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

Commonsense reasoning is one of the key problems in natural languageprocessing, but the relative scarcity of labeled data holds back the progressfor languages other than English. Pretrained cross-lingual models are a sourceof powerful language-agnostic representations, yet their inherent reasoningcapabilities are still actively studied. In this work, we design a simpleapproach to commonsense reasoning which trains a linear classifier with weightsof multi-head attention as features. To evaluate this approach, we create amultilingual Winograd Schema corpus by processing several datasets from priorwork within a standardized pipeline and measure cross-lingual generalizationability in terms of out-of-sample performance. The method performscompetitively with recent supervised and unsupervised approaches forcommonsense reasoning, even when applied to other languages in a zero-shotmanner. Also, we demonstrate that most of the performance is given by the samesmall subset of attention heads for all studied languages, which providesevidence of universal reasoning capabilities in multilingual encoders.

It's All in the Heads: Using Attention Heads as a Baseline for Cross-Lingual Transfer in Commonsense Reasoning