@InProceedings{zhang-EtAl:2017:I17-12,
  author    = {Zhang, Jingyi  and  Utiyama, Masao  and  Sumita, Eiichro  and  Neubig, Graham  and  Nakamura, Satoshi},
  title     = {Improving Neural Machine Translation through Phrase-based Forced Decoding},
  booktitle = {Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {152--162},
  abstract  = {Compared to traditional statistical machine translation (SMT), neural machine
	translation (NMT) often sacrifices adequacy for the sake of fluency. We propose
	a method to combine the advantages of traditional SMT and NMT by exploiting an
	existing phrase-based SMT model to compute the phrase-based decoding cost for
	an NMT output and then using the phrase-based decoding cost to rerank the
	n-best NMT outputs. The main challenge in implementing this approach is that
	NMT outputs may not be in the search space of the standard phrase-based
	decoding algorithm, because the search space of phrase-based SMT is limited by
	the phrase-based translation rule table. We propose a soft forced decoding
	algorithm, which can always successfully find a decoding path for any NMT
	output. We show that using the forced decoding cost to rerank the NMT outputs
	can successfully improve translation quality on four different language pairs.},
  url       = {http://www.aclweb.org/anthology/I17-1016}
}