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 multi-event extraction aims to extract the structuralinformation from a given document automatically. Most recent approaches usuallyinvolve two steps: (1) modeling entity interactions; (2) decoding entityinteractions into events. However, such approaches ignore a global view ofinter-dependency of multiple events. Moreover, an event is decoded byiteratively merging its related entities as arguments, which might suffer fromerror propagation and is computationally inefficient. In this paper, we proposean alternative approach for document-level multi-event extraction with eventproxy nodes and Hausdorff distance minimization. The event proxy nodes,representing pseudo-events, are able to build connections with other eventproxy nodes, essentially capturing global information. The Hausdorff distancemakes it possible to compare the similarity between the set of predicted eventsand the set of ground-truth events. By directly minimizing Hausdorff distance,the model is trained towards the global optimum directly, which improvesperformance and reduces training time. Experimental results show that our modeloutperforms previous state-of-the-art method in F1-score on two datasets withonly a fraction of training time.

Document-Level Multi-Event Extraction with Event Proxy Nodes and Hausdorff Distance Minimization