@InProceedings{wieting-mallinson-gimpel:2017:EMNLP2017,
  author    = {Wieting, John  and  Mallinson, Jonathan  and  Gimpel, Kevin},
  title     = {Learning Paraphrastic Sentence Embeddings from Back-Translated Bitext},
  booktitle = {Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {274--285},
  abstract  = {We consider the problem of learning general-purpose, paraphrastic sentence
	embeddings in the setting of Wieting et al. (2016b). We use neural machine
	translation to generate sentential paraphrases via back-translation of
	bilingual sentence pairs. We evaluate the paraphrase pairs by their ability to
	serve as training data for learning paraphrastic sentence embeddings. We find
	that the data quality is stronger than prior work based on bitext and on par
	with manually-written English paraphrase pairs, with the advantage that our
	approach can scale up to generate large training sets for many languages and
	domains. We experiment with several language pairs and data sources, and
	develop a variety of data filtering techniques. In the process, we explore how
	neural machine translation output differs from human-written sentences, finding
	clear differences in length, the amount of repetition, and the use of rare
	words.},
  url       = {https://www.aclweb.org/anthology/D17-1026}
}