arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1606.02245cs.CLcs.NE
收藏

用于机器阅读的迭代交替神经注意

Iterative Alternating Neural Attention for Machine Reading

Maluuba Research(Maluuba研究院);University of Montréal(蒙特利尔大学)

Alessandro Sordoni, Philip Bachman, Adam Trischler, Yoshua Bengio

摘要:

我们提出了一种新的神经注意力架构来处理机器理解任务,例如回答关于文档的完形填空式查询。与以前的模型不同,我们没有将查询折叠成单个向量,而是部署了一个迭代的交替注意力机制,允许对查询和文档进行细粒度的探索。我们的模型在标准机器理解基准测试中的表现优于最先进的基线,例如CNN新闻文章和儿童图书测试(CBT)数据集。

英文摘要:

We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document. Unlike previous models, we do not collapse the query into a single vector, instead we deploy an iterative alternating attention mechanism that allows a fine-grained exploration of both the query and the document. Our model outperforms state-of-the-art baselines in standard machine comprehension benchmarks such as CNN news articles and the Children's Book Test (CBT) dataset.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑