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

Existing research has shown that a multilingual pre-trained language modelfine-tuned with one (source) language also performs well on downstream tasksfor non-source languages, even though no fine-tuning is done on theselanguages. However, there is a clear gap between the performance of the sourcelanguage and that of the non-source languages. This paper analyzes thefine-tuning process, discovers when the performance gap changes and identifieswhich network weights affect the overall performance most. Additionally, thepaper seeks to answer to what extent the gap can be reduced by reducingforgetting. Based on the analysis results, a method named Fine-tuning slow andfast with four training policies is proposed to address these issues.Experimental results show the proposed method outperforms baselines by a clearmargin.

Analyzing and Reducing the Performance Gap in Cross-Lingual Transfer with Fine-tuning Slow and Fast