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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recent work pre-training Transformers with self-supervised objectives onlarge text corpora has shown great success when fine-tuned on downstream NLPtasks including text summarization. However, pre-training objectives tailoredfor abstractive text summarization have not been explored. Furthermore there isa lack of systematic evaluation across diverse domains. In this work, wepropose pre-training large Transformer-based encoder-decoder models on massivetext corpora with a new self-supervised objective. In PEGASUS, importantsentences are removed/masked from an input document and are generated togetheras one output sequence from the remaining sentences, similar to an extractivesummary. We evaluated our best PEGASUS model on 12 downstream summarizationtasks spanning news, science, stories, instructions, emails, patents, andlegislative bills. Experiments demonstrate it achieves state-of-the-artperformance on all 12 downstream datasets measured by ROUGE scores. Our modelalso shows surprising performance on low-resource summarization, surpassingprevious state-of-the-art results on 6 datasets with only 1000 examples.Finally we validated our results using human evaluation and show that our modelsummaries achieve human performance on multiple datasets.

PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization