Recurrent Neural Networks with Mixed Hierarchical Structures for Natural Language Processing
2021 International Joint Conference on Neural Networks (IJCNN)(2021)
摘要
Hierarchical structures exist in both linguistics and Natural Language Processing (NLP) tasks. How to design RNNs to learn hierarchical representations of natural languages remains a long-standing challenge. In this paper, we define two different types of boundaries referred to as static and dynamic boundaries, respectively, and then use them to construct a multilayer hierarchical structure for do...
更多查看译文
关键词
Recurrent neural networks,Detectors,Linguistics,Nonhomogeneous media,Natural language processing,Task analysis
AI 理解论文
溯源树
样例
![](https://originalfileserver.aminer.cn/sys/aminer/pubs/mrt_preview.jpeg)
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要