@InProceedings{grzegorczyk-kurdziel:2017:RepL4NLP,
  author    = {Grzegorczyk, Karol  and  Kurdziel, Marcin},
  title     = {Binary Paragraph Vectors},
  booktitle = {Proceedings of the 2nd Workshop on Representation Learning for NLP},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {121--130},
  abstract  = {Recently Le \& Mikolov described two log-linear models, called Paragraph Vector,
	that can be used to learn state-of-the-art distributed representations of
	documents. Inspired by this work, we present Binary Paragraph Vector models:
	simple neural networks that learn short binary codes for fast information
	retrieval. We show that binary paragraph vectors outperform autoencoder-based
	binary codes, despite using fewer bits. We also evaluate their precision in
	transfer learning settings, where binary codes are inferred for documents
	unrelated to the training corpus. Results from these experiments indicate that
	binary paragraph vectors can capture semantics relevant for various
	domain-specific documents. Finally, we present a model that simultaneously
	learns short binary codes and longer, real-valued representations. This model
	can be used to rapidly retrieve a short list of highly relevant documents from
	a large document collection.},
  url       = {http://www.aclweb.org/anthology/W17-2615}
}