Inner Attention based Recurrent Neural Networks for Answer Selection

	Inner Attention based Recurrent Neural Networks for Answer Selection
	Wang Bingning; Liu Kang; Zhao Jun
	2016
会议日期	2016
会议地点	德国
关键词	Answer Selection Question Answering Deep Learning
卷号	Volumn 1, Long Paper
页码	1288-1297
英文摘要	Attention based recurrent neural networks have shown advantages in representing natural language sentences (Hermann et al., 2015; Rocktäschel et al., 2015; Tan et al., 2015). Based on recurrent neural networks (RNN), external attention information was added to hidden representations to get an attentive sentence representation. Despite the improvement over non- attentive models, the attention mechanism under RNN is not well studied. In this work, we analyze the deficiency of traditional attention based RNN models quantitatively and qualitatively. Then we present three new RNN models that add attention information before RNN hidden representation, which shows advantage in representing sentence and achieves new state- of-art results in answer selection task.
语种	英语
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/20182]
专题	自动化研究所_模式识别国家重点实验室_自然语言处理团队
通讯作者	Liu Kang
作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Wang Bingning,Liu Kang,Zhao Jun. Inner Attention based Recurrent Neural Networks for Answer Selection[C]. 见:. 德国. 2016.