记忆神经网络的研究与发展  

Review on Research and Development of Memory Neural Networks

作　　者：梁天新 杨小平[1] 王良[1] 张永俊[1] 朱艳丽 许翠 LIANG Tian-Xin;YANG Xiao-Ping;WANG Liang;ZHANG Yong-Jun;ZHU Yan-Li;XU Cui(School of Information, Renmin Universityof China, Beijing 100872, China)

机构地区：[1]中国人民大学信息学院,北京100872

出　　处：《软件学报》2017年第11期2905-2924,共20页Journal of Software

基　　金：国家自然科学基金(61772537)~~

摘　　要：首先,根据记忆神经网络训练形式的不同,介绍了强监督模型和弱监督模型的结构特征和各自应用场景以及处理方式,总结了两类主要模型的优缺点;随后,对两类模型的发展和应用(包括模型创新和应用创新)进行了简要综述,总结了各类新模型在处理自然语言过程中所起的关键作用;最后梳理了记忆神经网络处理自然语言所面临的复杂性挑战,并预测了记忆神经网络未来的发展方向.Firstly,in this paper,the key features of memory neural networks in the strongly supervised model and the weakly supervised model and introduced.Then the corresponding application scenarios and processing methods,as well as the advantages and disadvantages of the two models are summarized.Next,a brief survey on the development and application of the two models （including the innovation on the model and the innovation in application） is provided,and the key roles of individual innovative models in the natural language processing are summarized.Finally,the complex challenges of memory neural networks in the natural language processing and the future development of memory neural networks are also discussed.

关 键 词：自然语言处理 人工智能 记忆神经网络 递归神经网络 机器学习 问答 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]