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

Cross-lingual text summarization aims at generating a document summary in onelanguage given input in another language. It is a practically important butunder-explored task, primarily due to the dearth of available data. Existingmethods resort to machine translation to synthesize training data, but suchpipeline approaches suffer from error propagation. In this work, we propose anend-to-end cross-lingual text summarization model. The model uses reinforcementlearning to directly optimize a bilingual semantic similarity metric betweenthe summaries generated in a target language and gold summaries in a sourcelanguage. We also introduce techniques to pre-train the model leveragingmonolingual summarization and machine translation objectives. Experimentalresults in both English--Chinese and English--German cross-lingualsummarization settings demonstrate the effectiveness of our methods. Inaddition, we find that reinforcement learning models with bilingual semanticsimilarity as rewards generate more fluent sentences than strong baselines.

A Deep Reinforced Model for Zero-Shot Cross-Lingual Summarization with Bilingual Semantic Similarity Rewards