@InProceedings{cao-EtAl:2016:COLING2,
  author    = {Cao, Hailong  and  Zhao, Tiejun  and  ZHANG, Shu  and  Meng, Yao},
  title     = {A Distribution-based Model to Learn Bilingual Word Embeddings},
  booktitle = {Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers},
  month     = {December},
  year      = {2016},
  address   = {Osaka, Japan},
  publisher = {The COLING 2016 Organizing Committee},
  pages     = {1818--1827},
  abstract  = {We introduce a distribution based model to learn bilingual word embeddings from
	monolingual data. It is simple, effective and does not require any parallel
	data or any seed lexicon. We take advantage of the fact that word embeddings
	are usually in form of dense real-valued low-dimensional vector and therefore
	the distribution of them can be accurately estimated. A novel cross-lingual
	learning objective is proposed which directly matches the distributions of word
	embeddings in one language with that in the other language. During the joint
	learning process, we dynamically estimate the distributions of word embeddings
	in two languages respectively and minimize the dissimilarity between them
	through standard back propagation algorithm. Our learned bilingual word
	embeddings allow to group each word and its translations together in the shared
	vector space. We demonstrate the utility of the learned embeddings on the task
	of finding word-to-word translations from monolingual corpora. Our model
	achieved encouraging performance on data in both related languages and
	substantially different languages.},
  url       = {http://aclweb.org/anthology/C16-1171}
}