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

Recent advancements in NLP have given us models like mBERT and XLMR that canserve over 100 languages. The languages that these models are evaluated on,however, are very few in number, and it is unlikely that evaluation datasetswill cover all the languages that these models support. Potential solutions tothe costly problem of dataset creation are to translate datasets to newlanguages or use template-filling based techniques for creation. This paperproposes an alternate solution for evaluating a model across languages whichmake use of the existing performance scores of the model on languages that aparticular task has test sets for. We train a predictor on these performancescores and use this predictor to predict the model's performance in differentevaluation settings. Our results show that our method is effective in fillingthe gaps in the evaluation for an existing set of languages, but might requireadditional improvements if we want it to generalize to unseen languages.

Predicting the Performance of Multilingual NLP Models