2
1. Digital Content Technology Research Center, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China; 2. National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China
Abstract：Based on several popular methods of statistical machine translation combination, an improved multiple-system combination framework is proposed. This framework integrates Minimum Bayes-Risk (MBR) decoding and multi-feature Confusion Network (CN) decoding techniques with the following steps(1)MBR decoding technique is used to select the hypothesis with minimum risk as an alignment reference from several N-best results produced by translation systems ; (2)CN is constructed by aligning the other hypotheses with the reference. Based on log-linear model, the CN introduces more knowledge sources into the selection of optimal path. Compared with the best system without combination, the proposed framework has 2.19% improvement in BLEU score. Inaddition, we present a modified Translation Edit Rate (TER)—GIZA-TER metric for CN alignment, which facilitates a more effective phrase re-ordering. The significance tests demonstrate the validness of the proposed methods.
[1] Philipp Koehn, Franz J. Och, and Daniel Marcu. Statistical phrase-based translation [C]//HLT-NAACL, 2003. [2] Franz J. Och and H. Ney. The alignment template approach to statistical machine translation [J]. Computational Linguistics, 2004,30(4):417-449. [3] David Chiang. A hierarchical phrase-based model for statistical machine translation [C]//ACL, 2005. [4] Kenji Yamada and Kevin Knight. A syntax-based statistical translation model [C]//ACL, 2001. [5] J. G. Fiscus. A Post-Processing System to Yield Reduced Word Error Rates: Recognizer Output Voting Error Reduction (ROVER) [C]//IEEE Workshop on Automatic Speech Recognition and Understanding, 1997. [6] S. Kumar and W. Byrne. Minimum Bayes-risk decoding for statistical machine translation [C]//HLT-NAACL, 2004. [7] K.C. Sim, W. Byrne, M. Gales, H. Sahbi and P. Woodland. Consensus Network Decoding For Statistical Machine Translation System [C]//ICASSP, 2007. [8] Sanjika Hewavitharana, Bing Zhao, Almut Silja Hildebrand, Matthias Eck, Chiori Hori, Stephan Vogel and Alex Waibel. The CMU Statistical Machine Translation System for IWSLT2005 [C]//IWSLT, 2005. [9] E. Matusov, N. Ueffing and H. Ney. Computing Consensus Translation from Multiple Machine Translation Systems Using Enhanced Hypotheses Alignment [C]//EACL, 2006. [10] F. J. Och and H. Ney. A Systematic Comparison of Various Statistical Alignment Models [J]. Computational Linguistics, 2003, 29(1):19-51. [11] Antti-Veikko I. Rosti, Necip Fazil Ayan, Bing Xiang, Spyros Matsoukas, Richard Schwartz and Bonnie J.Dorrt. Combing Outputs from Multiple Machine Translation Systems[C]//HLT-NAACL, 2007. [12] H. Schwenk and J. L. Gauvain. Improved ROVER using language model information [C]//ISCA ITRW, 2000. [13] K. Papineni, S. Roukos, T. Ward, and W. Zhu. Bleu: a method for automatic evaluation of machine translation [D]. Technical Report RC22176, IBM Research Division, 2001. [14] Peter F. Brown, Stephen A. Della Pietra, Vincent J. Della Pietra, and Robert L. Mercer. The mathematics of statistical machine translation: Parameter estimation [J]. Computational Linguistics, 19(2):263-311, 1993. [15] Wei Wei, Wei Pang, Zhendong Yang, Zhenbiao Chen, Chengqing Zong, Bo Xu. CASIA SMT System for TC-STAR Evaluation Campaign 2006 [C]//TC-STAR workshop, 2006. [16] Philipp Koehn, et al. Edinburgh System Description for the 2005 IWSLT Speech Translation Evaluation [C]//International Workshop on Spoken Language Translation, 2005. [17] Yaser Al-Onaizan, Kishore Papineni. Distortion Models For Statistical Machine Translation [C]//Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL, 2006. [18] Philipp Koehn. Statistical Significance Tests for Machine Translation Evaluation [C]//Proceedings of the EMNLP, 2004. [19] Ying Zhang, Stephan Vogel. Measuring Confidence Intervals for the Machine Translation Evaluation Metrics [C]//Proceedings of the 10th International Conference on Theoretical and Methodological Issues in Machine Translation (TMI), 2004. [20] 魏玮,杜金华,徐波. 基于分层语块分析的统计翻译研究[J]. 中文信息学报,21,2007(5): 87-90.
2008, Vol. 22 
