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 semantic matching requires an agent to determine the semanticrelation between two sentences, where much recent progress has been made by theadvancement of representation learning techniques and inspiration of humanbehaviors. Among all these methods, attention mechanism plays an essential roleby selecting important parts effectively. However, current attention methodseither focus on all the important parts in a static way or only select oneimportant part at one attention step dynamically, which leaves a large spacefor further improvement. To this end, in this paper, we design a novel DynamicGaussian Attention Network (DGA-Net) to combine the advantages of currentstatic and dynamic attention methods. More specifically, we first leveragepre-trained language model to encode the input sentences and construct semanticrepresentations from a global perspective. Then, we develop a Dynamic GaussianAttention (DGA) to dynamically capture the important parts and correspondinglocal contexts from a detailed perspective. Finally, we combine the globalinformation and detailed local information together to decide the semanticrelation of sentences comprehensively and precisely. Extensive experiments ontwo popular sentence semantic matching tasks demonstrate that our proposedDGA-Net is effective in improving the ability of attention mechanism.

DGA-Net Dynamic Gaussian Attention Network for Sentence Semantic Matching