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

Text summarization aims to extract essential information from a piece of textand transform the text into a concise version. Existing unsupervisedabstractive summarization models leverage recurrent neural networks frameworkwhile the recently proposed transformer exhibits much more capability.Moreover, most of previous summarization models ignore abundant unlabeledcorpora resources available for pretraining. In order to address these issues,we propose TED, a transformer-based unsupervised abstractive summarizationsystem with pretraining on large-scale data. We first leverage the lead bias innews articles to pretrain the model on millions of unlabeled corpora. Next, wefinetune TED on target domains through theme modeling and a denoisingautoencoder to enhance the quality of generated summaries. Notably, TEDoutperforms all unsupervised abstractive baselines on NYT, CNN/DM and EnglishGigaword datasets with various document styles. Further analysis shows that thesummaries generated by TED are highly abstractive, and each component in theobjective function of TED is highly effective.

TED: A Pretrained Unsupervised Summarization Model with Theme Modeling and Denoising