Enhanced question understanding with dynamic memory networks for textual question answering

作者：

Highlights：

• Introducing global and hierarchical salient features of inputs.

• Adopting a modified network to extract hierarchical salient features of a question.

• Finding a method to utilize these features to construct multiple feature sets.

摘要

•Introducing global and hierarchical salient features of inputs.•Adopting a modified network to extract hierarchical salient features of a question.•Finding a method to utilize these features to construct multiple feature sets.

论文关键词：Dynamic memory networks,Attention based GRU,Textual question answering

论文评审过程：Received 29 September 2016, Revised 1 March 2017, Accepted 2 March 2017, Available online 10 March 2017, Version of Record 17 March 2017.

论文官网地址：https://doi.org/10.1016/j.eswa.2017.03.006