| 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. |
| 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 |
| DOI：10.13328/j.cnki.jos.005334 |
| 分类号: |
| 基金项目:国家自然科学基金（61772537） |
|
| Review on Research and Development of Memory Neural Networks |
|
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
|
| Abstract: |
| 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. |
| Key words: natural language processing artificial intelligence memory neural network recurrent neural network machine learning question answering |
