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

Pre-trained multilingual language models have become an important buildingblock in multilingual natural language processing. In the present paper, weinvestigate a range of such models to find out how well they transferdiscourse-level knowledge across languages. This is done with a systematicevaluation on a broader set of discourse-level tasks than has been previouslybeen assembled. We find that the XLM-RoBERTa family of models consistently showthe best performance, by simultaneously being good monolingual models anddegrading relatively little in a zero-shot setting. Our results also indicatethat model distillation may hurt the ability of cross-lingual transfer ofsentence representations, while language dissimilarity at most has a modesteffect. We hope that our test suite, covering 5 tasks with a total of 22languages in 10 distinct families, will serve as a useful evaluation platformfor multilingual performance at and beyond the sentence level.

Probing Multilingual Language Models for Discourse