@InProceedings{chen-EtAl:2017:CoNLL2,
  author    = {Chen, Huadong  and  Huang, Shujian  and  Chiang, David  and  DAI, XIN-YU  and  CHEN, Jiajun},
  title     = {Top-Rank Enhanced Listwise Optimization for Statistical Machine Translation},
  booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {90--99},
  abstract  = {Pairwise ranking methods are the most widely used discriminative training
	approaches for structure prediction problems in natural language processing
	(NLP). Decomposing the problem of ranking hypotheses into pairwise comparisons
	enables simple and efficient solutions. However, neglecting the global ordering
	of the hypothesis list may hinder learning. We propose a listwise learning
	framework for structure prediction problems such as machine translation. Our
	framework directly models the entire translation list’s ordering to learn
	parameters which may better fit the given listwise samples. Furthermore, we
	propose top-rank enhanced loss functions, which are more sensitive to ranking
	errors at higher positions. Experiments on a large-scale Chinese-English
	translation task show that both our listwise learning framework and top-rank
	enhanced listwise losses lead to significant improvements in translation
	quality.},
  url       = {http://aclweb.org/anthology/K17-1011}
}