@InProceedings{khayrallah-EtAl:2018:WNMT2018,
  author    = {Khayrallah, Huda  and  Thompson, Brian  and  Duh, Kevin  and  Koehn, Philipp},
  title     = {Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation},
  booktitle = {Proceedings of the 2nd Workshop on Neural Machine Translation and Generation},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {36--44},
  abstract  = {Supervised domain adaptation---where a large generic corpus and a smaller in-domain corpus are both available for training---is a challenge for neural machine translation (NMT). Standard practice is to train a generic model and use it to initialize a second model, then continue training the second model on in-domain data to produce an in-domain model. We add an auxiliary term to the training objective during continued training that minimizes the cross entropy between the in-domain model's output word distribution and that of the out-of-domain model to prevent the model's output from differing too much from the original out-of-domain model. We perform experiments on EMEA (descriptions of medicines) and TED (rehearsed presentations), initialized from a general domain (WMT) model. Our method shows improvements over standard continued training by up to 1.5 BLEU.},
  url       = {http://www.aclweb.org/anthology/W18-2705}
}