Employing External Rich Knowledge for Machine Comprehension

	Employing External Rich Knowledge for Machine Comprehension
	Wang Bingning; Guo Shangmin; Liu Kang; He Shizhu; Zhao Jun
	2016
会议名称	Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence
页码	2929-2935
会议日期	2016-7
会议地点	美国纽约
摘要	Recently proposed machine comprehension (MC) applicationisanefforttodealwithnaturallanguage understanding problem. However, the small size of machine comprehension labeled data confines the application of deep neural networks architectures that have shown advantage in semantic inference tasks. Previous methods use a lot of NLP tools to extract linguistic features but only gain little improvement over simple baseline. In this paper, we build an attention-based recurrent neural network model, train it with the help of external knowledge which is semantically relevant to machine comprehension, and achieves a new state-of-the-art result.
关键词	Machine Comprehension Question Answering Deep Learning
收录类别	EI
语种	英语
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/41123
专题	多模态人工智能系统全国重点实验室_自然语言处理
通讯作者	Liu Kang
推荐引用方式 GB/T 7714	Wang Bingning,Guo Shangmin,Liu Kang,et al. Employing External Rich Knowledge for Machine Comprehension[C],2016:2929-2935.