@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{shoeybi2019megatron,
  title={Megatron-lm: Training multi-billion parameter language models using model parallelism},
  author={Shoeybi, Mohammad and Patwary, Mostofa and Puri, Raul and LeGresley, Patrick and Casper, Jared and Catanzaro, Bryan},
  journal={arXiv preprint arXiv:1909.08053},
  year={2019}
}

@InProceedings{maas2011,
  author    = {Maas, Andrew L. and Daly, Raymond E. and Pham, Peter T. and Huang, Dan and Ng, Andrew Y. and Potts, Christopher},
  title     = {Learning Word Vectors for Sentiment Analysis},
  booktitle = {Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies},
  month     = {June},
  year      = {2011},
  address   = {Portland, Oregon, USA},
  publisher = {Association for Computational Linguistics},
  pages     = {142--150},
  url       = {http://www.aclweb.org/anthology/P11-1015}
}

@inproceedings{socher2013,
    title = "Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank",
    author = "Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning, Christopher D. and Ng, Andrew and Potts, Christopher",
    booktitle = "Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2013",
    address = "Seattle, Washington, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://www.aclweb.org/anthology/D13-1170",
    pages = "1631--1642",
}

@article{lim2018chemical,
  title={Chemical--gene relation extraction using recursive neural network},
  author={Lim, Sangrak and Kang, Jaewoo},
  journal={Database},
  volume={2018},
  year={2018},
  publisher={Oxford Academic}
}

@inproceedings{li2007scalable,
  title={Scalable term selection for text categorization},
  author={Li, Jingyang and Sun, Maosong},
  booktitle={Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL)},
  pages={774--782},
  year={2007}
}

@misc{lee2019biobert,
    title={BioBERT: a pre-trained biomedical language representation model for biomedical text mining},
    author={Jinhyuk Lee and Wonjin Yoon and Sungdong Kim and Donghyeon Kim and Sunkyu Kim and Chan Ho So and Jaewoo Kang},
    year={2019},
    eprint={1901.08746},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

@misc{shin2020biomegatron,
      title={BioMegatron: Larger Biomedical Domain Language Model},
      author={Hoo-Chang Shin and Yang Zhang and Evelina Bakhturina and Raul Puri and Mostofa Patwary and Mohammad Shoeybi and Raghav Mani},
      year={2020},
      eprint={2010.06060},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}

@article{vaswani2017attention,
  title={Attention is all you need},
  author={Vaswani, Ashish and Shazeer, Noam and Parmar, Niki and Uszkoreit, Jakob and Jones, Llion and Gomez, Aidan N and Kaiser, Lukasz and Polosukhin, Illia},
  journal={arXiv preprint arXiv:1706.03762},
  year={2017}
}

@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{provilkov2019bpe,
  title={Bpe-dropout: Simple and effective subword regularization},
  author={Provilkov, Ivan and Emelianenko, Dmitrii and Voita, Elena},
  journal={arXiv preprint arXiv:1910.13267},
  year={2019}
}

@article{post2018call,
  title={A call for clarity in reporting BLEU scores},
  author={Post, Matt},
  journal={arXiv preprint arXiv:1804.08771},
  year={2018}
}

@misc{zhang2021sgdqa,
      title={SGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services}, 
      author={Yang Zhang and Vahid Noroozi and Evelina Bakhturina and Boris Ginsburg},
      year={2021},
      eprint={2105.08049},
      archivePrefix={arXiv},
      primaryClass={cs.CL}
}