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 1705.02269cs.CLcs.LG
收藏

顺序注意:一种上下文感知的机器阅读对齐函数

Sequential Attention: A Context-Aware Alignment Function for Machine Reading

Center for Data Science(数据科学中心);New York University(纽约大学)

Sebastian Brarda, Philip Yeres, Samuel R. Bowman

摘要:

在本文中,我们提出了一个神经网络模型,它具有一个新的顺序注意层,通过为输入序列中的单词分配权重来扩展软注意力,这种方式不仅考虑了单词与查询的匹配程度,还考虑了周围单词的匹配程度。我们在阅读理解任务上(在谁做了什么和CNN数据集上)评估了这种方法,并表明它极大地提高了一个强大的基线-斯坦福阅读器-并且与最先进的水平竞争。

英文摘要:

In this paper we propose a neural network model with a novel Sequential Attention layer that extends soft attention by assigning weights to words in an input sequence in a way that takes into account not just how well that word matches a query, but how well surrounding words match. We evaluate this approach on the task of reading comprehension (on the Who did What and CNN datasets) and show that it dramatically improves a strong baseline--the Stanford Reader--and is competitive with the state of the art.

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。

↑