@InProceedings{morishita-EtAl:2017:NMT,
  author    = {Morishita, Makoto  and  Oda, Yusuke  and  Neubig, Graham  and  Yoshino, Koichiro  and  Sudoh, Katsuhito  and  Nakamura, Satoshi},
  title     = {An Empirical Study of Mini-Batch Creation 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     = {61--68},
  abstract  = {Training of neural machine translation (NMT) models usually uses mini-batches
	for efficiency purposes.
	During the mini-batched training process, it is necessary to pad shorter
	sentences in a mini-batch to be equal in length to the longest sentence therein
	for efficient computation.
	Previous work has noted that sorting the corpus based on the sentence length
	before making mini-batches reduces the amount of padding and increases the
	processing speed.
	However, despite the fact that mini-batch creation is an essential step in NMT
	training, widely used NMT toolkits implement disparate strategies for doing so,
	which have not been empirically validated or compared.
	This work investigates mini-batch creation strategies with experiments over two
	different datasets.
	Our results suggest that the choice of a mini-batch creation strategy has a
	large effect on NMT training and some length-based sorting strategies do not
	always work well compared with simple shuffling.},
  url       = {http://www.aclweb.org/anthology/W17-3208}
}