@InProceedings{lan-EtAl:2017:EMNLP20171,
  author    = {Lan, Wuwei  and  Qiu, Siyu  and  He, Hua  and  Xu, Wei},
  title     = {A Continuously Growing Dataset of Sentential Paraphrases},
  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     = {1224--1234},
  abstract  = {A major challenge in paraphrase research is the lack of parallel corpora. In
	this paper, we present a new method to collect large-scale sentential
	paraphrases from Twitter by linking tweets through shared URLs. The main
	advantage of our method is its simplicity, as it gets rid of the classifier or
	human in the loop needed to select data before annotation and subsequent
	application of paraphrase identification algorithms in the previous work.
	We present the largest human-labeled paraphrase corpus to date of 51,524
	sentence pairs and the first cross-domain benchmarking for automatic paraphrase
	identification. In addition, we show that more than 30,000 new sentential
	paraphrases can be easily and continuously captured every month at ~70\%
	precision, and demonstrate their utility for downstream NLP tasks through
	phrasal paraphrase extraction. We make our code and data freely available.},
  url       = {https://www.aclweb.org/anthology/D17-1126}
}