@inproceedings{longpre-etal-2019-exploration,
    title = "An Exploration of Data Augmentation and Sampling Techniques for Domain-Agnostic Question Answering",
    author = "Longpre, Shayne  and
      Lu, Yi  and
      Tu, Zhucheng  and
      DuBois, Chris",
    editor = "Fisch, Adam  and
      Talmor, Alon  and
      Jia, Robin  and
      Seo, Minjoon  and
      Choi, Eunsol  and
      Chen, Danqi",
    booktitle = "Proceedings of the 2nd Workshop on Machine Reading for Question Answering",
    month = nov,
    year = "2019",
    address = "Hong Kong, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/D19-5829/",
    doi = "10.18653/v1/D19-5829",
    pages = "220--227",
    abstract = "To produce a domain-agnostic question answering model for the Machine Reading Question Answering (MRQA) 2019 Shared Task, we investigate the relative benefits of large pre-trained language models, various data sampling strategies, as well as query and context paraphrases generated by back-translation. We find a simple negative sampling technique to be particularly effective, even though it is typically used for datasets that include unanswerable questions, such as SQuAD 2.0. When applied in conjunction with per-domain sampling, our XLNet (Yang et al., 2019)-based submission achieved the second best Exact Match and F1 in the MRQA leaderboard competition."
}