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

Multi-lingual contextualized embeddings, such as multilingual-BERT (mBERT),have shown success in a variety of zero-shot cross-lingual tasks. However,these models are limited by having inconsistent contextualized representationsof subwords across different languages. Existing work addresses this issue bybilingual projection and fine-tuning technique. We propose a data augmentationframework to generate multi-lingual code-switching data to fine-tune mBERT,which encourages model to align representations from source and multiple targetlanguages once by mixing their context information. Compared with the existingwork, our method does not rely on bilingual sentences for training, andrequires only one training process for multiple target languages. Experimentalresults on five tasks with 19 languages show that our method leads tosignificantly improved performances for all the tasks compared with mBERT.

CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLP