English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Hierarchical structures exist in both linguistics and Natural LanguageProcessing (NLP) tasks. How to design RNNs to learn hierarchicalrepresentations of natural languages remains a long-standing challenge. In thispaper, we define two different types of boundaries referred to as static anddynamic boundaries, respectively, and then use them to construct a multi-layerhierarchical structure for document classification tasks. In particular, wefocus on a three-layer hierarchical structure with static word- and sentence-layers and a dynamic phrase-layer. LSTM cells and two boundary detectors areused to implement the proposed structure, and the resulting network is calledthe {\em Recurrent Neural Network with Mixed Hierarchical Structures}(MHS-RNN). We further add three layers of attention mechanisms to the MHS-RNNmodel. Incorporating attention mechanisms allows our model to use moreimportant content to construct document representation and enhance itsperformance on document classification tasks. Experiments on five differentdatasets show that the proposed architecture outperforms previous methods onall the five tasks.

Recurrent Neural Networks with Mixed Hierarchical Structures for Natural Language Processing