@InProceedings{schwenk-douze:2017:RepL4NLP,
  author    = {Schwenk, Holger  and  Douze, Matthijs},
  title     = {Learning Joint Multilingual Sentence Representations with Neural Machine Translation},
  booktitle = {Proceedings of the 2nd Workshop on Representation Learning for NLP},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {157--167},
  abstract  = {In this paper, we use the framework of neural machine translation to learn
	joint sentence representations across six very different languages. Our aim is
	that a representation which is independent of the language, is likely to
	capture the underlying semantics.  We define a new cross-lingual similarity
	measure, compare up to 1.4M sentence representations and study the
	characteristics of close sentences.
	We provide experimental evidence that sentences that are close in embedding
	space are indeed semantically highly related, but often have quite different
	structure and syntax.  These relations also hold when comparing sentences in
	different languages.},
  url       = {http://www.aclweb.org/anthology/W17-2619}
}