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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent studies on event detection (ED) haveshown that the syntacticdependency graph canbe employed in graph convolution neural net-works (GCN) toachieve state-of-the-art per-formance. However, the computation of thehiddenvectors in such graph-based models isagnostic to the trigger candidate words,po-tentially leaving irrelevant information for thetrigger candidate for eventprediction. In addi-tion, the current models for ED fail to exploitthe overallcontextual importance scores of thewords, which can be obtained via thedepen-dency tree, to boost the performance. In thisstudy, we propose a novelgating mechanismto filter noisy information in the hidden vec-tors of the GCNmodels for ED based on theinformation from the trigger candidate. Wealsointroduce novel mechanisms to achievethe contextual diversity for the gates andtheimportance score consistency for the graphsand models in ED. The experimentsshow thatthe proposed model achieves state-of-the-artperformance on two EDdatasets

Event Detection: Gate Diversity and Syntactic Importance Scoresfor Graph Convolution Neural Networks