@InProceedings{calixto-liu:2017:EMNLP2017,
  author    = {Calixto, Iacer  and  Liu, Qun},
  title     = {Incorporating Global Visual Features into Attention-based 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     = {992--1003},
  abstract  = {We introduce multi-modal, attention-based neural machine translation (NMT)
	models which incorporate visual features into different parts of both the
	encoder and the decoder. Global image features are extracted using a
	pre-trained convolutional neural network and are incorporated (i) as words in
	the source sentence, (ii) to initialise the encoder hidden state, and (iii) as
	additional data to initialise the decoder hidden state. In our experiments, we
	evaluate translations into English and German, how different strategies to
	incorporate global image features compare and which ones perform best. We also
	study the impact that adding synthetic multi-modal, multilingual data brings
	and find that the additional data have a positive impact on multi-modal NMT
	models. We report new state-of-the-art results and our best models also
	significantly improve on a comparable phrase-based Statistical MT (PBSMT) model
	trained on the Multi30k data set according to all metrics evaluated. To the
	best of our knowledge, it is the first time a purely neural model significantly
	improves over a PBSMT model on all metrics evaluated on this data set.},
  url       = {https://www.aclweb.org/anthology/D17-1105}
}