@InProceedings{neishi-EtAl:2017:WAT2017,
  author    = {Neishi, Masato  and  Sakuma, Jin  and  Tohda, Satoshi  and  Ishiwatari, Shonosuke  and  Yoshinaga, Naoki  and  Toyoda, Masashi},
  title     = {A Bag of Useful Tricks for Practical Neural Machine Translation: Embedding Layer Initialization and Large Batch Size},
  booktitle = {Proceedings of the 4th Workshop on Asian Translation (WAT2017)},
  month     = {November},
  year      = {2017},
  address   = {Taipei, Taiwan},
  publisher = {Asian Federation of Natural Language Processing},
  pages     = {99--109},
  abstract  = {In this paper, we describe the team UT-IIS's system and results for the WAT
	2017 translation tasks. We further investigated several tricks including a
	novel technique for initializing embedding layers using only the parallel
	corpus, which increased the BLEU score by 1.28, found a practical large batch
	size of 256, and gained insights regarding hyperparameter settings. Ultimately,
	our system obtained a better result than the state-of-the-art system of WAT
	2016. Our code is available on https://github.com/nem6ishi/wat17.},
  url       = {http://www.aclweb.org/anthology/W17-5708}
}