This paper describes a novel hierarchical attention network for reading
comprehension style question answering, which aims to answer questions for a
given narrative paragraph. In the proposed method, attention and fusion are
conducted horizontally and vertically across layers at different levels of
granularity between question and paragraph. Specifically, it first encode the
question and paragraph with fine-grained language embeddings, to better capture
the respective representations at semantic level. Then it proposes a
multi-granularity fusion approach to fully fuse information from both global
and attended representations. Finally, it introduces a hierarchical attention
network to focuses on the answer span progressively with multi-level
softalignment. Extensive experiments on the large-scale SQuAD and TriviaQA
datasets validate the effectiveness of the proposed method. At the time of
writing the paper (Jan. 12th 2018), our model achieves the first position on
the SQuAD leaderboard for both single and ensemble models. We also achieves
state-of-the-art results on TriviaQA, AddSent and AddOne-Sent datasets.

本文提出了一种新颖的分层注意力网络，用于阅读理解式问题回答，在问题和段落之间的不同粒度层次上水平和垂直进行注意力和融合。通过具有精细语言嵌入的问题和段落的编码，引入多粒度融合方法来全面融合来自全局和受关注表示的信息。最后，引入分层注意力网络，通过多级软对齐逐步聚焦于答案跨度。广泛的实验在大规模 SQuAD 和 TriviaQA 数据集上验证了所提出方法的有效性，同时在 TriviatQA、AddSent 和 AddOne-Sent 数据集上达到了最先进的结果。