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

Media houses reporting on public figures, often come with their own biasesstemming from their respective worldviews. A characterization of theseunderlying patterns helps us in better understanding and interpreting newsstories. For this, we need diverse or subjective summarizations, which may notbe amenable for classifying into predefined class labels. This work proposes azero-shot approach for non-extractive or generative characterizations of personentities from a corpus using GPT-2. We use well-articulated articles fromseveral well-known news media houses as a corpus to build a sound argument forthis approach. First, we fine-tune a GPT-2 pre-trained language model with acorpus where specific person entities are characterized. Second, we furtherfine-tune this with demonstrations of person entity characterizations, createdfrom a corpus of programmatically constructed characterizations. This twicefine-tuned model is primed with manual prompts consisting of entity names thatwere not previously encountered in the second fine-tuning, to generate a simplesentence about the entity. The results were encouraging, when compared againstactual characterizations from the corpus.

Characterizing Latent Perspectives of Media Houses Towards Public Figures