@InProceedings{freitag-alonaizan:2017:NMT,
  author    = {Freitag, Markus  and  Al-Onaizan, Yaser},
  title     = {Beam Search Strategies for Neural Machine Translation},
  booktitle = {Proceedings of the First Workshop on Neural Machine Translation},
  month     = {August},
  year      = {2017},
  address   = {Vancouver},
  publisher = {Association for Computational Linguistics},
  pages     = {56--60},
  abstract  = {The basic concept in Neural Machine Translation (NMT) is to train a large
	Neural Network that maximizes the translation performance on a given parallel
	corpus. NMT is then using a simple left-to-right beam-search decoder to
	generate new translations that approximately maximize the trained conditional
	probability. The current beam search strategy generates the target sentence
	word by word from left-to-right while keeping a fixed amount of active
	candidates at each time step. First, this simple search is less adaptive as it
	also expands candidates whose scores are much worse than the current best.
	Secondly, it does not expand hypotheses if they are not within the best scoring
	candidates, even if their scores are close to the best one. The latter one can
	be avoided by increasing the beam size until no performance improvement can be
	observed. While you can reach better performance, this has the drawback of a
	slower decoding speed. In this paper, we concentrate on speeding up the decoder
	by applying a more flexible beam search strategy whose candidate size may vary
	at each time step depending on the candidate scores. We speed up the original
	decoder by up to 43% for the two language pairs German to English and Chinese
	to English without losing any translation quality.},
  url       = {http://www.aclweb.org/anthology/W17-3207}
}