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

Sentence classification is one of the basic tasks of natural languageprocessing. Convolution neural network (CNN) has the ability to extract n-gramsfeatures through convolutional filters and capture local correlations betweenconsecutive words in parallel, so CNN is a popular neural network architectureto dealing with the task. But restricted by the width of convolutional filters,it is difficult for CNN to capture long term contextual dependencies. Attentionis a mechanism that considers global information and pays more attention tokeywords in sentences, thus attention mechanism is cooperated with CNN networkto improve performance in sentence classification task. In our work, we don'tfocus on keyword in a sentence, but on which CNN's output feature map is moreimportant. We propose a Squeeze-and-Excitation Convolutional neural Network(SECNN) for sentence classification. SECNN takes the feature maps from multipleCNN as different channels of sentence representation, and then, we can utilizechannel attention mechanism, that is SE attention mechanism, to enable themodel to learn the attention weights of different channel features. The resultsshow that our model achieves advanced performance in the sentenceclassification task.

SECNN: Squeeze-and-Excitation Convolutional Neural Network for Sentence Classification