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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Structured pruning has been extensively studied on monolingual pre-trainedlanguage models and is yet to be fully evaluated on their multilingualcounterparts. This work investigates three aspects of structured pruning onmultilingual pre-trained language models: settings, algorithms, and efficiency.Experiments on nine downstream tasks show several counter-intuitive phenomena:for settings, individually pruning for each language does not induce a betterresult; for algorithms, the simplest method performs the best; for efficiency,a fast model does not imply that it is also small. To facilitate the comparisonon all sparsity levels, we present Dynamic Sparsification, a simple approachthat allows training the model once and adapting to different model sizes atinference. We hope this work fills the gap in the study of structured pruningon multilingual pre-trained models and sheds light on future research.

Probing Structured Pruning on Multilingual Pre-trained Models: Settings, Algorithms, and Efficiency