@InProceedings{dahlmann-EtAl:2017:EMNLP2017,
  author    = {Dahlmann, Leonard  and  Matusov, Evgeny  and  Petrushkov, Pavel  and  Khadivi, Shahram},
  title     = {Neural Machine Translation Leveraging Phrase-based Models in a Hybrid Search},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {1411--1420},
  abstract  = {In this paper, we introduce a hybrid search for attention-based neural machine
	translation (NMT). A target phrase learned with statistical MT models extends a
	hypothesis in the NMT beam search when the attention of the NMT model focuses
	on the source words translated by this phrase. Phrases added in this way are
	scored with the NMT model, but also with SMT features including phrase-level
	translation probabilities and a target language model. Experimental results on
	German-to-English news domain and English-to-Russian e-commerce domain 
	translation tasks show that using phrase-based models in NMT search improves MT
	quality by up to 2.3\% BLEU absolute as compared to a strong NMT baseline.},
  url       = {https://www.aclweb.org/anthology/D17-1148}
}