@InProceedings{goto-tanaka:2017:NMT,
  author    = {Goto, Isao  and  Tanaka, Hideki},
  title     = {Detecting Untranslated Content 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     = {47--55},
  abstract  = {Despite its promise, neural machine translation (NMT) has a serious problem in
	that source content may be mistakenly left untranslated. The ability to detect
	untranslated content is important for the practical use of NMT. We evaluate two
	types of probability with which to detect untranslated content: the cumulative
	attention (ATN) probability and back translation (BT) probability from the
	target sentence to the source sentence. Experiments on detecting untranslated
	content in Japanese-English patent translations show that ATN and BT are each
	more effective than random choice, BT is more effective than ATN, and the
	combination of the two provides further improvements. We also confirmed the
	effectiveness of using ATN and BT to rerank the n-best NMT outputs.},
  url       = {http://www.aclweb.org/anthology/W17-3206}
}