@InProceedings{chen-gimpel:2018:N18-2,
  author    = {Chen, Mingda  and  Gimpel, Kevin},
  title     = {Smaller Text Classifiers with Discriminative Cluster Embeddings},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {739--745},
  abstract  = {Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a hard word clustering in an end-to-end manner. We use the Gumbel-Softmax distribution to maximize over the latent clustering while minimizing the task loss. We propose variations that selectively assign additional parameters to words, which further improves accuracy while still remaining parameter-efficient.},
  url       = {http://www.aclweb.org/anthology/N18-2116}
}