@InProceedings{kim-schamper-ney:2017:EACLshort,
  author    = {Kim, Yunsu  and  Schamper, Julian  and  Ney, Hermann},
  title     = {Unsupervised Training for Large Vocabulary Translation Using Sparse Lexicon and Word Classes},
  booktitle = {Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers},
  month     = {April},
  year      = {2017},
  address   = {Valencia, Spain},
  publisher = {Association for Computational Linguistics},
  pages     = {650--656},
  abstract  = {We address for the first time unsupervised training for a translation task with
	hundreds of thousands of vocabulary words. We scale up the
	expectation-maximization (EM) algorithm to learn a large translation table
	without any parallel text or seed lexicon. First, we solve the memory
	bottleneck and enforce the sparsity with a simple thresholding scheme for the
	lexicon. Second, we initialize the lexicon training with word classes, which
	efficiently boosts the performance. Our methods produced promising results on
	two large-scale unsupervised translation tasks.},
  url       = {http://www.aclweb.org/anthology/E17-2103}
}