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

Even though large pre-trained multilingual models (e.g. mBERT, XLM-R) haveled to significant performance gains on a wide range of cross-lingual NLPtasks, success on many downstream tasks still relies on the availability ofsufficient annotated data. Traditional fine-tuning of pre-trained models usingonly a few target samples can cause over-fitting. This can be quite limiting asmost languages in the world are under-resourced. In this work, we investigatecross-lingual adaptation using a simple nearest neighbor few-shot (<15 samples)inference technique for classification tasks. We experiment using a total of 16distinct languages across two NLP tasks- XNLI and PAWS-X. Our approachconsistently improves traditional fine-tuning using only a handful of labeledsamples in target locales. We also demonstrate its generalization capabilityacross tasks.

Nearest Neighbour Few-Shot Learning for Cross-lingual Classification