Existing literature on Question Answering (QA) mostly focuses on algorithmic
novelty, data augmentation, or increasingly large pre-trained language models
like XLNet and RoBERTa. Additionally, a lot of systems on the QA leaderboards
do not have associated research documentation in order to successfully
replicate their experiments. In this paper, we outline these algorithmic
components such as Attention-over-Attention, coupled with data augmentation and
ensembling strategies that have shown to yield state-of-the-art results on
benchmark datasets like SQuAD, even achieving super-human performance. Contrary
to these prior results, when we evaluate on the recently proposed Natural
Questions benchmark dataset, we find that an incredibly simple approach of
transfer learning from BERT outperforms the previous state-of-the-art system
trained on 4 million more examples than ours by 1.9 F1 points. Adding
ensembling strategies further improves that number by 2.3 F1 points.

文章研究了问题回答领域（Question Answering）中各种算法模型以及增强数据方法，提出了基于 Attention-over-Attention 等方法的组合以及数据增强和集成策略，可在 SQuAD 等基准数据集上取得超人的表现。但在最新的自然问题基准数据集上，相对简单的 BERT 迁移学习方法取得了超过先前表现最优系统 1.9 F1 点的优异表现，并且添加集成策略进一步提高了 2.3 F1 点。