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

Previous studies have proved that cross-lingual knowledge distillation cansignificantly improve the performance of pre-trained models for cross-lingualsimilarity matching tasks. However, the student model needs to be large in thisoperation. Otherwise, its performance will drop sharply, thus making itimpractical to be deployed to memory-limited devices. To address this issue, wedelve into cross-lingual knowledge distillation and propose a multi-stagedistillation framework for constructing a small-size but high-performancecross-lingual model. In our framework, contrastive learning, bottleneck, andparameter recurrent strategies are combined to prevent performance from beingcompromised during the compression process. The experimental resultsdemonstrate that our method can compress the size of XLM-R and MiniLM by morethan 50\%, while the performance is only reduced by about 1%.

Multi-stage Distillation Framework for Cross-Lingual Semantic Similarity Matching