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

Multimodal summarization with multimodal output (MSMO) generates a summarywith both textual and visual content. Multimodal news report containsheterogeneous contents, which makes MSMO nontrivial. Moreover, it is observedthat different modalities of data in the news report correlate hierarchically.Traditional MSMO methods indistinguishably handle different modalities of databy learning a representation for the whole data, which is not directlyadaptable to the heterogeneous contents and hierarchical correlation. In thispaper, we propose a hierarchical cross-modality semantic correlation learningmodel (HCSCL) to learn the intra- and inter-modal correlation existing in themultimodal data. HCSCL adopts a graph network to encode the intra-modalcorrelation. Then, a hierarchical fusion framework is proposed to learn thehierarchical correlation between text and images. Furthermore, we construct anew dataset with relevant image annotation and image object label informationto provide the supervision information for the learning procedure. Extensiveexperiments on the dataset show that HCSCL significantly outperforms thebaseline methods in automatic summarization metrics and fine-grained diversitytests.

Hierarchical Cross-Modality Semantic Correlation Learning Model for Multimodal Summarization