@InProceedings{athiwaratkun-wilson-anandkumar:2018:Long,
  author    = {Athiwaratkun, Ben  and  Wilson, Andrew  and  Anandkumar, Anima},
  title     = {Probabilistic FastText for Multi-Sense Word Embeddings},
  booktitle = {Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  month     = {July},
  year      = {2018},
  address   = {Melbourne, Australia},
  publisher = {Association for Computational Linguistics},
  pages     = {1--11},
  abstract  = {We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams. This representation allows the model to share the ``strength'' across sub-word structures (e.g. Latin roots), producing accurate representations of rare, misspelt, or even unseen words. Moreover, each component of the mixture can capture a different word sense. Probabilistic FastText outperforms both FastText, which has no probabilistic model, and dictionary-level probabilistic embeddings, which do not incorporate subword structures, on several word-similarity benchmarks, including English RareWord and foreign language datasets. We also achieve state-of-art performance on benchmarks that measure ability to discern different meanings. Thus, our model is the first to achieve best of both the worlds: multi-sense representations while having enriched semantics on rare words.},
  url       = {http://www.aclweb.org/anthology/P18-1001}
}