Maximum Rank Correlation Training for Statistical Machine Translation

  title={Maximum Rank Correlation Training for Statistical Machine Translation},
  author={Daqi Zheng and Yifan He and Yang Liu and Qun Liu},
We propose Maximum Ranking Correlation (MRC) as an objective function in discriminative tuning of parameters in a linear model of Statistical Machine Translation (SMT). We try to maximize the ranking correlation between sentence level BLEU (SBLEU) scores and model scores of the N-best list, while the MERT paradigm focuses on the potential 1best candidates of the N-best list. After we optimize the MER and the MRC objectives using an multiple objective optimization algorithm at the same time, we… CONTINUE READING
2 Citations
28 References
Similar Papers


Publications citing this paper.


Publications referenced by this paper.
Showing 1-10 of 28 references

Tuning as ranking

  • P Koehn, F J. Och
  • Proc . of EMNLP .
  • 2011

A word alignment

  • Qingyang Hong
  • 2009

Effi - cient minimum error rate training and minimum bayes - risk decoding for translation hypergraphs and lattices

  • R. E. Banchs
  • 2009

Improving the objective

  • Y. He, A. Way
  • 2009
2 Excerpts

Stabilizing minimum error rate training

  • J Graehl, K Knight, D Marcu, S DeNeefe, W Wang, I Thayer
  • 2009

Similar Papers

Loading similar papers…