Recurrent Neural Networks with Mixed Hierarchical Structures for Natural Language Processing
Recurrent Neural Networks with Mixed Hierarchical Structures for Natural Language Processing
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 …