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

Progress in sentence simplification has been hindered by a lack of labeledparallel simplification data, particularly in languages other than English. Weintroduce MUSS, a Multilingual Unsupervised Sentence Simplification system thatdoes not require labeled simplification data. MUSS uses a novel approach tosentence simplification that trains strong models using sentence-levelparaphrase data instead of proper simplification data. These models leverageunsupervised pretraining and controllable generation mechanisms to flexiblyadjust attributes such as length and lexical complexity at inference time. Wefurther present a method to mine such paraphrase data in any language fromCommon Crawl using semantic sentence embeddings, thus removing the need forlabeled data. We evaluate our approach on English, French, and Spanishsimplification benchmarks and closely match or outperform the previous bestsupervised results, despite not using any labeled simplification data. We pushthe state of the art further by incorporating labeled simplification data.

MUSS: Multilingual Unsupervised Sentence Simplification by Mining Paraphrases