bibliography.bib

@article{gage1994new,
  title={A new algorithm for data compression},
  author={Gage, Philip},
  journal={C Users Journal},
  volume={12},
  number={2},
  pages={23--38},
  year={1994},
  publisher={McPherson, KS: R \& D Publications, c1987-1994.}
}

@article{devlin2018bert,
	title={Bert: Pre-training of deep bidirectional transformers for language understanding},
	author={Devlin, Jacob and Chang, Ming-Wei and Lee, Kenton and Toutanova, Kristina},
	journal={arXiv preprint arXiv:1810.04805},
	year={2018}
}

@article{brown2020language,
	title={Language models are few-shot learners},
	author={Brown, Tom B and Mann, Benjamin and Ryder, Nick and Subbiah, Melanie and Kaplan, Jared and Dhariwal, Prafulla and Neelakantan, Arvind and Shyam, Pranav and Sastry, Girish and Askell, Amanda and others},
	journal={arXiv preprint arXiv:2005.14165},
	year={2020}
}

@article{sennrich2015neural,
	title={Neural machine translation of rare words with subword units},
	author={Sennrich, Rico and Haddow, Barry and Birch, Alexandra},
	journal={arXiv preprint arXiv:1508.07909},
	year={2015}
}

@article{mikolov2013efficient,
	title={Efficient estimation of word representations in vector space},
	author={Mikolov, Tomas and Chen, Kai and Corrado, Greg and Dean, Jeffrey},
	journal={arXiv preprint arXiv:1301.3781},
	year={2013}
}