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 pre-trained language models, such as mBERT and XLM-R, have shownimpressive cross-lingual ability. Surprisingly, both of them use multilingualmasked language model (MLM) without any cross-lingual supervision or aligneddata. Despite the encouraging results, we still lack a clear understanding ofwhy cross-lingual ability could emerge from multilingual MLM. In our work, weargue that cross-language ability comes from the commonality between languages.Specifically, we study three language properties: constituent order,composition and word co-occurrence. First, we create an artificial language bymodifying property in source language. Then we study the contribution ofmodified property through the change of cross-language transfer results ontarget language. We conduct experiments on six languages and two cross-lingualNLP tasks (textual entailment, sentence retrieval). Our main conclusion is thatthe contribution of constituent order and word co-occurrence is limited, whilethe composition is more crucial to the success of cross-linguistic transfer.

Cross-Lingual Ability of Multilingual Masked Language Models: A Study of Language Structure