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

We tackle the problem of zero-shot cross-lingual transfer in NLP tasks viathe use of language adapters (LAs). Most of the earlier works have exploredtraining with adapter of a single source (often English), and testing eitherusing the target LA or LA of another related language. Training target LArequires unlabeled data, which may not be readily available for low resourceunseen languages: those that are neither seen by the underlying multilinguallanguage model (e.g., mBERT), nor do we have any (labeled or unlabeled) datafor them. We posit that for more effective cross-lingual transfer, instead ofjust one source LA, we need to leverage LAs of multiple (linguistically orgeographically related) source languages, both at train and test-time - whichwe investigate via our novel neural architecture, ZGUL. Extensiveexperimentation across four language groups, covering 15 unseen targetlanguages, demonstrates improvements of up to 3.2 average F1 points overstandard fine-tuning and other strong baselines on POS tagging and NER tasks.We also extend ZGUL to settings where either (1) some unlabeled data or (2)few-shot training examples are available for the target language. We find thatZGUL continues to outperform baselines in these settings too.

ZGUL: Zero-shot Generalization to Unseen Languages using Multi-source Ensembling of Language Adapters