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

We introduce a new task, MultiMedia Event Extraction (M2E2), which aims toextract events and their arguments from multimedia documents. We develop thefirst benchmark and collect a dataset of 245 multimedia news articles withextensively annotated events and arguments. We propose a novel method, WeaklyAligned Structured Embedding (WASE), that encodes structured representations ofsemantic information from textual and visual data into a common embeddingspace. The structures are aligned across modalities by employing a weaklysupervised training strategy, which enables exploiting available resourceswithout explicit cross-media annotation. Compared to uni-modal state-of-the-artmethods, our approach achieves 4.0% and 9.8% absolute F-score gains on textevent argument role labeling and visual event extraction. Compared tostate-of-the-art multimedia unstructured representations, we achieve 8.3% and5.0% absolute F-score gains on multimedia event extraction and argument rolelabeling, respectively. By utilizing images, we extract 21.4% more eventmentions than traditional text-only methods.

Cross-media Structured Common Space for Multimedia Event Extraction