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

Multilingual pre-trained language models (MPLMs) not only can handle tasks indifferent languages but also exhibit surprising zero-shot cross-lingualtransferability. However, MPLMs usually are not able to achieve comparablesupervised performance on rich-resource languages compared to thestate-of-the-art monolingual pre-trained models. In this paper, we aim toimprove the multilingual model's supervised and zero-shot performancesimultaneously only with the resources from supervised languages. Our approachis based on transferring knowledge from high-performance monolingual modelswith a teacher-student framework. We let the multilingual model learn frommultiple monolingual models simultaneously. To exploit the model'scross-lingual transferability, we propose MBLM (multi-branch multilinguallanguage model), a model built on the MPLMs with multiple language branches.Each branch is a stack of transformers. MBLM is trained with thezero-shot-aware training strategy that encourages the model to learn from themixture of zero-shot representations from all the branches. The results on twocross-lingual classification tasks show that, with only the task's superviseddata used, our method improves both the supervised and zero-shot performance ofMPLMs.

Cross-Lingual Text Classification with Multilingual Distillation and Zero-Shot-Aware Training