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

Multilingual pretrained language models serve as repositories of multilingualfactual knowledge. Nevertheless, a substantial performance gap of factualknowledge probing exists between high-resource languages and low-resourcelanguages, suggesting limited implicit factual knowledge transfer acrosslanguages in multilingual pretrained language models. This paper investigatesthe feasibility of explicitly transferring relatively rich factual knowledgefrom English to non-English languages. To accomplish this, we propose twoparameter-free $\textbf{L}$anguage $\textbf{R}$epresentation$\textbf{P}$rojection modules (LRP2). The first module converts non-Englishrepresentations into English-like equivalents, while the second module revertsEnglish-like representations back into representations of the correspondingnon-English language. Experimental results on the mLAMA dataset demonstratethat LRP2 significantly improves factual knowledge retrieval accuracy andfacilitates knowledge transferability across diverse non-English languages. Wefurther investigate the working mechanism of LRP2 from the perspectives ofrepresentation space and cross-lingual knowledge neuron.

Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?