@InProceedings{calixto-liu:2017:RANLP,
  author    = {Calixto, Iacer  and  Liu, Qun},
  title     = {Sentence-Level Multilingual Multi-modal Embedding for Natural Language Processing},
  booktitle = {Proceedings of the International Conference Recent Advances in Natural Language Processing, RANLP 2017},
  month     = {September},
  year      = {2017},
  address   = {Varna, Bulgaria},
  publisher = {INCOMA Ltd.},
  pages     = {139--148},
  abstract  = {We propose a novel discriminative ranking model that learns embeddings from
	multilingual and multi-modal data, meaning that our model can take advantage of
	images and descriptions in multiple languages to improve embedding quality. To
	that end, we introduce an objective function that uses pairwise ranking adapted
	to the case of three or more input sources. We compare our model against
	different baselines, and evaluate the robustness of our embeddings on
	image--sentence ranking (ISR), semantic textual similarity (STS), and neural
	machine translation (NMT). We find that the additional multilingual signals
	lead to improvements on all three tasks, and we highlight that our model can be
	used to consistently improve the adequacy of translations generated with NMT
	models when re-ranking n-best lists.},
  url       = {https://doi.org/10.26615/978-954-452-049-6_020}
}