用于文本理解的门控注意力读者

Jun, 2016

Gated-Attention Readers for Text Comprehension

Bhuwan Dhingra, Hanxiao Liu, William W. Cohen, Ruslan Salakhutdinov

TL;DR本文研究了如何在文档中回答填空题的问题，通过引入多跳结构和基于参考嵌入和递归神经网络的新型注意力机制，我们的Gated-Attention Reader模型能够生成查询特定的文档表示来准确地选择答案，并在三个基准数据集上获得最新的结果。

Abstract

In this paper we study the problem of answering cloze-style questions over short documents. We introduce a new attention mechanism which uses multiplicative interactions between the query embedding and intermedia