@InProceedings{micelibarone-EtAl:2017:EMNLP2017,
  author    = {Miceli Barone, Antonio Valerio  and  Haddow, Barry  and  Germann, Ulrich  and  Sennrich, Rico},
  title     = {Regularization techniques for fine-tuning in neural machine translation},
  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     = {1489--1494},
  abstract  = {We investigate techniques for supervised domain adaptation for neural machine
	translation where an existing model trained on a large out-of-domain dataset is
	adapted to a small in-domain dataset.  
	In this scenario, overfitting is a major challenge. We investigate a number of
	techniques to reduce overfitting and improve transfer learning, including
	regularization techniques such as dropout and L2-regularization towards an
	out-of-domain prior. In addition, we introduce tuneout, a novel regularization
	technique inspired by dropout.
	We apply these techniques, alone and in combination, to neural machine
	translation, obtaining improvements on IWSLT datasets for English->German and
	English$->Russian.
	We also investigate the amounts of in-domain training data needed for domain
	adaptation in NMT, and find a logarithmic relationship between the amount of
	training data and gain in BLEU score.},
  url       = {https://www.aclweb.org/anthology/D17-1156}
}