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/

Zendy Plus

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

Zendy Tools

Zendy Open

Diacritization plays a pivotal role in improving readability anddisambiguating the meaning of Arabic texts. Efforts have so far focused onmarking every eligible character (Full Diacritization). Comparativelyoverlooked, Partial Diacritzation (PD) is the selection of a subset ofcharacters to be marked to aid comprehension where needed. Research hasindicated that excessive diacritic marks can hinder skilled readers -- reducingreading speed and accuracy. We conduct a behavioral experiment and show thatpartially marked text is often easier to read than fully marked text, andsometimes easier than plain text. In this light, we introduceContext-Contrastive Partial Diacritization (CCPD) -- a novel approach to PDwhich integrates seamlessly with existing Arabic diacritization systems. CCPDprocesses each word twice, once with context and once without, and diacritizesonly the characters with disparities between the two inferences. Further, weintroduce novel indicators for measuring partial diacritization quality,essential for establishing this as a machine learning task. Lastly, weintroduce TD2, a Transformer-variant of an established model which offers amarkedly different performance profile on our proposed indicators compared toall other known systems.

A Context-Contrastive Inference Approach To Partial Diacritization