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

ive text summarization is one of the areas influenced by theemergence of pre-trained language models. Current pre-training works inabstractive summarization give more points to the summaries with more words incommon with the main text and pay less attention to the semantic similaritybetween generated sentences and the original document. We propose ARMAN, aTransformer-based encoder-decoder model pre-trained with three novel objectivesto address this issue. In ARMAN, salient sentences from a document are selectedaccording to a modified semantic score to be masked and form a pseudo summary.To summarize more accurately and similar to human writing patterns, we appliedmodified sentence reordering. We evaluated our proposed models on sixdownstream Persian summarization tasks. Experimental results show that ourproposed model achieves state-of-the-art performance on all six summarizationtasks measured by ROUGE and BERTScore. Our models also outperform prior worksin textual entailment, question paraphrasing, and multiple choice questionanswering. Finally, we established a human evaluation and show that using thesemantic score significantly improves summarization results.

ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization