@InProceedings{saunders-EtAl:2018:Short,
  author    = {Saunders, Danielle  and  Stahlberg, Felix  and  de Gispert, Adrià  and  Byrne, Bill},
  title     = {Multi-representation ensembles and delayed SGD updates improve syntax-based NMT},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {319--325},
  abstract  = {We explore strategies for incorporating target syntax into Neural Machine Translation. We specifically focus on syntax in ensembles containing multiple sentence representations. We formulate beam search over such ensembles using WFSTs, and describe a delayed SGD update training procedure that is especially effective for long representations like linearized syntax. Our approach gives state-of-the-art performance on a difficult Japanese-English task.},
  url       = {http://www.aclweb.org/anthology/P18-2051}
}