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

Document-level event argument extraction poses new challenges of long inputand cross-sentence inference compared to its sentence-level counterpart.However, most prior works focus on capturing the relations between candidatearguments and the event trigger in each event, ignoring two crucial points: a)non-argument contextual clue information; b) the relevance among argumentroles. In this paper, we propose a SCPRG (Span-trigger-based Contextual Poolingand latent Role Guidance) model, which contains two novel and effective modulesfor the above problem. The Span-Trigger-based Contextual Pooling(STCP)adaptively selects and aggregates the information of non-argument clue wordsbased on the context attention weights of specific argument-trigger pairs frompre-trained model. The Role-based Latent Information Guidance (RLIG) moduleconstructs latent role representations, makes them interact throughrole-interactive encoding to capture semantic relevance, and merges them intocandidate arguments. Both STCP and RLIG introduce no more than 1% newparameters compared with the base model and can be easily applied to otherevent extraction models, which are compact and transplantable. Experiments ontwo public datasets show that our SCPRG outperforms previous state-of-the-artmethods, with 1.13 F1 and 2.64 F1 improvements on RAMS and WikiEventsrespectively. Further analyses illustrate the interpretability of our model.

Enhancing Document-level Event Argument Extraction with Contextual Clues and Role Relevance