@InProceedings{mu-bhat-viswanath:2017:Short,
  author    = {Mu, Jiaqi  and  Bhat, Suma  and  Viswanath, Pramod},
  title     = {Representing Sentences as Low-Rank Subspaces},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {629--634},
  abstract  = {Sentences are important semantic units of natural language. A generic,
	distributional representation of sentences that can capture the latent
	semantics is beneficial to multiple downstream applications. We observe a
	simple geometry of sentences -- the word representations of a given sentence
	(on average 10.23 words in all SemEval datasets with a standard deviation 4.84)
	roughly lie in a low-rank subspace (roughly, rank 4). Motivated by this
	observation, we represent a sentence by the low-rank subspace spanned by its
	word vectors. Such an unsupervised representation is empirically validated via
	semantic textual similarity tasks on 19 different datasets, where it
	outperforms the sophisticated neural network models,  including skip-thought
	vectors, by 15% on average.},
  url       = {http://aclweb.org/anthology/P17-2099}
}