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

In document-level event extraction (DEE) task, event arguments always scatteracross sentences (across-sentence issue) and multiple events may lie in onedocument (multi-event issue). In this paper, we argue that the relationinformation of event arguments is of great significance for addressing theabove two issues, and propose a new DEE framework which can model the relationdependencies, called Relation-augmented Document-level Event Extraction(ReDEE). More specifically, this framework features a novel and tailoredtransformer, named as Relation-augmented Attention Transformer (RAAT). RAAT isscalable to capture multi-scale and multi-amount argument relations. To furtherleverage relation information, we introduce a separate event relationprediction task and adopt multi-task learning method to explicitly enhanceevent extraction performance. Extensive experiments demonstrate theeffectiveness of the proposed method, which can achieve state-of-the-artperformance on two public datasets. Our code is available at https://github.com/TencentYoutuResearch/RAAT.

RAAT: Relation-Augmented Attention Transformer for Relation Modeling in Document-Level Event Extraction