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 address an important gap in detecting political bias in news articles.Previous works that perform document classification can be influenced by thewriting style of each news outlet, leading to overfitting and limitedgeneralizability. Our approach overcomes this limitation by considering boththe sentence-level semantics and the document-level rhetorical structure,resulting in a more robust and style-agnostic approach to detecting politicalbias in news articles. We introduce a novel multi-head hierarchical attentionmodel that effectively encodes the structure of long documents through adiverse ensemble of attention heads. While journalism follows a formalizedrhetorical structure, the writing style may vary by news outlet. We demonstratethat our method overcomes this domain dependency and outperforms previousapproaches for robustness and accuracy. Further analysis and human evaluationdemonstrate the ability of our model to capture common discourse structures injournalism. Our code is available at:https://github.com/xfactlab/emnlp2023-Document-Hierarchy

Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy